Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy.

OBJECTIVE: This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs). METHODS: We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score. RESULTS: For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV). CONCLUSION: Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.

Noninvasive imaging signatures of HER2 and HR using ADC in invasive breast cancer: repeatability, reproducibility, and association with pathological complete response to neoadjuvant chemotherapy.

BACKGROUND: The immunohistochemical test (IHC) of HER2 and HR can provide prognostic information and treatment guidance for invasive breast cancer patients. We aimed to develop noninvasive image signatures ISHER2 and ISHR of HER2 and HR, respectively. We independently evaluate their repeatability, reproducibility, and association with pathological complete response (pCR) to neoadjuvant chemotherapy. METHODS: Pre-treatment DWI, IHC receptor status HER2/HR, and pCR to neoadjuvant chemotherapy of 222 patients from the multi-institutional ACRIN 6698 trial were retrospectively collected. They were pre-separated for development, independent validation, and test-retest. 1316 image features were extracted from DWI-derived ADC maps within manual tumor segmentations. ISHER2 and ISHR were developed by RIDGE logistic regression using non-redundant and test-retest reproducible features relevant to IHC receptor status. We evaluated their association with pCR using area under receiver operating curve (AUC) and odds ratio (OR) after binarization. Their reproducibility was further evaluated using the test-retest set with intra-class coefficient of correlation (ICC). RESULTS: A 5-feature ISHER2 targeting HER2 was developed (AUC = 0.70, 95% CI 0.59 to 0.82) and validated (AUC = 0.72, 95% CI 0.58 to 0.86) with high perturbation repeatability (ICC = 0.92) and test-retest reproducibility (ICC = 0.83). ISHR was developed using 5 features with higher association with HR during development (AUC = 0.75, 95% CI 0.66 to 0.84) and validation (AUC = 0.74, 95% CI 0.61 to 0.86) and similar repeatability (ICC = 0.91) and reproducibility (ICC = 0.82). Both image signatures showed significant associations with pCR with AUC of 0.65 (95% CI 0.50 to 0.80) for ISHER2 and 0.64 (95% CI 0.50 to 0.78) for ISHER2 in the validation cohort. Patients with high ISHER2 were more likely to achieve pCR to neoadjuvant chemotherapy with validation OR of 4.73 (95% CI 1.64 to 13.65, P value = 0.006). Low ISHR patients had higher pCR with OR = 0.29 (95% CI 0.10 to 0.81, P value = 0.021). Molecular subtypes derived from the image signatures showed comparable pCR prediction values to IHC-based molecular subtypes (P value > 0.05). CONCLUSION: Robust ADC-based image signatures were developed and validated for noninvasive evaluation of IHC receptors HER2 and HR. We also confirmed their value in predicting treatment response to neoadjuvant chemotherapy. Further evaluations in treatment guidance are warranted to fully validate their potential as IHC surrogates.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling.

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients' anatomy. However, the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians. Moreover, some potentially useful quantitative information in medical images, especially that which is not visible to the naked eye, is often ignored during clinical practice. In contrast, radiomics performs high-throughput feature extraction from medical images, which enables quantitative analysis of medical images and prediction of various clinical endpoints. Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis, demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine. However, radiomics remains in a developmental phase as numerous technical challenges have yet to be solved, especially in feature engineering and statistical modeling. In this review, we introduce the current utility of radiomics by summarizing research on its application in the diagnosis, prognosis, and prediction of treatment responses in patients with cancer. We focus on machine learning approaches, for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling. Furthermore, we introduce the stability, reproducibility, and interpretability of features, and the generalizability and interpretability of models. Finally, we offer possible solutions to current challenges in radiomics research.

Respiratory-Correlated 4-Dimensional Magnetic Resonance Fingerprinting for Liver Cancer Radiation Therapy Motion Management.

