Understanding Sources of Variation to Improve the Reproducibility of Radiomics

Mastering CT-based radiomic research in lung cancer: a practical guide from study design to critical appraisal

Radiomics is a health technology that has the potential to extract clinically meaningful biomarkers from standard of care imaging. Despite a wealth of exploratory analysis performed on scans acquired from patients with lung cancer and existing guidelines describing some of the key steps, no radiomic-based biomarker has been widely accepted. This is primarily due to limitations with methodology, data analysis, and interpretation of the available studies. There is currently a lack of guidance relating to the entire radiomic workflow from study design to critical appraisal. This guide, written with early career lung cancer researchers, describes a more complete radiomic workflow. Lung cancer image analysis is the focus due to some of the unique challenges encountered such as patient movement from breathing. The guide will focus on CT imaging as these are the most common scans performed on patients with lung cancer. The aim of this article is to support the production of high-quality research that has the potential to positively impact outcome of patients with lung cancer.

PET radiomics for histologic subtype classification of non-small cell lung cancer: a systematic review and meta-analysis

PURPOSE

To systematically review the literature and perform a meta-analysis of PET radiomics for histologic subtype classification in non-small cell lung cancer (NSCLC).

METHODS

PubMed, Embase, Scopus, and Web of Science databases were systematically searched in English on human subjects for studies on distinguishing adenocarcinoma (ADC) from squamous cell carcinoma (SCC) using PET radiomics published from inception until November 2024. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and the Radiomics Quality Score (RQS) were utilized to assess the methodological quality of the included studies. The area under the receiver operating characteristic curves (AUC) was pooled to estimate predictive performance. An overall effect size was estimated using a random-effects model. Statistical heterogeneity was evaluated by the I2 value. Subgroup analyses were conducted to explore sources of heterogeneity.

RESULTS

Twelve studies were included in the analysis, yielding a pooled AUC of 0.92 (95% confidence interval [CI]: 0.89-0.94). Despite this promising result, the studies showed limitations in both study design and methodological quality, as evidenced by a median RQS of 11/36. A significant degree of heterogeneity was observed among the studies, with an I2 of 92.20% (95% CI: 89.01-95.39) for sensitivity and 89.29% (95% CI: 84.48-94.10) for specificity.

CONCLUSIONS

This meta-analysis highlights the potential utility of PET radiomics in distinguishing ADC from SCC. However, the observed high heterogeneity indicates substantial methodological variability across the included studies. Future research should focus on standardization, transparency, and multicenter collaborations to improve the reliability and clinical applicability of PET radiomics for histologic subtype classification in NSCLC.

The impact of Inter-observation variation on radiomic features of pulmonary nodules

Objective

In this study, we aimed to comprehensively and systematically analyze the radiomic features of pulmonary nodules and explore the influence of inter-observation variation (IOV) in segmentation regions of interest (ROI) on radiomic features, providing reference information for pulmonary nodule radiomics research.

Method

Six clinicians with varying experience and expertise manually outlined ROIs for 232 pulmonary nodules, while an artificial intelligence (AI) algorithm was trained for automated segmentation. The segmentation by the most experienced cardiothoracic diagnostician (Doctor A) served as the reference standard. Inter-observer variability was assessed through diameter measurements, segmentation ROI consistency analysis, and radiomic features stability analysis.

Results

Of all radiomics features analyzed, 1071 (85.96%) demonstrated good stability (overall concordance correlation coefficient [OCCC] ≥ 0.75), with 766 (61.48%) exhibiting very good stability (OCCC ≥ 0.90). Among the eight radiomic feature types, Original _first-order, Original_GLCM, Original_GLRLM, Original_GLSZM, LOG, and wavelet features all achieved stability rates exceeding 80.00%, with 91.59% of the LOG features having good stability. The Original features showed good stability (median OCCC: 0.92-0.95, IQR: 0.12-0.19), both in the overall distribution and in the different feature categories. The median OCCC value for the LOG features (median: 0.94, IQR: 0.08) was significantly higher than that for the Wavelet features (median: 0.91, IQR: 0.13). There was no statistically significant difference in stability between the Original and LOG feature subgroups (P > 0.05). In contrast, statistically significant differences were observed between the wavelet feature subgroups (P < 0.05), with Wavelet_LLL and Wavelet_LLH transformation yielding higher stability.

Conclusion

Segmentation results indicated that while IOV influenced radiomic features of pulmonary nodules, most (85.96%) of the features were well stabilized and relatively unaffected. Enhancing segmentation ROI consistency helps minimize the impact of IOV on the radiomic features of pulmonary nodule images. Original and LOG features demonstrated high stability, whereas Wavelet features were more susceptible to IOV.

Impact of harmonization on predicting complications in head and neck cancer after radiotherapy using MRI radiomics and machine learning techniques

BACKGROUND

Variations in medical images specific to individual scanners restrict the use of radiomics in both clinical practice and research. To create reproducible and generalizable radiomics-based models for outcome prediction and assessment, data harmonization is essential.

PURPOSE

This study aims to investigate the impact of harmonization in performance of machine learning-based radiomics model toward the prediction of radiotherapy-induced toxicity (early and late sticky saliva and xerostomia) in head and neck cancer (HNC) patients after radiation therapy usingT 1 $T_1$ andT 2 $T_2$ -weighted magnetic resonance (MR) images.

METHODS

A total of 85 HNC patients who underwent radiotherapy was studied. Radiomic features were extracted fromT 1 $T_1$ andT 2 $T_2$ -weighted MR images with standardized protocols. Data harmonization was performed using ComBat algorithm to reduce inter-center variability. Besides imaging features, both dosimetric and demographic features were extracted and used in our model. Recursive feature elimination was employed as feature selection method to identify the most important variables. Ten classification algorithms, including eXtreme Gradient Boosting (XGBoost), multilayer perceptron (MLP), support vector machines (SVM), random forest (RF), k-nearest neighbor (KNN), Naive Bayes (NB), logistic regression (LR), and decision tree (DT), boosted generalized linear model (GLMB), and stack learning (SL) were utilized and compared to develop predictive models. This evaluation comparisons were performed before and after harmonization to demonstrate its significance.

RESULTS

Our results indicate that harmonization consistently enhances predictive performance across various complications and imaging modalities. In early and late sticky saliva prediction usingT 1 $T_1$ -weighted images, the SVM and RF models achieved an impressive area under the curve (AUC) of 0.88 ± $\pm$ 0.09 and 0.97 ± $\pm$ 0.05 with harmonization versus 0.42 ± $\pm$ 0.12 and 0.83 ± $\pm$ 0.08 without harmonization, respectively. Similarly, in early and late xerostomia prediction, the model attained an AUC of 0.79 ± $\pm$ 0.15 and 0.61 ± $\pm$ 0.14 with harmonization and 0.55 ± $\pm$ 0.17 and 0.46 ± $\pm$ 0.14 without harmonization.

CONCLUSION

Our study highlights the importance of harmonization techniques in improving the performance of predictive models utilizing magnetic resonance imaging radiomics features. While harmonization consistently enhanced performance for sticky saliva and early xerostomia usingT 1 $T_1$ -weighted features, the prediction of early and late xerostomia usingT 2 $T_2$ -weighted features remains challenging. These findings try to develop accurate and reliable predictive models in medical imaging, that contribute to improve patient care and treatment outcomes.

Radiomics Results for Adrenal Mass Characterization Are Stable and Reproducible Under Different Software

Background: This study aims to investigate stability and reproducibility of radiomics biomarkers for adrenal lesion characterization across different software packages. Methods: Unenhanced CT images from patients with adrenal tumors were analyzed. Radiomic features were extracted using SOPHIA Radiomics and SIBEX software. The datasets underwent Z-score normalization. Statistical comparisons were made using two-sample t-tests and Spearman correlation coefficients. Three classification models-Logistic Regression, Linear Discriminant Analysis, and Linear Support Vector Machine-were trained on the datasets. Model performance was evaluated using accuracy, precision, recall, F1 score, and ROC curves. Feature importance and the statistical significance of model performance differences were also analyzed. Results: The t-test results showed no significant differences in the radiomic features extracted by SOPHIA and SIBEX (p-values all equal to 1.0). Spearman correlation coefficients were high for most features, suggesting a strong similarity between the two software tools. Classification models generally performed better on the SOPHIA dataset, with higher accuracy and precision. Feature importance analysis identified "Quadratic mean" and "Strength" as consistently influential features. Paired t-tests indicated significant differences in accuracy and precision, while Wilcoxon signed-rank tests did not find significant differences across all performance metrics. Conclusions: Radiomic features extracted by SOPHIA and SIBEX are comparable, but slight variations in model performance highlight the need for standardized extraction protocols and fine-tuning of predictive features. The study underscores the importance of ensuring the stability and reproducibility of radiomics features for reliable clinical application in adrenal lesion characterization.

Radiomics in Dermatological Optical Coherence Tomography (OCT): Feature Repeatability, Reproducibility, and Integration into Diagnostic Models in a Prospective Study

BACKGROUND/OBJECTIVES

Radiomics has seen substantial growth in medical imaging; however, its potential in optical coherence tomography (OCT) has not been widely explored. We systematically evaluate the repeatability and reproducibility of handcrafted radiomics features (HRFs) from OCT scans of benign nevi and examine the impact of bin width (BW) selection on HRF stability. The effect of using stable features on a radiomics classification model was also assessed.

