Tumor and Perirenal Adipose Tissue Radiomic Models for Pathological T-Stage Prediction and Biological Exploration in Clear Cell Renal Cell Carcinoma.

ObjectivesWe aimed to develop a combined model based on clinical and radiomic features to classify fracture age.MethodsWe included 1219 rib fractures from 239 patients from our center between March 2016 and September 2022. We created an external dataset using 120 rib fractures from 32 patients from another center between October 2019 and August 2023. According to tasks (fracture age between < 3 and ≥ 3 weeks, 3–12, and > 12 weeks), the internal dataset was randomly divided into training and internal test sets. A radiomic model was built using radiomic features. A combined model was constructed using clinical features and radiomic signatures by multivariate logistic regression, visualized as a nomogram. Internal and external test sets were used to validate model performance.ResultsFor classifying fracture age between < 3 and ≥ 3 weeks, the combined model had higher areas under the curve (AUCs) than the radiomic model in the training set (0.915 vs 0.900, p = 0.009), internal test (0.897 vs 0.854, p < 0.001), and external test sets (0.881 vs 0.811, p = 0.003). For classifying fracture age between 3–12 and > 12 weeks, the combined model had higher AUCs than the radiomic model in the training model (0.848 vs 0.837, p = 0.12) and internal test sets (0.818 vs 0.793, p < 0.003). In the external test set, the AUC of the nomogram-assisted radiologist was 0.966.ConclusionThe combined radiomic and clinical model showed good performance and has the potential to assist in the classification of rib fracture age. This will be beneficial for clinical practice and forensic decision-making.Critical relevance statementThis study describes the development of a combined radiomic and clinical model with good performance in the classification of the age of rib fractures, with potential clinical and forensic applications.Key points• Complex factors make it difficult to determine the age of a fracture.• Our model based on radiomic features performed well in classifying fracture age.• Associating the radiomic features with clinical features improved the model’s performance.Graphical

This study aimed to establish a mammography-based radiomics model for predicting the risk of estrogen receptor (ER)-positive, lymph node (LN)-negative invasive breast cancer recurrence based on Oncotype DX and validated it by using multicenter data. A total of 304 potentially eligible patients with pre-operative mammography images and available Oncotype DX score were retrospectively enrolled from two hospitals. The patients were grouped as training set (168 patients), internal test set (72 patients), and external test set (64 patients). Radiomics features were extracted from the mammography images of each patient. Spearman correlation analysis, analysis of variance, and least absolute shrinkage and selection operator regression were performed to reduce the redundant features in the training set, and the least absolute shrinkage and selection operator algorithm was used to construct the radiomics signature based on selected features. Multivariate logistic regression was utilized to construct classification models that included radiomics signature and clinical risk factors to predict low vs intermediate and high recurrence risk of ER-positive, LN-negative invasive breast cancer in the training set. The models were evaluated with the receiver operating characteristic curve in the training set. The internal and external test sets were used to confirm the discriminatory power of the models. The clinical usefulness was evaluated by using decision curve analysis. The radiomics signature consisting of three radiomics features achieved favorable prediction performance. The multivariate logistic regression model including radiomics signature and clinical risk factors (tumor grade and HER 2) showed good performance with areas under the curve of 0.92 (95% confidence interval [CI] 0.86 to 0.97), 0.88 (95% CI 0.75 to 1.00), and 0.84 (95% CI 0.69 to 0.99) in the training, internal and external test sets, respectively. The DCA indicated that when the threshold probability is ranges from 0.1 to 1.0, the radiomics model adds more net benefit than the "treat all" or "treat none" scheme in internal and external test sets. As a non-invasive pre-operative prediction tool, the mammography-based radiomics model incorporating radiomics and clinical factors show favorable predictive performance for predicting the risk of ER-positive, LN-negative invasive breast cancer recurrence based on Oncotype DX. The mammography-based radiomics model incorporating radiomics and clinical factors shows favorable predictive performance for predicting the risk of ER-positive, LN-negative invasive breast cancer recurrence.

