Applications and limitations of radiomics

Application of radiomics in acute and severe non-neoplastic diseases: A literature review

Radiomics involves the integration of computer technology, big data analysis, and clinical medicine. Currently, there have been initial advancements in the fields of acute cerebrovascular disease and cardiovascular disease. The objective of radiomics is to extract quantitative features from medical images for analysis to predict the risk or treatment outcome, help in differential diagnosis, and guide clinical decisions and management. Radiomics applied research has reached a more advanced stage yet encounters several obstacles, including the need for standardization of radiomics features and alignment with treatment requirements for acute and severe illnesses. Future research should aim to seamlessly incorporate radiomics with various disciplines, leverage big data and artificial intelligence advancements, cater to the requirements of acute and critical medicine, and enhance the effectiveness of technological innovation and application in diagnosing and treating acute and critical illnesses.

CT-based radiomics model for predicting perineural invasion status in gastric cancer

PURPOSE

Perineural invasion (PNI) is an independent risk factor for poor prognosis in gastric cancer (GC) patients. This study aimed to develop and validate predictive models based on CT imaging and clinical features to predict PNI status in GC patients.

METHODS

This retrospective study included 291 GC patients (229 in the training cohort and 62 in the validation cohort) who underwent gastrectomy between January 2020 and August 2022. The clinical data and preoperative abdominal contrast-enhanced computed tomography (CECT) images were collected. Radiomics features were extracted from the venous phase of CECT images. The intraclass correlation coefficient (ICC), Pearson correlation coefficient, and t-test were applied for radiomics feature selection. The random forest algorithm was used to construct a radiomics signature and calculate the radiomics feature score (Rad-score). A hybrid model was built by aggregating the Rad-score and clinical predictors. The area under the receiver operating characteristic curve (ROC) and decision curve analysis (DCA) were used to evaluate the prediction performance of the radiomics, clinical, and hybrid models.

RESULTS

A total of 994 radiomics features were extracted from the venous phase images of each patient. Finally, 5 radiomics features were selected and used to construct a radiomics signature. The hybrid model demonstrated strong predictive ability for PNI, with AUCs of 0.833 (95% CI: 0.779-0.887) and 0.806 (95% CI: 0.628-0.983) in the training and validation cohorts, respectively. The DCA showed that the hybrid model had good clinical utility.

CONCLUSION

We established three models, and the hybrid model that combined the Rad-score and clinical predictors had a high potential for predicting PNI in GC patients.

Machine learning-based multiparametric CT radiomics for predicting microvascular invasion before nephrectomy in clear cell renal cell carcinoma

PURPOSE

This study aimed to investigate the value of integrating computed tomography (CT)-based tumor radiomics features with clinical parameters for preoperative prediction of microvascular invasion (MVI) in clear cell renal cell carcinoma (ccRCC).

METHODS

We retrospectively analyzed data from a single-center cohort of ccRCC patients. Radiomics features were extracted from preoperative multiphasic CT scans (unenhanced, corticomedullary, and nephrographic phases). Following dimensionality reduction and feature selection, eight machine learning algorithms were evaluated to identify the optimal radiomics model. Independent clinical predictors were determined through univariate and multivariate analyses. A nomogram integrating the radiomics signature (rad-score) with significant clinical parameters was subsequently developed. Model performance was assessed using the area under the curve (AUC), decision curve analysis (DCA), and calibration curve analysis (CAC).

RESULTS

Of 143 initially enrolled patients, 110 met inclusion criteria after screening, with 5502 radiomics features extracted. The support vector classifier (SVM) model demonstrated the highest discriminative ability, achieving mean AUCs of 0.976 (training cohort) and 0.892 (test cohort), significantly outperforming the clinical model (training AUC = 0.935, test AUC = 0.933). The nomogram showed superior diagnostic performance, with AUCs of 0.958 (test). DCA and CAC confirmed its clinical utility and robustness.

CONCLUSIONS

Multiparametric CT radiomics models enable non-invasive prediction of MVI status in ccRCC, with the SVM-based algorithm showing optimal performance. The integrated nomogram provides excellent and consistent diagnostic accuracy, offering a valuable preoperative tool for clinical decision-making.

Multi-sequence MRI based radiomics nomogram for prediction expression of programmed death ligand 1 in thymic epithelial tumor

Background

High expression levels of programmed death receptor 1 (PD-1) and its ligand 1 (PD-L1) have been observed in thymic epithelial tumors (TET), suggesting their potential as prognostic indicators for disease progression and the effectiveness of immunotherapy in TET. The conventional method obtaining PD-L1 was challenging due to invasive sampling and tumor heterogeneity.

Methods

A total of 124 patients with pathologically confirmed TET (57 PD-L1 positive, 67 PD-L1 negative) were retrospectively enrolled and allocated into training and validation cohorts in a ratio of 7:3. Radiomics features were extracted from T1-weighted, T2-weighted fat suppression, and apparent diffusion coefficient (ADC) map images to establish a radiomics signature in the training cohort. Multivariate logistic regression analysis was conducted to develop a combined radiomics nomogram that incorporated clinical, conventional MR features, or ADC model for evaluation purposes. The performance of each model was compared using receiver operating characteristics analysis, while discrimination, calibration, and clinical efficiency of the combined radiomics nomogram were assessed.

Results

The radiomics signature, consisting of four features, demonstrated a favorable ability to predict and differentiate between PD-L1 positive and negative TET patients. The combined radiomics nomogram, which incorporates the peri-cardial invasion sign, ADC value, WHO classification, and radiomics signature, showed excellent performance (training cohort: area under the curve [AUC] = 0.903; validation cohorts: AUC = 0.894). The calibration curve and decision curve analysis further confirmed the clinical usefulness of this combined model. The decision curve analysis demonstrated the clinical utility of the integrated radiomics nomogram.

Conclusions

The radiomics signature serves as a valuable tool for predicting the PD-L1 status of TET patients. Furthermore, the integration of radiomics nomogram enhances the personalized prediction capability.

Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model

Background

Colorectal cancer is a prevalent malignancy with a significant risk of metastasis, including to bones, which severely impacts patient outcomes. Accurate prediction of bone metastasis risk is crucial for optimizing treatment strategies and improving prognosis.

Purpose

This study aims to develop a predictive model combining radiomics and Vision Transformer (ViT) deep learning techniques to assess the risk of bone metastasis in colorectal cancer patients using both plain and contrast-enhanced CT images.

Materials and methods

We conducted a retrospective analysis of 155 colorectal cancer patients, including 81 with bone metastasis and 74 without. Radiomic features were extracted from segmented tumors on both plain and contrast-enhanced CT images. LASSO regression was applied to select key features, which were then used to build traditional machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, LightGBM, and XGBoost. Additionally, a dual-modality ViT model was trained on the same CT images, with a late fusion strategy employed to combine outputs from the different modalities. Model performance was evaluated using AUC-ROC, accuracy, sensitivity, and specificity, and differences were statistically assessed using DeLong's test.

Results

The ViT model demonstrated superior predictive performance, achieving an AUC of 0.918 on the test set, significantly outperforming all traditional radiomics-based models. The SVM model, while the best among traditional models, still underperformed compared to the ViT model. The ViT model's strength lies in its ability to capture complex spatial relationships and long-range dependencies within the imaging data, which are often missed by traditional models. DeLong's test confirmed the statistical significance of the ViT model's enhanced performance, highlighting its potential as a powerful tool for predicting bone metastasis risk in colorectal cancer patients.

Conclusion

The integration of radiomics with ViT-based deep learning offers a robust and accurate method for predicting bone metastasis risk in colorectal cancer patients. The ViT model's ability to analyze dual-modality CT imaging data provides greater precision in risk assessment, which can improve clinical decision-making and personalized treatment strategies. These findings underscore the promise of advanced deep learning models in enhancing the accuracy of metastasis prediction. Further validation in larger, multicenter studies is recommended to confirm the generalizability of these results.

Deep learning network based on high-resolution magnetic resonance vessel wall imaging combined with attention mechanism for predicting stroke recurrence in patients with symptomatic intracranial atherosclerosis

Background

High-resolution magnetic resonance vessel wall imaging (HR-VWI) offers enhanced visualization of vascular structures, thereby facilitating the deep learning (DL) network's acquisition of more extensive and detailed image information. This study aimed to develop a high-precision integrated model leveraging DL with an attention mechanism based on HR-VWI for predicting recurrent stroke in patients with symptomatic intracranial atherosclerotic stenosis (sICAS).

Methods

A retrospective study was conducted involving 363 sICAS patients who underwent HR-VWI, with data divided into a training set (n=254) from Center 1 (The First Affiliated Hospital of Xinxiang Medical University) and a test set (n=109) from Center 2 (The Sixth People's Hospital of Shanghai Jiao Tong University). Two convolutional neural network (CNN) models, ResNet50 and DenseNet169, were employed as feature extractors to capture image information from culprit plaques in HR-VWI. Integrating the Transformer attention mechanism, an advanced ensemble model, Trans-CNN, was constructed to predict stroke recurrence in sICAS patients. Model performance was evaluated using receiver operating characteristic (ROC) curves, with DeLong's test for comparing models. Additionally, decision curve analysis (DCA) and calibration curves were utilized to assess the model's practical and clinical value.

Results

Trans-CNN demonstrated superior predictive performance, outperforming other models in both the training and test sets. Specifically, in the training set, Trans-CNN achieved an area under the curve (AUC) of 0.951 [95% confidence interval (CI): 0.923-0.974], accuracy of 0.880 (95% CI: 0.797-0.937), sensitivity of 0.900 (95% CI: 0.836-1.000), and specificity of 0.882 (95% CI: 0.757-0.948). Similarly, in the test set, it achieved an AUC of 0.912 (95% CI: 0.839-0.969), accuracy of 0.858 (95% CI: 0.743-0.936), sensitivity of 0.880 (95% CI: 0.693-1.000), and specificity of 0.810 (95% CI: 0.690-0.976). The AUC improvement of Trans-CNN over all other models was statistically significant (DeLong's test, P<0.05). Calibration curve analysis revealed good agreement between predicted probabilities and observed outcomes in both sets. DCA further underscored the potential value of Trans-CNN in guiding clinical decision-making.

