Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

Radiomics predict the WHO/ISUP nuclear grade and survival in clear cell renal cell carcinoma

OBJECTIVES

This study aimed to assess the predictive value of radiomics derived from intratumoral and peritumoral regions and to develop a radiomics nomogram to predict preoperative nuclear grade and overall survival (OS) in patients with clear cell renal cell carcinoma (ccRCC).

METHODS

The study included 395 patients with ccRCC from our institution. The patients in Center A (anonymous) institution were randomly divided into a training cohort (n = 284) and an internal validation cohort (n = 71). An external validation cohort comprising 40 patients from Center B also was included. Computed tomography (CT) radiomics features were extracted from the internal area of the tumor (IAT) and IAT combined peritumoral areas of the tumor at 3 mm (PAT 3 mm) and 5 mm (PAT 5 mm). Independent predictors from both clinical and radiomics scores (Radscore) were used to construct a radiomics nomogram. Kaplan-Meier analysis with a log-rank test was performed to evaluate the correlation between factors and OS.

RESULTS

The PAT 5-mm radiomics model (RM) exhibited exceptional predictive capability for grading, achieving an area under the curves of 0.80, 0.80, and 0.90 in the training, internal validation, and external validation cohorts. The nomogram and RM gained from the PAT 5-mm region were more clinically useful than the clinical model. The association between OS and predicted nuclear grade derived from the PAT 5-mm Radscore and the nomogram-predicted score was statistically significant (p < 0.05).

CONCLUSION

The CT-based radiomics and nomograms showed valuable predictive capabilities for the World Health Organization/International Society of Urological Pathology grade and OS in patients with ccRCC.

CRITICAL RELEVANCE STATEMENT

The intratumoral and peritumoral radiomics are feasible and promising to predict nuclear grade and overall survival in patients with clear cell renal cell carcinoma, which can contribute to the development of personalized preoperative treatment strategies.

KEY POINTS

The multi-regional radiomics features are associated with clear cell renal cell carcinoma (ccRCC) grading and prognosis. The combination of intratumoral and peritumoral 5 mm regional features demonstrated superior predictive performance for grading. The nomogram and radiomics models have a broad range of clinical applications.

Identification of clear cell renal cell carcinoma subtypes by integrating radiomics and transcriptomics

Objective

This study aimed to delineate the clear cell renal cell carcinoma (ccRCC) intrinsic subtypes through unsupervised clustering of radiomics and transcriptomics data and to evaluate their associations with clinicopathological features, prognosis, and molecular characteristics.

Methods

Using a retrospective dual-center approach, we gathered transcriptomic and clinical data from ccRCC patients registered in The Cancer Genome Atlas and contrast-enhanced computed tomography images from The Cancer Imaging Archive and local databases. Following the segmentation of images, radiomics feature extraction, and feature preprocessing, we performed unsupervised clustering based on the "CancerSubtypes" package to identify distinct radiotranscriptomic subtypes, which were then correlated with clinical-pathological, prognostic, immune, and molecular characteristics.

Results

Clustering identified three subtypes, C1, C2, and C3, each of which displayed unique clinicopathological, prognostic, immune, and molecular distinctions. Notably, subtypes C1 and C3 were associated with poorer survival outcomes than subtype C2. Pathway analysis highlighted immune pathway activation in C1 and metabolic pathway prominence in C2. Gene mutation analysis identified VHL and PBRM1 as the most commonly mutated genes, with more mutated genes observed in the C3 subtype. Despite similar tumor mutation burdens, microsatellite instability, and RNA interference across subtypes, C1 and C3 demonstrated greater tumor immune dysfunction and rejection. In the validation cohort, the various subtypes showed comparable results in terms of clinicopathological features and prognosis to those observed in the training cohort, thus confirming the efficacy of our algorithm.

Conclusion

Unsupervised clustering based on radiotranscriptomics can identify the intrinsic subtypes of ccRCC, and radiotranscriptomic subtypes can characterize the prognosis and molecular features of tumors, enabling noninvasive tumor risk stratification.

Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization

Background and purpose

Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs).

Materials and methods

Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance.

Results

Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization.

Conclusions

To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.

Information fusion for fully automated segmentation of head and neck tumors from PET and CT images

BACKGROUND

PET/CT images combining anatomic and metabolic data provide complementary information that can improve clinical task performance. PET image segmentation algorithms exploiting the multi-modal information available are still lacking.

PURPOSE

Our study aimed to assess the performance of PET and CT image fusion for gross tumor volume (GTV) segmentations of head and neck cancers (HNCs) utilizing conventional, deep learning (DL), and output-level voting-based fusions.

METHODS

The current study is based on a total of 328 histologically confirmed HNCs from six different centers. The images were automatically cropped to a 200 × 200 head and neck region box, and CT and PET images were normalized for further processing. Eighteen conventional image-level fusions were implemented. In addition, a modified U2-Net architecture as DL fusion model baseline was used. Three different input, layer, and decision-level information fusions were used. Simultaneous truth and performance level estimation (STAPLE) and majority voting to merge different segmentation outputs (from PET and image-level and network-level fusions), that is, output-level information fusion (voting-based fusions) were employed. Different networks were trained in a 2D manner with a batch size of 64. Twenty percent of the dataset with stratification concerning the centers (20% in each center) were used for final result reporting. Different standard segmentation metrics and conventional PET metrics, such as SUV, were calculated.