ObjectivesThis study aimed to develop a computed tomography (CT)-based radiomics model to predict central lymph node metastases (CLNM) preoperatively in patients with papillary thyroid carcinoma (PTC).MethodsIn this retrospective study, 678 patients with PTC were enrolled from Yantai Yuhuangding Hot3spital (n=605) and the Affiliated Hospital of Binzhou Medical University (n=73) within August 2010 to December 2020. The patients were randomly divided into a training set (n=423), an internal test set (n=182), and an external test set (n=73). Radiomics features of each patient were extracted from preoperative plain scan and contrast-enhanced CT images (arterial and venous phases). One-way analysis of variance (ANOVA) and least absolute shrinkage and selection operator algorithm were used for feature selection. The K-nearest neighbor, logistics regression, decision tree, linear-support vector machine (linear-SVM), Gaussian-SVM, and polynomial-SVM algorithms were used to establish radiomics models for CLNM prediction. The clinical risk factors were selected by ANOVA and multivariate logistic regression. Incorporated with clinical risk factors, a combined radiomics model was established for the preoperative prediction of CLNM in patients with PTCs. The performance of the combined radiomics model was evaluated using the receiver operating characteristic (ROC) and calibration curves in the training and test sets. The clinical usefulness was evaluated through decision curve analysis (DCA).ResultsA total of 4227 radiomic features were extracted from the CT images of each patient, and 14 non-zero coefficient features associated with CLNM were selected. Four clinical variables (sex, age, tumor diameter, and CT-reported lymph node status) were significantly associated with CLNM. Linear-SVM led to the best prediction model, which incorporated radiomic features and clinical risk factors. Areas under the ROC curves of 0.747 (95% confidence interval [CI] 0.706–0.782), 0.710 (95% CI 0.634–0.786), and 0.764 (95% CI 0.654–0.875) were obtained in the training, internal, and external test sets, respectively. The linear-SVM algorithm also showed better sensitivity (0.702 [95% CI 0.600–0.790] vs. 0.477 [95% CI 0.409–0.545]) and accuracy (0.670 [95% CI 0.600–0.738] vs. 0.642 [95% CI 0.569–0.712]) than an experienced radiologist in the internal test set in the combined radiomics model. The calibration plot reflected a favorable agreement between the actual and estimated probabilities of CLNM. The DCA indicated the clinical usefulness of the combined radiomics model.ConclusionThe combined radiomics model is a non-invasive preoperative tool that incorporates radiomic features and clinical risk factors to predict CLNM in patients with PTC.

To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by theDice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Coronary computed tomography angiography provides valuable information for evaluating the difficulty of chronic total occlusion (CTO) percutaneous coronary intervention. This study aimed to investigate the value of CTO plaque characteristics derived from radiomics analysis for predicting the difficulty of percutaneous coronary intervention. Patients with CTO were retrospectively enrolled from a hospital as training and internal test sets and from the other 2 territory hospitals as external test sets. Radiomics characteristics were extracted from the CTO segment on coronary computed tomography angiography. Radiomics and combined models were developed to predict successful guidewire crossing within 30 minutes (guidewire success) of CTO percutaneous coronary intervention. Subgroup analysis was conducted to investigate the influence of potential risk factors on the radiomics model performance. A total of 551 patients (median, 60; interquartile range, 52.00-66.00 years, 460 men) with 565 CTO lesions were finally enrolled. In the training, internal test, and external test sets, 203 of 357, 85 of 149, and 38 of 59 CTO lesions achieved guidewire success, respectively. Six radiomics features were selected for constructing the radiomics model. In the external test set, the area under the receiver operating characteristic curve of the radiomics model was significantly higher than prior prediction models (P<0.05 for all) with the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity of 0.86, 74.58%, 81.58%, and 61.90%, respectively. The performance of the radiomics model was dependent on calcification, CTO location, adjacent branch(es), and operator caseload. CTO characteristics revealed by radiomics analysis can be used as effective imaging biomarkers for predicting guidewire success. However, the performance of the radiomics model depends on anatomic and operator factors.

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set (n = 334), internal test set (n = 142), external test set (n = 141), outcome cohort (n = 121), and RNA sequencing analysis set (n = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival (P < .01) and overall survival (P < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Summers in this issue.

Dual-energy CT Radiomics Combined with Quantitative Parameters for Differentiating Lung Adenocarcinoma From Squamous Cell Carcinoma: A Dual-center Study

The aim of this study was to generate and validate artificial delayed-phase technetium-99m methoxyisobutylisonitrile scintigraphy (aMIBI) images from early-phase technetium-99m methoxyisobutylisonitrile scintigraphy (eMIBI) images. This retrospective study included patients with hyperparathyroidism who underwent dual-phase technetium-99m methoxyisobutylisonitrile (MIBI) scintigraphy at 2 centers. The patients were divided into a training set (n = 980), an internal test set (n = 100), and an external test set (n = 253). The generation of aMIBI images from eMIBI images was performed using an unpaired image-to-image translation method. Receiver operating characteristic curves and the area under the curves (AUCs) were used to evaluate the diagnostic performance of aMIBI and eMIBI images in identifying hyperfunctioning parathyroid lesions in both the internal and external test sets. In addition, an artificial intelligence (AI)-assisted diagnostic model combining aMIBI and clinical data was evaluated. The AUCs of aMIBI images were significantly higher than those of eMIBI images (internal test set: 0.944 vs 0.658, P < 0.001; external test set: 0.900 vs 0.761, P < 0.001). The performance of the AI-assisted diagnostic models combining aMIBI images and clinical data was significantly better than those of the aMIBI-only models in both the internal (AUC: 0.974 vs 0.944, P = 0.020) and external (AUC: 0.953 vs 0.900, P < 0.001) test sets. The diagnostic performance of aMIBI images in identifying hyperfunctioning parathyroid lesions was significantly superior to that of eMIBI images in patients with hyperparathyroidism. Models combining aMIBI images with clinical information enhanced the diagnostic performance even further.