METHODS

In this prospective study, 20 volunteers underwent test-retest OCT imaging of 40 benign nevi, resulting in 80 scans. The repeatability and reproducibility of HRFs extracted from manually delineated regions of interest (ROIs) were assessed using concordance correlation coefficients (CCCs) across BWs ranging from 5 to 50. A unique set of stable HRFs was identified at each BW after removing highly correlated features to eliminate redundancy. These robust features were incorporated into a multiclass radiomics classifier trained to distinguish benign nevi, basal cell carcinoma (BCC), and Bowen's disease.

RESULTS

Six stable HRFs were identified across all BWs, with a BW of 25 emerging as the optimal choice, balancing repeatability and the ability to capture meaningful textural details. Additionally, intermediate BWs (20-25) yielded 53 reproducible features. A classifier trained with six stable features achieved a 90% accuracy and AUCs of 0.96 and 0.94 for BCC and Bowen's disease, respectively, compared to a 76% accuracy and AUCs of 0.86 and 0.80 for a conventional feature selection approach.

CONCLUSIONS

This study highlights the critical role of BW selection in enhancing HRF stability and provides a methodological framework for optimizing preprocessing in OCT radiomics. By demonstrating the integration of stable HRFs into diagnostic models, we establish OCT radiomics as a promising tool to aid non-invasive diagnosis in dermatology.

Predictive value of tumoral and peritumoral radiomic features in neoadjuvant chemotherapy response for breast cancer: a retrospective study

BACKGROUND

Neoadjuvant chemotherapy (NACT) improves surgical outcomes for breast cancer patients, with pathologic complete response (pCR) correlated with enhanced survival. The role of radiomics, particularly from peritumoral tissue, in predicting pCR remains under investigation.

METHODS

This retrospective study analyzed radiomic features from pretreatment dynamic contrast-enhanced breast MRI scans of 150 patients undergoing NACT. A proportional approach was used to define peritumoral zones, assessed both with a 10% and 30% extension, allowing more standardized assessments relative to the tumor size. Radiomic features were evaluated alongside clinical and biological data to predict pCR. The association of clinical/biological and radiomic features with pCR to NACT was evaluated using univariate and multivariate analysis, logistic regression, and a random forest model. A clinical/biological model, a radiomic model, and a combined clinical/biological and 4 radiomic models for predicting the response to NACT were constructed. Area under the curve (AUC) and 95% confidence intervals (CIs) were used to assess the performance of the models.

RESULTS

Ninety-five patients (average age 47 years) were finally included. HER2 + , basal-like molecular subtypes, and a high level of Ki67 (≥ 20%) were associated with a higher likelihood of pCR to NACT. The combined clinical-biological-radiomic model, especially with a 10% peritumoral extension, showed improved predictive accuracy (AUC 0.76, CI 0.65-0.85) compared to models using clinical-biological data alone (AUC 0.73, CI 0.63-0.83).

CONCLUSIONS

Integrating peritumoral radiomic features with clinical and biological data enhances the prediction of pCR to NACT, underscoring the potential of a multifaceted approach in treatment personalization.

Comparing quantitative imaging biomarker alliance volumetric CT classifications with RECIST response categories

Purpose

To assess agreement between CT volumetry change classifications derived from Quantitative Imaging Biomarker Alliance Profile cut-points (ie, QIBA CTvol classifications) and the Response Evaluation Criteria in Solid Tumors (RECIST) categories.

Materials and Methods

Target lesions in lung, liver, and lymph nodes were randomly chosen from patients in 10 historical clinical trials for various cancers, ensuring a balanced representation of lesion types, diameter ranges described in the QIBA Profile, and variations in change magnitudes. Three radiologists independently segmented these lesions at baseline and follow-up scans using 2 software tools. Two types of predefined disagreements were assessed: Type I: substantive disagreement, where the disagreement between QIBA CTvol classifications and RECIST categories could not be attributed to the improved sensitivity of volumetry in detecting changes; and Type II: disagreement potentially arising from the improved sensitivity of volumetry in detecting changes. The proportion of lesions with disagreements between QIBA CTvol and RECIST, as well as the type of disagreements, was reported along with 95% CIs, both overall and within subgroups representing various factors.

Results

A total of 2390 measurements from 478 lesions (158 lungs, 170 livers, 150 lymph nodes) in 281 patients were included. QIBA CTvol agreed with RECIST in 66.6% of interpretations. Of the 33.4% of interpretations with discrepancies, substantive disagreement (Type I) occurred in only 1.5% (95% CI: [0.8%, 2.1%]). Factors such as scanner vendor (P = .584), segmentation tool (P = .331), and lesion type (P = .492) were not significant predictors of disagreement. Significantly more disagreements were observed for larger lesions (≥50 mm, as defined in the QIBA Profile).

Conclusion

We conclude that QIBA CTvol classifications agree with RECIST categories.

Textural heterogeneity of liver lesions in CT imaging - comparison of colorectal and pancreatic metastases

PURPOSE

Tumoral heterogeneity poses a challenge for personalized cancer treatments. Especially in metastasized cancer, it remains a major limitation for successful targeted therapy, often leading to drug resistance due to tumoral escape mechanisms. This work explores a non-invasive radiomics-based approach to capture textural heterogeneity in liver lesions and compare it between colorectal cancer (CRC) and pancreatic cancer (PDAC).

MATERIALS AND METHODS

In this retrospective single-center study 73 subjects (42 CRC, 31 PDAC) with 1291 liver metastases (430 CRC, 861 PDAC) were segmented fully automated on contrast-enhanced CT images by a UNet for medical images. Radiomics features were extracted using the Python package Pyradiomics. The mean coefficient of variation (CV) was calculated patient-wise for each feature to quantify the heterogeneity. An unpaired t-test identified features with significant differences in feature variability between CRC and PDAC metastases.

RESULTS

In both colorectal and pancreatic liver metastases, interlesional heterogeneity in imaging can be observed using quantitative imaging features. 75 second-order features were extracted to compare the varying textural characteristics. In total, 18 radiomics features showed a significant difference (p < 0.05) in their expression between the two malignancies. Out of these, 16 features showed higher levels of variability within the cohort of pancreatic metastases, which, as illustrated in a radar plot, suggests greater textural heterogeneity for this entity.

CONCLUSIONS

Radiomics has the potential to identify the interlesional heterogeneity of CT texture among individual liver metastases. In this proof-of-concept study for the quantification and comparison of imaging-related heterogeneity in liver metastases a variation in the extent of heterogeneity levels in CRC and PDAC liver metastases was shown.

Radiomic features of PET/CT imaging of large B cell lymphoma lesions predicts CAR T cell therapy efficacy

Background

Relapsed and refractory Diffuse large B cell lymphoma (DLBCL) can be successfully treated with axicabtagene ciloleucel (axi-cel), a CD19-directed autologous chimeric antigen receptor T cell (CAR-T) therapy. Diagnostic image-based features could help identify the patients who would clinically respond to this advanced immunotherapy.

Purpose

The aim of this study was to establish a radiomic image feature-based signature derived from positron emission tomography/computed tomography (PET/CT), including metabolic tumor burden, which can predict a durable response to CAR-T therapy in refractory/relapsed DLBCL.

Methods

We conducted a retrospective review of 155 patients with relapsed/refractory DLBCL treated with axi-cel CAR-T therapy. The patients' disease involvement was evaluated based on nodal or extranodal sites. A sub-cohort of these patients with at least one nodal lesion (n=124) was assessed, while an overlapping sub-cohort (n=94) had at least one extranodal lesion. The lesion regions were characterized using 306 quantitative imaging metrics for PET images and CT images independently. Principal component (PC) analysis was performed to reduce the dimensionality in feature-based functional categories: size (n=38), shape (n=9), and texture (n=259). The selected features were used to build prediction models for survival at 1 year and tested for prognosis to overall/progression-free survival (OS/PFS) using a Kaplan-Meier (KM) plot.

Results

The Shape-based PC features of the largest extranodal lesion on PET were predictive of 1-year survival (AUC 0.68 [0.43,0.94]) and prognostic of OS/PFS (p<0.018). Metabolic tumor volume (MTV) was an independent predictor with an area under the curve (AUC) of 0.74 [0.58, 0.87]. Combining these features improved the predictor performance (AUC of 0.78 [0.7, 0.87]). Additionally, the Shape-based PC features were unrelated to total MTV (Spearman's ρ of 0.359, p≤ 0.001).

Conclusion

Our study found that shape-based radiomic features on PET imaging were predictive of treatment outcome (1-year survival) and prognostic of overall survival. We also found non-size-based radiomic predictors that had comparable performance to MTV and provided complementary information to improve the predictability of treatment outcomes.

Annotated test-retest dataset of lung cancer CT scan images reconstructed at multiple imaging parameters

Quantitative imaging biomarkers (QIB) are increasingly used in clinical research to advance precision medicine approaches in oncology. Computed tomography (CT) is a modality of choice for cancer diagnosis, prognosis, and response assessment due to its reliability and global accessibility. Here, we contribute to the cancer imaging community through The Cancer Imaging Archive (TCIA) by providing investigator-initiated, same-day repeat CT scan images of 32 non-small cell lung cancer (NSCLC) patients, along with radiologist-annotated lesion contours as a reference standard. Each scan was reconstructed into 6 image settings using various combinations of three slice thicknesses (1.25 mm, 2.5 mm, 5 mm) and two reconstruction kernels (lung, standard; GE CT equipment), which spans a wide range of CT imaging reconstruction parameters commonly used in lung cancer clinical practice and clinical trials. This holds considerable value for advancing the development of robust Radiomics, Artificial Intelligence (AI) and machine learning (ML) methods.