RESULTS

In single modalities, PET had a reasonable performance with a Dice score of 0.77 ± 0.09, while CT did not perform acceptably and reached a Dice score of only 0.38 ± 0.22. Conventional fusion algorithms obtained a Dice score range of [0.76-0.81] with guided-filter-based context enhancement (GFCE) at the low-end, and anisotropic diffusion and Karhunen-Loeve transform fusion (ADF), multi-resolution singular value decomposition (MSVD), and multi-level image decomposition based on latent low-rank representation (MDLatLRR) at the high-end. All DL fusion models achieved Dice scores of 0.80. Output-level voting-based models outperformed all other models, achieving superior results with a Dice score of 0.84 for Majority_ImgFus, Majority_All, and Majority_Fast. A mean error of almost zero was achieved for all fusions using SUVpeak , SUVmean and SUVmedian .

CONCLUSION

PET/CT information fusion adds significant value to segmentation tasks, considerably outperforming PET-only and CT-only methods. In addition, both conventional image-level and DL fusions achieve competitive results. Meanwhile, output-level voting-based fusion using majority voting of several algorithms results in statistically significant improvements in the segmentation of HNC.

Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics

PURPOSE

Glioblastoma Multiforme (GBM) represents the predominant aggressive primary tumor of the brain with short overall survival (OS) time. We aim to assess the potential of radiomic features in predicting the time-to-event OS of patients with GBM using machine learning (ML) algorithms.

MATERIALS AND METHODS

One hundred nineteen patients with GBM, who had T1-weighted contrast-enhanced and T2-FLAIR MRI sequences, along with clinical data and survival time, were enrolled. Image preprocessing methods included 64 bin discretization, Laplacian of Gaussian (LOG) filters with three Sigma values and eight variations of Wavelet Transform. Images were then segmented, followed by the extraction of 1212 radiomic features. Seven feature selection (FS) methods and six time-to-event ML algorithms were utilized. The combination of preprocessing, FS, and ML algorithms (12 × 7 × 6 = 504 models) was evaluated by multivariate analysis.

RESULTS

Our multivariate analysis showed that the best prognostic FS/ML combinations are the Mutual Information (MI)/Cox Boost, MI/Generalized Linear Model Boosting (GLMB) and MI/Generalized Linear Model Network (GLMN), all of which were done via the LOG (Sigma = 1 mm) preprocessing method (C-index = 0.77). The LOG filter with Sigma = 1 mm preprocessing method, MI, GLMB and GLMN achieved significantly higher C-indices than other preprocessing, FS, and ML methods (all p values < 0.05, mean C-indices of 0.65, 0.70, and 0.64, respectively).

CONCLUSION

ML algorithms are capable of predicting the time-to-event OS of patients using MRI-based radiomic and clinical features. MRI-based radiomics analysis in combination with clinical variables might appear promising in assisting clinicians in the survival prediction of patients with GBM. Further research is needed to establish the applicability of radiomics in the management of GBM in the clinic.

A multi-model based on radiogenomics and deep learning techniques associated with histological grade and survival in clear cell renal cell carcinoma

OBJECTIVES

This study aims to evaluate the efficacy of multi-model incorporated by radiomics, deep learning, and transcriptomics features for predicting pathological grade and survival in patients with clear cell renal cell carcinoma (ccRCC).

METHODS

In this study, data were collected from 177 ccRCC patients, including radiomics features, deep learning (DL) features, and RNA sequencing data. Diagnostic models were then created using these data through least absolute shrinkage and selection operator (LASSO) analysis. Additionally, a multi-model was developed by combining radiomics, DL, and transcriptomics features. The prognostic performance of the multi-model was evaluated based on progression-free survival (PFS) and overall survival (OS) outcomes, assessed using Harrell's concordance index (C-index). Furthermore, we conducted an analysis to investigate the relationship between the multi-model and immune cell infiltration.

RESULTS

The multi-model demonstrated favorable performance in discriminating pathological grade, with area under the ROC curve (AUC) values of 0.946 (95% CI: 0.912-0.980) and 0.864 (95% CI: 0.734-0.994) in the training and testing cohorts, respectively. Additionally, it exhibited statistically significant prognostic performance for predicting PFS and OS. Furthermore, the high-grade group displayed a higher abundance of immune cells compared to the low-grade group.

CONCLUSIONS

The multi-model incorporated radiomics, DL, and transcriptomics features demonstrated promising performance in predicting pathological grade and prognosis in patients with ccRCC.

CRITICAL RELEVANCE STATEMENT

We developed a multi-model to predict the grade and survival in clear cell renal cell carcinoma and explored the molecular biological significance of the multi-model of different histological grades.

KEY POINTS

1. The multi-model achieved an AUC of 0.864 for assessing pathological grade. 2. The multi-model exhibited an association with survival in ccRCC patients. 3. The high-grade group demonstrated a greater abundance of immune cells.

Dual-Centre Harmonised Multimodal Positron Emission Tomography/Computed Tomography Image Radiomic Features and Machine Learning Algorithms for Non-small Cell Lung Cancer Histopathological Subtype Phenotype Decoding

AIMS

We aimed to build radiomic models for classifying non-small cell lung cancer (NSCLC) histopathological subtypes through a dual-centre dataset and comprehensively evaluate the effect of ComBat harmonisation on the performance of single- and multimodality radiomic models.