PURPOSE: The objective of this study was to develop a respiratory-correlated (RC) 4-dimensional (4D) imaging technique based on magnetic resonance fingerprinting (MRF) (RC-4DMRF) for liver tumor motion management in radiation therapy. METHODS AND MATERIALS: Thirteen patients with liver cancer were prospectively enrolled in this study. k-space MRF signals of the liver were acquired during free-breathing using the fast acquisition with steady-state precession sequence on a 3T scanner. The signals were binned into 8 respiratory phases based on respiratory surrogates, and interphase displacement vector fields were estimated using a phase-specific low-rank optimization method. Hereafter, the tissue property maps, including T1 and T2 relaxation times, and proton density, were reconstructed using a pyramid motion-compensated method that alternatively optimized interphase displacement vector fields and subspace images. To evaluate the efficacy of RC-4DMRF, amplitude motion differences and Pearson correlation coefficients were determined to assess measurement agreement in tumor motion between RC-4DMRF and cine magnetic resonance imaging (MRI); mean absolute percentage errors of the RC-4DMRF-derived tissue maps were calculated to reveal tissue quantification accuracy using digital human phantom; and tumor-to-liver contrast-to-noise ratio of RC-4DMRF images was compared with that of planning CT and contrast-enhanced MRI (CE-MRI) images. A paired Student t test was used for statistical significance analysis with a P value threshold of .05. RESULTS: RC-4DMRF achieved excellent agreement in motion measurement with cine MRI, yielding the mean (± standard deviation) Pearson correlation coefficients of 0.95 ± 0.05 and 0.93 ± 0.09 and amplitude motion differences of 1.48 ± 1.06 mm and 0.81 ± 0.64 mm in the superior-inferior and anterior-posterior directions, respectively. Moreover, RC-4DMRF achieved high accuracy in tissue property quantification, with mean absolute percentage errors of 8.8%, 9.6%, and 5.0% for T1, T2, and proton density, respectively. Notably, the tumor contrast-to-noise ratio in RC-4DMRI-derived T1 maps (6.41 ± 3.37) was found to be the highest among all tissue property maps, approximately equal to that of CE-MRI (6.96 ± 1.01, P = .862), and substantially higher than that of planning CT (2.91 ± 1.97, P = .048). CONCLUSIONS: RC-4DMRF demonstrated high accuracy in respiratory motion measurement and tissue properties quantification, potentially facilitating tumor motion management in liver radiation therapy.

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy.

PURPOSE: The study aimed to predict acute radiation esophagitis (ARE) with grade ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics. METHODS: 161 patients with stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose-volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training-testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy. RESULTS: Among all patients, 51 developed ARE grade ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively. CONCLUSIONS: In LALC patients treated with CRT IMRT, the ARE grade ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

Radiomics-Based Detection of COVID-19 from Chest X-ray Using Interpretable Soft Label-Driven TSK Fuzzy Classifier.

The COVID-19 pandemic has posed a significant global public health threat with an escalating number of new cases and death toll daily. The early detection of COVID-related CXR abnormality potentially allows the early isolation of suspected cases. Chest X-Ray (CXR) is a fast and highly accessible imaging modality. Recently, a number of CXR-based AI models have been developed for the automated detection of COVID-19. However, most existing models are difficult to interpret due to the use of incomprehensible deep features in their models. Confronted with this, we developed an interpretable TSK fuzzy system in this study for COVID-19 detection using radiomics features extracted from CXR images. There are two main contributions. (1) When TSK fuzzy systems are applied to classification tasks, the commonly used binary label matrix of training samples is transformed into a soft one in order to learn a more discriminant transformation matrix and hence improve classification accuracy. (2) Based on the assumption that the samples in the same class should be kept as close as possible when they are transformed into the label space, the compactness class graph is introduced to avoid overfitting caused by label matrix relaxation. Our proposed model for a multi-categorical classification task (COVID-19 vs. No-Findings vs. Pneumonia) was evaluated using 600 CXR images from publicly available datasets and compared against five state-of-the-art AI models in aspects of classification accuracy. Experimental findings showed that our model achieved classification accuracy of over 83%, which is better than the state-of-the-art models, while maintaining high interpretability.

Lung Subregion Partitioning by Incremental Dose Intervals Improves Omics-Based Prediction for Acute Radiation Pneumonitis in Non-Small-Cell Lung Cancer Patients.