Conclusions

The integrated model combining DL with an attention mechanism based on HR-VWI exhibits excellent performance in assessing the risk of stroke recurrence in sICAS patients. This advancement holds significant potential in assisting clinicians in diagnosis and developing individualized treatment strategies.

Radiomic Cardiac MRI Signatures for Predicting Ventricular Arrhythmias in Patients With Nonischemic Dilated Cardiomyopathy

BACKGROUND

Risk stratification in patients with nonischemic dilated cardiomyopathy (DCM) remains challenging. Although late gadolinium enhancement (LGE) cardiovascular magnetic resonance is recognized as a major risk factor for ventricular tachycardia/ventricular fibrillation (VT/VF), the prognostic value of LGE radiomics is unknown.

OBJECTIVES

The purpose of this study was to investigate if radiomic analysis of LGE images can improve arrhythmia risk stratification in patients with DCM beyond current clinical and imaging markers.

METHODS

In a 2-center retrospective study, patients with DCM were identified among those who received primary prevention implantable cardioverter-defibrillators (ICDs) according to the clinical guidelines and had a cardiovascular magnetic resonance before ICD implantation. The study included patients with DCM from the Cleveland Clinic Foundation for model development and patients with DCM from Beth Israel Deaconess Medical Center for external validation. Left ventricular myocardial radiomic features were extracted from LGE images. The primary outcome was appropriate ICD intervention defined as shock or antitachycardia pacing for VT/VF. Consensus clustering and pairwise correlation were used to identify the radiomic signature. To assess the prognostic value of LGE radiomics, we built 2 logistic regression models using the development data: 1) model 1, including clinical risk factors and scar presence and 2) model 2, which combines model 1 and LGE radiomics.

RESULTS

In total, 270 patients with DCM (61% male, age 58 ± 13 years) in development data and 113 patients with DCM (71% male, age 55 ± 14 years) in external validation were included. VT/VF occurred in 40 (15%) patients in development and 16 (15%) in external validation cohorts over a median follow-up period of 4.0 (IQR: 2.5-6.1) and 2.6 (IQR: 1.2-4.1) years, respectively. Consensus clustering and pairwise correlation revealed 3 distinct radiomic features. Model 2 showed a higher C-statistic than model 1 (0.71 [95% CI: 0.62-0.80] vs 0.61 [95% CI: 0.53-0.71]; P = 0.028 in development and 0.70 [95% CI: 0.59-0.85] vs 0.61 [95% CI: 0.46-0.77]; P = 0.025 in external validation). This also significantly improved risk stratification with a continuous net reclassification index of 0.60 [95% CI: 0.29-0.91; P < 0.001] in development and of 0.29 [95% CI: 0.26-0.56; P = 0.03] in external validation. Additionally, 1 radiomic feature, namely the gray level co-occurrence matrix autocorrelation, was an independent predictor of VT/VF in both development (HR: 1.45 [95% CI: 1.10-1.91]; P = 0.01) and in external validation (HR: 2.38 [95% CI: 1.28-4.42]; P = 0.01).

CONCLUSIONS

In this proof-of-concept study, radiomic analysis of LGE images provides additional prognostic value beyond LGE presence in predicting arrhythmia in patients with DCM.

Predicting Hospitalization Length in Geriatric Patients Using Artificial Intelligence and Radiomics

(1) Background: Predicting hospitalization length for COVID-19 patients is crucial for optimizing resource allocation and patient management. Radiomics, combined with machine learning (ML), offers a promising approach by extracting quantitative imaging features from CT scans. The aim of the present study is to use and adapt machine learning (ML) architectures, exploiting CT radiomics information, and analyze algorithms' capability to predict hospitalization at the time of patient admission. (2) Methods: The original CT lung images of 168 COVID-19 patients underwent two segmentations, isolating the ground glass area of the lung parenchyma. After an isotropic voxel resampling and wavelet and Laplacian of Gaussian filtering, 92 intensity and texture radiomics features were extracted. Feature reduction was conducted by applying a last absolute shrinkage and selection operator (LASSO) to the radiomic features set. Three ML classification algorithms, linear support vector machine (LSVM), medium neural network (MNN), and ensemble subspace discriminant (ESD), were trained and validated through a 5-fold cross-validation technique. Model performance was assessed using accuracy, sensitivity, specificity, precision, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). (3) Results: The LSVM classifier achieved the highest predictive performance, with an accuracy of 86.0% and an AUC of 0.93. However, reliable outcomes are also registered when MNN and ESD architecture are used. (4) Conclusions: The study shows that radiomic features can be used to build a machine learning framework for predicting patient hospitalization duration. The findings suggest that radiomics-based ML models can accurately predict COVID-19 hospitalization length.

Omics sciences for cervical cancer precision medicine from the perspective of the tumor immune microenvironment

Immunotherapies have demonstrated notable clinical benefits in the treatment of cervical cancer (CC). However, the development of therapeutic resistance and diverse adverse effects in immunotherapy stem from complex interactions among biological processes and factors within the tumor immune microenvironment (TIME). Advanced omic technologies offer novel insights into a more expansive and thorough layer of the TIME. Furthermore, integrating multidimensional omics within the frameworks of systems biology and computational methodologies facilitates the generation of interpretable data outputs to characterize the clinical and biological trajectories of tumor behavior. In this review, we present advanced omics technologies that utilize various clinical samples to address scientific inquiries related to immunotherapies for CC, highlighting their utility in identifying metastasis dissemination, recurrence risk, and therapeutic resistance in patients treated with immunotherapeutic approaches. This review elaborates on the strategy for integrating multi-omics data through artificial intelligence algorithms. Additionally, an analysis of the obstacles encountered in the multi-omics analysis process and potential avenues for future research in this domain are presented.

Prediction of Chemotherapy Response in Locally Advanced Breast Cancer Patients at Pre-Treatment Using CT Textural Features and Machine Learning: Comparison of Feature Selection Methods

RATIONALE

Neoadjuvant chemotherapy (NAC) is a key element of treatment for locally advanced breast cancer (LABC). Predicting the response of NAC for patients with LABC before initiating treatment would be valuable to customize therapies and ensure the delivery of effective care.

OBJECTIVE

Our objective was to develop predictive measures of tumor response to NAC prior to starting for LABC using machine learning and textural computed tomography (CT) features in different level of frequencies.

MATERIALS AND METHODS

A total of 851 textural biomarkers were determined from CT images and their wavelet coefficients for 117 patients with LABC to evaluate the response to NAC. A machine learning pipeline was designed to classify response to NAC treatment for patients with LABC. For training predictive models, three models including all features (wavelet and original image features), only wavelet and only original-image features were considered. We determined features from CT images in different level of frequencies using wavelet transform. Additionally, we conducted a comparison of feature selection methods including mRMR, Relief, Rref QR decomposition, nonnegative matrix factorization and perturbation theory feature selection techniques.

RESULTS

Of the 117 patients with LABC evaluated, 82 (70%) had clinical-pathological response to chemotherapy and 35 (30%) had no response to chemotherapy. The best performance for hold-out data splitting was obtained using the KNN classifier using the Top-5 features, which were obtained by mRMR, for all features (accuracy = 77%, specificity = 80%, sensitivity = 56%, and balanced-accuracy = 68%). Likewise, the best performance for leave-one-out data splitting could be obtained by the KNN classifier using the Top-5 features, which was obtained by mRMR, for all features (accuracy = 75%, specificity = 76%, sensitivity = 62%, and balanced-accuracy = 72%).

CONCLUSIONS

The combination of original textural features and wavelet features results in a greater predictive accuracy of NAC response for LABC patients. This predictive model can be utilized to predict treatment outcomes prior to starting, and clinicians can use it as a recommender system to modify treatment.

Radiomics analysis of 18F-FDG PET/CT for visceral pleural invasion in non-small cell lung cancer with pleural attachment

AIM

This study aimed to establish and validate a preoperative model that integrates clinical factors and radiomic features from 2-[18F]-fluoro-2-deoxy-D-glucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) for predicting visceral pleural invasion (VPI) in non-small cell lung cancer (NSCLC) with radiological pleural attachment.

MATERIALS AND METHODS

A total of 974 NSCLC patients (408 with VPI-present and 566 with VPI-absent) were retrospectively included from two medical centres. Clinical data and PET/CT radiomic features were collected. The optimal predictors from these radiomic features were selected to create the radiomics score (Rad-score) for the PET/CT radiomics model. Significant clinical factors and Rad-scores were incorporated into a combined PET/CT radiomics-clinical model. The predictive performance of the models was assessed using receiver operating characteristic (ROC) analysis.

RESULTS

The combined PET/CT radiomics-clinical model predicted VPI status with areas under the ROC curve (AUCs) of 0.869, 0.858, and 0.863 in the training set (n=569), internal validation set (n=245), and external validation set (n=160), respectively. These were significantly higher than the AUCs of the PET/CT radiomics model, which were 0.828, 0.782, and 0.704 (all P<0.001). In patients with a maximum tumour diameter (Dmax) ≤ 3 cm (n=537) and in patients with adenocarcinoma (n=659), the AUCs of the combined model were 0.876 and 0.877, respectively. A nomogram based on the combined model was developed, with well-fitted calibration curves.

CONCLUSION

The combined PET/CT radiomics-clinical model provides an advantage in predicting VPI status in NSCLC with pleural attachment.

Ensemble of fine-tuned machine learning models for hysterectomy prediction in pregnant women using magnetic resonance images

Purpose

Identifying pregnant patients at high risk of hysterectomy before giving birth informs clinical management and improves outcomes. We aim to develop machine learning models to predict hysterectomy in pregnant women with placenta accreta spectrum (PAS).

Approach

We developed five machine learning models using information from magnetic resonance images and combined them with topographic maps and radiomic features to predict hysterectomy. The models were trained, optimized, and evaluated on data from 241 patients, in groups of 157, 24, and 60 for training, validation, and testing, respectively.

Results

We assessed the models individually as well as using an ensemble approach. When these models are combined, the ensembled model produced the best performance and achieved an area under the curve of 0.90, a sensitivity of 90.0%, and a specificity of 90.0% for predicting hysterectomy.