MATERIALS AND METHODS

A public dataset of NSCLC patients from two independent centres was used. Two image fusion methods, namely guided filtering-based fusion and image fusion based on visual saliency map and weighted least square optimisation, were used. Radiomic features were extracted from each scan, including first-order, texture and moment-invariant features. Subsequently, ComBat harmonisation was applied to the extracted features from computed tomography (CT), positron emission tomography (PET) and fused images to correct the centre effect. For feature selection, least absolute shrinkage and selection operator (Lasso) and recursive feature elimination (RFE) were investigated. For machine learning, logistic regression (LR), support vector machine (SVM) and AdaBoost were evaluated for classifying NSCLC subtypes. Training and evaluation of the models were carried out in a robust framework to offset plausible errors and performance was reported using area under the curve, balanced accuracy, sensitivity and specificity before and after harmonisation. N-way ANOVA was used to assess the effect of different factors on the performance of the models.

RESULTS

Support vector machine fed with selected features by recursive feature elimination from a harmonised PET feature set achieved the highest performance (area under the curve = 0.82) in classifying NSCLC histopathological subtypes. Although the performance of the models did not significantly improve for CT images after harmonisation, the performance of PET and guided filtering-based fusion feature signatures significantly improved for almost all models. Although the selection of the image modality and feature selection methods was effective on the performance of the model (ANOVA P-values <0.001), machine learning and harmonisation did not change the performance significantly (ANOVA P-values = 0.839 and 0.292, respectively).

CONCLUSION

This study confirmed the potential of radiomic analysis on PET, CT and hybrid images for histopathological classification of NSCLC subtypes.

Risk Stratification and Overall Survival Prediction in Advanced Gastric Cancer Patients Based on Whole-Volume MRI Radiomics

BACKGROUND

The prognosis of advanced gastric cancer (AGC) patients has attracted much attention, but there is a lack of evaluation method. MRI-based radiomics has the potential to evaluate AGC patients' prognosis.

PURPOSE

To identify and validate the risk stratification and overall survival (OS) in AGC patients using MRI-based radiomics.

STUDY TYPE

Retrospective.

SUBJECTS

A total of 233 patients (168 males, 63.6 ± 11.1 years; 65 females, 59.7 ± 11.8 years) confirmed AGC were collected. The data were randomly divided into a training (164) and validation set (69).

SEQUENCE

A 3.0 T, axial T2-weighted, diffusion-weighted imaging, and contrast-enhanced T1-weighted (CE-T1WI).

ASSESSMENT

Radiologist 1 segmented 233 patients and radiologist 2 segmented randomly 50 patients on CE-T1WI. The risk score (RS) was summed by each sample based on the radiomics features and correlation coefficients. Patients were followed up for 7-67 months (median 41; 138 dead and 95 alive).

STATISTICAL TESTS

The intraclass correlation coefficient (ICC) and Kappa value were calculated. Differences in survival analysis were assessed by Kaplan-Meier curves and log-rank test. Cox-regression analysis was performed to identify the radiomics features and clinical indicators associated with OS. The calibration curves were built to assess the model. A two-tailed P value < 0.05 was considered statistically significant.

RESULTS

Integrated with age, lymphovascular invasion (LVI) and RS, a survival combined model was built. The area under the curve (AUC) for predicting 3-year and 5-year OS was 0.765 and 0.788 in the training set, 0.757 and 0.729 in the validation set. There was no significant difference between the radiomics model and survival combined model for 3-year (0.690 vs. 0.757, P = 0.425) and 5-year OS (0.687 vs. 729, P = 0.412) in the validation set. The calibration curves showed a high degree of fit for the survival combined model.

DATA CONCLUSION

This study established a survival combined model that might help AGC patients in future clinical decision-making.

EVIDENCE LEVEL

33 TECHNICAL EFFICACY: Stage 5.

Insights into Renal Cell Carcinoma with Novel Imaging Approaches

This article presents a comprehensive overview of new imaging approaches and techniques for improving the assessment of renal masses and renal cell carcinoma. The Bosniak classification, version 2019, as well as the clear cell likelihood score, version 2.0, will be discussed as new imaging algorithms using established techniques. Additionally, newer modalities, such as contrast-enhanced ultrasound, dual energy computed tomography, and molecular imaging, will be discussed in conjunction with emerging radiomics and artificial intelligence techniques. Current diagnostic algorithms combined with newer approaches may be an effective way to overcome existing limitations in renal mass and RCC characterization.

Machine learning-based diagnosis and risk classification of coronary artery disease using myocardial perfusion imaging SPECT: A radiomics study

This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models' evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.

CT radiomics prediction of CXCL9 expression and survival in ovarian cancer

BACKGROUND

C-X-C motif chemokine ligand 9 (CXCL9), which is involved in the pathological processes of various human cancers, has become a hot topic in recent years. We developed a radiomic model to identify CXCL9 status in ovarian cancer (OC) and evaluated its prognostic significance.