Purpose: To evaluate the effectiveness of features obtained from our proposed incremental-dose-interval-based lung subregion segmentation (IDLSS) for predicting grade ≥ 2 acute radiation pneumonitis (ARP) in lung cancer patients upon intensity-modulated radiotherapy (IMRT). (1) Materials and Methods: A total of 126 non-small-cell lung cancer patients treated with IMRT were retrospectively analyzed. Five lung subregions (SRs) were generated by the intersection of the whole lung (WL) and five sub-regions receiving incremental dose intervals. A total of 4610 radiomics features (RF) from pre-treatment planning computed tomographic (CT) and 213 dosiomics features (DF) were extracted. Six feature groups, including WL-RF, WL-DF, SR-RF, SR-DF, and the combined feature sets of WL-RDF and SR-RDF, were generated. Features were selected by using a variance threshold, followed by a Student t-test. Pearson's correlation test was applied to remove redundant features. Subsequently, Ridge regression was adopted to develop six models for ARP using the six feature groups. Thirty iterations of resampling were implemented to assess overall model performance by using the area under the Receiver-Operating-Characteristic curve (AUC), accuracy, precision, recall, and F1-score. (2) Results: The SR-RDF model achieved the best classification performance and provided significantly better predictability than the WL-RDF model in training cohort (Average AUC: 0.98 ± 0.01 vs. 0.90 ± 0.02, p < 0.001) and testing cohort (Average AUC: 0.88 ± 0.05 vs. 0.80 ± 0.04, p < 0.001). Similarly, predictability of the SR-DF model was significantly stronger than that of the WL-DF model in training cohort (Average AUC: 0.88 ± 0.03 vs. 0.70 ± 0.030, p < 0.001) and in testing cohort (Average AUC: 0.74 ± 0.08 vs. 0.65 ± 0.06, p < 0.001). By contrast, the SR-RF model significantly outperformed the WL-RF model only in the training set (Average AUC: 0.93 ± 0.02 vs. 0.85 ± 0.03, p < 0.001), but not in the testing set (Average AUC: 0.79 ± 0.05 vs. 0.77 ± 0.07, p = 0.13). (3) Conclusions: Our results demonstrated that the IDLSS method improved model performance for classifying ARP with grade ≥ 2 when using dosiomics or combined radiomics-dosiomics features.

Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma.

Background: Using high robust radiomic features in modeling is recommended, yet its impact on radiomic model is unclear. This study evaluated the radiomic model's robustness and generalizability after screening out low-robust features before radiomic modeling. The results were validated with four datasets and two clinically relevant tasks. Materials and methods: A total of 1,419 head-and-neck cancer patients' computed tomography images, gross tumor volume segmentation, and clinically relevant outcomes (distant metastasis and local-regional recurrence) were collected from four publicly available datasets. The perturbation method was implemented to simulate images, and the radiomic feature robustness was quantified using intra-class correlation of coefficient (ICC). Three radiomic models were built using all features (ICC > 0), good-robust features (ICC > 0.75), and excellent-robust features (ICC > 0.95), respectively. A filter-based feature selection and Ridge classification method were used to construct the radiomic models. Model performance was assessed with both robustness and generalizability. The robustness of the model was evaluated by the ICC, and the generalizability of the model was quantified by the train-test difference of Area Under the Receiver Operating Characteristic Curve (AUC). Results: The average model robustness ICC improved significantly from 0.65 to 0.78 (P< 0.0001) using good-robust features and to 0.91 (P< 0.0001) using excellent-robust features. Model generalizability also showed a substantial increase, as a closer gap between training and testing AUC was observed where the mean train-test AUC difference was reduced from 0.21 to 0.18 (P< 0.001) in good-robust features and to 0.12 (P< 0.0001) in excellent-robust features. Furthermore, good-robust features yielded the best average AUC in the unseen datasets of 0.58 (P< 0.001) over four datasets and clinical outcomes. Conclusions: Including robust only features in radiomic modeling significantly improves model robustness and generalizability in unseen datasets. Yet, the robustness of radiomic model has to be verified despite building with robust radiomic features, and tightly restricted feature robustness may prevent the optimal model performance in the unseen dataset as it may lower the discrimination power of the model.

Building reliable radiomic models using image perturbation.

