Radiomics analysis of pancreas based on dual-energy computed tomography for the detection of type 2 diabetes mellitus

Objective

To utilize radiomics analysis on dual-energy CT images of the pancreas to establish a quantitative imaging biomarker for type 2 diabetes mellitus.

Materials and methods

In this retrospective study, 78 participants (45 with type 2 diabetes mellitus, 33 without) underwent a dual energy CT exam. Pancreas regions were segmented automatically using a deep learning algorithm. From these regions, radiomics features were extracted. Additionally, 24 clinical features were collected for each patient. Both radiomics and clinical features were then selected using the least absolute shrinkage and selection operator (LASSO) technique and then build classifies with random forest (RF), support vector machines (SVM) and Logistic. Three models were built: one using radiomics features, one using clinical features, and a combined model.

Results

Seven radiomic features were selected from the segmented pancreas regions, while eight clinical features were chosen from a pool of 24 using the LASSO method. These features were used to build a combined model, and its performance was evaluated using five-fold cross-validation. The best classifier type is Logistic and the reported area under the curve (AUC) values on the test dataset were 0.887 (0.73-1), 0.881 (0.715-1), and 0.922 (0.804-1) for the respective models.

Conclusion

Radiomics analysis of the pancreas on dual-energy CT images offers potential as a quantitative imaging biomarker in the detection of type 2 diabetes mellitus.

Radiomics analysis of R2* maps to predict early recurrence of single hepatocellular carcinoma after hepatectomy

Objectives

This study aimed to evaluate the effectiveness of radiomics analysis with R2* maps in predicting early recurrence (ER) in single hepatocellular carcinoma (HCC) following partial hepatectomy.

Methods

We conducted a retrospective analysis involving 202 patients with surgically confirmed single HCC having undergone preoperative magnetic resonance imaging between 2018 and 2021 at two different institutions. 126 patients from Institution 1 were assigned to the training set, and 76 patients from Institution 2 were assigned to the validation set. A least absolute shrinkage and selection operator (LASSO) regularization was conducted to operate a logistic regression, then features were identified to construct a radiomic score (Rad-score). Uni- and multi-variable tests were used to assess the correlations of clinicopathological features and Rad-score with ER. We then established a combined model encompassing the optimal Rad-score and clinical-pathological risk factors. Additionally, we formulated and validated a predictive nomogram for predicting ER in HCC. The nomogram's discrimination, calibration, and clinical utility were thoroughly evaluated.

Results

Multivariable logistic regression revealed the Rad-score, microvascular invasion (MVI), and α fetoprotein (AFP) level > 400 ng/mL as significant independent predictors of ER in HCC. We constructed a nomogram based on these significant factors. The areas under the receiver operator characteristic curve of the nomogram and precision-recall curve were 0.901 and 0.753, respectively, with an F1 score of 0.831 in the training set. These values in the validation set were 0.827, 0.659, and 0.808.

Conclusion

The nomogram that integrates the radiomic score, MVI, and AFP demonstrates high predictive efficacy for estimating the risk of ER in HCC. It facilitates personalized risk classification and therapeutic decision-making for HCC patients.

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Introduction

This study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners.

Materials and methods

Preoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson’s correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The “Kidney Tumor Segmentation 2019” (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist’s.

Results

The training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model’s performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69.

Conclusion

Radiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

Radiomics and Machine Learning for Detecting Scar Tissue on CT Delayed Enhancement Imaging

Background

Delayed enhancement CT (CT-DE) has been evaluated as a tool for the detection of myocardial scar and compares well to the gold standard of MRI with late gadolinium enhancement (MRI-LGE). Prior work has established that high performance can be achieved with manual reading; however, few studies have looked at quantitative measures to differentiate scar and healthy myocardium on CT-DE or automated analysis.

Methods

Eighteen patients with clinically indicated MRI-LGE were recruited for CT-DE at multiple 80 and 100 kV post contrast imaging. Left ventricle segmentation was performed on both imaging modalities, along with scar segmentation on MRI-LGE. Segmentations were registered together and scar regions were estimated on CT-DE. 93 radiomic features were calculated and analysed for their ability to differentiate between scarred and non-scarred myocardium regions. Machine learning (ML) classifiers were trained using the strongest set of radiomic features to classify segments containing scar on CT-DE. Features and classifiers were compared across both tube voltages and combined-energy images.

Results

There were 59 and 51 statistically significant features in the 80 and 100 kV images respectively. Combined-energy imaging increased this to 63 with more features having area under the curve (AUC) above 0.9. The 10 highest AUC features for each image were used in the ML classifiers. The 100 kV images produced the best ML classifier, a support vector machine with an AUC of 0.88 (95% CI 0.87-0.90). Comparable performance was achieved with both the 80 kV and combined-energy images.

Conclusions

CT-DE can be quantitatively analyzed using radiomic feature calculations. These features may be suitable for ML classification techniques to prospectively identify AHA segments with performance comparable to previously reported manual reading. Future work on larger CT-DE datasets is warranted to establish optimum imaging parameters and features.

CT-Based Radiomics Analysis to Predict Histopathological Outcomes Following Liver Resection in Colorectal Liver Metastases

Simple Summary

The objective of the study was to assess the radiomic features obtained by computed tomography (CT) examination as prognostic biomarkers in patients with colorectal liver metastases, in order to predict histopathological outcomes following liver resection. We obtained good performance considering the single significant textural metric in the identification of the front of tumor growth (expansive versus infiltrative) and tumor budding (high grade versus low grade or absent), in the recognition of mucinous type, and in the detection of recurrences.