METHODS

We analyzed enhanced CT scans, transcriptome sequencing data, and corresponding clinical characteristics of CXCL9 in OC using the TCIA and TCGA databases. We used the repeat least absolute shrinkage (LASSO) and recursive feature elimination(RFE) methods to determine radiomic features after extraction and normalization. We constructed a radiomic model for CXCL9 prediction based on logistic regression and internal tenfold cross-validation. Finally, a 60-month overall survival (OS) nomogram was established to analyze survival data based on Cox regression.

RESULTS

CXCL9 mRNA levels and several other genes involving in T-cell infiltration were significantly relevant to OS in OC patients. The radiomic score (rad_score) of our radiomic model was calculated based on the five features for CXCL9 prediction. The areas under receiver operating characteristic (ROC) curves (AUC-ROC) for the training cohort was 0.781, while that for the validation cohort was 0.743. Patients with a high rad_score had better overall survival (P < 0.001). In addition, calibration curves and decision curve analysis (DCA) showed good consistency between the prediction and actual observations, demonstrating the clinical utility of our model.

CONCLUSION

In patients with OC, the radiomics signature(RS) of CT scans can distinguish the level of CXCL9 expression and predict prognosis, potentially fulfilling the ultimate purpose of precision medicine.

Post-revascularization Ejection Fraction Prediction for Patients Undergoing Percutaneous Coronary Intervention Based on Myocardial Perfusion SPECT Imaging Radiomics: a Preliminary Machine Learning Study

In this study, the ability of radiomics features extracted from myocardial perfusion imaging with SPECT (MPI-SPECT) was investigated for the prediction of ejection fraction (EF) post-percutaneous coronary intervention (PCI) treatment. A total of 52 patients who had undergone pre-PCI MPI-SPECT were enrolled in this study. After normalization of the images, features were extracted from the left ventricle, initially automatically segmented by k-means and active contour methods, and finally edited and approved by an expert radiologist. More than 1700 2D and 3D radiomics features were extracted from each patient's scan. A cross-combination of three feature selections and seven classifier methods was implemented. Three classes of no or dis-improvement (class 1), improved EF from 0 to 5% (class 2), and improved EF over 5% (class 3) were predicted by using tenfold cross-validation. Lastly, the models were evaluated based on accuracy, AUC, sensitivity, specificity, precision, and F-score. Neighborhood component analysis (NCA) selected the most predictive feature signatures, including Gabor, first-order, and NGTDM features. Among the classifiers, the best performance was achieved by the fine KNN classifier, which yielded mean accuracy, AUC, sensitivity, specificity, precision, and F-score of 0.84, 0.83, 0.75, 0.87, 0.78, and 0.76, respectively, in 100 iterations of classification, within the 52 patients with 10-fold cross-validation. The MPI-SPECT-based radiomic features are well suited for predicting post-revascularization EF and therefore provide a helpful approach for deciding on the most appropriate treatment.

Development and Validation of CT-Based Radiomics Signature for Overall Survival Prediction in Multi-organ Cancer

The malignant tumors in nature share some common morphological characteristics. Radiomics is not only images but also data; we think that a probability exists in a set of radiomics signatures extracted from CT scan images of one cancer tumor in one specific organ also be utilized for overall survival prediction in different types of cancers in different organs. The retrospective study enrolled four data sets of cancer patients in three different organs (420, 157, 137, and 191 patients for lung 1 training, lung 2 testing, and two external validation set: kidney and head and neck, respectively). In the training set, radiomics features were obtained from CT scan images, and essential features were chosen by LASSO algorithm. Univariable and multivariable analyses were then conducted to find a radiomics signature via Cox proportional hazard regression. The Kaplan-Meier curve was performed based on the risk score. The integrated time-dependent area under the ROC curve (iAUC) was calculated for each predictive model. In the training set, Kaplan-Meier curve classified patients as high or low-risk groups (p-value < 0.001; log-rank test). The risk score of radiomics signature was locked and independently evaluated in the testing set, and two external validation sets showed significant differences (p-value < 0.05; log-rank test). A combined model (radiomics + clinical) showed improved iAUC in lung 1, lung 2, head and neck, and kidney data set are 0.621 (95% CI 0.588, 0.654), 0.736 (95% CI 0.654, 0.819), 0.732 (95% CI 0.655, 0.809), and 0.834 (95% CI 0.722, 0.946), respectively. We believe that CT-based radiomics signatures for predicting overall survival in various cancer sites may exist.

Role of AI and Radiomic Markers in Early Diagnosis of Renal Cancer and Clinical Outcome Prediction: A Brief Review

Globally, renal cancer (RC) is the 10th most common cancer among men and women. The new era of artificial intelligence (AI) and radiomics have allowed the development of AI-based computer-aided diagnostic/prediction (AI-based CAD/CAP) systems, which have shown promise for the diagnosis of RC (i.e., subtyping, grading, and staging) and prediction of clinical outcomes at an early stage. This will absolutely help reduce diagnosis time, enhance diagnostic abilities, reduce invasiveness, and provide guidance for appropriate management procedures to avoid the burden of unresponsive treatment plans. This survey mainly has three primary aims. The first aim is to highlight the most recent technical diagnostic studies developed in the last decade, with their findings and limitations, that have taken the advantages of AI and radiomic markers derived from either computed tomography (CT) or magnetic resonance (MR) images to develop AI-based CAD systems for accurate diagnosis of renal tumors at an early stage. The second aim is to highlight the few studies that have utilized AI and radiomic markers, with their findings and limitations, to predict patients' clinical outcome/treatment response, including possible recurrence after treatment, overall survival, and progression-free survival in patients with renal tumors. The promising findings of the aforementioned studies motivated us to highlight the optimal AI-based radiomic makers that are correlated with the diagnosis of renal tumors and prediction/assessment of patients' clinical outcomes. Finally, we conclude with a discussion and possible future avenues for improving diagnostic and treatment prediction performance.