Prediction of early recurrence of adult-type diffuse gliomas following radiotherapy using multi-modal magnetic resonance images

BACKGROUND

Adult-type diffuse gliomas are among the central nervous system's most aggressive malignant primary neoplasms. Despite advancements in systemic therapies and technological improvements in radiation oncology treatment delivery, the survival outcome for these patients remains poor. Fast and accurate assessment of tumor response to oncologic treatments is crucial, as it can enable the early detection of recurrent or refractory gliomas, thereby allowing timely intervention with life-prolonging salvage therapies.

PURPOSE

Radiomics is a developing field with great potential to improve medical image interpretation. This study aims to apply a radiomics-based predictive model for classifying response to radiotherapy within the first 3 months post-treatment.

METHODS

Ninety-five patients were selected from the Burdenko Glioblastoma Progression Dataset. Tumor regions were delineated in the axial plane on contrast-enhanced T1(CE T1W) and T2 fluid-attenuated inversion recovery (T2_FLAIR) magnetic resonance imaging (MRI). Hand-crafted radiomic (HCR) features, including first- and second-order features, were extracted using PyRadiomics (3.7.6) in Python (3.10). Then, recursive feature elimination with a random forest (RF) classifier was applied for feature dimensionality reduction. RF and support vector machine (SVM) classifiers were built to predict treatment outcomes using the selected features. Leave-one-out cross-validation was employed to tune hyperparameters and evaluate the models.

RESULTS

For each segmented target, 186 HCR features were extracted from the MRI sequence. Using the top-ranked radiomic features from a combination of CE T1W and T2_FLAIR, an optimized classifier achieved the highest averaged area under the curve (AUC) of 0.829 ± 0.075 using the RF classifier. The HCR features of CE T1W produced the worst outcomes among all models (0.603 ± 0.024 and 0.615 ± 0.075 for RF and SVM classifiers, respectively).

CONCLUSIONS

We developed and evaluated a radiomics-based predictive model for early tumor response to radiotherapy, demonstrating excellent performance supported by high AUC values. This model, harnessing radiomic features from multi-modal MRI, showed superior predictive performance compared to single-modal MRI approaches. These results underscore the potential of radiomics in clinical decision support for this disease process.

Using high-repeatable radiomic features improves the cross-institutional generalization of prognostic model in esophageal squamous cell cancer receiving definitive chemoradiotherapy

OBJECTIVES

Repeatability is crucial for ensuring the generalizability and clinical utility of radiomics-based prognostic models. This study aims to investigate the repeatability of radiomic feature (RF) and its impact on the cross-institutional generalizability of the prognostic model for predicting local recurrence-free survival (LRFS) and overall survival (OS) in esophageal squamous cell cancer (ESCC) receiving definitive (chemo) radiotherapy (dCRT).

METHODS

Nine hundred and twelve patients from two hospitals were included as training and external validation sets, respectively. Image perturbations were applied to contrast-enhanced computed tomography to generate perturbed images. Six thousand five hundred ten RFs from different feature types, bin widths, and filters were extracted from the original and perturbed images separately to evaluate RF repeatability by intraclass correlation coefficient (ICC). The high-repeatable and low-repeatable RF groups grouped by the median ICC were further analyzed separately by feature selection and multivariate Cox proportional hazards regression model for predicting LRFS and OS.

RESULTS

First-order statistical features were more repeatable than texture features (median ICC: 0.70 vs 0.42-0.62). RFs from LoG had better repeatability than that of wavelet (median ICC: 0.70-0.84 vs 0.14-0.64). Features with smaller bin widths had higher repeatability (median ICC of 8-128: 0.65-0.47). For both LRFS and OS, the performance of the models based on high- and low-repeatable RFs remained stable in the training set with similar C-index (LRFS: 0.65 vs 0.67, p = 0.958; OS: 0.64 vs 0.65, p = 0.651), while the performance of the model based on the low-repeatable group was significantly lower than that based on the high-repeatable group in the external validation set (LRFS: 0.61 vs 0.67, p = 0.013; OS: 0.56 vs 0.63, p = 0.013).

CONCLUSIONS

Applying high-repeatable RFs in modeling could safeguard the cross-institutional generalizability of the prognostic model in ESCC.

CRITICAL RELEVANCE STATEMENT

The exploration of repeatable RFs in different diseases and different types of imaging is conducive to promoting the proper use of radiomics in clinical research.

KEY POINTS

The repeatability of RFs impacts the generalizability of the radiomic model. The high-repeatable RFs safeguard the cross-institutional generalizability of the model. Smaller bin width helps improve the repeatability of RFs.

Computed tomography radiomics models of tumor differentiation in canine small intestinal tumors

Radiomics models have been widely exploited in oncology for the investigation of tumor classification, as well as for predicting tumor response to treatment and genomic sequence; however, their performance in veterinary gastrointestinal tumors remains unexplored. Here, we sought to investigate and compare the performance of radiomics models in various settings for differentiating among canine small intestinal adenocarcinoma, lymphoma, and spindle cell sarcoma. Forty-two small intestinal tumors were contoured using four different segmentation methods: pre- or post-contrast, each with or without the inclusion of intraluminal gas. The mesenteric lymph nodes of pre- and post-contrast images were also contoured. The bin settings included bin count and bin width of 16, 32, 64, 128, and 256. Multinomial logistic regression, random forest, and support vector machine models were used to construct radiomics models. Using features from both primary tumors and lymph nodes showed significantly better performance than modeling using only the radiomics features of primary tumors, which indicated that the inclusion of mesenteric lymph nodes aids model performance. The support vector machine model exhibited significantly superior performance compared with the multinomial logistic regression and random forest models. Combining radiologic findings with radiomics features improved performance compared to using only radiomics features, highlighting the importance of radiologic findings in model building. A support vector machine model consisting of radiologic findings, primary tumors, and lymph node radiomics features with bin count 16 in post-contrast images with the exclusion of intraluminal gas showed the best performance among the various models tested. In conclusion, this study suggests that mesenteric lymph node segmentation and radiological findings should be integrated to build a potent radiomics model capable of differentiating among small intestinal tumors.

Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study

BACKGROUND

Microsatellite instability (MSI) status is a strong predictor of response to immunotherapy of colorectal cancer. Radiogenomic approaches promise the ability to gain insight into the underlying tumor biology using non-invasive routine clinical images. This study investigates the association between tumor morphology and the status of MSI versus microsatellite stability (MSS), validating a novel radiomic signature on an external multicenter cohort.

METHODS

Preoperative computed tomography scans with matched MSI status were retrospectively collected for 243 colorectal cancer patients from three hospitals: Seoul National University Hospital (SNUH); Netherlands Cancer Institute (NKI); and Fondazione IRCCS Istituto Nazionale dei Tumori, Milan Italy (INT). Radiologists delineated primary tumors in each scan, from which radiomic features were extracted. Machine learning models trained on SNUH data to identify MSI tumors underwent external validation using NKI and INT images. Performances were compared in terms of area under the receiving operating curve (AUROC).

RESULTS

We identified a radiomic signature comprising seven radiomic features that were predictive of tumors with MSS or MSI (AUROC 0.69, 95% confidence interval [CI] 0.54-0.84, p = 0.018). Integrating radiomic and clinical data into an algorithm improved predictive performance to an AUROC of 0.78 (95% CI 0.60-0.91, p = 0.002) and enhanced the reliability of the predictions.

CONCLUSION

Differences in the radiomic morphological phenotype between tumors MSS or MSI could be detected using radiogenomic approaches. Future research involving large-scale multicenter prospective studies that combine various diagnostic data is necessary to refine and validate more robust, potentially tumor-agnostic MSI radiogenomic models.

RELEVANCE STATEMENT

Noninvasive radiomic signatures derived from computed tomography scans can predict MSI in colorectal cancer, potentially augmenting traditional biopsy-based methods and enhancing personalized treatment strategies.

KEY POINTS

Noninvasive CT-based radiomics predicted MSI in colorectal cancer, enhancing stratification. A seven-feature radiomic signature differentiated tumors with MSI from those with MSS in multicenter cohorts. Integrating radiomic and clinical data improved the algorithm's predictive performance.

Enhancing the Clinical Utility of Radiomics: Addressing the Challenges of Repeatability and Reproducibility in CT and MRI

Radiomics, which integrates the comprehensive characterization of imaging phenotypes with machine learning algorithms, is increasingly recognized for its potential in the diagnosis and prognosis of oncological conditions. However, the repeatability and reproducibility of radiomic features are critical challenges that hinder their widespread clinical adoption. This review aims to address the paucity of discussion regarding the factors that influence the reproducibility and repeatability of radiomic features and their subsequent impact on the application of radiomic models. We provide a synthesis of the literature on the repeatability and reproducibility of CT/MR-based radiomic features, examining sources of variation, the number of reproducible features, and the availability of individual feature repeatability indices. We differentiate sources of variation into random effects, which are challenging to control but can be quantified through simulation methods such as perturbation, and biases, which arise from scanner variability and inter-reader differences and can significantly affect the generalizability of radiomic model performance in diverse settings. Four suggestions for repeatability and reproducibility studies are suggested: (1) detailed reporting of variation sources, (2) transparent disclosure of calculation parameters, (3) careful selection of suitable reliability indices, and (4) comprehensive reporting of reliability metrics. This review underscores the importance of random effects in feature selection and harmonizing biases between development and clinical application settings to facilitate the successful translation of radiomic models from research to clinical practice.