Abstract

Purpose: We aimed to assess the efficacy of radiomic features extracted by computed tomography (CT) in predicting histopathological outcomes following liver resection in colorectal liver metastases patients, evaluating recurrence, mutational status, histopathological characteristics (mucinous), and surgical resection margin. Methods: This retrospectively approved study included a training set and an external validation set. The internal training set included 49 patients with a median age of 60 years and 119 liver colorectal metastases. The validation cohort consisted of 28 patients with single liver colorectal metastasis and a median age of 61 years. Radiomic features were extracted using PyRadiomics on CT portal phase. Nonparametric Kruskal–Wallis tests, intraclass correlation, receiver operating characteristic (ROC) analyses, linear regression modeling, and pattern recognition methods (support vector machine (SVM), k-nearest neighbors (KNN), artificial neural network (NNET), and decision tree (DT)) were considered. Results: The median value of intraclass correlation coefficients for the features was 0.92 (range 0.87–0.96). The best performance in discriminating expansive versus infiltrative front of tumor growth was wavelet_HHL_glcm_Imc2, with an accuracy of 79%, a sensitivity of 84%, and a specificity of 67%. The best performance in discriminating expansive versus tumor budding was wavelet_LLL_firstorder_Mean, with an accuracy of 86%, a sensitivity of 91%, and a specificity of 65%. The best performance in differentiating the mucinous type of tumor was original_firstorder_RobustMeanAbsoluteDeviation, with an accuracy of 88%, a sensitivity of 42%, and a specificity of 100%. The best performance in identifying tumor recurrence was the wavelet_HLH_glcm_Idmn, with an accuracy of 85%, a sensitivity of 81%, and a specificity of 88%. The best linear regression model was obtained with the identification of recurrence considering the linear combination of the 16 significant textural metrics (accuracy of 97%, sensitivity of 94%, and specificity of 98%). The best performance for each outcome was reached using KNN as a classifier with an accuracy greater than 86% in the training and validation sets for each classification problem; the best results were obtained with the identification of tumor front growth considering the seven significant textural features (accuracy of 97%, sensitivity of 90%, and specificity of 100%). Conclusions: This study confirmed the capacity of radiomics data to identify several prognostic features that may affect the treatment choice in patients with liver metastases, in order to obtain a more personalized approach.

Progression-Free Survival Prediction in Small Cell Lung Cancer Based on Radiomics Analysis of Contrast-Enhanced CT

Purposes and Objectives

The aim of this study was to predict the progression-free survival (PFS) in patients with small cell lung cancer (SCLC) by radiomic signature from the contrast-enhanced computed tomography (CT).

Methods

A total of 186 cases with pathological confirmed small cell lung cancer were retrospectively assembled. First, 1,218 radiomic features were automatically extracted from tumor region of interests (ROIs) on the lung window and mediastinal window, respectively. Then, the prognostic and robust features were selected by machine learning methods, such as (1) univariate analysis based on a Cox proportional hazard (CPH) model, (2) redundancy removing using the variance inflation factor (VIF), and (3) multivariate importance analysis based on random survival forests (RSF). Finally, PFS predictive models were established based on RSF, and their performances were evaluated using the concordance index (C-index) and the cumulative/dynamic area under the curve (C/D AUC).

Results

In total, 11 radiomic features (6 for mediastinal window and 5 for lung window) were finally selected, and the predictive model constructed from them achieved a C-index of 0.7531 and a mean C/D AUC of 0.8487 on the independent test set, better than the predictions by single clinical features (C-index = 0.6026, mean C/D AUC = 0.6312), and single radiomic features computed in lung window (C-index = 0.6951, mean C/D AUC = 0.7836) or mediastinal window (C-index = 0.7192, mean C/D AUC = 0.7964).

Conclusion

The radiomic features computed from tumor ROIs on both lung window and mediastinal window can predict the PFS for patients with SCLC by a high accuracy, which could be used as a useful tool to support the personalized clinical decision for the diagnosis and patient management of patients with SCLC.

Radiomics-Based Detection of Radionecrosis Using Harmonized Multiparametric MRI

In this study, a radiomics analysis was conducted to provide insights into the differentiation of radionecrosis and tumor progression in multiparametric MRI in the context of a multicentric clinical trial. First, the sensitivity of radiomic features to the unwanted variability caused by different protocol settings was assessed for each modality. Then, the ability of image normalization and ComBat-based harmonization to reduce the scanner-related variability was evaluated. Finally, the performances of several radiomic models dedicated to the classification of MRI examinations were measured. Our results showed that using radiomic models trained on harmonized data achieved better predictive performance for the investigated clinical outcome (balanced accuracy of 0.61 with the model based on raw data and 0.72 with ComBat harmonization). A comparison of several models based on information extracted from different MR modalities showed that the best classification accuracy was achieved with a model based on MR perfusion features in conjunction with clinical observation (balanced accuracy of 0.76 using LASSO feature selection and a Random Forest classifier). Although multimodality did not provide additional benefit in predictive power, the model based on T1-weighted MRI before injection provided an accuracy close to the performance achieved with perfusion.