Myocardial Perfusion SPECT Imaging Radiomic Features and Machine Learning Algorithms for Cardiac Contractile Pattern Recognition

A U-shaped contraction pattern was shown to be associated with a better Cardiac resynchronization therapy (CRT) response. The main goal of this study is to automatically recognize left ventricular contractile patterns using machine learning algorithms trained on conventional quantitative features (ConQuaFea) and radiomic features extracted from Gated single-photon emission computed tomography myocardial perfusion imaging (GSPECT MPI). Among 98 patients with standard resting GSPECT MPI included in this study, 29 received CRT therapy and 69 did not (also had CRT inclusion criteria but did not receive treatment yet at the time of data collection, or refused treatment). A total of 69 non-CRT patients were employed for training, and the 29 were employed for testing. The models were built utilizing features from three distinct feature sets (ConQuaFea, radiomics, and ConQuaFea + radiomics (combined)), which were chosen using Recursive feature elimination (RFE) feature selection (FS), and then trained using seven different machine learning (ML) classifiers. In addition, CRT outcome prediction was assessed by different treatment inclusion criteria as the study's final phase. The MLP classifier had the highest performance among ConQuaFea models (AUC, SEN, SPE = 0.80, 0.85, 0.76). RF achieved the best performance in terms of AUC, SEN, and SPE with values of 0.65, 0.62, and 0.68, respectively, among radiomic models. GB and RF approaches achieved the best AUC, SEN, and SPE values of 0.78, 0.92, and 0.63 and 0.74, 0.93, and 0.56, respectively, among the combined models. A promising outcome was obtained when using radiomic and ConQuaFea from GSPECT MPI to detect left ventricular contractile patterns by machine learning.

Integrating CT-based radiomic model with clinical features improves long-term prognostication in high-risk prostate cancer

Objective

High-risk prostate cancer (PCa) is often treated by prostate-only radiotherapy (PORT) owing to its favourable toxicity profile compared to whole-pelvic radiotherapy. Unfortunately, more than 50% patients still developed disease progression following PORT. Conventional clinical factors may be unable to identify at-risk subgroups in the era of precision medicine. In this study, we aimed to investigate the prognostic value of pre-treatment planning computed tomography (pCT)-based radiomic features and clinical attributes to predict 5-year progression-free survival (PFS) in high-risk PCa patients following PORT.

Materials and methods

A total of 176 biopsy-confirmed PCa patients who were treated at the Hong Kong Princess Margaret Hospital were retrospectively screened for eligibility. Clinical data and pCT of one hundred eligible high-risk PCa patients were analysed. Radiomic features were extracted from the gross-tumour-volume (GTV) with and without applying Laplacian-of-Gaussian (LoG) filter. The entire patient cohort was temporally stratified into a training and an independent validation cohort in a ratio of 3:1. Radiomics (R), clinical (C) and radiomic-clinical (RC) combined models were developed by Ridge regression through 5-fold cross-validation with 100 iterations on the training cohort. A model score was calculated for each model based on the included features. Model classification performance on 5-year PFS was evaluated in the independent validation cohort by average area-under-curve (AUC) of receiver-operating-characteristics (ROC) curve and precision-recall curve (PRC). Delong's test was used for model comparison.

Results

The RC combined model which contains 6 predictive features (tumour flatness, root-mean-square on fine LoG-filtered image, prostate-specific antigen serum concentration, Gleason score, Roach score and GTV volume) was the best-performing model (AUC = 0.797, 95%CI = 0.768-0.826), which significantly outperformed the R-model (AUC = 0.795, 95%CI = 0.774-0.816) and C-model (AUC = 0.625, 95%CI = 0.585-0.665) in the independent validation cohort. Besides, only the RC model score significantly classified patients in both cohorts into progression and progression-free groups regarding their 5-year PFS (p< 0.05).

Conclusion

Combining pCT-based radiomic and clinical attributes provided superior prognostication value regarding 5-year PFS in high-risk PCa patients following PORT. A large multi-centre study will potentially aid clinicians in implementing personalised treatment for this vulnerable subgroup in the future.

Complexity in radiological morphology predicts worse prognosis and is associated with an increase in proteasome component levels in clear cell renal cell carcinoma

Background

We previously reported preoperative radiological morphology (RM) as an independent predictor for pathological upstaging after partial nephrectomy in patients with T1 renal cell carcinoma (RCC).

Purpose

To investigate the prognostic importance of RM in all stages and the molecular characteristics underlying the differences between each type of RM in patients with clear cell RCC (ccRCC).

Design setting and participants

The Cancer Imaging Archive datasets (TCIA), comprising CT images and RNA-sequencing data, were used (n = 163). Specimens from 63 patients with ccRCC at our institution and their CT images were used. All images were divided into three types according to RM classification.