Conclusions

Various machine learning models were developed to predict hysterectomy in pregnant women with PAS, which may have potential clinical applications to help improve patient management.

Evaluating the prognostic value of radiomics and clinical features in metastatic prostate cancer using [68Ga]Ga-PSMA-11 PET/CT

Prostate cancer is a significant global health issue due to its high incidence and poor outcomes in metastatic disease. This study aims to develop models predicting overall survival for patients with metastatic biochemically recurrent prostate cancer, potentially helping to identify high-risk patients and enabling more tailored treatment options. A multi-centre cohort of 180 such patients underwent [68Ga]Ga-PSMA-11 PET/CT scans, with lesions semi-automatically segmented and radiomic features extracted from lesions. The analysis included two phases: univariable and multivariable. Univariable analysis used Kaplan-Meier curves and Cox proportional hazards models to correlate individual features with overall survival. Multivariable analysis used the LASSO Cox proportional hazards method to create 13 models: radiomics-only, clinical-only, and various combinations of radiomic and clinical features. Each model included six features and was bootstrapped 1000 times to obtain concordance indices with 95% confidence intervals, followed by optimism correction. In the univariable analysis, 6 out of 8 clinical features and 68 out of 89 radiomic features were significantly correlated with overall survival, including age, disease stage, total lesional uptake and total lesional volume. The optimism-corrected concordance indices from the multivariable models were 0.722 (95% CI 0.653-0.784) for the clinical model, 0.681 (95% CI 0.616-0.745) for the radiomics model, and 0.704 (95% CI 0.648-0.768) for the combined model with three clinical and three radiomic features, when extracting radiomic features from the largest lesion only. While univariable analysis showed significant prognostic value for many radiomic features, their integration into multivariable models did not improve predictive accuracy beyond clinical features alone.

Evaluating the impact of the Radiomics Quality Score: a systematic review and meta-analysis

OBJECTIVES

Conduct a systematic review and meta-analysis on the application of the Radiomics Quality Score (RQS).

MATERIALS AND METHODS

A search was conducted from January 1, 2022, to December 31, 2023, for systematic reviews which implemented the RQS. Identification of articles prior to 2022 was via a previously published review. Quality scores of individual radiomics papers, their associated criteria scores, and these scores from all readers were extracted. Errors in the application of RQS criteria were noted and corrected. The RQS of radiomics papers were matched with the publication date, imaging modality, and country, where available.

RESULTS

A total of 130 systematic reviews were included, and individual quality scores 117/130 (90.0%), criteria scores 98/130 (75.4%), and multiple reader data 24/130 (18.5%) were extracted. 3258 quality scores were correlated with the radiomics study date of publication. Criteria scoring errors were discovered in 39/98 (39.8%) of articles. Overall mean RQS was 9.4 ± 6.4 (95% CI, 9.1-9.6) (26.1% ± 17.8% (25.3%-26.7%)). Quality scores were positively correlated with publication year (Pearson R = 0.32, p < 0.01) and significantly higher after publication of the RQS (year < 2018, 5.6 ± 6.1 (5.1-6.1); year ≥ 2018, 10.1 ± 6.1 (9.9-10.4); p < 0.01). Only 233/3258 (7.2%) scores were ≥ 50% of the maximum RQS. Quality scores were significantly different across imaging modalities (p < 0.01). Ten criteria were positively correlated with publication year, and one was negatively correlated.

CONCLUSION

Radiomics study adherence to the RQS is increasing with time, although a vast majority of studies are developmental and rarely provide a high level of evidence to justify the clinical translation of proposed models.

KEY POINTS

Question What level of adherence to the Radiomics Quality Score have radiomics studies achieved to date, has it increased with time, and is it sufficient? Findings A meta-analysis of 3258 quality scores extracted from 130 review articles resulted in a mean score of 9.4 ± 6.4. Quality scores were positively correlated with time. Clinical relevance Although quality scores of radiomics studies have increased with time, many studies have not demonstrated sufficient evidence for clinical translation. As new appraisal tools emerge, the current role of the Radiomics Quality Score may change.

Multi-parametric MRI Habitat Radiomics Based on Interpretable Machine Learning for Preoperative Assessment of Microsatellite Instability in Rectal Cancer

RATIONALE AND OBJECTIVES

This study constructed an interpretable machine learning model based on multi-parameter MRI sub-region habitat radiomics and clinicopathological features, aiming to preoperatively evaluate the microsatellite instability (MSI) status of rectal cancer (RC) patients.

MATERIALS AND METHODS

This retrospective study recruited 291 rectal cancer patients with pathologically confirmed MSI status and randomly divided them into a training cohort and a testing cohort at a ratio of 8:2. First, the K-means method was used for cluster analysis of tumor voxels, and sub-region radiomics features and classical radiomics features were respectively extracted from multi-parameter MRI sequences. Then, the synthetic minority over-sampling technique method was used to balance the sample size, and finally, the features were screened. Prediction models were established using logistic regression based on clinicopathological variables, classical radiomics features, and MSI-related sub-region radiomics features, and the contribution of each feature to the model decision was quantified by the Shapley-Additive-Explanations (SHAP) algorithm.

RESULTS

The area under the curve (AUC) of the sub-region radiomics model in the training and testing groups was 0.848 and 0.8, respectively, both better than that of the classical radiomics and clinical models. The combined model performed the best, with AUCs of 0.908 and 0.863 in the training and testing groups, respectively.

CONCLUSION

We developed and validated a robust combined model that integrates clinical variables, classical radiomics features, and sub-region radiomics features to accurately determine the MSI status of RC patients. We visualized the prediction process using SHAP, enabling more effective personalized treatment plans and ultimately improving RC patient survival rates.

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.

Development and validation of a robust MRI-based nomogram incorporating radiomics and deep features for preoperative glioma grading: a multi-center study

Background

Gliomas, the most common primary brain tumors, are classified into low-grade glioma (LGG) and high-grade glioma (HGG) based on aggressiveness. Accurate preoperative differentiation is vital for effective treatment and prognosis, but traditional methods like biopsy have limitations, such as sampling errors and procedural risks. This study introduces a comprehensive model that combines radiomics features (RFs) and deep features (DFs) from magnetic resonance imaging (MRI) scans, integrating clinical factors with advanced imaging features to enhance diagnostic precision for preoperative glioma grading.

Methods

In this retrospective multi-center study [2017-2022], 582 patients underwent preoperative contrast-enhanced T1-weighted (CE-T1w) and T2-weighted fluid-attenuated inversion recovery (T2w FLAIR) MRI. The dataset, divided into 407 training and 175 testing cases, included 340 LGGs and 242 HGGs. RFs and DFs were extracted from CE-T1w images, and radiomic scores (rad-score) and deep scores (deep-score) were calculated. Additionally, a clinical model based on demographics and MRI findings (CE-T1w and T2w FLAIR imaging) was developed. A nomogram model integrating rad-score, deep-score, and clinical factors was constructed using multivariate logistic regression analysis. Decision curve analysis (DCA) was employed to evaluate the nomogram's clinical utility in distinguishing between HGGs and LGGs.

Results

The study included 582 patients (mean age: 52±14 years; 57.91% male). No significant differences in age or sex were found between the training and testing groups (P>0.05). For RFs, 73.02% of the 215 extracted features were selected based on inter-class correlation coefficients (ICCs), while for DFs, 38.27% of the 15,680 extracted features were selected. Optimal penalization coefficients lambda (λ) for RFs and DFs were determined using a five-fold cross-validation and minimal criteria process. The resulting receiver operating characteristic-area under the curve (ROC-AUC) values were 0.93 [95% confidence interval (CI): 0.91-0.94] for the training set and 0.91 (95% CI: 0.89-0.93) for the testing set. The Hosmer-Lemeshow test yielded P values of 0.619 and 0.547 for the training and testing sets, respectively, indicating satisfactory calibration. The nomogram demonstrated the highest net benefit (NB) up to a threshold of 0.7, followed by DFs and RFs.

Conclusions

This study underscores the efficacy of integrating RFs and DFs alongside clinical data to accurately predict the pathological grading of HGGs and LGGs, offering a comprehensive approach for clinical decision-making.

Radiomic Fingerprinting of the Peritumoral Edema in Brain Tumors

BACKGROUND/OBJECTIVES

Tumor interactions with their surrounding environment, particularly in the case of peritumoral edema, play a significant role in tumor behavior and progression. While most studies focus on the radiomic features of the tumor core, this work investigates whether peritumoral edema exhibits distinct radiomic fingerprints specific to glioma (GLI), meningioma (MEN), and metastasis (MET). By analyzing these patterns, we aim to deepen our understanding of the tumor microenvironment's role in tumor development and progression.

METHODS

Radiomic features were extracted from peritumoral edema regions in T1-weighted (T1), post-gadolinium T1-weighted (T1-c), T2-weighted (T2), and T2 Fluid-Attenuated Inversion Recovery (T2-FLAIR) sequences. Three classification tasks using those features were then conducted: differentiating between Low-Grade Glioma (LGG) and High-Grade Glioma (HGG), distinguishing GLI from MET and MEN, and examining all four tumor types, i.e., LGG, HGG, MET, and MEN, to observe how tumor-specific signatures manifest in peritumoral edema. Model performance was assessed using balanced accuracy derived from 10-fold cross-validation.

RESULTS

The radiomic fingerprints specific to tumor types were more distinct in the peritumoral regions of T1-c images compared to other modalities. The best models, utilizing all features extracted from the peritumoral regions of T1-c images, achieved balanced accuracies of 0.86, 0.81, and 0.76 for the LGG-HGG, GLI-MET-MEN, and LGG-HGG-MET-MEN tasks, respectively.

CONCLUSIONS

This study demonstrates that peritumoral edema, as characterized by radiomic features extracted from MRIs, contains fingerprints specific to tumor type, providing a non-invasive approach to understanding tumor-brain interactions. The results of this study hold the potential for predicting recurrence, distinguishing progression from pseudo-progression, and assessing treatment-induced changes, particularly in gliomas.