Radiomics and artificial intelligence applications in pediatric brain tumors

BACKGROUND

The study of central nervous system (CNS) tumors is particularly relevant in the pediatric population because of their relatively high frequency in this demographic and the significant impact on disease- and treatment-related morbidity and mortality. While both morphological and non-morphological magnetic resonance imaging techniques can give important information concerning tumor characterization, grading, and patient prognosis, increasing evidence in recent years has highlighted the need for personalized treatment and the development of quantitative imaging parameters that can predict the nature of the lesion and its possible evolution. For this purpose, radiomics and the use of artificial intelligence software, aimed at obtaining valuable data from images beyond mere visual observation, are gaining increasing importance. This brief review illustrates the current state of the art of this new imaging approach and its contributions to understanding CNS tumors in children.

DATA SOURCES

We searched the PubMed, Scopus, and Web of Science databases using the following key search terms: ("radiomics" AND/OR "artificial intelligence") AND ("pediatric AND brain tumors"). Basic and clinical research literature related to the above key research terms, i.e., studies assessing the key factors, challenges, or problems of using radiomics and artificial intelligence in pediatric brain tumors management, was collected.

RESULTS

A total of 63 articles were included. The included ones were published between 2008 and 2024. Central nervous tumors are crucial in pediatrics due to their high frequency and impact on disease and treatment. MRI serves as the cornerstone of neuroimaging, providing cellular, vascular, and functional information in addition to morphological features for brain malignancies. Radiomics can provide a quantitative approach to medical imaging analysis, aimed at increasing the information obtainable from the pixels/voxel grey-level values and their interrelationships. The "radiomic workflow" involves a series of iterative steps for reproducible and consistent extraction of imaging data. These steps include image acquisition for tumor segmentation, feature extraction, and feature selection. Finally, the selected features, via training predictive model (CNN), are used to test the final model.

CONCLUSIONS

In the field of personalized medicine, the application of radiomics and artificial intelligence (AI) algorithms brings up new and significant possibilities. Neuroimaging yields enormous amounts of data that are significantly more than what can be gained from visual studies that radiologists can undertake on their own. Thus, new partnerships with other specialized experts, such as big data analysts and AI specialists, are desperately needed. We believe that radiomics and AI algorithms have the potential to move beyond their restricted use in research to clinical applications in the diagnosis, treatment, and follow-up of pediatric patients with brain tumors, despite the limitations set out.

Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review

BACKGROUND

Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality.

MATERIALS AND METHODS

We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters' influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups.

RESULTS

After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models' best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works.

CONCLUSIONS

From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

Mitigating the impact of image processing variations on tumour [18F]-FDG-PET radiomic feature robustness

Radiomics analysis of [18F]-fluorodeoxyglucose ([18F]-FDG) PET images could be leveraged for personalised cancer medicine. However, the inherent sensitivity of radiomic features to intensity discretisation and voxel interpolation complicates its clinical translation. In this work, we evaluated the robustness of tumour [18F]-FDG-PET radiomic features to 174 different variations in intensity resolution or voxel size, and determined whether implementing parameter range conditions or dependency corrections could improve their robustness. Using 485 patient images spanning three cancer types: non-small cell lung cancer (NSCLC), melanoma, and lymphoma, we observed features were more sensitive to intensity discretisation than voxel interpolation, especially texture features. In most of our investigations, the majority of non-robust features could be made robust by applying parameter range conditions. Correctable features, which were generally fewer than conditionally robust, showed systematic dependence on bin configuration or voxel size that could be minimised by applying corrections based on simple mathematical equations. Melanoma images exhibited limited robustness and correctability relative to NSCLC and lymphoma. Our study provides an in-depth characterisation of the sensitivity of [18F]-FDG-PET features to image processing variations and reinforces the need for careful selection of imaging biomarkers prior to any clinical application.

Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network

This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.

The impact of the combat method on radiomics feature compensation and analysis of scanners from different manufacturers

BACKGROUND

This study investigated whether the Combat compensation method can remove the variability of radiomic features extracted from different scanners, while also examining its impact on the subsequent predictive performance of machine learning models.

MATERIALS AND METHODS

135 CT images of Credence Cartridge Radiomic phantoms were collected and screened from three scanners manufactured by Siemens, Philips, and GE. 100 radiomic features were extracted and 20 radiomic features were screened according to the Lasso regression method. The radiomic features extracted from the rubber and resin-filled regions in the cartridges were labeled into different categories for evaluating the performance of the machine learning model. Radiomics features were divided into three groups based on the different scanner manufacturers. The radiomic features were randomly divided into training and test sets with a ratio of 8:2. Five machine learning models (lasso, logistic regression, random forest, support vector machine, neural network) were employed to evaluate the impact of Combat on radiomic features. The variability among radiomic features were assessed using analysis of variance (ANOVA) and principal component analysis (PCA). Accuracy, precision, recall, and area under the receiver curve (AUC) were used as evaluation metrics for model classification.

RESULTS

The principal component and ANOVA analysis results show that the variability of different scanner manufacturers in radiomic features was removed (P˃0.05). After harmonization with the Combat algorithm, the distributions of radiomic features were aligned in terms of location and scale. The performance of machine learning models for classification improved, with the Random Forest model showing the most significant enhancement. The AUC value increased from 0.88 to 0.92.

CONCLUSIONS

The Combat algorithm has reduced variability in radiomic features from different scanners. In the phantom CT dataset, it appears that the machine learning model's classification performance may have improved after Combat harmonization. However, further investigation and validation are required to fully comprehend Combat's impact on radiomic features in medical imaging.

Influence of image preprocessing on the segmentation-based reproducibility of radiomic features: in vivo experiments on discretization and resampling parameters

PURPOSE

To systematically investigate the impact of image preprocessing parameters on the segmentation-based reproducibility of magnetic resonance imaging (MRI) radiomic features.

METHODS

The MRI scans of 50 patients were included from the multi-institutional Brain Tumor Segmentation 2021 public glioma dataset. Whole tumor volumes were manually segmented by two independent readers, with the participation of eight readers. Radiomic features were extracted from two sequences: T2-weighted (T2) and contrast-enhanced T1-weighted (T1ce). Two methods were considered for discretization: bin count (i.e., relative discretization) and bin width (i.e., absolute discretization). Ten discretization (five for each method) and five resampling parameters were varied while other parameters were fixed. The intraclass correlation coefficient (ICC) was used for reliability analysis based on two commonly used cut-off values (0.75 and 0.90).

RESULTS

Image preprocessing parameters had a significant impact on the segmentation-based reproducibility of radiomic features. The bin width method yielded more reproducible features than the bin count method. In discretization experiments using the bin width on both sequences, according to the ICC cut-off values of 0.75 and 0.90, the rate of reproducible features ranged from 70% to 84% and from 35% to 57%, respectively, with an increasing percentage trend as parameter values decreased (from 84 to 5 for T2; 100 to 6 for T1ce). In the resampling experiments, these ranged from 53% to 74% and from 10% to 20%, respectively, with an increasing percentage trend from lower to higher parameter values (physical voxel size; from 1 x 1 x 1 to 2 x 2 x 2 mm3).

CONCLUSION

The segmentation-based reproducibility of radiomic features appears to be substantially influenced by discretization and resampling parameters. Our findings indicate that the bin width method should be used for discretization and lower bin width and higher resampling values should be used to allow more reproducible features.

Clinical prediction of microvascular invasion in hepatocellular carcinoma using an MRI-based graph convolutional network model integrated with nomogram

OBJECTIVES

Based on enhanced MRI, a prediction model of microvascular invasion (MVI) for hepatocellular carcinoma (HCC) was developed using graph convolutional network (GCN) combined nomogram.

METHODS

We retrospectively collected 182 HCC patients confirmed histopathologically, all of them performed enhanced MRI before surgery. The patients were randomly divided into training and validation groups. Radiomics features were extracted from the arterial phase (AP), portal venous phase (PVP), and delayed phase (DP), respectively. After removing redundant features, the graph structure by constructing the distance matrix with the feature matrix was built. Screening the superior phases and acquired GCN Score (GS). Finally, combining clinical, radiological and GS established the predicting nomogram.

RESULTS

27.5% (50/182) patients were with MVI positive. In radiological analysis, intratumoural artery (P = 0.007) was an independent predictor of MVI. GCN model with grey-level cooccurrence matrix-grey-level run length matrix features exhibited area under the curves of the training group was 0.532, 0.690, and 0.885 and the validation group was 0.583, 0.580, and 0.854 for AP, PVP, and DP, respectively. DP was selected to develop final model and got GS. Combining GS with diameter, corona enhancement, mosaic architecture, and intratumoural artery constructed a nomogram which showed a C-index of 0.884 (95% CI: 0.829-0.927).

CONCLUSIONS

The GCN model based on DP has a high predictive ability. A nomogram combining GS, clinical and radiological characteristics can be a simple and effective guiding tool for selecting HCC treatment options.

ADVANCES IN KNOWLEDGE

GCN based on MRI could predict MVI on HCC.

Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study

Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.