Outcome measurements and statistical analysis

Relationships with outcome were analyzed using Cox regression analysis and log-rank test.

Results and limitations

The irregular type was a significant independent predictor of worse disease-free survival (odds ratio: 2.22, p = 0.037) compared to round and lobular types in TCIA datasets. The irregular type showed a significant increase in both mRNA and protein expression of proteasome components, PSMB1 and PSMB3. Moreover, high expression of their coding genes shortened the progression-free survival of the patients with ccRCC who received sunitinib or avelumab plus axitinib therapy. The study limitations include the qualitative classification of RM and the need for novel radiomics and texture analysis techniques.

Conclusions

Investigating RM on pre-treatment CT scans can effectively predict worse prognosis. Increased RM complexity may indirectly predict drug sensitivity via increased expression of PSMB1 and PSMB3 in patients with ccRCC. Specific targeting of the ubiquitin-proteasome system might be a novel treatment strategy for ccRCC with increased RM complexity.

Patient summary

The clinical and morphological characteristics of patients with ccRCC vary greatly according to cancer staging. In this study, we built upon our prior findings of the prognostic importance of RM in T1 RCC and expanded it to encompass all stages of RCC, using a series of patients from a Japanese hospital.

The Impact of Image Acquisition Parameters and ComBat Harmonization on the Predictive Performance of Radiomics: A Renal Cell Carcinoma Model

Radiomics, one of the potential methods for developing clinical biomarker, is one of the exponentially growing research fields. In addition to its potential, several limitations have been identified in this field, and most importantly the effects of variations in imaging parameters on radiomic features (RFs). In this study, we investigate the potential of RFs to predict overall survival in patients with clear cell renal cell carcinoma, as well as the impact of ComBat harmonization on the performance of RF models. We assessed the robustness of the results by performing the analyses a thousand times. Publicly available CT scans of 179 patients were retrospectively collected and analyzed. The scans were acquired using different imaging vendors and parameters in different medical centers. The performance was calculated by averaging the metrics over all runs. On average, the clinical model significantly outperformed the radiomic models. The use of ComBat harmonization, on average, did not significantly improve the performance of radiomic models. Hence, the variability in image acquisition and reconstruction parameters significantly affect the performance of radiomic models. The development of radiomic specific harmonization techniques remain a necessity for the advancement of the field.

Multimodal ultrasound fusion network for differentiating between benign and malignant solid renal tumors

Objective: We aim to establish a deep learning model called multimodal ultrasound fusion network (MUF-Net) based on gray-scale and contrast-enhanced ultrasound (CEUS) images for classifying benign and malignant solid renal tumors automatically and to compare the model’s performance with the assessments by radiologists with different levels of experience.

Methods: A retrospective study included the CEUS videos of 181 patients with solid renal tumors (81 benign and 100 malignant tumors) from June 2012 to June 2021. A total of 9794 B-mode and CEUS-mode images were cropped from the CEUS videos. The MUF-Net was proposed to combine gray-scale and CEUS images to differentiate benign and malignant solid renal tumors. In this network, two independent branches were designed to extract features from each of the two modalities, and the features were fused using adaptive weights. Finally, the network output a classification score based on the fused features. The model’s performance was evaluated using five-fold cross-validation and compared with the assessments of the two groups of radiologists with different levels of experience.

Results: For the discrimination between benign and malignant solid renal tumors, the junior radiologist group, senior radiologist group, and MUF-Net achieved accuracy of 70.6%, 75.7%, and 80.0%, sensitivity of 89.3%, 95.9%, and 80.4%, specificity of 58.7%, 62.9%, and 79.1%, and area under the receiver operating characteristic curve of 0.740 (95% confidence internal (CI): 0.70–0.75), 0.794 (95% CI: 0.72–0.83), and 0.877 (95% CI: 0.83–0.93), respectively.

Conclusion: The MUF-Net model can accurately classify benign and malignant solid renal tumors and achieve better performance than senior radiologists.

Key points: The CEUS video data contain the entire tumor microcirculation perfusion characteristics. The proposed MUF-Net based on B-mode and CEUS-mode images can accurately distinguish between benign and malignant solid renal tumors with an area under the receiver operating characteristic curve of 0.877, which surpasses senior radiologists’ assessments by a large margin.