TransAnaNet: Transformer-based anatomy change prediction network for head and neck cancer radiotherapy

BACKGROUND

Adaptive radiotherapy (ART) can compensate for the dosimetric impact of anatomic change during radiotherapy of head-neck cancer (HNC) patients. However, implementing ART universally poses challenges in clinical workflow and resource allocation, given the variability in patient response and the constraints of available resources. Therefore, the prediction of anatomical change during radiotherapy for HNC patients is of importance to optimize patient clinical benefit and treatment resources. Current studies focus on developing binary ART eligibility classification models to identify patients who would experience significant anatomical change, but these models lack the ability to present the complex patterns and variations in anatomical changes over time. Vision Transformers (ViTs) represent a recent advancement in neural network architectures, utilizing self-attention mechanisms to process image data. Unlike traditional Convolutional Neural Networks (CNNs), ViTs can capture global contextual information more effectively, making them well-suited for image analysis and image generation tasks that involve complex patterns and structures, such as predicting anatomical changes in medical imaging.

PURPOSE

The purpose of this study is to assess the feasibility of using a ViT-based neural network to predict radiotherapy-induced anatomic change of HNC patients.

METHODS

We retrospectively included 121 HNC patients treated with definitive chemoradiotherapy (CRT) or radiation alone. We collected the planning computed tomography image (pCT), planned dose, cone beam computed tomography images (CBCTs) acquired at the initial treatment (CBCT01) and Fraction 21 (CBCT21), and primary tumor volume (GTVp) and involved nodal volume (GTVn) delineated on both pCT and CBCTs of each patient for model construction and evaluation. A UNet-style Swin-Transformer-based ViT network was designed to learn the spatial correspondence and contextual information from embedded image patches of CT, dose, CBCT01, GTVp, and GTVn. The deformation vector field between CBCT01 and CBCT21 was estimated by the model as the prediction of anatomic change, and deformed CBCT01 was used as the prediction of CBCT21. We also generated binary masks of GTVp, GTVn, and patient body for volumetric change evaluation. We used data from 101 patients for training and validation, and the remaining 20 patients for testing. Image and volumetric similarity metrics including mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), Dice coefficient, and average surface distance were used to measure the similarity between the target image and predicted CBCT. Anatomy change prediction performance of the proposed model was compared to a CNN-based prediction model and a traditional ViT-based prediction model.

RESULTS

The predicted image from the proposed method yielded the best similarity to the real image (CBCT21) over pCT, CBCT01, and predicted CBCTs from other comparison models. The average MSE, PSNR, and SSIM between the normalized predicted CBCT and CBCT21 are 0.009, 20.266, and 0.933, while the average Dice coefficient between body mask, GTVp mask, and GTVn mask is 0.972, 0.792, and 0.821, respectively.

CONCLUSIONS

The proposed method showed promising performance for predicting radiotherapy-induced anatomic change, which has the potential to assist in the decision-making of HNC ART.

Expiration CT Gas Trapping Measures with Texture-Based Radiomics Improves Association with Lung Function and Lung Function Decline in COPD

RATIONALE AND OBJECTIVES

Several methods quantify gas-trapping on expiration computed tomography (CT) images, but they do not consider the spatial relationship of voxels. The objective of this study was to determine if the addition of expiration CT texture-based radiomics features to existing gas-trapping measurements improves model performance for lung function, lung function decline, COPD classification and visual gas-trapping.

MATERIALS AND METHODS

CanCOLD participants performed spirometry, plethysmography and CT chest imaging at full-inspiration/expiration with radiologist-assessed gas-trapping. Quantitative CT measurements were performed: low attenuation areas≤-856HU (LAA856), ratio of expiratory-to-inspiratory mean lung attenuation (E/I MLA), and difference between expiratory-inspiratory lung volumes between -856 and -950 HU (RVC856-950). Texture-based radiomics analysis generated 95 features; LASSO regression coefficients were summed to create a representative variable (RadScore). Multivariable linear regression models determined associations for baseline RV/TLC, FEV1/FVC, FEV1, FEF25-75, and 6-year ΔFEV1, with established CT gas-trapping and RadScore. Binary logistic regression determined associations for COPD classification and visual gas-trapping.

RESULTS

1111 participants were investigated (n=234 never-smokers, n=325 at-risk, n=314 mild COPD, n=238 moderate-severe COPD). In separate models for baseline RV/TLC, FEV1/FVC, FEV1, and FEF25-75, ΔFEV1, COPD classification and visual gas-trapping, all CT gas-trapping and CT RadScore measurements were independently significant (p<0.05). When CT gas-trapping and CT RadScore were included in the same model, all model performance metrics improved significantly (p<0.05).

CONCLUSION

CT measures extracted from full-expiratory images that quantify the distribution, not just extent, of gas-trapping provide important information related to lung function and lung function decline in COPD.

SUMMARY STATEMENT

Full-expiratory CT texture-based radiomics improves model performance when used in combination with conventional gas-trapping measurements for lung function and lung function decline, COPD classification and presence of visual gas-trapping.

Modernizing Neuro-Oncology: The Impact of Imaging, Liquid Biopsies, and AI on Diagnosis and Treatment

Advances in neuro-oncology have transformed the diagnosis and management of brain tumors, which are among the most challenging malignancies due to their high mortality rates and complex neurological effects. Despite advancements in surgery and chemoradiotherapy, the prognosis for glioblastoma multiforme (GBM) and brain metastases remains poor, underscoring the need for innovative diagnostic strategies. This review highlights recent advancements in imaging techniques, liquid biopsies, and artificial intelligence (AI) applications addressing current diagnostic challenges. Advanced imaging techniques, including diffusion tensor imaging (DTI) and magnetic resonance spectroscopy (MRS), improve the differentiation of tumor progression from treatment-related changes. Additionally, novel positron emission tomography (PET) radiotracers, such as 18F-fluoropivalate, 18F-fluoroethyltyrosine, and 18F-fluluciclovine, facilitate metabolic profiling of high-grade gliomas. Liquid biopsy, a minimally invasive technique, enables real-time monitoring of biomarkers such as circulating tumor DNA (ctDNA), extracellular vesicles (EVs), circulating tumor cells (CTCs), and tumor-educated platelets (TEPs), enhancing diagnostic precision. AI-driven algorithms, such as convolutional neural networks, integrate diagnostic tools to improve accuracy, reduce interobserver variability, and accelerate clinical decision-making. These innovations advance personalized neuro-oncological care, offering new opportunities to improve outcomes for patients with central nervous system tumors. We advocate for future research integrating these tools into clinical workflows, addressing accessibility challenges, and standardizing methodologies to ensure broad applicability in neuro-oncology.

Computed Tomography-Image-Based Glioma Grading Using Radiomics and Machine Learning: A Proof-of-Principle Study

BACKGROUND/OBJECTIVES

In recent years, numerous studies have been published on determining the WHO grade of central nervous system (CNS) tumors using machine learning algorithms. These studies are usually based on magnetic resonance imaging (MRI) and sometimes also on positron emission tomography (PET) images. To date, however, there are virtually no corresponding studies based on routinely generated computed tomography (CT) images. The aim of our proof-of-concept study is to investigate whether machine learning-based tumor diagnosis is also possible using CT images.

METHODS

We investigate the differentiability of histologically confirmed low-grade and high-grade gliomas. Three conventional machine learning algorithms and a neural net are tested. In addition, we analyze which of the common imaging methods (MRI or CT) appears to be best suited for the diagnostic question under investigation when machine learning algorithms are used. For this purpose, we compare our results based on CT images with numerous studies based on MRI scans.

RESULTS

Our best-performing model includes six features and is obtained using univariate analysis for feature preselection and a Naive Bayes approach for model construction. Using independent test data, this model yields a mean AUC of 0.903, a mean accuracy of 0.839, a mean sensitivity of 0.807 and a mean specificity of 0.864.

CONCLUSIONS

Our results demonstrate that low-grade and high-grade gliomas can be differentiated with high accuracy using machine learning algorithms, not only based on the usual MRI scans, but also based on CT images. In the future, such CT-image-based models can help to further accelerate brain tumor diagnostics and to reduce the number of necessary biopsies.

Radiomics in rectal cancer: current status of use and advances in research

Rectal cancer is a leading cause of morbidity and mortality among patients with malignant tumors in China. In light of the advances made in therapeutic approaches such as neoadjuvant therapy and total mesorectal excision, precise preoperative assessment has become crucial for developing a personalized treatment plan. As an emerging technology, radiomics has gained widespread application in the diagnosis, assessment of treatment response, and analysis of prognosis for rectal cancer by extracting high-throughput quantitative features from medical images. Radiomics thus demonstrates considerable potential for optimizing clinical decision-making. In this paper, we reviewed recent research focusing on advances in the use of radiomics for managing rectal cancer. The review covers TNM staging of tumors, assessment of neoadjuvant therapy outcomes, and survival prediction. We also discuss the challenges and prospects for future developments in translational medicine, particularly the need for data standardization, consistent feature extraction methodologies, and rigorous model validation.

Preoperative prediction of pituitary neuroendocrine tumor invasion using multiparametric MRI radiomics

Objective

The invasiveness of pituitary neuroendocrine tumor is an important basis for formulating individualized treatment plans and improving the prognosis of patients. Radiomics can predict invasiveness preoperatively. To investigate the value of multiparameter magnetic resonance imaging (mpMRI) radiomics in predicting pituitary neuroendocrine tumor invasion into the cavernous sinus (CS) before surgery.

Patients and methods

The clinical data of 133 patients with pituitary neuroendocrine tumor (62 invasive and 71 non-invasive) confirmed by surgery and pathology who underwent preoperative mpMRI examination were retrospectively analyzed. Data were divided into training set and testing set according to different field strength equipment. Radiomics features were extracted from the manually delineated regions of interest in T1WI, T2WI and CE-T1, and the best radiomics features were screened by LASSO algorithm. Single radiomics model (T1WI, T2WI, CE-T1) and combined radiomics model (T1WI+T2WI+CE-T1) were constructed respectively. In addition, clinical features were screened to establish clinical model. Finally, the prediction model was evaluated by ROC curve, calibration curve and decision curve analysis (DCA).