Impact of image pre-processing methods on computed tomography radiomics features in chronic obstructive pulmonary disease

Computed tomography (CT) imaging texture-based radiomics analysis can be used to assess chronic obstructive pulmonary disease (COPD). However, different image pre-processing methods are commonly used, and how these different methods impact radiomics features and lung disease assessment, is unknown. The purpose of this study was to develop an image pre-processing pipeline to investigate how various pre-processing combinations impact radiomics features and their use for COPD assessment. Spirometry and CT images were obtained from the multi-centered Canadian Cohort of Obstructive Lung Disease study. Participants were divided based on assessment site and were further dichotomized as No COPD or COPD within their participant groups. An image pre-processing pipeline was developed, calculating 32 grey level co-occurrence matrix radiomics features. The pipeline included lung segmentation, airway segmentation or no segmentation, image resampling or no resampling, and either no pre-processing, binning, edgmentation, or thresholding pre-processing techniques. A three-way analysis of variance was used for method comparison. A nested 10-fold cross validation using logistic regression and multiple linear regression models were constructed to classify COPD and assess correlation with lung function, respectively. Logistic regression performance was evaluated using the area under the receiver operating characteristic curve (AUC). A total of 1210 participants (Sites 1-8: No COPD:n = 447, COPD:n = 413; and Site 9: No COPD:n = 155, COPD:n = 195) were evaluated. Between the two participant groups, at least 16/32 features were different between airway segmentation/no segmentation (P ≤ 0.04), at least 29/32 features were different between no resampling/resampling (P ≤ 0.04), and 32/32 features were different between the pre-processing techniques (P < 0.0001). Features generated using the resampling/edgmentation and resampling/thresholding pre-processing combinations, regardless of airway segmentation, performed the best in COPD classification (AUC ≥ 0.718), and explained the most variance with lung function (R² ≥ 0.353). Therefore, the image pre-processing methods completed prior to CT radiomics feature extraction significantly impacted extracted features and their ability to assess COPD.

Multiple Survival Outcome Prediction of Glioblastoma Patients Based on Multiparametric MRI

PURPOSE

Construction of radiomics models for the individualized estimation of multiple survival stratification in glioblastoma (GBM) patients using the multiregional information extracted from multiparametric MRI that could facilitate clinical decision-making for GBM patients.

MATERIALS AND METHODS

A total of 134 eligible GBM patients were selected from The Cancer Genome Atlas. These patients were separated into the long-term and short-term survival groups according to the median of individual survival indicators: overall survival (OS), progression-free survival (PFS), and disease-specific survival (DSS). Then, the patients were divided into a training set and a validation set in a ratio of 2:1. Radiomics features (n = 5,152) were extracted from multiple regions of the GBM using multiparametric MRI. Then, radiomics signatures that are related to the three survival indicators were respectively constructed using the analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) regression for each patient in the training set. Based on a Cox proportional hazards model, the radiomics model was further constructed by combining the signature and clinical risk factors.

RESULTS

The constructed radiomics model showed a promising discrimination ability to differentiate in the training set and validation set of GBM patients with survival indicators of OS, PFS, and DSS. Both the four MRI modalities and five tumor subregions have different effects on the three survival indicators of GBM. The favorable calibration and decision curve analysis indicated the clinical decision value of the radiomics model. The performance of models of the three survival indicators was different but excellent; the best model achieved C indexes of 0.725, 0.677, and 0.724, respectively, in the validation set.

CONCLUSION

Our results show that the proposed radiomics models have favorable predictive accuracy on three survival indicators and can provide individualized probabilities of survival stratification for GBM patients by using multiparametric and multiregional MRI features.

Radiomic Features of Multi-ROI and Multi-Phase MRI for the Prediction of Microvascular Invasion in Solitary Hepatocellular Carcinoma

Objectives

To develop and validate an MR radiomics-based nomogram to predict the presence of MVI in patients with solitary HCC and further evaluate the performance of predictors for MVI in subgroups (HCC ≤ 3 cm and > 3 cm).

Materials and Methods

Between May 2015 and October 2020, 201 patients with solitary HCC were analysed. Radiomic features were extracted from precontrast T₁WI, arterial phase, portal venous phase, delayed phase and hepatobiliary phase images in regions of the intratumoral, peritumoral and their combining areas. The mRMR and LASSO algorithms were used to select radiomic features related to MVI. Clinicoradiological factors were selected by using backward stepwise regression with AIC. A nomogram was developed by incorporating the clinicoradiological factors and radiomics signature. In addition, the radiomic features and clinicoradiological factors related to MVI were separately evaluated in the subgroups (HCC ≤ 3 cm and > 3 cm).

Results

Histopathological examinations confirmed MVI in 111 of the 201 patients (55.22%). The radiomics signature showed a favourable discriminatory ability for MVI in the training set (AUC, 0.896) and validation set (AUC, 0.788). The nomogram incorporating peritumoral enhancement, tumour growth type and radiomics signature showed good discrimination in the training (AUC, 0.932) and validation sets (AUC, 0.917) and achieved well-fitted calibration curves. Subgroup analysis showed that tumour growth type was a predictor for MVI in the HCC ≤ 3 cm cohort and peritumoral enhancement in the HCC > 3 cm cohort; radiomic features related to MVI varied between the HCC ≤ 3 cm and HCC > 3 cm cohort. The performance of the radiomics signature improved noticeably in both the HCC ≤ 3 cm (AUC, 0.953) and HCC > 3 cm cohorts (AUC, 0.993) compared to the original training set.