Contrast Agent Dynamics Determine Radiomics Profiles in Oncologic Imaging

BACKGROUND

The reproducibility of radiomics features extracted from CT and MRI examinations depends on several physiological and technical factors. The aim was to evaluate the impact of contrast agent timing on the stability of radiomics features using dynamic contrast-enhanced perfusion CT (dceCT) or MRI (dceMRI) in prostate and lung cancers.

METHODS

Radiomics features were extracted from dceCT or dceMRI images in patients with biopsy-proven peripheral prostate cancer (pzPC) or biopsy-proven non-small cell lung cancer (NSCLC), respectively. Features that showed significant differences between contrast phases were identified using linear mixed models. An L2-penalized logistic regression classifier was used to predict class labels for pzPC and unaffected prostate regions-of-interest (ROIs).

RESULTS

Nine pzPC and 28 NSCLC patients, who were imaged with dceCT and/or dceMRI, were included in this study. After normalizing for individual enhancement patterns by defining seven individual phases based on a reference vessel, 19, 467 and 128 out of 1204 CT features showed significant temporal dynamics in healthy prostate parenchyma, prostate tumors and lung tumors, respectively. CT radiomics-based classification accuracy of healthy and tumor ROIs was highly dependent on contrast agent phase. For dceMRI, 899 and 1027 out of 1118 features were significantly dependent on time after contrast agent injection for prostate and lung tumors.

CONCLUSIONS

CT and MRI radiomics features in both prostate and lung tumors are significantly affected by interindividual differences in contrast agent dynamics.

Biodistribution Assessment of a Novel 68Ga-Labeled Radiopharmaceutical in a Cancer Overexpressing CCK2R Mouse Model: Conventional and Radiomics Methods for Analysis

The aim of the present study consists of the evaluation of the biodistribution of a novel 68Ga-labeled radiopharmaceutical, [68Ga]Ga-NODAGA-Z360, injected into Balb/c nude mice through histopathological analysis on bioptic samples and radiomics analysis of positron emission tomography/computed tomography (PET/CT) images. The 68Ga-labeled radiopharmaceutical was designed to specifically bind to the cholecystokinin receptor (CCK2R). This receptor, naturally present in healthy tissues such as the stomach, is a biomarker for numerous tumors when overexpressed. In this experiment, Balb/c nude mice were xenografted with a human epidermoid carcinoma A431 cell line (A431 WT) and overexpressing CCK2R (A431 CCK2R+), while controls received a wild-type cell line. PET images were processed, segmented after atlas-based co-registration and, consequently, 112 radiomics features were extracted for each investigated organ / tissue. To confirm the histopathology at the tissue level and correlate it with the degree of PET uptake, the studies were supported by digital pathology. As a result of the analyses, the differences in radiomics features in different body districts confirmed the correct targeting of the radiopharmaceutical. In preclinical imaging, the methodology confirms the importance of a decision-support system based on artificial intelligence algorithms for the assessment of radiopharmaceutical biodistribution.

Advancements in Pancreatic Cancer Detection: Integrating Biomarkers, Imaging Technologies, and Machine Learning for Early Diagnosis

Artificial intelligence (AI) has come to play a pivotal role in revolutionizing medical practices, particularly in the field of pancreatic cancer detection and management. As a leading cause of cancer-related deaths, pancreatic cancer warrants innovative approaches due to its typically advanced stage at diagnosis and dismal survival rates. Present detection methods, constrained by limitations in accuracy and efficiency, underscore the necessity for novel solutions. AI-driven methodologies present promising avenues for enhancing early detection and prognosis forecasting. Through the analysis of imaging data, biomarker profiles, and clinical information, AI algorithms excel in discerning subtle abnormalities indicative of pancreatic cancer with remarkable precision. Moreover, machine learning (ML) algorithms facilitate the amalgamation of diverse data sources to optimize patient care. However, despite its huge potential, the implementation of AI in pancreatic cancer detection faces various challenges. Issues such as the scarcity of comprehensive datasets, biases in algorithm development, and concerns regarding data privacy and security necessitate thorough scrutiny. While AI offers immense promise in transforming pancreatic cancer detection and management, ongoing research and collaborative efforts are indispensable in overcoming technical hurdles and ethical dilemmas. This review delves into the evolution of AI, its application in pancreatic cancer detection, and the challenges and ethical considerations inherent in its integration.

Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods

PURPOSE

To evaluate robustness of a radiomics-based support vector machine (SVM) model for detection of visually occult PDA on pre-diagnostic CTs by simulating common variations in image acquisition and radiomics workflow using image perturbation methods.

METHODS

Eighteen algorithmically generated-perturbations, which simulated variations in image noise levels (σ, 2σ, 3σ, 5σ), image rotation [both CT image and the corresponding pancreas segmentation mask by 45° and 90° in axial plane], voxel resampling (isotropic and anisotropic), gray-level discretization [bin width (BW) 32 and 64)], and pancreas segmentation (sequential erosions by 3, 4, 6, and 8 pixels and dilations by 3, 4, and 6 pixels from the boundary), were introduced to the original (unperturbed) test subset (n = 128; 45 pre-diagnostic CTs, 83 control CTs with normal pancreas). Radiomic features were extracted from pancreas masks of these additional test subsets, and the model's performance was compared vis-a-vis the unperturbed test subset.

RESULTS

The model correctly classified 43 out of 45 pre-diagnostic CTs and 75 out of 83 control CTs in the unperturbed test subset, achieving 92.2% accuracy and 0.98 AUC. Model's performance was unaffected by a three-fold increase in noise level except for sensitivity declining to 80% at 3σ (p = 0.02). Performance remained comparable vis-a-vis the unperturbed test subset despite variations in image rotation (p = 0.99), voxel resampling (p = 0.25-0.31), change in gray-level BW to 32 (p = 0.31-0.99), and erosions/dilations up to 4 pixels from the pancreas boundary (p = 0.12-0.34).

CONCLUSION

The model's high performance for detection of visually occult PDA was robust within a broad range of clinically relevant variations in image acquisition and radiomics workflow.

Reproducibility in Radiomics: A Comparison of Feature Extraction Methods and Two Independent Datasets

Radiomics involves the extraction of information from medical images that are not visible to the human eye. There is evidence that these features can be used for treatment stratification and outcome prediction. However, there is much discussion about the reproducibility of results between different studies. This paper studies the reproducibility of CT texture features used in radiomics, comparing two feature extraction implementations, namely the MATLAB toolkit and Pyradiomics, when applied to independent datasets of CT scans of patients: (i) the open access RIDER dataset containing a set of repeat CT scans taken 15 min apart for 31 patients (RIDER Scan 1 and Scan 2, respectively) treated for lung cancer; and (ii) the open access HN1 dataset containing 137 patients treated for head and neck cancer. Gross tumor volume (GTV), manually outlined by an experienced observer available on both datasets, was used. The 43 common radiomics features available in MATLAB and Pyradiomics were calculated using two intensity-level quantization methods with and without an intensity threshold. Cases were ranked for each feature for all combinations of quantization parameters, and the Spearman's rank coefficient, rs, calculated. Reproducibility was defined when a highly correlated feature in the RIDER dataset also correlated highly in the HN1 dataset, and vice versa. A total of 29 out of the 43 reported stable features were found to be highly reproducible between MATLAB and Pyradiomics implementations, having a consistently high correlation in rank ordering for RIDER Scan 1 and RIDER Scan 2 (rs > 0.8). 18/43 reported features were common in the RIDER and HN1 datasets, suggesting they may be agnostic to disease site. Useful radiomics features should be selected based on reproducibility. This study identified a set of features that meet this requirement and validated the methodology for evaluating reproducibility between datasets.

Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data

Aim

The goal of this study was to get optimal brain tumor features from magnetic resonance imaging (MRI) images and classify them based on the three groups of the tumor region: Peritumoral edema, enhancing-core, and necrotic tumor core, using machine learning classification models.

Materials and Methods

This study's dataset was obtained from the multimodal brain tumor segmentation challenge. A total of 599 brain MRI studies were employed, all in neuroimaging informatics technology initiative format. The dataset was divided into training, validation, and testing subsets online test dataset (OTD). The dataset includes four types of MRI series, which were combined together and processed for intensity normalization using contrast limited adaptive histogram equalization methodology. To extract radiomics features, a python-based library called pyRadiomics was employed. Particle-swarm optimization (PSO) with varying inertia weights was used for feature optimization. Inertia weight with a linearly decreasing strategy (W1), inertia weight with a nonlinear coefficient decreasing strategy (W2), and inertia weight with a logarithmic strategy (W3) were different strategies used to vary the inertia weight for feature optimization in PSO. These selected features were further optimized using the principal component analysis (PCA) method to further reducing the dimensionality and removing the noise and improve the performance and efficiency of subsequent algorithms. Support vector machine (SVM), light gradient boosting (LGB), and extreme gradient boosting (XGB) machine learning classification algorithms were utilized for the classification of images into different tumor regions using optimized features. The proposed method was also tested on institute test data (ITD) for a total of 30 patient images.

Results

For OTD test dataset, the classification accuracy of SVM was 0.989, for the LGB model (LGBM) was 0.992, and for the XGB model (XGBM) was 0.994, using the varying inertia weight-PSO optimization method and the classification accuracy of SVM was 0.996 for the LGBM was 0.998, and for the XGBM was 0.994, using PSO and PCA-a hybrid optimization technique. For ITD test dataset, the classification accuracy of SVM was 0.994 for the LGBM was 0.993, and for the XGBM was 0.997, using the hybrid optimization technique.