Results

A total of 10 radiomics features were selected from 306 primitive features. The combined radiomics model had the highest prediction efficiency. The area under curve (AUC) of the training set was 0.885 (95% CI, 0.819-0.952), and the accuracy, sensitivity, and specificity were 0.951,0.826, and 0.725. The AUC of the testing set was 0.864 (95% CI, 0.744-0.985), and the accuracy, sensitivity, and specificity were 0.829,0.952, and 0.700. DCA showed that the combined radiomics model had higher clinical net benefit.

Conclusion

The combined radiomics model based on mpMRI can effectively and accurately predict the invasiveness of pituitary neuroendocrine tumor to CS preoperatively, and provide decision-making basis for clinical individualized treatment.

Utilizing machine-learning techniques on MRI radiomics to identify primary tumors in brain metastases

Objective

To develop a machine learning-based clinical and/or radiomics model for predicting the primary site of brain metastases using multiparametric magnetic resonance imaging (MRI).

Materials and methods

A total of 202 patients (87 males, 115 females) with 439 brain metastases were retrospectively included, divided into training sets (brain metastases of lung cancer [BMLC] n = 194, brain metastases of breast cancer [BMBC] n = 108, brain metastases of gastrointestinal tumor [BMGiT] n = 48) and test sets (BMLC n = 50, BMBC n = 27, BMGiT n = 12). A total of 3,404 quantitative image features were obtained through semi-automatic segmentation from MRI images (T1WI, T2WI, FLAIR, and T1-CE). Intra-class correlation coefficient (ICC) was used to examine segmentation stability between two radiologists. Radiomics features were selected using analysis of variance (ANOVA), recursive feature elimination (RFE), and Kruskal-Wallis test. Three machine learning classifiers were used to build the radiomics model, which was validated using five-fold cross-validation on the training set. A comprehensive model combining radiomics and clinical features was established, and the diagnostic performance was compared by area under the curve (AUC) and evaluated in an independent test set.

Results

The radiomics model differentiated BMGiT from BMLC (13 features, AUC = 0.915 ± 0.071) or BMBC (20 features, AUC = 0.954 ± 0.064) with high accuracy, while the classification between BMLC and BMBC was unsatisfactory (11 features, AUC = 0.729 ± 0.114). However, the combined model incorporating radiomics and clinical features improved the predictive performance, with AUC values of 0.965 for BMLC vs. BMBC, 0.991 for BMLC vs. BMGiT, and 0.935 for BMBC vs. BMGiT.

Conclusion

The machine learning-based radiomics model demonstrates significant potential in distinguishing the primary sites of brain metastases, and may assist screening of primary tumor when brain metastasis is suspected whereas history of primary tumor is absent.

Volumetric measurement of manually drawn segmentations in cone beam computed tomography images of newly formed bone after sinus floor augmentation with bovine-derived bone substitutes

INTRODUCTION

Precise volumetric measurement of newly formed bone after maxillary sinus floor augmentation (MSFA) can help clinicians in planning for dental implants. This study aimed to introduce a novel modular framework to facilitate volumetric calculations based on manually drawn segmentations of user-defined areas of interest on cone-beam computed tomography (CBCT) images MATERIAL & METHODS: Two interconnected networks for manual segmentation of a defined volume of interest and dental implant volume calculation, respectively, were used in parallel. The volume data of dental implant manufacturers were used for reference. The efficacy of this framework was demonstrated through practical applications for collecting CBCT data from patients after MSFA with the same quantity of two different bovine-derived bone substitutes: xenohybrid composite bone (Group I, n = 10) and hydroxyapatite (Group II, n = 10). The study was approved by the central Ethical Review Board of the federal state of Lower Austria (approval number: GS4-EK-4/451-2021). The volumes were measured immediately (T1) and 6 months (T2) after MSFA and before insertion of the dental implant. All measurements were analyzed for inter- and intravariability. P-values of >0.05 were obtained from the t-test analysis RESULTS: The manual delineation of Group II (n = 10) was easier than that of Group I (n = 10) due to the visual contrast of the CBCT scan. The mean volume was 861.65 ± 290.02 mm³ at T1 and 875.9 ± 288.96 mm³ at T2. This shows a moderate dispersion around the mean value, which indicates variability of the analyzed data DISCUSSION: The proposed network may be useful for the development of computer-based diagnostic systems for assessing the success of MSFA with bone replacement materials. The volumetric stability achieved with the two bone replacement materials were comparable.

Enhancing brain tumor classification by integrating radiomics and deep learning features: A comprehensive study utilizing ensemble methods on MRI scans

BACKGROUND AND OBJECTIVE

This study aims to assess the effectiveness of combining radiomics features (RFs) with deep learning features (DFs) for classifying brain tumors-specifically Glioma, Meningioma, and Pituitary Tumor-using MRI scans and advanced ensemble learning techniques.

METHODS

A total of 3064 T1-weighted contrast-enhanced brain MRI scans were analyzed. RFs were extracted using Pyradiomics, while DFs were obtained from a 3D convolutional neural network (CNN). These features were used both individually and together to train a range of machine learning models, including Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), AdaBoost, Bagging, k-Nearest Neighbors (KNN), and Multi-Layer Perceptrons (MLP). To enhance the accuracy of these models, ensemble approaches such as Stacking, Voting, and Boosting were employed. LASSO feature selection and five-fold cross-validation were utilized to ensure the models' robustness.

RESULTS

The results demonstrated that combining RFs and DFs significantly improved the model's performance compared to using either feature set alone. The best performance was achieved using the combined RF + DF approach with ensemble methods, particularly Boosting, which resulted in an accuracy of 95.0%, an AUC of 0.92, a sensitivity of 88%, and a specificity of 90%. Conversely, models utilizing only RFs or DFs showed lower performance, with RFs reaching an AUC of 0.82 and DFs achieving an AUC of 0.85.

CONCLUSION

The integration of RFs and DFs, along with advanced ensemble methods, significantly improves the accuracy and reliability of brain tumor classification using MRI. This approach shows strong clinical potential, with opportunities for further enhancing generalizability and precision through additional MRI sequences and advanced machine learning techniques.

Development and validation of a radiomic prediction model for TACC3 expression and prognosis in non-small cell lung cancer using contrast-enhanced CT imaging

BACKGROUNDS

Non-small cell lung cancer (NSCLC) prognosis remains poor despite treatment advances, and classical prognostic indicators often fall short in precision medicine. Transforming acidic coiled-coil protein-3 (TACC3) has been identified as a critical factor in tumor progression and immune infiltration across cancers, including NSCLC. Predicting TACC3 expression through radiomic features may provide valuable insights into tumor biology and aid clinical decision-making. However, its predictive value in NSCLC remains unexplored. Therefore, we aimed to construct and validate a radiomic model to predict TACC3 levels and prognosis in patients with NSCLC.

MATERIALS AND METHODS

Genomic data and contrast-enhanced computed tomography (CT) images were sourced from The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO) database, and The Cancer Imaging Archive (TCIA). A total of 320 cases of lung adenocarcinoma from TCGA and 122 cases of NSCLC from GEO were used for prognostic analysis. Sixty-three cases from TCIA and GEO were included for radiomics feature extraction and model development. The radiomics model was constructed using logistic regression (LR) and support vector machine (SVM) algorithms. We predicted TACC3 expression and evaluated its correlation with NSCLC prognosis using contrast-enhanced CT-based radiomics.

RESULTS

TACC3 expression significantly influenced NSCLC prognosis. High TACC3 levels were associated with reduced overall survival, potentially mediated by immune microenvironment and tumor progression regulation. LR and SVM algorithms achieved AUC of 0.719 and 0.724, respectively, which remained at 0.701 and 0.717 after five-fold cross-validation.

CONCLUSION

Contrast-enhanced CT-based radiomics can non-invasively predict TACC3 expression and provide valuable prognostic information, contributing to personalized treatment strategies.

From images to clinical insights: an educational review on radiomics in lung diseases

Radiological imaging is a cornerstone in the clinical workup of lung diseases. Radiomics represents a significant advancement in clinical lung imaging, offering a powerful tool to complement traditional qualitative image analysis. Radiomic features are quantitative and computationally describe shape, intensity, texture and wavelet characteristics from medical images that can uncover detailed and often subtle information that goes beyond the visual capabilities of radiological examiners. By extracting this quantitative information, radiomics can provide deep insights into the pathophysiology of lung diseases and support clinical decision-making as well as personalised medicine approaches. In this educational review, we provide a step-by-step guide to radiomics-based medical image analysis, discussing the technical challenges and pitfalls, and outline the potential clinical applications of radiomics in diagnosing, prognosticating and evaluating treatment responses in respiratory medicine.

Ultrasound-Based Deep Learning Radiomics Nomogram for Tumor and Axillary Lymph Node Status Prediction After Neoadjuvant Chemotherapy

RATIONALE AND OBJECTIVES

This study aims to explore the feasibility of the deep learning radiomics nomogram (DLRN) for predicting tumor status and axillary lymph node metastasis (ALNM) after neoadjuvant chemotherapy (NAC) in patients with breast cancer. Additionally, we employ a Cox regression model for survival analysis to validate the effectiveness of the fusion algorithm.

MATERIALS AND METHODS

A total of 243 patients who underwent NAC were retrospectively included between October 2014 and July 2022. The DLRN integrated clinical characteristics as well as radiomics and deep transfer learning features extracted from ultrasound (US) images. The diagnostic performance of DLRN was evaluated by constructing ROC curves, and the clinical usefulness of models was assessed using decision curve analysis (DCA). A survival model was developed to validate the effectiveness of the fusion algorithm.

RESULTS

In the training cohort, the DLRN yielded area under the receiver operating characteristic curve values of 0.984 and 0.985 for the tumor and LNM, while 0.892 and 0.870, respectively, in the test cohort. The consistency indices (C-index) of the nomogram were 0.761 and 0.731, respectively, in the training and test cohorts. The Kaplan-Meier survival curves showed that patients in the high-risk group had significantly poorer overall survival than patients in the low-risk group (P < 0.05).

CONCLUSION

The US-based DLRN model could hold promise as clinical guidance for predicting the status of tumors and LNM after NAC in patients with breast cancer. This fusion model can also predict the prognosis of patients, which could help clinicians make better clinical decisions.