Conclusions

The preoperative nomogram integrating clinicoradiological risk factors and the MR radiomics signature showed favourable predictive efficiency for predicting MVI in patients with solitary HCC. The clinicoradiological factors and radiomic features related to MVI varied between subgroups (HCC ≤ 3 cm and > 3 cm). The performance of radiomics signature for MVI prediction was improved in both the subgroups.

Computed tomography-based radiomic analysis for prediction of treatment response to salvage chemoradiotherapy for locoregional lymph node recurrence after curative esophagectomy

Objective

To investigate the capability of computed tomography (CT) radiomic features to predict the therapeutic response and local control of the locoregional recurrence lymph node (LN) after curative esophagectomy by chemoradiotherapy.

Methods

This retrospective study included 129 LN from 77 patients (training cohort: 102 LN from 59 patients; validation cohort: 27 LN from 18 patients) with postoperative esophageal squamous cell carcinoma (ESCC). The region of the tumor was contoured in pretreatment contrast‐enhanced CT images. The least absolute shrinkage and selection operator with logistic regression was used to identify radiomic predictors in the training cohort. Model performance was evaluated using the area under the receiver operating characteristic curves (AUC). The Kaplan–Meier method was used to determine the local recurrence time of cancer.

Results

The radiomic model suggested seven features that could be used to predict treatment response. The AUCs in training and validated cohorts were 0.777 (95% CI: 0.667–0.878) and 0.765 (95% CI: 0.556–0.975), respectively. A significant difference in the radiomic scores (Rad‐scores) between response and nonresponse was observed in the two cohorts (p < 0.001, 0.034, respectively). Two features were identified for classifying whether there will be relapse in 2 years. AUC was 0.857 (95% CI: 0.780–0.935) in the training cohort. The local control time of the high Rad‐score group was higher than the low group in both cohorts (p < 0.001 and 0.025, respectively). As inferred from the Cox regression analysis, the low Rad‐score was a high‐risk factor for local recurrence within 2 years.

Conclusions

The radiomic approach can be used as a potential imaging biomarker to predict treatment response and local control of recurrence LN in ESCC patients.

A Pipeline for Predicting the Treatment Response of Neoadjuvant Chemoradiotherapy for Locally Advanced Rectal Cancer Using Single MRI Modality: Combining Deep Segmentation Network and Radiomics Analysis Based on "Suspicious Region"

Patients with locally advanced rectal cancer (LARC) who achieve a pathologic complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) typically have a good prognosis. An early and accurate prediction of the treatment response, i.e., whether a patient achieves pCR, could significantly help doctors make tailored plans for LARC patients. This study proposes a pipeline of pCR prediction using a combination of deep learning and radiomics analysis. Taking into consideration missing pre-nCRT magnetic resonance imaging (MRI), as well as aiming to improve the efficiency for clinical application, the pipeline only included a post-nCRT T2-weighted (T2-w) MRI. Unlike other studies that attempted to carefully find the region of interest (ROI) using a pre-nCRT MRI as a reference, we placed the ROI on a “suspicious region”, which is a continuous area that has a high possibility to contain a tumor or fibrosis as assessed by radiologists. A deep segmentation network, termed the two-stage rectum-aware U-Net (tsraU-Net), is designed to segment the ROI to substitute for a time-consuming manual delineation. This is followed by a radiomics analysis model based on the ROI to extract the hidden information and predict the pCR status. The data from a total of 275 patients were collected from two hospitals and partitioned into four datasets: Seg-T (N = 88) for training the tsraUNet, Rad-T (N = 107) for building the radiomics model, In-V (N = 46) for internal validation, and Ex-V (N = 34) for external validation. The proposed method achieved an area under the curve (AUC) of 0.829 (95% confidence interval [CI]: 0.821, 0.837) on In-V and 0.815 (95% CI, 0.801, 0.830) on Ex-V. The performance of the method was considerable and stable in two validation sets, indicating that the well-designed pipeline has the potential to be used in real clinical procedures.

Technical Note: On the development of an outcome-driven frequency filter for improving Radiomics-based modeling of Human Papilloma Virus (HPV) in patients with oropharyngeal squamous cell carcinomas

PURPOSE

To implement an outcome-driven frequency filter for improving radiomics-based modeling of human papilloma virus (HPV) for patients with oropharyngeal squamous cell carcinoma (OPSCC).

METHODS AND MATERIALS

One hundred twenty-eight OPSCC patients with known HPV status (60-HPV+ and 68-HPV-, confirmed by immunohistochemistry-P16 protein testing) were retrospectively studied. A 3D Discrete Fourier Transform was applied on contrast-enhanced CT images of patient gross tumor volumes (GTV's) to transform intensity distributions to the frequency domain and estimate frequency power spectrums of HPV- and HPV+ patient cohorts. Statistical analyses were performed to rank frequency bands contributing towards prediction of HPV status. An outcome-driven frequency filter was designed accordingly and applied to GTV frequency information. 3D Inverse-Discrete-Fourier-Transform was applied to reconstruct HPV-related frequency-filtered images. Radiomics features (11 feature-categories) were extracted from pre- and post- frequency filtered images using our previously published 'ROdiomiX' software. Least-Absolute-Shrinkage-and-Selection-Operation (Lasso) combined with a Generalized-Linear-Model (Lasso-GLM) was developed to identify and rank feature subsets with optimal information for prediction of HPV+/-. Radiomics-based Lasso-GLM classifiers (pre- and post-frequency filtered) were constructed and validated using a random permutation sampling and nested cross-validation techniques. Average Area Under Receiver Operating Characteristic (AUC), and Positive and Negative Predictive values (PPV, NPV) were computed to estimate generalization error and prediction performance.