Radiomic model reliability is a central premise for its clinical translation. Presently, it is assessed using test-retest or external data, which, unfortunately, is often scarce in reality. Therefore, we aimed to develop a novel image perturbation-based method (IPBM) for the first of its kind toward building a reliable radiomic model. We first developed a radiomic prognostic model for head-and-neck cancer patients on a training (70%) and evaluated on a testing (30%) cohort using C-index. Subsequently, we applied the IPBM to CT images of both cohorts (Perturbed-Train and Perturbed-Test cohort) to generate 60 additional samples for both cohorts. Model reliability was assessed using intra-class correlation coefficient (ICC) to quantify consistency of the C-index among the 60 samples in the Perturbed-Train and Perturbed-Test cohorts. Besides, we re-trained the radiomic model using reliable RFs exclusively (ICC > 0.75) to validate the IPBM. Results showed moderate model reliability in Perturbed-Train (ICC: 0.565, 95%CI 0.518-0.615) and Perturbed-Test (ICC: 0.596, 95%CI 0.527-0.670) cohorts. An enhanced reliability of the re-trained model was observed in Perturbed-Train (ICC: 0.782, 95%CI 0.759-0.815) and Perturbed-Test (ICC: 0.825, 95%CI 0.782-0.867) cohorts, indicating validity of the IPBM. To conclude, we demonstrated capability of the IPBM toward building reliable radiomic models, providing community with a novel model reliability assessment strategy prior to prospective evaluation.

Deep Learning-Based Automatic Assessment of Radiation Dermatitis in Patients With Nasopharyngeal Carcinoma.

PURPOSE: Radiation dermatitis (RD) is a common, unpleasant side effect of patients receiving radiation therapy. In clinical practice, the severity of RD is graded manually through visual inspection, which is labor intensive and often leads to large interrater variations. To overcome these shortcomings, this study aimed to develop an automatic RD assessment based on deep learning (DL) techniques that could efficiently assist the RD severity classification in clinical application. METHODS AND MATERIALS: A total of 1205 photographs of the head and neck region were collected from patients with nasopharyngeal carcinoma (NPC) undergoing radiation therapy. The severity of RD in these photographs was graded by 5 qualified assessors based on the Radiation Therapy Oncology Group guidance. An end-to-end RD grading framework was developed by combining a DL-based segmentation network and a DL-based RD severity classifier, which are used for segmenting the neck region from the camera-captured photographs and grading, respectively. U-Net was used for segmentation and another convolutional neural network classifier (DenseNet-121) was applied to RD severity classification. Dice similarity coefficient was used to evaluate the performance of segmentation. Severity classification was evaluated by several metrics, including overall accuracy, precision, recall, and F1 score. RESULTS: Results of segmentation showed that the averaged dice similarity coefficients were 91.2% and 90.8% for front and side view, respectively. For RD severity classification, the overall accuracy of test photographs was 83.0%. Our method accurately classified 90.5% of grade 0, 67.2% of grade 1, 93.8% of grade 2, and 100% of above grade 2 cases. The overall prediction performance was comparable with human assessors. There was no significant difference in accuracy when using manually or automatically segmented regions (P = .683). CONCLUSIONS: We have successfully demonstrated a DL-based method for automatic assessment of RD severity in patients with NPC. This method holds great potential for efficient and effective assessing and monitoring of RD in patients with NPC.

A Multi-Center Study of CT-Based Neck Nodal Radiomics for Predicting an Adaptive Radiotherapy Trigger of Ill-Fitted Thermoplastic Masks in Patients with Nasopharyngeal Carcinoma.

Significant lymph node shrinkage is common in patients with nasopharyngeal carcinoma (NPC) throughout radiotherapy (RT) treatment, causing ill-fitted thermoplastic masks (IfTMs). To deal with this, an ad hoc adaptive radiotherapy (ART) may be required to ensure accurate and safe radiation delivery and to maintain treatment efficacy. Presently, the entire procedure for evaluating an eligible ART candidate is time-consuming, resource-demanding, and highly inefficient. In the artificial intelligence paradigm, the pre-treatment identification of NPC patients at risk for IfTMs has become greatly demanding for achieving efficient ART eligibility screening, while no relevant studies have been reported. Hence, we aimed to investigate the capability of computed tomography (CT)-based neck nodal radiomics for predicting IfTM-triggered ART events in NPC patients via a multi-center setting. Contrast-enhanced CT and the clinical data of 124 and 58 NPC patients from Queen Elizabeth Hospital (QEH) and Queen Mary Hospital (QMH), respectively, were retrospectively analyzed. Radiomic (R), clinical (C), and combined (RC) models were developed using the ridge algorithm in the QEH cohort and evaluated in the QMH cohort using the median area under the receiver operating characteristics curve (AUC). Delong's test was employed for model comparison. Model performance was further assessed on 1000 replicates in both cohorts separately via bootstrapping. The R model yielded the highest "corrected" AUC of 0.784 (BCa 95%CI: 0.673-0.859) and 0.723 (BCa 95%CI: 0.534-0.859) in the QEH and QMH cohort following bootstrapping, respectively. Delong's test indicated that the R model performed significantly better than the C model in the QMH cohort (p < 0.0001), while demonstrating no significant difference compared to the RC model (p = 0.5773). To conclude, CT-based neck nodal radiomics was capable of predicting IfTM-triggered ART events in NPC patients in this multi-center study, outperforming the traditional clinical model. The findings of this study provide valuable insights for future study into developing an effective screening strategy for ART eligibility in NPC patients in the long run, ultimately alleviating the workload of clinical practitioners, streamlining ART procedural efficiency in clinics, and achieving personalized RT for NPC patients in the future.