Conclusion

The results suggest that the proposed method can be used to classify a brain tumor as used in this study to classify the tumor region into three groups: Peritumoral edema, enhancing-core, and necrotic tumor core. This was done by extracting the different features of the tumor, such as its shape, grey level, gray-level co-occurrence matrix, etc., and then choosing the best features using hybrid optimal feature selection techniques. This was done without much human expertise and in much less time than it would take a person.

A combination of radiomic features, clinic characteristics, and serum tumor biomarkers to predict the possibility of the micropapillary/solid component of lung adenocarcinoma

BACKGROUND

Invasive lung adenocarcinoma with MPP/SOL components has a poor prognosis and often shows a tendency to recurrence and metastasis. This poor prognosis may require adjustment of treatment strategies. Preoperative identification is essential for decision-making for subsequent treatment.

OBJECTIVE

This study aimed to preoperatively predict the probability of MPP/SOL components in lung adenocarcinomas by a comprehensive model that includes radiomics features, clinical characteristics, and serum tumor biomarkers.

DESIGN

A retrospective case control, diagnostic accuracy study.

METHODS

This study retrospectively recruited 273 patients (males: females, 130: 143; mean age ± standard deviation, 63.29 ± 10.03 years; range 21-83 years) who underwent resection of invasive lung adenocarcinoma. Sixty-one patients (22.3%) were diagnosed with lung adenocarcinoma with MPP/SOL components. Radiomic features were extracted from CT before surgery. Clinical, radiomic, and combined models were developed using the logistic regression algorithm. The clinical and radiomic signatures were integrated into a nomogram. The diagnostic performance of the models was evaluated using the area under the curve (AUC). Studies were scored according to the Radiomics Quality Score and Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines.

RESULTS

The radiomics model achieved the best AUC values of 0.858 and 0.822 in the training and test cohort, respectively. Tumor size (T_size), solid tumor size (ST_size), consolidation-to-tumor ratio (CTR), years of smoking, CYFRA 21-1, and squamous cell carcinoma antigen were used to construct the clinical model. The clinical model achieved AUC values of 0.741 and 0.705 in the training and test cohort, respectively. The nomogram showed higher AUCs of 0.894 and 0.843 in the training and test cohort, respectively.

CONCLUSION

This study has developed and validated a combined nomogram, a visual tool that integrates CT radiomics features with clinical indicators and serum tumor biomarkers. This innovative model facilitates the differentiation of micropapillary or solid components within lung adenocarcinoma and achieves a higher AUC, indicating superior predictive accuracy.

Computed Tomography-derived intratumoral and peritumoral radiomics in predicting EGFR mutation in lung adenocarcinoma

OBJECTIVE

To investigate the value of Computed Tomography (CT) radiomics derived from different peritumoral volumes of interest (VOIs) in predicting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients.

MATERIALS AND METHODS

A retrospective cohort of 779 patients who had pathologically confirmed lung adenocarcinoma were enrolled. 640 patients were randomly divided into a training set, a validation set, and an internal testing set (3:1:1), and the remaining 139 patients were defined as an external testing set. The intratumoral VOI (VOI_I) was manually delineated on the thin-slice CT images, and seven peritumoral VOIs (VOI_P) were automatically generated with 1, 2, 3, 4, 5, 10, and 15 mm expansion along the VOI_I. 1454 radiomic features were extracted from each VOI. The t-test, the least absolute shrinkage and selection operator (LASSO), and the minimum redundancy maximum relevance (mRMR) algorithm were used for feature selection, followed by the construction of radiomics models (VOI_I model, VOI_P model and combined model). The performance of the models were evaluated by the area under the curve (AUC).

RESULTS

399 patients were classified as EGFR mutant (EGFR+), while 380 were wild-type (EGFR-). In the training and validation sets, internal and external testing sets, VOI4 (intratumoral and peritumoral 4 mm) model achieved the best predictive performance, with AUCs of 0.877, 0.727, and 0.701, respectively, outperforming the VOI_I model (AUCs of 0.728, 0.698, and 0.653, respectively).

CONCLUSIONS

Radiomics extracted from peritumoral region can add extra value in predicting EGFR mutation status of lung adenocarcinoma patients, with the optimal peritumoral range of 4 mm.

Current state of radiomics in hepatobiliary and pancreatic malignancies

Rising in incidence, hepatobiliary and pancreatic (HPB) cancers continue to exhibit dismal long-term survival. The overall poor prognosis of HPB cancers is reflective of the advanced stage at which most patients are diagnosed. Late diagnosis is driven by the often-asymptomatic nature of these diseases, as well as a dearth of screening modalities. Additionally, standard imaging modalities fall short of providing accurate and detailed information regarding specific tumor characteristics, which can better inform surgical planning and sequencing of systemic therapy. Therefore, precise therapeutic planning must be delayed until histopathological examination is performed at the time of resection. Given the current shortcomings in the management of HPB cancers, investigations of numerous noninvasive biomarkers, including circulating tumor cells and DNA, proteomics, immunolomics, and radiomics, are underway. Radiomics encompasses the extraction and analysis of quantitative imaging features. Along with summarizing the general framework of radiomics, this review synthesizes the state of radiomics in HPB cancers, outlining its role in various aspects of management, present limitations, and future applications for clinical integration. Current literature underscores the utility of radiomics in early detection, tumor characterization, therapeutic selection, and prognostication for HPB cancers. Seeing as single-center, small studies constitute the majority of radiomics literature, there is considerable heterogeneity with respect to steps of the radiomics workflow such as segmentation, or delineation of the region of interest on a scan. Nonetheless, the introduction of the radiomics quality score (RQS) demonstrates a step towards greater standardization and reproducibility in the young field of radiomics. Altogether, in the setting of continually improving artificial intelligence algorithms, radiomics represents a promising biomarker avenue for promoting enhanced and tailored management of HPB cancers, with the potential to improve long-term outcomes for patients.

Improving radiology workflow using ChatGPT and artificial intelligence

Artificial Intelligence is a branch of computer science that aims to create intelligent machines capable of performing tasks that typically require human intelligence. One of the branches of artificial intelligence is natural language processing, which is dedicated to studying the interaction between computers and human language. ChatGPT is a sophisticated natural language processing tool that can understand and respond to complex questions and commands in natural language. Radiology is a vital aspect of modern medicine that involves the use of imaging technologies to diagnose and treat medical conditions artificial intelligence, including ChatGPT, can be integrated into radiology workflows to improve efficiency, accuracy, and patient care. ChatGPT can streamline various radiology workflow steps, including patient registration, scheduling, patient check-in, image acquisition, interpretation, and reporting. While ChatGPT has the potential to transform radiology workflows, there are limitations to the technology that must be addressed, such as the potential for bias in artificial intelligence algorithms and ethical concerns. As technology continues to advance, ChatGPT is likely to become an increasingly important tool in the field of radiology, and in healthcare more broadly.

Machine learning for differentiation of lipid-poor adrenal adenoma and subclinical pheochromocytoma based on multiphase CT imaging radiomics

BACKGROUND

There is a paucity of research investigating the application of machine learning techniques for distinguishing between lipid-poor adrenal adenoma (LPA) and subclinical pheochromocytoma (sPHEO) based on radiomic features extracted from non-contrast and dynamic contrast-enhanced computed tomography (CT) scans of the abdomen.

METHODS

We conducted a retrospective analysis of multiphase spiral CT scans, including non-contrast, arterial, venous, and delayed phases, as well as thin- and thick-thickness images from 134 patients with surgically and pathologically confirmed. A total of 52 patients with LPA and 44 patients with sPHEO were randomly assigned to training/testing sets in a 7:3 ratio. Additionally, a validation set was comprised of 22 LPA cases and 16 sPHEO cases from two other hospitals. We used 3D Slicer and PyRadiomics to segment tumors and extract radiomic features, respectively. We then applied T-test and least absolute shrinkage and selection operator (LASSO) to select features. Six binary classifiers, including K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP), were employed to differentiate LPA from sPHEO. Receiver operating characteristic (ROC) curves and area under the curve (AUC) values were compared using DeLong's method.

RESULTS

All six classifiers showed good diagnostic performance for each phase and slice thickness, as well as for the entire CT data, with AUC values ranging from 0.706 to 1. Non-contrast CT densities of LPA were significantly lower than those of sPHEO (P < 0.001). However, using the optimal threshold for non-contrast CT density, sensitivity was only 0.743, specificity 0.744, and AUC 0.828. Delayed phase CT density yielded a sensitivity of 0.971, specificity of 0.641, and AUC of 0.814. In radiomics, AUC values for the testing set using non-contrast CT images were: KNN 0.919, LR 0.979, DT 0.835, RF 0.967, SVM 0.979, and MLP 0.981. In the validation set, AUC values were: KNN 0.891, LR 0.974, DT 0.891, RF 0.964, SVM 0.949, and MLP 0.979.

CONCLUSIONS

The machine learning model based on CT radiomics can accurately differentiate LPA from sPHEO, even using non-contrast CT data alone, making contrast-enhanced CT unnecessary for diagnosing LPA and sPHEO.