RESULTS

Among 192 radiomic features, 15 features were found to be statistically significant discriminators between HPV+/- cohorts on post-frequency filtered CE-CT images; 14 such radiomic features were observed on pre-frequency filtered datasets. Discriminant features included tumor morphology and intensity contrast. Performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were: AUC/PPV/NPV = 0.789/0.755/0.805 and 0.850/0.808/0.877 respectively. Nested-CV performances for prediction of HPV for the pre- and post-frequency filtered Lasso-GLM classifiers were: AUC/PPV/NPV = 0.814/0.725/0.877 and 0.890/0.820/0.911 respectively.

CONCLUSION

Albeit subject to confirmation in a larger cohort, this pilot study presents encouraging results on the importance of frequency analysis prior to radiomic feature extraction toward enhancement of model performance for characterizing HPV in patients with OPSCC. This article is protected by copyright. All rights reserved.

Pre-Operative Prediction of Mediastinal Node Metastasis Using Radiomics Model Based on 18F-FDG PET/CT of the Primary Tumor in Non-Small Cell Lung Cancer Patients

Purpose: We investigated whether a fluorine-18-fluorodeoxy glucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT)-based radiomics model (RM) could predict the pathological mediastinal lymph node staging (pN staging) in patients with non-small cell lung cancer (NSCLC) undergoing surgery.

Methods: A total of 716 patients with a clinicopathological diagnosis of NSCLC were included in this retrospective study. The prediction model was developed in a training cohort that consisted of 501 patients. Radiomics features were extracted from the ¹⁸F-FDG PET/CT of the primary tumor. Support vector machine and extremely randomized trees were used to build the RM. Internal validation was assessed. An independent testing cohort contained the remaining 215 patients. The performances of the RM and clinical node staging (cN staging) in predicting pN staging (pN0 vs. pN1 and N2) were compared for each cohort. The area under the curve (AUC) of the receiver operating characteristic curve was applied to assess the model's performance.

Results: The AUC of the RM [0.81 (95% CI, 0.771–0.848); sensitivity: 0.794; specificity: 0.704] for the predictive performance of pN1 and N2 was significantly better than that of cN in the training cohort [0.685 (95% CI, 0.644–0.728); sensitivity: 0.804; specificity: 0.568], (P-value = 8.29e-07, as assessed by the Delong test). In the testing cohort, the AUC of the RM [0.766 (95% CI, 0.702–0.830); sensitivity: 0.688; specificity: 0.704] was also significantly higher than that of cN [0.685 (95% CI, 0.619–0.747); sensitivity: 0.799; specificity: 0.568], (P = 0.0371, Delong test).

Conclusions: The RM based on ¹⁸F-FDG PET/CT has a potential for the pN staging in patients with NSCLC, suggesting that therapeutic planning could be tailored according to the predictions.

Combination of Quantitative MRI Fat Fraction and Texture Analysis to Evaluate Spastic Muscles of Children With Cerebral Palsy

Background: Cerebral palsy (CP) is the most common cause of physical disability in childhood. Muscle pathologies occur due to spasticity and contractures; therefore, diagnostic imaging to detect pathologies is often required. Imaging has been used to assess torsion or estimate muscle volume, but additional methods for characterizing muscle composition have not thoroughly been investigated. MRI fat fraction (FF) measurement can quantify muscle fat and is often a part of standard imaging in neuromuscular dystrophies. To date, FF has been used to quantify muscle fat and assess function in CP. In this study, we aimed to utilize a radiomics and FF analysis along with the combination of both methods to differentiate affected muscles from healthy ones.

Materials and Methods: A total of 9 patients (age range 8–15 years) with CP and 12 healthy controls (age range 9–16 years) were prospectively enrolled (2018–2020) after ethics committee approval. Multi-echo Dixon acquisition of the calf muscles was used for FF calculation. The images of the second echo (TE = 2.87 ms) were used for feature extraction from the soleus, gastrocnemius medialis, and gastrocnemius lateralis muscles. The least absolute shrinkage and selection operator (LASSO) regression was employed for feature selection. RM, FF model (FFM), and combined model (CM) were built for each calf muscle. The receiver operating characteristic (ROC) curve and their respective area under the curve (AUC) values were used to evaluate model performance.

Results: In total, the affected legs of 9 CP patients and the dominant legs of 12 healthy controls were analyzed. The performance of RM for soleus, gastrocnemius medialis, and gastrocnemius lateralis (AUC 0.92, 0.92, 0.82, respectively) was better than the FFM (AUC 0.88, 0.85, 0.69, respectively). The combination of both models always had a better performance than RM or FFM (AUC 0.95, 0.93, 0.83). FF was higher in the patient group (FF_S 9.1%, FF_GM 8.5%, and FF_GL 10.2%) than control group (FF_S 3.3%, FF_GM 4.1%, FF_GL 6.6%).

Conclusion: The combination of MRI quantitative fat fraction analysis and texture analysis of muscles is a promising tool to evaluate muscle pathologies due to CP in a non-invasive manner.