High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms

We aimed to construct a prediction model based on computed tomography (CT) radiomics features to classify COVID-19 patients into severe-, moderate-, mild-, and non-pneumonic. A total of 1110 patients were studied from a publicly available dataset with 4-class severity scoring performed by a radiologist (based on CT images and clinical features). The entire lungs were segmented and followed by resizing, bin discretization and radiomic features extraction. We utilized two feature selection algorithms, namely bagging random forest (BRF) and multivariate adaptive regression splines (MARS), each coupled to a classifier, namely multinomial logistic regression (MLR), to construct multiclass classification models. The dataset was divided into 50% (555 samples), 20% (223 samples), and 30% (332 samples) for training, validation, and untouched test datasets, respectively. Subsequently, nested cross-validation was performed on train/validation to select the features and tune the models. All predictive power indices were reported based on the testing set. The performance of multi-class models was assessed using precision, recall, F1-score, and accuracy based on the 4 × 4 confusion matrices. In addition, the areas under the receiver operating characteristic curves (AUCs) for multi-class classifications were calculated and compared for both models. Using BRF, 23 radiomic features were selected, 11 from first-order, 9 from GLCM, 1 GLRLM, 1 from GLDM, and 1 from shape. Ten features were selected using the MARS algorithm, namely 3 from first-order, 1 from GLDM, 1 from GLRLM, 1 from GLSZM, 1 from shape, and 3 from GLCM features. The mean absolute deviation, skewness, and variance from first-order and flatness from shape, and cluster prominence from GLCM features and Gray Level Non Uniformity Normalize from GLRLM were selected by both BRF and MARS algorithms. All selected features by BRF or MARS were significantly associated with four-class outcomes as assessed within MLR (All p values < 0.05). BRF + MLR and MARS + MLR resulted in pseudo-R² prediction performances of 0.305 and 0.253, respectively. Meanwhile, there was a significant difference between the feature selection models when using a likelihood ratio test (p value = 0.046). Based on confusion matrices for BRF + MLR and MARS + MLR algorithms, the precision was 0.856 and 0.728, the recall was 0.852 and 0.722, whereas the accuracy was 0.921 and 0.861, respectively. AUCs (95% CI) for multi-class classification were 0.846 (0.805-0.887) and 0.807 (0.752-0.861) for BRF + MLR and MARS + MLR algorithms, respectively. Our models based on the utilization of radiomic features, coupled with machine learning were able to accurately classify patients according to the severity of pneumonia, thus highlighting the potential of this emerging paradigm in the prognostication and management of COVID-19 patients.

Myocardial Function Prediction After Coronary Artery Bypass Grafting Using MRI Radiomic Features and Machine Learning Algorithms

The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images in patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 patients who had visible scars on short-axis LGE-CMR images and were candidates for CABG surgery were selected and enrolled in this study. MR imaging was performed preoperatively using a 1.5-T MRI scanner. All images were segmented by two expert radiologists (in consensus). Prior to extraction of radiomics features, all MR images were resampled to an isotropic voxel size of 1.8 × 1.8 × 1.8 mm³. Subsequently, intensities were quantized to 64 discretized gray levels and a total of 93 features were extracted. The applied algorithms included a smoothly clipped absolute deviation (SCAD)-penalized support vector machine (SVM) and the recursive partitioning (RP) algorithm as a robust classifier for binary classification in this high-dimensional and non-sparse data. All models were validated with repeated fivefold cross-validation and 10,000 bootstrapping resamples. Ten and seven features were selected with SCAD-penalized SVM and RP algorithm, respectively, for CABG responder/non-responder classification. Considering univariate analysis, the GLSZM gray-level non-uniformity-normalized feature achieved the best performance (AUC: 0.62, 95% CI: 0.53-0.76) with SCAD-penalized SVM. Regarding multivariable modeling, SCAD-penalized SVM obtained an AUC of 0.784 (95% CI: 0.64-0.92), whereas the RP algorithm achieved an AUC of 0.654 (95% CI: 0.50-0.82). In conclusion, different radiomics texture features alone or combined in multivariate analysis using machine learning algorithms provide prognostic information regarding myocardial function in patients after CABG.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

A Clinical-Radiomics Nomogram Based on the Apparent Diffusion Coefficient (ADC) for Individualized Prediction of the Risk of Early Relapse in Advanced Sinonasal Squamous Cell Carcinoma: A 2-Year Follow-Up Study

Purpose

To develop and validate a nomogram model combining radiomic features and clinical characteristics to preoperatively predict the risk of early relapse (ER) in advanced sinonasal squamous cell carcinomas (SNSCCs).

Methods

A total of 152 SNSCC patients (clinical stage III-IV) who underwent diffusion-weighted imaging (DWI) were included in this study. The training cohort included 106 patients assessed at the headquarters of our hospital using MR scanner 1. The testing cohort included 46 patients assessed at the branch of our hospital using MR scanner 2. Least absolute shrinkage and selection operator (LASSO) regression was applied for feature selection and radiomic signature (radscore) construction. Multivariable logistic regression analysis was applied to identify independent predictors. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve analysis (DCA). Furthermore, the patients were classified into high- or low-risk ER subgroups according to the optimal cutoff value of the nomogram using X-tile. The recurrence-free survival probability (RFS) of each subgroup was assessed.

Results

ER was noted in 69 patients. The radscore included 8 selected radiomic features. The radscore, T stage and surgical margin were independent predictors. The nomogram showed better performance (AUC = 0.92) than either the radscore or the clinical factors in the training cohort (P < 0.050). In the testing cohort, the nomogram showed better performance (AUC = 0.92) than the clinical factors (P = 0.016) and tended to show better performance than the radscore (P = 0.177). The nomogram demonstrated good calibration and clinical utility. Kaplan-Meier analysis showed that the 2-year RFS rate for low-risk patients was significantly greater than that for high-risk patients in both the training and testing cohorts (P < 0.001).

Conclusions

The ADC-based radiomic nomogram model is potentially useful in predicting the risk of ER in advanced SNSCCs.

COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients

BACKGROUND

We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients.

METHODS

Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported.

RESULTS

In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance.

CONCLUSION

Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.