Review of the use of radiomics to assess the risk of recurrence in early-stage non-small cell lung cancer

Background and Objective

Radiomics is an emerging field of advanced image analysis that has shown promise as a non-invasive, companion diagnostic in predicting clinical outcomes and response assessments in solid tumors. Radiomics aims to extract high-content information from medical images not visible to the naked eye, especially in early-stage non-small cell lung cancer (NSCLC) patients. Although these patients are being identified by early detection programs, it remains unclear which patients would benefit from adjuvant treatment versus active surveillance. Having a radiomic signature(s) that could predict early recurrence would be beneficial. In this review, an overview of the basic radiomic approaches used to evaluate solid tumors on radiologic scans, including NSCLC is provided followed by a review of relevant literature that supports the use of radiomics to help predict tumor recurrence in early-stage NSCLC patients.

Methods

A review of the radiomic literature from 1985 to present focusing on the prediction of disease recurrence in early-stage NSCLC was conducted. PubMed database was searched using key terms for radiomics and NSCLC. A total of 41 articles were identified and 13 studies were considered suitable for inclusion based upon study population, patient number (n>50), use of well described radiomic methodologies, suitable model building features, and well-defined testing/training and validation where feasible.

Key Content and Findings

Examples of using radiomics in early-stage NSCLC patients will be presented, where disease free survival is a primary consideration. A summary of the findings demonstrates the importance of both the intratumor and peritumoral radiomic signals as a marker of outcomes.

Conclusions

The value of radiomic information for predicting disease recurrence in early-stage NSCLC patients is accumulating. However, overcoming several challenges along with the lack of prospective trials, has inhibited it use as a clinical decision-making support tool in early-stage NSCLC.

Associations between Vertebral Localized Contrast Changes and Adjacent Annular Fissures in Patients with Low Back Pain: A Radiomics Approach

Low back pain (LBP) is multifactorial and associated with various spinal tissue changes, including intervertebral disc fissures, vertebral pathology, and damaged endplates. However, current radiological markers lack specificity and individualized diagnostic capability, and the interactions between the various markers are not fully clear. Radiomics, a data-driven analysis of radiological images, offers a promising approach to improve evaluation and deepen the understanding of spinal changes related to LBP. This study investigated possible associations between vertebral changes and annular fissures using radiomics. A dataset of 61 LBP patients who underwent conventional magnetic resonance imaging followed by discography was analyzed. Radiomics features were extracted from segmented vertebrae and carefully reduced to identify the most relevant features associated with annular fissures. The results revealed three important texture features that display concentrated high-intensity gray levels, extensive regions with elevated gray levels, and localized areas with reduced gray levels within the vertebrae. These features highlight patterns within vertebrae that conventional classification systems cannot reflect on distinguishing between vertebrae adjacent to an intervertebral disc with or without an annular fissure. As such, the present study reveals associations that contribute to the understanding of pathophysiology and may provide improved diagnostics of LBP.

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients

PURPOSE

To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery.

MATERIALS AND METHODS

Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21-27 mm³) and binning (32-128 grey levels) in a 15 parameter's sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR.

RESULTS

Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60-0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08).

CONCLUSIONS

The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

Radiomics and Radiogenomics in Pelvic Oncology: Current Applications and Future Directions

Radiomics refers to the conversion of medical imaging into high-throughput, quantifiable data in order to analyse disease patterns, guide prognosis and aid decision making. Radiogenomics is an extension of radiomics that combines conventional radiomics techniques with molecular analysis in the form of genomic and transcriptomic data, serving as an alternative to costly, labour-intensive genetic testing. Data on radiomics and radiogenomics in the field of pelvic oncology remain novel concepts in the literature. We aim to perform an up-to-date analysis of current applications of radiomics and radiogenomics in the field of pelvic oncology, particularly focusing on the prediction of survival, recurrence and treatment response. Several studies have applied these concepts to colorectal, urological, gynaecological and sarcomatous diseases, with individual efficacy yet poor reproducibility. This article highlights the current applications of radiomics and radiogenomics in pelvic oncology, as well as the current limitations and future directions. Despite a rapid increase in publications investigating the use of radiomics and radiogenomics in pelvic oncology, the current evidence is limited by poor reproducibility and small datasets. In the era of personalised medicine, this novel field of research has significant potential, particularly for predicting prognosis and guiding therapeutic decisions. Future research may provide fundamental data on how we treat this cohort of patients, with the aim of reducing the exposure of high-risk patients to highly morbid procedures.

A pilot study of MRI radiomics for high-risk prostate cancer stratification in 1.5 T MR-guided radiotherapy

PURPOSE

To investigate the potential value of MRI radiomics obtained from a 1.5 T MRI-guided linear accelerator (MR-LINAC) for D'Amico high-risk prostate cancer (PC) classification in MR-guided radiotherapy (MRgRT).

METHODS

One hundred seventy-six consecutive PC patients underwent 1.5 T MRgRT treatment were retrospectively enrolled. Each patient received one or two pretreatment T₂ -weighted MRI scans on a 1.5 T MR-LINAC. The endpoint was to differentiate high-risk from low/intermediate-risk PC based on D'Amico criteria using MRI-radiomics. Totally 1023 features were extracted from clinical target volume (CTV) and planning target volume (PTV). Intraclass correlation coefficient of scan-rescan repeatability, feature correlation, and recursive feature elimination were used for feature dimension reduction. Least absolute shrinkage and selection operator regression was employed for model construction. Receiver operating characteristic area under the curve (AUC) analysis was used for model performance assessment in both training and testing data.

RESULTS

One hundred and eleven patients fulfilled all criteria were finally included: 76 for training and 35 for testing. The constructed MRI-radiomics models extracted from CTV and PTV achieved the AUC of 0.812 and 0.867 in the training data, without significant difference (P = 0.083). The model performances remained in the testing. The sensitivity, specificity, and accuracy were 85.71%, 64.29%, and 77.14% for the PTV-based model; and 71.43%, 71.43%, and 71.43% for the CTV-based model. The corresponding AUCs were 0.718 and 0.750 (P = 0.091) for CTV- and PTV-based models.

CONCLUSION

MRI-radiomics obtained from a 1.5 T MR-LINAC showed promising results in D'Amico high-risk PC stratification, potentially helpful for the future PC MRgRT. Prospective studies with larger sample sizes and external validation are warranted for further verification.

Inconsistent Partitioning and Unproductive Feature Associations Yield Idealized Radiomic Models

Background Radiomics is the extraction of predefined mathematic features from medical images for the prediction of variables of clinical interest. While some studies report superlative accuracy of radiomic machine learning (ML) models, the published methodology is often incomplete, and the results are rarely validated in external testing data sets. Purpose To characterize the type, prevalence, and statistical impact of methodologic errors present in radiomic ML studies. Materials and Methods Radiomic ML publications were reviewed for the presence of performance-inflating methodologic flaws. Common flaws were subsequently reproduced with randomly generated features interpolated from publicly available radiomic data sets to demonstrate the precarious nature of reported findings. Results In an assessment of radiomic ML publications, the authors uncovered two general categories of data analysis errors: inconsistent partitioning and unproductive feature associations. In simulations, the authors demonstrated that inconsistent partitioning augments radiomic ML accuracy by 1.4 times from unbiased performance and that correcting for flawed methodologic results in areas under the receiver operating characteristic curve approaching a value of 0.5 (random chance). With use of randomly generated features, the authors illustrated that unproductive associations between radiomic features and gene sets can imply false causality for biologic phenomenon. Conclusion Radiomic machine learning studies may contain methodologic flaws that undermine their validity. This study provides a review template to avoid such flaws. © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Jacobs in this issue.

Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization

Background and purpose

Radiomics models trained with limited single institution data are often not reproducible and generalisable. We developed radiomics models that predict loco-regional recurrence within two years of radiotherapy with private and public datasets and their combinations, to simulate small and multi-institutional studies and study the responsiveness of the models to feature selection, machine learning algorithms, centre-effect harmonization and increased dataset sizes.

Materials and methods

562 patients histologically confirmed and treated for locally advanced head-and-neck cancer (LA-HNC) from two public and two private datasets; one private dataset exclusively reserved for validation. Clinical contours of primary tumours were not recontoured and were used for Pyradiomics based feature extraction. ComBat harmonization was applied, and LASSO-Logistic Regression (LR) and Support Vector Machine (SVM) models were built. 95% confidence interval (CI) of 1000 bootstrapped area-under-the-Receiver-operating-curves (AUC) provided predictive performance. Responsiveness of the models' performance to the choice of feature selection methods, ComBat harmonization, machine learning classifier, single and pooled data was evaluated.

Results

LASSO and SelectKBest selected 14 and 16 features, respectively; three were overlapping. Without ComBat, the LR and SVM models for three institutional data showed AUCs (CI) of 0.513 (0.481-0.559) and 0.632 (0.586-0.665), respectively. Performances following ComBat revealed AUCs of 0.559 (0.536-0.590) and 0.662 (0.606-0.690), respectively. Compared to single cohort AUCs (0.562-0.629), SVM models from pooled data performed significantly better at AUC = 0.680.

Conclusions

Multi-institutional retrospective data accentuates the existing variabilities that affect radiomics. Carefully designed prospective, multi-institutional studies and data sharing are necessary for clinically relevant head-and-neck cancer prognostication models.