Technical Note: ROdiomiX: A validated software for radiomics analysis of medical images in radiation oncology

PURPOSE

This study introduces an in-house-designed software platform (ROdiomiX) for the radiomics analysis of medical images in radiation oncology. ROdiomiX is a MATLAB-based framework for the computation of radiomic features and feature aggregation techniques in compliance with the Image-Biomarker-Standardization-Initiative (IBSI) guidelines, which includes preprocessing protocols and quantitative benchmark results for analysis of computational phantom images.

METHODS AND MATERIALS

The ROdiomiX software system consists of a series of computation cores implemented on the basis of the guidelines proposed by the IBSI. It is capable of quantitative computation of the following 11 different feature categories: Local-Intensity, Intensity-Histogram, Intensity-Based-Statistical, Intensity-Volume-Histogram, Gray-Level-Co-occurrence, Gray-Level-Run-Length, Gray-Level-Size-Zone, Gray-Level-Distance-Zone, Neighborhood-Grey-Tone-Difference, Neighboring-Grey-Level-Dependence, and Morphological feature. ROdiomiX was validated against benchmark values for the IBSI 3D digital phantom, as well as one designed in-house (HFH). The intraclass correlation coefficient (ICC) for estimating the degree of absolute agreement between ROdiomiX computation and benchmark values for different features at the 95% confidence level (CL) was used for comparison.

RESULTS

Among the 11 feature categories with 149 total features including 10 different feature aggregation methods (following the IBSI guidelines), the percent difference between absolute feature values computed by the ROdiomiX software and benchmark values reported for IBSI and HFH digital phantoms were 0.14% + 0.43% and 0.11% + 0.27%, respectively. The ICC values were >0.997 for all ten feature categories for both the IBSI and HFH digital phantoms.

CONCLUSION

The authors successfully developed a platform for computation of quantitative radiomic features. The image preprocessing and computational software cores were designed following the procedures specified by the IBSI. Benchmarking testing was in excellent agreement against the IBSI- and HFH-designed computational phantoms.

Radiomics Analysis of Susceptibility Weighted Imaging for Hepatocellular Carcinoma: Exploring the Correlation between Histopathology and Radiomics Features

Purpose:

No previous researches have extracted radiomics features from susceptibility weighted imaging (SWI) for biomedical applications. This research aimed to explore the correlation between histopathology of hepatocellular carcinoma (HCC) and radiomics features extracted from SWI.

Methods:

A total of 53 patients were ultimately enrolled into this retrospective study with MR examinations undertaken at a 3T scanner. About 107 radiomics features were extracted from SWI images of each patient. Then, the Spearman correlation test was performed to evaluate the correlation between the SWI-derived radiomics features and histopathologic indexes including histopathologic grade, microvascular invasion (MVI) as well as the expression status of cytokeratin 7 (CK-7), cytokeratin 19 (CK-19) and Glypican-3 (GPC-3). With SWI-derived radiomics features utilized as independent variables, four logistic regression-based diagnostic models were established for diagnosing patients with positive CK-7, CK-19, GPC-3 and high histopathologic grade, respectively. Then, receiver operating characteristic analysis was performed to evaluate the diagnostic performance.

Results:

A total of 11, 32, 18 and one SWI-derived radiomics features were significantly correlated with histopathologic grade, the expression of CK-7, the expression of CK-19 and the expression of GPC-3 (P < 0.05), respectively. None of the SWI-derived radiomics features was correlated with MVI status. The areas under the curve were 0.905, 0.837, 0.800 and 0.760 for diagnosing patients with positive CK-19, positive CK-7, high histopathologic grade and positive GPC-3.

Conclusion:

Extracting the radiomics features from SWI images was feasible to evaluate multiple histopathologic indexes of HCC.

[18F]FDG PET immunotherapy radiomics signature (iRADIOMICS) predicts response of non-small-cell lung cancer patients treated with pembrolizumab

Background

Immune checkpoint inhibitors have changed the paradigm of cancer treatment; however, non-invasive biomarkers of response are still needed to identify candidates for non-responders. We aimed to investigate whether immunotherapy [¹⁸F]FDG PET radiomics signature (iRADIOMICS) predicts response of metastatic non-small-cell lung cancer (NSCLC) patients to pembrolizumab better than the current clinical standards.

Patients and methods

Thirty patients receiving pembrolizumab were scanned with [¹⁸F]FDG PET/CT at baseline, month 1 and 4. Associations of six robust primary tumour radiomics features with overall survival were analysed with Mann-Whitney U-test (MWU), Cox proportional hazards regression analysis, and ROC curve analysis. iRADIOMICS was constructed using univariate and multivariate logistic models of the most promising feature(s). Its predictive power was compared to PD-L1 tumour proportion score (TPS) and iRECIST using ROC curve analysis. Prediction accuracies were assessed with 5-fold cross validation.

Results

The most predictive were baseline radiomics features, e.g. Small Run Emphasis (MWU, p = 0.001; hazard ratio = 0.46, p = 0.007; AUC = 0.85 (95% CI 0.69–1.00)). Multivariate iRADIOMICS was found superior to the current standards in terms of predictive power and timewise with the following AUC (95% CI) and accuracy (standard deviation): iRADIOMICS (baseline), 0.90 (0.78–1.00), 78% (18%); PD-L1 TPS (baseline), 0.60 (0.37–0.83), 53% (18%); iRECIST (month 1), 0.79 (0.62–0.95), 76% (16%); iRECIST (month 4), 0.86 (0.72–1.00), 76% (17%).