Predicting the WHO/ISUP Grade of Clear Cell Renal Cell Carcinoma Through CT-Based Tumoral and Peritumoral Radiomics

Objectives

This study aims to establish predictive logistic models for the World Health Organization/International Society of Urological Pathology (WHO/ISUP) grades of clear cell renal cell carcinoma (ccRCC) based on tumoral and peritumoral radiomics.

Methods

A cohort of 370 patients with pathologically confirmed ccRCCs were included in this retrospective study between January 2014 and December 2020 according to the WHO/ISUP grading system. The volume of interests of triphasic computed tomography images were depicted manually using the “itk-SNAP” software, and the radiomics features were calculated. The cohort was segmented into the training cohort and validation cohort with a random proportion of 7:3. After extraction of radiomics features by analysis of variance (ANOVA) or Mann-Whitney U test, correlation analysis, and the least absolute shrinkage and selection operator (LASSO) method, the logistic models of tumoral radiomics (LR-tumor) and peritumoral radiomics (LR-peritumor) were developed. The LR-peritumor was subdivided into LR-peritumor-2mm, LR-peritumor-5mm, and LR-peritumor-10mm, and the LR-peritumor-2mm was subdivided into LR-peritumor-kid and LR-peritumor-fat based on the neighboring tissues of ccRCCs. Finally, an integrative model of tumoral and peritumoral radiomics (LR-tumor/peritumor) was built. The value of areas under the receiver operator characteristics curve (AUCs) was calculated to assess the efficacy of the models.

Results

There were 209 low-grade and 161 high-grade ccRCCs enrolled. The AUCs of LR-tumor in CT images of venous phase were 0.802 in the training cohort and 0.796 in the validation cohort. The AUCs were higher in the LR-peritumor-2mm than those in LR-peritumor-5mm and LR-peritumor-10mm (training cohort: 0.788 vs. 0.788 and 0.759; validation cohort: 0.787 vs. 0.785 and 0.758). Moreover, the AUCs of LR-peritumor-fat were higher compared with those of LR-peritumor-kid. The LR-tumor/peritumor displayed the highest AUCs of 0.812 in the training cohort and 0.804 in the validation cohort.

Conclusions

The tumoral and peritumoral radiomics helped to predict the WHO/ISUP grades of ccRCCs. On the diagnostic performance of peritumoral radiomics, better results were seen for the LR-peritumor-2mm and LR-peritumor-fat.

Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection

OBJECTIVE

Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.

METHODS

Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm³ voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation.

RESULTS

In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis.

CONCLUSION

This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).

Overall Survival Prognostic Modelling of Non-small Cell Lung Cancer Patients Using Positron Emission Tomography/Computed Tomography Harmonised Radiomics Features: The Quest for the Optimal Machine Learning Algorithm

AIMS

Despite the promising results achieved by radiomics prognostic models for various clinical applications, multiple challenges still need to be addressed. The two main limitations of radiomics prognostic models include information limitation owing to single imaging modalities and the selection of optimum machine learning and feature selection methods for the considered modality and clinical outcome. In this work, we applied several feature selection and machine learning methods to single-modality positron emission tomography (PET) and computed tomography (CT) and multimodality PET/CT fusion to identify the best combinations for different radiomics modalities towards overall survival prediction in non-small cell lung cancer patients.

MATERIALS AND METHODS

A PET/CT dataset from The Cancer Imaging Archive, including subjects from two independent institutions (87 and 95 patients), was used in this study. Each cohort was used once as training and once as a test, followed by averaging of the results. ComBat harmonisation was used to address the centre effect. In our proposed radiomics framework, apart from single-modality PET and CT models, multimodality radiomics models were developed using multilevel (feature and image levels) fusion. Two different methods were considered for the feature-level strategy, including concatenating PET and CT features into a single feature set and alternatively averaging them. For image-level fusion, we used three different fusion methods, namely wavelet fusion, guided filtering-based fusion and latent low-rank representation fusion. In the proposed prognostic modelling framework, combinations of four feature selection and seven machine learning methods were applied to all radiomics modalities (two single and five multimodalities), machine learning hyper-parameters were optimised and finally the models were evaluated in the test cohort with 1000 repetitions via bootstrapping. Feature selection and machine learning methods were selected as popular techniques in the literature, supported by open source software in the public domain and their ability to cope with continuous time-to-event survival data. Multifactor ANOVA was used to carry out variability analysis and the proportion of total variance explained by radiomics modality, feature selection and machine learning methods was calculated by a bias-corrected effect size estimate known as ω².

RESULTS

Optimum feature selection and machine learning methods differed owing to the applied radiomics modality. However, minimum depth (MD) as feature selection and Lasso and Elastic-Net regularized generalized linear model (glmnet) as machine learning method had the highest average results. Results from the ANOVA test indicated that the variability that each factor (radiomics modality, feature selection and machine learning methods) introduces to the performance of models is case specific, i.e. variances differ regarding different radiomics modalities and fusion strategies. Overall, the greatest proportion of variance was explained by machine learning, except for models in feature-level fusion strategy.

CONCLUSION

The identification of optimal feature selection and machine learning methods is a crucial step in developing sound and accurate radiomics risk models. Furthermore, optimum methods are case specific, differing due to the radiomics modality and fusion strategy used.