Radiomics Applications in Head and Neck Tumor Imaging: A Narrative Review

Recent advances in machine learning and artificial intelligence technology have ensured automated evaluation of medical images. As a result, quantifiable diagnostic and prognostic biomarkers have been created. We discuss radiomics applications for the head and neck region in this paper. Molecular characterization, categorization, prognosis and therapy recommendation are given special consideration. In a narrative manner, we outline the fundamental technological principles, the overall idea and usual workflow of radiomic analysis and what seem to be the present and potential challenges in normal clinical practice. Clinical oncology intends for all of this to ensure informed decision support for personalized and useful cancer treatment. Head and neck cancers present a unique set of diagnostic and therapeutic challenges. These challenges are brought on by the complicated anatomy and heterogeneity of the area under investigation. Radiomics has the potential to address these barriers. Future research must be interdisciplinary and focus on the study of certain oncologic functions and outcomes, with external validation and multi-institutional cooperation in order to achieve this.

Determining the reliable feature change in longitudinal radiomics studies: A methodological approach using the reliable change index

PURPOSE

Determination of reliable change of radiomics feature over time is essential and vital in delta-radiomics, but has not yet been rigorously examined. This study attempts to propose a methodological approach using reliable change index (RCI), a statistical metric to determine the reliability of quantitative biomarker changes by accounting for the baseline measurement standard error, in delta-radiomics. The use of RCI was demonstrated with the MRI data acquired from a group of prostate cancer (PCa) patients treated by 1.5 T MRI-guided radiotherapy (MRgRT).

METHODS

Fifty consecutive PCa patients who underwent five-fractionated MRgRT were retrospectively included, and 1023 radiomics features were extracted from the clinical target volume (CTV) and planning target volume (PTV). The two MRI datasets acquired at the first fraction (MRI11 and MRI21) were used to calculate the baseline feature reliability against image acquisition using intraclass correlation coefficient (ICC). The RCI was constructed based on the baseline feature measurement standard deviation, ICC, and feature value differences at two time points between the fifth (MRI51) and the first fraction MRI (MRI11). The reliable change of features was determined in each patient only if the calculated RCI was over 1.96 or smaller than -1.96. The feature changes between MRI51 and MRI11 were correlated to two patient-reported quality-of-life clinical endpoints of urinary domain summary score (UDSS) and bowel domain summary score (BDSS) in 35 patients using the Spearman correlation test. Only the significant correlations between a feature that was reliably changed in ≥7 patients (20%) by RCI and an endpoint were considered as true significant correlations.

RESULTS

The 352 (34.4%) and 386 (37.7%) features among all 1023 features were determined by RCI to be reliably changed in more than five (10%) patients in the CTV and PTV, respectively. Nineteen features were found reliably changed in the CTV and 31 features in the PTV, respectively, in 10 (20%) or more patients. These features were not necessarily associated with significantly different longitudinal feature values (group p-value < 0.05). Most reliably changed features in more than 10 patients had excellent or good baseline test-retest reliability ICC, while none showed poor reliability. The RCI method ruled out the features to be reliably changed when substantial feature measurement bias was presented. After applying the RCI criterion, only four and five true significant correlations were confirmed with UDSS and BDSS in the CTV, respectively, with low true significance correlation rates of 10.8% (4/37) and 17.9% (5/28). No true significant correlations were found in the PTV.

CONCLUSIONS

The RCI method was proposed for delta-radiomics and demonstrated using PCa MRgRT data. The RCI has advantages over some other statistical metrics commonly used in the previous delta-radiomics studies, and is useful to reliably identify the longitudinal radiomics feature change on an individual basis. This proposed RCI method should be helpful for the development of essential feature selection methodology in delta-radiomics.

Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT

OBJECTIVE

To evaluate whether an imaging classifier for radiology practice can improve lung nodule classification and follow-up.

METHODS

A machine learning classifier was developed and trained using imaging data from the National Lung Screening Trial (NSLT) to produce a malignancy risk score (malignancy Similarity Index [mSI]) for individual lung nodules. In addition to NLST cohorts, external cohorts were developed from a tertiary referral lung cancer screening program data set and an external nonscreening data set of all nodules detected on CT. Performance of the mSI combined with Lung-RADS was compared with Lung-RADS alone and the Mayo and Brock risk calculators.

RESULTS

We analyzed 963 subjects and 1,331 nodules across these cohorts. The mSI was comparable in accuracy (area under the curve = 0.89) to existing clinical risk models (area under the curve = 0.86-0.88) and independently predictive in the NLST cohort of 704 nodules. When compared with Lung-RADS, the mSI significantly increased sensitivity across all cohorts (25%-117%), with significant increases in specificity in the screening cohorts (17%-33%). When used in conjunction with Lung-RADS, use of mSI would result in earlier diagnoses and reduced follow-up across cohorts, including the potential for early diagnosis in 42% of malignant NLST nodules from prior-year CT scans.

CONCLUSION

A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI added predictive value independent of existing radiological and clinical variables. These results suggest the generalizability and potential clinical impact of a tool that is straightforward to implement in practice.

Translating Data Science Results into Precision Oncology Decisions: A Mini Review

While reviewing and discussing the potential of data science in oncology, we emphasize medical imaging and radiomics as the leading contextual frameworks to measure the impacts of Artificial Intelligence (AI) and Machine Learning (ML) developments. We envision some domains and research directions in which radiomics should become more significant in view of current barriers and limitations.

Feature selection methods and predictive models in CT lung cancer radiomics

Radiomics is a technique that extracts quantitative features from medical images using data-characterization algorithms. Radiomic features can be used to identify tissue characteristics and radiologic phenotyping that is not observable by clinicians. A typical workflow for a radiomics study includes cohort selection, radiomic feature extraction, feature and predictive model selection, and model training and validation. While there has been increasing attention given to radiomic feature extraction, standardization, and reproducibility, currently, there is a lack of rigorous evaluation of feature selection methods and predictive models. Herein, we review the published radiomics investigations in CT lung cancer and provide an overview of the commonly used radiomic feature selection methods and predictive models. We also compare limitations of various methods in clinical applications and present sources of uncertainty associated with those methods. This review is expected to help raise awareness of the impact of radiomic feature and model selection methods on the integrity of radiomics studies.

Advances in CT features and radiomics of checkpoint inhibitor-related pneumonitis: A short review

Checkpoint inhibitor-related pneumonitis (CIP) is a complication of immunotherapy for malignant tumors that severely limits the treatment cycles as well as endangers patients' health. The chest CT imaging features or typing of CIP and the application of radiomics will contribute to the precise prevention, early diagnosis and instant treatment of CIP. This article reviews the advances in the CT features and the application of radiomics in CIP.

A review of radiomics and genomics applications in cancers: the way towards precision medicine

The application of radiogenomics in oncology has great prospects in precision medicine. Radiogenomics combines large volumes of radiomic features from medical digital images, genetic data from high-throughput sequencing, and clinical-epidemiological data into mathematical modelling. The amalgamation of radiomics and genomics provides an approach to better study the molecular mechanism of tumour pathogenesis, as well as new evidence-supporting strategies to identify the characteristics of cancer patients, make clinical decisions by predicting prognosis, and improve the development of individualized treatment guidance. In this review, we summarized recent research on radiogenomics applications in solid cancers and presented the challenges impeding the adoption of radiomics in clinical practice. More standard guidelines are required to normalize radiomics into reproducible and convincible analyses and develop it as a mature field.

Resampling and harmonization for mitigation of heterogeneity in image parameters of baseline scans

Our study investigates the effects of heterogeneity in image parameters on the reproducibility of prognostic performance of models built using radiomic biomarkers. We compare the prognostic performance of models derived from the heterogeneity-mitigated features with that of models obtained from raw features, to assess whether reproducibility of prognostic scores improves upon application of our methods. We used two datasets: The Breast I-SPY1 dataset-Baseline DCE-MRI scans of 156 women with locally advanced breast cancer, treated with neoadjuvant chemotherapy, publicly available via The Cancer Imaging Archive (TCIA); The NSCLC IO dataset-Baseline CT scans of 107 patients with stage 4 non-small cell lung cancer (NSCLC), treated with pembrolizumab immunotherapy at our institution. Radiomic features (n = 102) are extracted from the tumor ROIs. We use a variety of resampling and harmonization scenarios to mitigate the heterogeneity in image parameters. The patients were divided into groups based on batch variables. For each group, the radiomic phenotypes are combined with the clinical covariates into a prognostic model. The performance of the groups is assessed using the c-statistic, derived from a Cox proportional hazards model fitted on all patients within a group. The heterogeneity-mitigation scenario (radiomic features, derived from images that have been resampled to minimum voxel spacing, are harmonized using the image acquisition parameters as batch variables) gave models with highest prognostic scores (for e.g., IO dataset; batch variable: high kernel resolution-c-score: 0.66). The prognostic performance of patient groups is not comparable in case of models built using non-heterogeneity mitigated features (for e.g., I-SPY1 dataset; batch variable: small pixel spacing-c-score: 0.54, large pixel spacing-c-score: 0.65). The prognostic performance of patient groups is closer in case of heterogeneity-mitigated scenarios (for e.g., scenario-harmonize by voxel spacing parameters: IO dataset; thin slice-c-score: 0.62, thick slice-c-score: 0.60). Our results indicate that accounting for heterogeneity in image parameters is important to obtain more reproducible prognostic scores, irrespective of image site or modality. For non-heterogeneity mitigated models, the prognostic scores are not comparable across patient groups divided based on batch variables. This study can be a step in the direction of constructing reproducible radiomic biomarkers, thus increasing their application in clinical decision making.