Brain Tumor Assessment: Integrating PET/Computed Tomography and MR Imaging Modalities

While MR imaging is the main imaging modality to assess brain tumors, PET imaging has a specific role. Among the many tracers that have been proposed and are still being developed, 2-[18F]fluoro-2-deoxy-d-glucose ([18F]FDG) and O-(2-[18F]-fluoroethyl)-l-tyrosine ([18F]FET) PET remain the most solidly established in the clinics. In particular, [18F]FET has gained increased acceptance due to its higher sensitivity. In this paper, we present an overview of the current clinical status of brain tumor imaging, with emphasis on PET imaging.

Predicting Secondary Vertebral Compression Fracture After Vertebral Augmentation via CT-Based Machine Learning Radiomics-Clinical Model

RATIONALE AND OBJECTIVES

Secondary vertebral compression fractures (SVCF) are very common in patients after vertebral augmentation (VA). The aim of this study was to establish a radiomic-based model to predict SVCF and specify appropriate treatment strategies.

MATERIALS AND METHODS

Patients diagnosed with osteoporotic vertebral compression fracture (OVCF) and undergoing VA surgery at our center between 2017 and 2021 were subject to a retrospective analysis. Radiological features of the T6-L5 vertebrae were derived from CT images. Clustering analysis, t-test, and LASSO (least absolute shrinkage and selection operator) regression were used to identify the optimization characteristics. A radiological signature model was constructed through the best combination of 13 machine learning algorithms. Radiomics signature was integrated with clinical characteristics into a nomogram for clinical applications. The model reliability was assessed by receiver operating characteristic (ROC) curve, calibration curve, clinical decision analysis (DCA), log-rank test, and confusion matrix.

RESULTS

A total of 470 eligible patients (81 with SVCF and 389 without) were identified in the clinical cohort. Eight radiomics features were identified and incorporated into machine learning, and "XGBoost" model showed the best performance. Final logistic nomogram included radiomics signature (P < 0.001), bone cement volume (P = 0.034), and T-scores of L1-L4 (P = 0.001), and showed satisfactory prediction capability in training set (0.986, 95%CI 0.969-1.000) and verification set (0.884, 95%CI 0.823-0.946).

CONCLUSION

Our radiomics-clinical model based on machine learning showed potential to prospectively predict SVCF after VA and provide precise treatment strategies.

Development and validation of a radiomics-based nomogram for predicting two subtypes of HER2-negative breast cancer

Background

Breast cancer is the most common malignant tumor among women, with an increasing incidence each year. The subtypes of human epidermal growth factor receptor 2 (HER2)-negative breast cancer, classified as HER2-low and HER2-zero based on HER2 receptor expression, show differences in clinical characteristics, therapeutic approaches, and prognoses. Distinguishing between these subtypes is clinically valuable as it can impact treatment strategies, including the use of next-generation antibody-drug conjugates (ADCs) targeting HER2-low tumors. This study aimed to develop a nomogram based on dynamic magnetic resonance imaging (MRI) and clinical indicators to differentiate between HER2-low and HER2-zero subtypes in HER2-negative breast cancer patients.

Methods

This study included 214 breast cancer patients from two centers, Hospital A (Affiliated Hospital of Jining Medical University, n=178) and Hospital B (Ningyang No. 1 People's Hospital, n=36). HER2 status was determined by immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH). Among the participants, 112 cases were identified as HER2-low and 102 as HER2-zero. Patients from Hospital A were split into a training set and an internal test set in an 8:2 ratio, while the 36 patients from Hospital B were used as an external test set. Regions of interest (ROI) were delineated on phase 2 enhanced scans and diffusion weighted imaging (DWI) images, with features selected via Pearson correlation coefficients and least absolute shrinkage and selection operator (LASSO) regression. A K-Nearest Neighbor (KNN) model was employed to calculate the rad score, and clinical predictors (tumor maximum diameter and CA153) were identified through logistic regression analysis. These predictors, combined with the rad score, were incorporated into the final nomogram model. The model's accuracy was evaluated using area under curve (AUC) values in both the internal and external validation sets.

Results

The nomogram achieved AUC values of 0.873 and 0.859 in the internal and external validation sets, respectively, demonstrating superior performance over single-feature models. Decision curve analysis (DCA) indicated substantial net clinical benefits, and calibration curves displayed strong alignment between the model's predictions and actual outcomes in both sets.

Conclusions

This nomogram shows high accuracy and stability in differentiating HER2-low and HER2-zero subtypes among HER2-negative breast cancer patients, suggesting potential clinical utility in refining treatment decisions and identifying candidates for ADC therapy in HER2-low cases.

Diagnosis of traumatic liver injury on computed tomography using machine learning algorithms and radiomics features: The role of artificial intelligence for rapid diagnosis in emergency rooms

Background

The initial assessment of trauma is a time-consuming and challenging task. The purpose of this research is to examine the diagnostic effectiveness and usefulness of machine learning models paired with radiomics features to identify blunt traumatic liver injury in abdominal computed tomography (CT) images.

Materials and Methods

In this study, 600 CT scan images of people with mild and severe liver damage due to trauma and healthy people were collected from the Kaggle dataset. The axial images were segmented by an experienced radiologist, and radiomics features were extracted from each region of interest. Initially, 30 machine learning models were implemented, and finally, three machine learning models were selected including Light Gradient-Boosting Machine (LGBM), Ridge Classifier, and Extreme Gradient Boosting (XGBoost), and their performance was examined in more detail.

Results

The two criteria of precision and specificity of LGBM and XGBoost models in diagnosing mild liver injury were calculated to be 100%. Only 6.00% of cases were misdiagnosed by the LGBM model. The LGBM model achieved 100% sensitivity and 99.00% accuracy in diagnosing severe liver injury. The area under the receiver operating characteristic curve value and precision of this model were also calculated to be 99.00% and 98.00%, respectively.

Conclusion

The artificial intelligence models used in this study have great potential to improve patient care by assisting radiologists and other physicians in diagnosing and staging trauma-related liver injuries. These models can help prioritize positive studies, allow more rapid evaluation, and identify more severe injuries that may require immediate intervention.

Update report on the quality of gliomas radiomics: An integration of bibliometric and radiomics quality score

BACKGROUND

Despite the increasing number of publications on glioma radiomics, challenges persist in clinical translation.

AIM

To assess the development and reporting quality of radiomics in brain gliomas since 2019.

METHODS

A bibliometric analysis was conducted to reveal trends in brain glioma radiomics research. The Radiomics Quality Score (RQS), a metric for evaluating the quality of radiomics studies, was applied to assess the quality of adult-type diffuse glioma studies published since 2019. The total RQS score and the basic adherence rate for each item were calculated. Subgroup analysis by journal type and research objective was performed, correlating the total RQS score with journal impact factors.

RESULTS

The radiomics research in glioma was initiated in 2011 and has witnessed a surge since 2019. Among the 260 original studies, the median RQS score was 11, correlating with a basic compliance rate of 46.8%. Subgroup analysis revealed significant differences in domain 1 and its subitems (multiple segmentations) across journal types (P = 0.039 and P = 0.03, respectively). The Spearman correlation coefficients indicated that the total RQS score had a negative correlation with the Journal Citation Report category (-0.69) and a positive correlation with the five-year impact factors (0.318) of journals.

CONCLUSION

Glioma radiomics research quality has improved since 2019 but necessitates further advancement with higher publication standards.

[Identification of kidney stone types by deep learning integrated with radiomics features]

Currently, the types of kidney stones before surgery are mainly identified by human beings, which directly leads to the problems of low classification accuracy and inconsistent diagnostic results due to the reliance on human knowledge. To address this issue, this paper proposes a framework for identifying types of kidney stones based on the combination of radiomics and deep learning, aiming to achieve automated preoperative classification of kidney stones with high accuracy. Firstly, radiomics methods are employed to extract radiomics features released from the shallow layers of a three-dimensional (3D) convolutional neural network, which are then fused with the deep features of the convolutional neural network. Subsequently, the fused features are subjected to regularization, least absolute shrinkage and selection operator (LASSO) processing. Finally, a light gradient boosting machine (LightGBM) is utilized for the identification of infectious and non-infectious kidney stones. The experimental results indicate that the proposed framework achieves an accuracy rate of 84.5% for preoperative identification of kidney stone types. This framework can effectively distinguish between infectious and non-infectious kidney stones, providing valuable assistance in the formulation of preoperative treatment plans and the rehabilitation of patients after surgery.

Automated classification of pathological differentiation in head and neck squamous cell carcinoma using combined radiomics models from CET1WI and T2WI

OBJECTIVES

This study aims to develop an automated radiomics-based model to grade the pathological differentiation of head and neck squamous cell carcinoma (HNSCC) and to assess the influence of various magnetic resonance imaging (MRI) sequences on the model's performance.

MATERIALS AND METHODS

We retrospectively analyzed MRI data from 256 patients across two medical centers, including both contrast-enhanced T1-weighted images (CET1WI) and T2-weighted images (T2WI). Regions of interest were delineated for radiomics feature extraction, followed by dimensionality reduction. An XGBoost classifier was then employed to build the predictive model, with its classification efficiency assessed using receiver operating characteristic curves and the area under the curve (AUC).

RESULTS

In validation cohort, the AUC (macro/micro) values for models utilizing CET1WI, T2WI, and the combination of CET1WI and T2WI were 0.801/0.814, 0.741/0.798, and 0.885/0.895, respectively. The AUC for the three differentiations, ranging from well-differentiated to poorly differentiated, were 0.867, 0.909, and 0.837, respectively. The macro/micro precision, recall, and F1 scores of 0.688/0.736, 0.744/0.828, and 0.685/0.779 for the CET1WI + T2WI model.

CONCLUSION

This study demonstrates that constructing a radiomics model based on CET1WI and T2WI sequences can be used to predict the pathological differentiation grading of HNSCC patients.

CLINICAL RELEVANCE

This study suggests that a radiomics model integrating CET1WI and T2WI MRI sequences can effectively predict the pathological differentiation of HNSCC, providing an alternative diagnostic approach through non-invasive preoperative methods.

AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD

Endoscopy, histology, and cross-sectional imaging serve as fundamental pillars in the detection, monitoring, and prognostication of inflammatory bowel disease (IBD). However, interpretation of these studies often relies on subjective human judgment, which can lead to delays, intra- and interobserver variability, and potential diagnostic discrepancies. With the rising incidence of IBD globally coupled with the exponential digitization of these data, there is a growing demand for innovative approaches to streamline diagnosis and elevate clinical decision-making. In this context, artificial intelligence (AI) technologies emerge as a timely solution to address the evolving challenges in IBD. Early studies using deep learning and radiomics approaches for endoscopy, histology, and imaging in IBD have demonstrated promising results for using AI to detect, diagnose, characterize, phenotype, and prognosticate IBD. Nonetheless, the available literature has inherent limitations and knowledge gaps that need to be addressed before AI can transition into a mainstream clinical tool for IBD. To better understand the potential value of integrating AI in IBD, we review the available literature to summarize our current understanding and identify gaps in knowledge to inform future investigations.

Radiomic detection of abnormal brain regions in tuberous sclerosis complex

BACKGROUND

Radiomics refers to the extraction of quantitative information from medical images and is most commonly utilized in oncology to provide ancillary information for solid tumor diagnosis, prognosis, and treatment response. The traditional radiomic pipeline involves segmentation of volumes of interest with comparison to normal brain. In other neurologic disorders, such as epilepsy, lesion delineation may be difficult or impossible due to poor anatomic definition, small size, and multifocal or diffuse distribution. Tuberous sclerosis complex (TSC) is a rare genetic disease in which brain magnetic resonance imaging (MRI) demonstrates multifocal abnormalities with variable imaging and epileptogenic features.

PURPOSE

The purpose of this study was to develop a radiomic workflow for identification of abnormal brain regions in TSC, using a whole-brain atlas-based approach with generation of heatmaps based on signal deviation from normal controls.

METHODS

This was a retrospective pilot study utilizing high-resolution whole-brain 3D FLAIR MRI datasets from retrospective enrollment of tuberous sclerosis complex (TSC) patients and normal controls. Subjects underwent MRI including high-resolution 3D FLAIR sequences. Preprocessing included skull stripping, coregistration, and intensity normalization. Using the Brainnetome and Harvard-Oxford atlases, brain regions were parcellated into 318 discrete regions. Expert neuroradiologists spatially labeled all tubers in TSC patients using ITK-SNAP. The pyradiomics toolbox was used to extract 88 radiomic features based on IBSI guidelines, comparing tuber-affected and non-tuber-affected parenchyma in TSC patients, as well as normal brain tissue in control patients. For model training and validation, regions with tubers from 20 TSC patients and 30 normal control subjects were randomly divided into two training sets (80%) and two validation sets (20%). Additional model testing was performed on a separate group of 20 healthy controls. LASSO (least absolute shrinkage and selection operator) was used to perform variable selection and regularization to identify regions containing tubers. Relevant radiomic features selected by LASSO were combined to produce a radiomic score ω, defined as the sum of squared differences from average control group values. Region-specific ω scores were converted to heat maps and spatially coregistered with brain MRI to reflect overall radiomic deviation from normal.

RESULTS

The proposed radiomic workflow allows for quantification of deviation from normal in 318 regions of the brain with the use of a summative radiomic score ω. This score can be used to generate spatially registered heatmaps to identify brain regions with radiomic abnormalities. The pilot study of TSC showed radiomic scores ω that were statistically different in regions containing tubers from regions without tubers/normal brain (p < 0.0001). Our model exhibits an AUC of 0.81 (95% confidence interval: 0.78-0.84) on the testing set, and the best threshold obtained on the training set, when applied to the testing set, allows us to identify regions with tubers with a specificity of 0.91 and a sensitivity of 0.60.

CONCLUSION

We describe a whole-brain atlas-based radiomic approach to identify abnormal brain regions in TSC patients. This approach may be helpful for identifying specific regions of interest based on relatively greater signal deviation, particularly in clinical scenarios with numerous or poorly defined anatomic lesions.

Breast Cancer: Multi-b-Value Diffusion Weighted Habitat Imaging in Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy

RATIONALE AND OBJECTIVES

The aim of this study was to ascertain whether the utilization of multiple b-value diffusion-weighted habitat imaging, a technique that depicts tumor heterogeneity, could aid in identifying breast cancer patients who would derive substantial benefit from neoadjuvant chemotherapy (NAC).

MATERIALS AND METHODS

This prospective study enrolled 143 women (II-III breast cancer), who underwent multi-b-value diffusion-weighted imaging (DWI) in 3-T magnetic resonance (MR) before NAC. The patient cohort was partitioned into a training set (consisting of 100 patients, of which 36 demonstrated a pathologic complete response [pCR]) and a test set (featuring 43 patients, 16 of whom exhibited pCR). Utilizing the training set, predictive models for pCR, were constructed using different parameters: whole-tumor radiomics (ModelWH), diffusion-weighted habitat-imaging (ModelHabitats), conventional MRI features (ModelCF), along with combined models ModelHabitats+CF. The performance of these models was assessed based on the area under the receiver operating characteristic curve (AUC) and calibration slope.

RESULTS

In the prediction of pCR, ModelWH, ModelHabitats, ModelCF, and ModelHabitats+CF achieved AUCs of 0.733, 0.722, 0.705, and 0.756 respectively, within the training set. These scores corresponded to AUCs of 0.625, 0.801, 0.700, and 0.824 respectively in the test set. The DeLong test revealed no significant difference between ModelWH and ModelHabitats (P = 0.182), between ModelHabitats and ModelHabitats+CF (P = 0.113).

CONCLUSION

The habitat model we developed, incorporating first-order features along with conventional MRI features, has demonstrated accurate predication of pCR prior to NAC. This model holds the potential to augment decision-making processes in personalized treatment strategies for breast cancer.

Development and Validation of an 18F-FDG PET/CT-based Radiomics Nomogram for Predicting the Prognosis of Patients with Esophageal Squamous Cell Carcinoma

RATIONALE AND OBJECTIVES

The aim of this study was to develop and validate a nomogram, integrating clinical factors and radiomics features, capable of predicting overall survival (OS) in patients diagnosed with esophageal squamous cell carcinoma (ESCC).

METHODS

In this study, we retrospectively analyzed the case data of 130 patients with ESCC who underwent 18F-FDG PET/CT before treatment. Radiomics features associated with OS were screened by univariate Cox regression (p < 0.05). Further selection was performed by applying the least absolute shrinkage and selection operator Cox regression to generate the weighted Radiomics-score (Rad-score). Independent clinical risk factors were obtained by multivariate Cox regression, and a nomogram was constructed by combining Rad-score and independent risk factors. The predictive performance of the model for OS was assessed using the time-dependent receiver operating characteristic curve, concordance index (C-index), calibration curve, and decision curve analysis.

RESULTS

Five radiomics features associated with prognosis were finally screened, and a Rad-score was established. Multivariate Cox regression analysis revealed that surgery and clinical M stage were identified as independent risk factors for OS in ESCC. The combined clinical-radiomics nomogram exhibited C-index values of 0.768 (95% CI: 0.699-0.837) and 0.809 (95% CI: 0.695-0.923) in the training and validation cohorts, respectively. Ultimately, calibration curves and decision curves for the 1-, 2-, and 3-year OS demonstrated the satisfactory prognostic prediction and clinical utility of the nomogram.

CONCLUSION

The developed nomogram, leveraging 18F-FDG PET/CT radiomics and clinically independent risk factors, demonstrates a reliable prognostic prediction for patients with ESCC, potentially serving as a valuable tool for guiding and optimizing clinical treatment decisions in the future.

Sensitivity of CT-derived radiomic features to extraction libraries and gray-level discretization in the context of immune biomarker discovery

OBJECTIVES

Radiomics can predict patient outcomes by automatically extracting a large number of features from medical images. This study is aimed to investigate the sensitivity of radiomics features extracted from 2 different pipelines, namely, Pyradiomics and RaCat, as well as the impact of gray-level discretization on the discovery of immune checkpoint inhibitors (ICIs) biomarkers.

METHODS

A retrospective cohort of 164 non-small cell lung cancer patients administered with ICIs was used in this study. Radiomic features were extracted from the pre-treatment CT scans. Univariate models were used to assess the association of common radiomics features between 2 libraries with progression-free survival (PFS), programmed death ligand 1 (PD-L1), and tumour infiltrating lymphocytes (CD8 counts). In addition, we also examined the impact of gray-level discretization incorporated in Pyradiomics on the robustness of features across various clinical endpoints.

RESULTS

We extracted 1224, 441 radiomic features using Pyradiomics and RaCat, respectively. Among these, 75 features were found to be common between the 2 libraries. Our analysis revealed that the directionality of association between radiomic features and clinical endpoints is highly dependent on the library. Notably, a larger number of Pyradiomics features were statistically associated with PFS, whereas RaCat features showed a stronger association with PD-L1 expression. Furthermore, intensity-based features were found to have a consistent association with clinical endpoints regardless of the gray-level discretization parameters in Pyradiomics-extracted features.

CONCLUSIONS

This study highlights the heterogeneity of radiomics libraries and the gray-level discretization parameters that will impact the feature selection and predictive model development for biomarkers. Importantly, our work highlights the significance of standardizing radiomic features to facilitate translational studies that use imaging as an endpoint.

ADVANCES IN KNOWLEDGE

Our study emphasizes the need to select stable CT-derived handcrafted features to build immunotherapy biomarkers, which is a necessary precursor for multi-institutional validation of imaging biomarkers.

Prediction of iodine-125 seed implantation efficacy in lung cancer using an enhanced CT-based nomogram model

BACKGROUND

Lung cancer, a leading cause of death, sees variable outcomes with iodine-125 seed implantation. Predictive tools are lacking, complicating clinical decisions. This study integrates radiomics and clinical features to develop a predictive model, advancing personalized treatment.

OBJECTIVE

To construct a nomogram model combining enhanced CT image features and general clinical characteristics to evaluate the efficacy of radioactive iodine-125 seed implantation in lung cancer treatment.