A Deep-Ensemble-Level-Based Interpretable Takagi-Sugeno-Kang Fuzzy Classifier for Imbalanced Data.

Existing research reveals that the misclassification rate for imbalanced data depends heavily on the problematic areas due to the existence of small disjoints, class overlap, borderline, and rare data samples. In this study, by stacking zero-order Takagi-Sugeno-Kang (TSK) fuzzy subclassifiers on the minority class and its problematic areas in the deep ensemble, a novel deep-ensemble-level-based TSK fuzzy classifier (IDE-TSK-FC) for imbalanced data classification tasks is presented to achieve both promising classification performance and high interpretability of zero-order TSK fuzzy classifiers. Simultaneously, according to the stacked generalization principle, the proposed classifier lifts up oversampling from the data level to the deep ensemble level with a guarantee of enhanced generalization capability for class imbalance learning. In the structure of IDE-TSK-FC, the first interpretable zero-order TSK fuzzy subclassifier is built on the original training dataset. After that, several successive zero-order TSK fuzzy subclassifiers are stacked layer by layer on the newly identified problematic areas from the original training dataset plus the corresponding interpretable predictions obtained by the averaging strategy on all previous layers. IDE-TSK-FC simply takes the classical K -nearest neighboring algorithm at each layer to identify its problematic area that consists of the minority samples and its surrounding K majority neighbors. After randomly neglecting certain input features and randomly selecting the five Gaussian membership functions for all the chosen input features and the augmented feature in the premise of each fuzzy rule, each subclassifier can be quickly obtained by using the least learning machine to determine the consequent part of each fuzzy rule. The experimental results on both the public datasets and a real-world healthcare dataset demonstrate IDE-TSK-FC's superiority in class imbalanced learning.

Multi-Organ Omics-Based Prediction for Adaptive Radiation Therapy Eligibility in Nasopharyngeal Carcinoma Patients Undergoing Concurrent Chemoradiotherapy.

PURPOSE: To investigate the role of different multi-organ omics-based prediction models for pre-treatment prediction of Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC). METHODS AND MATERIALS: Pre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose and contour data of 135 NPC patients treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed for extraction of multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), and Contouromics (C), from a total of eight organ structures. During model development, patient cohort was divided into a training set and a hold-out test set in a ratio of 7 to 3 via 20 iterations. Four single-omics models (R, M, D, C) and four multi-omics models (RD, RC, RM, RMDC) were developed on the training data using Ridge and Multi-Kernel Learning (MKL) algorithm, respectively, under 10-fold cross validation, and evaluated on hold-out test data using average area under the receiver-operator-characteristics curve (AUC). The best-performing single-omics model was first determined by comparing the AUC distribution across the 20 iterations among the four single-omics models using two-sided student t-test, which was then retrained using MKL algorithm for a fair comparison with the four multi-omics models. RESULTS: The R model significantly outperformed all other three single-omics models (all p-value<0.0001), achieving an average AUC of 0.942 (95%CI: 0.938-0.946) and 0.918 (95%CI: 0.903-0.933) in training and hold-out test set, respectively. When trained with MKL, the R model (R_MKL) yielded an increased AUC of 0.984 (95%CI: 0.981-0.988) and 0.927 (95%CI: 0.905-0.948) in training and hold-out test set respectively, while demonstrating no significant difference as compared to all studied multi-omics models in the hold-out test sets. Intriguingly, Radiomic features accounted for the majority of the final selected features, ranging from 64% to 94%, in all the studied multi-omics models. CONCLUSIONS: Among all the studied models, the Radiomic model was found to play a dominant role for ART eligibility in NPC patients, and Radiomic features accounted for the largest proportion of features in all the multi-omics models.