Conclusions

Multivariate iRADIOMICS was identified as a promising imaging biomarker, which could improve management of metastatic NSCLC patients treated with pembrolizumab. The predicted non-responders could be offered other treatment options to improve their overall survival.

Preoperative Prediction of Microvascular Invasion of Hepatocellular Carcinoma: Radiomics Algorithm Based on Ultrasound Original Radio Frequency Signals

Background: To evaluate the accuracy of radiomics algorithm based on original radio frequency (ORF) signals for prospective prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) lesions.

Methods: In this prospective study, we enrolled 42 inpatients diagnosed with HCC from January 2018 to December 2018. All HCC lesions were proved by surgical resection and histopathology results, including 21 lesions with MVI. Ultrasound ORF data and grayscale ultrasound images of HCC lesions were collected before operation for further radiomics analysis. Three ultrasound feature maps were calculated using signal analysis and processing (SAP) technology in first feature extraction. The diagnostic accuracy of model based on ORF signals was compared with the model based on grayscale ultrasound images.

Results: A total of 1,050 radiomics features were extracted from ORF signals of each HCC lesion. The performance of MVI prediction model based on ORF was better than those based on grayscale ultrasound images. The best area under curve, accuracy, sensitivity, and specificity of ultrasound radiomics in prediction of MVI were 95.01, 92.86, 85.71, and 100%, respectively.

Conclusions: Radiomics algorithm based on ultrasound ORF data combined with SAP technology can effectively predict MVI, which has potential clinical application value for non-invasively preoperative prediction of MVI in HCC patients.

Establishment of a new non-invasive imaging prediction model for liver metastasis in colon cancer

The aim of this study was to develop and validate a new non-invasive artificial intelligence (AI) model based on preoperative computed tomography (CT) data to predict the presence of liver metastasis (LM) in colon cancer (CC). A total of forty-eight eligible CC patients were enrolled, including twenty-four patients with LM and twenty-four patients without LM. Six clinical factors and one hundred and fifty-two tumor image features extracted from CT data were utilized to develop three models: clinical, radiomics, and hybrid (a combination of clinical and radiomics features) using support vector machines with 5-fold cross-validation. The performance of each model was evaluated in terms of accuracy, specificity, sensitivity, and area under the curve (AUC). For the radiomics model, a total of four image features utilized to construct the model resulting in an accuracy of 83.87% for training and 79.50% for validation. The clinical model that employed two selected clinical variables had an accuracy of 69.82% and 69.50% for training and validation, respectively. The hybrid model that combined relevant image features and clinical variables improved accuracy of both training (90.63%) and validation (85.50%) sets. In terms of AUC, hybrid (0.96; 0.87) and radiomics models (0.91; 0.85) demonstrated a significant improvement compared with the clinical model (0.71; 0.69), and the hybrid model had the best prediction performance. In conclusion, the AI model developed using preoperative conventional CT data can accurately predict LM in CC patients without additional procedures. Furthermore, combining image features with clinical characteristics greatly improved the model's prediction performance. We have thus generated a promising tool that allows guidance and individualized surveillance of CC patients with high risks of LM.

A Multi-parametric MRI-Based Radiomics Signature and a Practical ML Model for Stratifying Glioblastoma Patients Based on Survival Toward Precision Oncology

Purpose: Predicting patients' survival outcomes is recognized of key importance to clinicians in oncology toward determining an ideal course of treatment and patient management. This study applies radiomics analysis on pre-operative multi-parametric MRI of patients with glioblastoma from multiple institutions to identify a signature and a practical machine learning model for stratifying patients into groups based on overall survival.

Methods: This study included 163 patients' data with glioblastoma, collected by BRATS 2018 Challenge from multiple institutions. In this proposed method, a set of 147 radiomics image features were extracted locally from three tumor sub-regions on standardized pre-operative multi-parametric MR images. LASSO regression was applied for identifying an informative subset of chosen features whereas a Cox model used to obtain the coefficients of those selected features. Then, a radiomics signature model of 9 features was constructed on the discovery set and it performance was evaluated for patients stratification into short- (<10 months), medium- (10–15 months), and long-survivors (>15 months) groups. Eight ML classification models, trained and then cross-validated, were tested to assess a range of survival prediction performance as a function of the choice of features.

Results: The proposed mpMRI radiomics signature model had a statistically significant association with survival (P < 0.001) in the training set, but was not confirmed (P = 0.110) in the validation cohort. Its performance in the validation set had a sensitivity of 0.476 (short-), 0.231 (medium-), and 0.600 (long-survivors), and specificity of 0.667 (short-), 0.732 (medium-), and 0.794 (long-survivors). Among the tested ML classifiers, the ensemble learning model's results showed superior performance in predicting the survival classes, with an overall accuracy of 57.8% and AUC of 0.81 for short-, 0.47 for medium-, and 0.72 for long-survivors using the LASSO selected features combined with clinical factors.

Conclusion: A derived GLCM feature, representing intra-tumoral inhomogeneity, was found to have a high association with survival. Clinical factors, when added to the radiomics image features, boosted the performance of the ML classification model in predicting individual glioblastoma patient's survival prognosis, which can improve prognostic quality a further step toward precision oncology.

Radiomics Analysis of Multiparametric MRI Evaluates the Pathological Features of Cervical Squamous Cell Carcinoma

BACKGROUND

Robust parameters to evaluate pathological aggressiveness are needed to provide individualized therapy for cervical cancer patients.