METHODS

Patients who underwent lung iodine-125 seed implantation at the Nuclear Medicine Department of Xiling Campus, Yichang Central People's Hospital from January 1, 2018, to January 31, 2024, were randomly divided into a training set (73 cases) and a test set (31 cases). Radiomic features were extracted from the enhanced CT images, and optimal clinical factors were analyzed to construct clinical, radiomics, and combined models. The best model was selected and validated for its role in assessing the efficacy of iodine-125 seed implantation in lung cancer patients.

RESULTS

Three clinical features and five significant radiomic features were successfully selected, and a combined nomogram model was constructed to evaluate the efficacy of iodine-125 seed implantation in lung cancer patients. The AUC values of the model in the training and test sets were 0.95 (95% CI: 0.91-0.99) and 0.83 (95% CI: 0.69-0.98), respectively. The calibration curve demonstrated good agreement between predicted and observed values, and the decision curve indicated that the combined model outperformed the clinical or radiomics model across the majority of threshold ranges.

CONCLUSION

A combined nomogram model was successfully developed to assess the efficacy of iodine-125 seed implantation in lung cancer patients, demonstrating good clinical predictive performance and high clinical value.

Predicting and Monitoring Immune Checkpoint Inhibitor Therapy Using Artificial Intelligence in Pancreatic Cancer

Pancreatic cancer remains one of the most lethal cancers, primarily due to its late diagnosis and limited treatment options. This review examines the challenges and potential of using immunotherapy to treat pancreatic cancer, highlighting the role of artificial intelligence (AI) as a promising tool to enhance early detection and monitor the effectiveness of these therapies. By synthesizing recent advancements and identifying gaps in the current research, this review aims to provide a comprehensive overview of how AI and immunotherapy can be integrated to develop more personalized and effective treatment strategies. The insights from this review may guide future research efforts and contribute to improving patient outcomes in pancreatic cancer management.

Test-retest repeatability of myocardial radiomic features from quantitative cardiac magnetic resonance T1 and T2 mapping

Radiomics of cardiac magnetic resonance (MR) imaging has proved to be potentially useful in the study of various myocardial diseases. Therefore, assessing the repeatability degree in radiomic features measurement is of fundamental importance. The aim of this study was to assess test-retest repeatability of myocardial radiomic features extracted from quantitative T1 and T2 maps. A representative group of 24 subjects (mean age 54 ± 18 years) referred for clinical cardiac MR imaging were enrolled in the study. For each subject, T1 and T2 mapping through MOLLI and T2-prepared TrueFISP acquisition sequences, respectively, were performed at 1.5 T. Then, 98 radiomic features of different classes (shape, first-order, second-order) were extracted from a region of interest encompassing the whole left ventricle myocardium in a short axis slice. The repeatability was assessed performing different and complementary analyses: intraclass correlation coefficient (ICC) and limits of agreement (LOA) (i.e., the interval within which 95% of the percentage differences between two repeated measures are expected to lie). Radiomic features were characterized by a relatively wide range of repeatability degree in terms of both ICC and LOA. Overall, 44.9% and 38.8% of radiomic features showed ICC values > 0.75 for T1 and T2 maps, respectively, while 25.5% and 23.4% of radiomic features showed LOA between ±10%. A subset of radiomic features for T1 (Mean, Median, 10Percentile, 90Percentile, RootMeanSquared, Imc2, RunLengthNonUniformityNormalized, RunPercentage and ShortRunEmphasis) and T2 (MaximumDiameter, RunLengthNonUniformityNormalized, RunPercentage, ShortRunEmphasis) maps presented both ICC > 0.75 and LOA between ±5%. Overall, radiomic features extracted from T1 maps showed better repeatability performance than those extracted from T2 maps, with shape features characterized by better repeatability than first-order and textural features. Moreover, only a limited subset of 9 and 4 radiomic features for T1 and T2 maps, respectively, showed high repeatability degree in terms of both ICC and LOA. These results confirm the importance of assessing test-retest repeatability degree in radiomic feature estimation and might be useful for a more effective/reliable use of myocardial T1 and T2 mapping radiomics in clinical or research studies.

Texture Analysis and Prediction of Response to Neoadjuvant Treatment in Patients with Locally Advanced Rectal Cancer

Background: The purpose of this study is to determine the relationship between the texture analysis extracted from preoperative rectal magnetic resonance (MR) studies and the response to neoadjuvant treatment. Materials and Methods: In total, 88 patients with rectal adenocarcinoma who underwent staging MR between 2017 and 2022 were retrospectively enrolled. After the completion of neoadjuvant treatment, they underwent surgical resection. The tumour regression grade (TRG) was collected. Patients with TRG 1–2 were classified as responders, while patients with TRG 3 to 5 were classified as non-responders. A texture analysis was conducted using LIFEx software (v 7.6.0), where T2-weighted MR sequences on oriented axial planes were uploaded, and a region of interest (ROI) was manually drawn on a single slice. Features with a Spearman correlation index > 0.5 have been discarded, and a LASSO feature selection has been applied. Selected features were trained using bootstrapping. Results: According to the TRG classes, 49 patients (55.8%) were considered responders, while 39 (44.2) were non-responders. Two features were associated with the responder class: GLCM_Homogeneity and Discretized Histo Entropy log 2. Regarding GLCM_Homogeneity, the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were 0.779 (95% CIs = 0.771–0.816), 86% (80–90), and 67% (60–71). Regarding Discretized Histo Entropy log 2, we found 0.775 AUC (0.700–0.801), 80% sensitivity (74–83), and 63% specificity (58–69). Combining both radiomics features the radiomics signature diagnostic accuracy increased (AUC = 0.844). Finally, the AUC of 1000 bootstraps were 0.810. Conclusions: Texture analysis can be considered an advanced tool for determining a possible correlation between pre-surgical MR data and the response to neoadjuvant therapy.

Predicting pathological complete response following neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer using merged model integrating MRI-based radiomics and deep learning data

BACKGROUND

To construct and compare merged models integrating clinical factors, MRI-based radiomics features and deep learning (DL) models for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).

METHODS

Totally 197 patients with LARC administered surgical resection after nCRT were assigned to cohort 1 (training and test sets); meanwhile, 52 cases were assigned to cohort 2 as a validation set. Radscore and DL models were established for predicting pCR applying pre- and post-nCRT MRI data, respectively. Different merged models integrating clinical factors, Radscore and DL model were constituted. Their predictive performances were validated and compared by receiver operating characteristic (ROC) and decision curve analyses (DCA).

RESULTS

Merged models were established integrating selected clinical factors, Radscore and DL model for pCR prediction. The areas under the ROC curves (AUCs) of the pre-nCRT merged model were 0.834 (95% CI: 0.737-0.931) and 0.742 (95% CI: 0.650-0.834) in test and validation sets, respectively. The AUCs of the post-nCRT merged model were 0.746 (95% CI: 0.636-0.856) and 0.737 (95% CI: 0.646-0.828) in test and validation sets, respectively. DCA showed that the pretreatment algorithm could yield enhanced clinically benefit than the post-nCRT approach.

CONCLUSIONS

The pre-nCRT merged model including clinical factors, Radscore and DL model constitutes an effective non-invasive tool for pCR prediction in LARC.

Texture Analysis in Volumetric Imaging for Dentomaxillofacial Radiology: Transforming Diagnostic Approaches and Future Directions

This narrative review explores texture analysis as a valuable technique in dentomaxillofacial diagnosis, providing an advanced method for quantification and characterization of different image modalities. The traditional imaging techniques rely primarily on visual assessment, which may overlook subtle variations in tissue structure. In contrast, texture analysis uses sophisticated algorithms to extract quantitative information from imaging data, thus offering deeper insights into the spatial distribution and relationships of pixel intensities. This process identifies unique "texture signatures", serving as markers for accurately characterizing tissue changes or pathological processes. The synergy between texture analysis and radiomics allows radiologists to transcend traditional size-based or semantic descriptors, offering a comprehensive understanding of imaging data. This method enhances diagnostic accuracy, particularly for the assessment of oral and maxillofacial pathologies. The integration of texture analysis with radiomics expands the potential for precise tissue characterization by moving beyond the limitations of human eye evaluations. This article reviews the current trends and methodologies in texture analysis within the field of dentomaxillofacial imaging, highlights its practical applications, and discusses future directions for research and dental clinical practice.

Comparison of diagnostic accuracy of radiomics parameter maps and standard reconstruction for the detection of liver lesions in computed tomography

Background

The liver is a frequent location of metastatic disease in various malignant tumor entities. Computed tomography (CT) is the most frequently employed modality for initial diagnosis. However, liver metastases may only be delineated vaguely on CT. Calculating radiomics features in feature maps can unravel textures not visible to the human eye on a standard CT reconstruction (SCTR). This study aimed to investigate the comparative diagnostic accuracy of radiomics feature maps and SCTR for liver metastases.

Materials and methods

Forty-seven patients with hepatic metastatic colorectal cancer were retrospectively enrolled. Whole-liver maps of original radiomics features were generated. A representative feature was selected for each feature class based on the visualization of example lesions from five patients. These maps and the conventional CT image data were viewed and evaluated by four readers in terms of liver parenchyma, number of lesions, visual contrast of lesions and diagnostic confidence. T-tests and chi²-tests were performed with a significance cut off of p<0.05 to compare the feature maps with SCRT, and the data were visualized as boxplots.

Results

Regarding the number of lesions detected, SCTR showed superior performance compared to radiomics maps. However, the feature map for firstorder RootMeanSquared was ranked superior in terms of very high visual contrast in 57.4% of cases, compared to 41.0% in standard reconstructions (p < 0.001). All other radiomics maps ranked significantly lower in visual contrast when compared to SCTR. For diagnostic confidence, firstorder RootMeanSquared reached very high ratings in 47.9% of cases, compared to 62.8% for SCTR (p < 0.001). The conventional CT images showed superior results in all categories for the other features investigated.

Conclusion

The application of firstorder RootMeanSquared feature maps may help visualize faintly demarcated liver lesions by increasing visual contrast. However, reading of SCTR remains necessary for diagnostic confidence.