PURPOSE

To investigate the radiomics analysis of multiparametric MRI to evaluate tumor grade, lymphovascular space invasion (LVSI), and lymph node (LN) metastasis of cervical squamous cell carcinoma (CSCC).

STUDY TYPE

Retrospective.

SUBJECTS

Fifty-six patients with histopathologically confirmed CSCC.

FIELD STRENGTH/SEQUENCE

3T, axial T₂ and T₂ with fat suppression (FS), diffusion-weighted imaging (DWI) (multi-b values), axial dynamic contrast enhanced (DCE) MRI (8 sec temporal resolution).

ASSESSMENT

Regions of interest were drawn around the tumor on each axial slice and fused to generate the whole tumor volume. Sixty-six radiomics features were derived from each image sequence, including axial T₂ and T₂ FS, ADC maps, and K_trans , V_e , and V_p maps from DCE MRI.

STATISTICAL TESTS

A univariate analysis was performed to assess each parameter's association with tumor grade and the presence of lymphovascular space invasion (LVSI) and lymph node (LN) metastasis. A principal component analysis was employed for dimension reduction and to generate new discriminative valuables. Using logistic regression, a discriminative model of each parameter was built and a receiver operating characteristic curve (ROC) was generated.

RESULTS

The area under the ROC curve (AUC) of anatomical, diffusion, and permeability parameters in discriminating the presence of LVSI ranged from 0.659 to 0.814, with V_e showing the best discriminative value. The AUC in discriminating the presence of LN metastasis and distinguishing tumor grade ranged from 0.747 to 0.850, 0.668 to 0.757, with ADC and V_e showing the best discriminative value, respectively.

DATA CONCLUSION

Functional maps exhibit better discriminative values than anatomical images for discriminating the pathological features of CSCC, with ADC maps showing the best discrimination performance for LN metastasis and V_e maps showing the best discriminative value for LVSI and tumor grade.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1141-1148.

Radiomic analysis in T2W and SPAIR T2W MRI: predict treatment response to chemoradiotherapy in esophageal squamous cell carcinoma

Background

To investigate the capability of radiomic analysis using T2-weighted (T2W) and spectral attenuated inversion-recovery T2-weighted (SPAIR T2W) magnetic resonance imaging (MRI) for predicting the therapeutic response of esophageal squamous cell carcinoma (ESCC) to chemoradiotherapy (CRT).

Methods

Pretreatment T2W- and SPAIR T2W-MRI of 68 ESCC patients (37 responders, 31 nonresponders) were analyzed. A number of 138 radiomic features were extracted from each image sequence respectively. Kruskal-Wallis test were performed to evaluate the capability of each feature on treatment response classification. Sensitivity and specificity for each of the studied features were derived using receiver operating characteristic (ROC) analysis. Support vector machine (SVM) and artificial neural network (ANN) models were constructed based on the training set (23 responders, 20 nonresponders) for the prediction of treatment response, and then the testing set (14 responders, 11 nonresponders) validated the reliability of the models. Comparison between the performances of the models was performed by using McNemar's test.

Results

Radiomic analysis showed significance in the prediction of treatment response. The analyses showed that complete responses (CRs) versus stable diseases (SDs), partial responses (PRs) versus SDs, and responders (CRs and PRs) versus nonresponders (SDs) could be differentiated by 26, 17, and 33 features (T2W: 11/11/15, SPAIR T2W: 15/6/18), respectively. The prediction models (ANN and SVM) based on features extracted from SPAIR T2W sequence (SVM: 0.929, ANN: 0.883) showed higher accuracy than those derived from T2W (SVM: 0.893, ANN: 0.861). No statistical difference was observed in the performance of the two classifiers (P=0.999).

Conclusions

Radiomic analysis based on pretreatment T2W- and SPAIR T2W-MRI can be served as imaging biomarkers to predict treatment response to CRT in ESCC patients.

Radiomic analysis in contrast-enhanced CT: predict treatment response to chemoradiotherapy in esophageal carcinoma

Objectives

To investigate the capability of computed-tomography (CT) radiomic features to predict the therapeutic response of Esophageal Carcinoma (EC) to chemoradiotherapy (CRT).

Methods

Pretreatment contrast-enhanced CT images of 49 EC patients (33 responders, 16 nonresponders) who received with CRT were retrospectively analyzed. The region of tumor was contoured by two radiologists. A total of 214 features were extracted from the tumor region. Kruskal-Wallis test and receiver operating characteristic (ROC) analysis were performed to evaluate the capability of each feature on treatment response classification. Support vector machine (SVM) and artificial neural network (ANN) algorithms were used to build models for prediction of the treatment response. The statistical difference between the performances of the models was assessed using McNemar's test.

Results

Radiomic-based classification showed significance in differentiating responders from nonresponders. Five features were found to discriminate nonresponders from responders (AUCs from 0.686 to 0.727). Considering these features, two features (Histogram2D_skewness: P = 0.015. Histogram2D_kurtosis: P = 0.039) were significant for differentiating SDs (stable disease) from PRs (partial response) and one feature (Histogram2D_skewness: P = 0.027) for differentiating SDs from CRs (complete response). Both classifiers showed potential in predicting the treatment response with higher accuracy (ANN: 0.972, SVM: 0.891). No statistically significant difference was observed in the performance of the two classifiers (P = 0.250).

Conclusions

CT-based radiomic features can be used as imaging biomarkers to predict tumor response to CRT in EC patients.