PurposeTo establish and validate a machine learning based radiomics model for detection of perineural invasion (PNI) in gastric cancer (GC).MethodsThis retrospective study included a total of 955 patients with GC selected from two centers; they were separated into training (n=603), internal testing (n=259), and external testing (n=93) sets. Radiomic features were derived from three phases of contrast-enhanced computed tomography (CECT) scan images. Seven machine learning (ML) algorithms including least absolute shrinkage and selection operator (LASSO), naïve Bayes (NB), k-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost) and support vector machine (SVM) were trained for development of optimal radiomics signature. A combined model was constructed by aggregating the radiomic signatures and important clinicopathological characteristics. The predictive ability of the radiomic model was then assessed with receiver operating characteristic (ROC) and calibration curve analyses in all three sets.ResultsThe PNI rates for the training, internal testing, and external testing sets were 22.1, 22.8, and 36.6%, respectively. LASSO algorithm was selected for signature establishment. The radiomics signature, consisting of 8 robust features, revealed good discrimination accuracy for the PNI in all three sets (training set: AUC = 0.86; internal testing set: AUC = 0.82; external testing set: AUC = 0.78). The risk of PNI was significantly associated with higher radiomics scores. A combined model that integrated radiomics and T stage demonstrated enhanced accuracy and excellent calibration in all three sets (training set: AUC = 0.89; internal testing set: AUC = 0.84; external testing set: AUC = 0.82).ConclusionThe suggested radiomics model exhibited satisfactory prediction performance for the PNI in GC.

Accurate diagnosis of breast lesions and discrimination of axillary lymph node (ALN) metastases largely depend on radiologist experience. To develop a deep learning-based whole-process system (DLWPS) for segmentation and diagnosis of breast lesions and discrimination of ALN metastasis. Retrospective. 1760 breast patients, who were divided into training and validation sets (1110 patients), internal (476 patients), and external (174 patients) test sets. 3.0T/dynamic contrast-enhanced (DCE)-MRI sequence. DLWPS was developed using segmentation and classification models. The DLWPS-based segmentation model was developed by the U-Net framework, which combined the attention module and the edge feature extraction module. The average score of the output scores of three networks was used as the result of the DLWPS-based classification model. Moreover, the radiologists' diagnosis without and with the DLWPS-assistance was explored. To reveal the underlying biological basis of DLWPS, genetic analysis was performed based on RNA-sequencing data. Dice similarity coefficient (DI), area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and kappa value. The segmentation model reached a DI of 0.828 and 0.813 in the internal and external test sets, respectively. Within the breast lesions diagnosis, the DLWPS achieved AUCs of 0.973 in internal test set and 0.936 in external test set. For ALN metastasis discrimination, the DLWPS achieved AUCs of 0.927 in internal test set and 0.917 in external test set. The agreement of radiologists improved with the DLWPS-assistance from 0.547 to 0.794, and from 0.848 to 0.892 in breast lesions diagnosis and ALN metastasis discrimination, respectively. Additionally, 10 breast cancers with ALN metastasis were associated with pathways of aerobic electron transport chain and cytoplasmic translation. The performance of DLWPS indicates that it can promote radiologists in the judgment of breast lesions and ALN metastasis and nonmetastasis. 4 TECHNICAL EFFICACY STAGE: 3.

Preoperative Extrapancreatic Extension Prediction in Patients with Pancreatic Cancer Using Multiparameter MRI and Machine Learning-Based Radiomics Model

This study aimed to assess the effectiveness of various machine learning models in identifying lymph node metastasis in colon cancer patients and to explore the potential benefits of combining clinicoradiological and radiomics features for improved diagnosis. Atotal of 260 patients with pathologically confirmed colon cancer were retrospectively included in study center1 and study center2 from January 2015 to August 2024. Atotal of 198 patients with colon cancer in center1 were randomly divided into atraining set (n = 138) and an internal testing set (n = 60) at aratio of 7:3. Patients in center2 were included in the external testing set (n = 62). Five clinical radiological features were used to establish aclinical model. Radiomics features were extracted from the computed tomography venous phase images, and four classifiers, including logistic regression, support vector machine, decision tree, and k‑nearest neighbor, were used to build machine learning models. In addition, acombined model was constructed by joining clinical, radiological, and radiogenomic features. The performance of these models was evaluated in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), receiver operating curve (ROC) and calibration curves in the training set, internal testing set, and external testing set to determine the diagnostic model with the highest predictive efficiency and to evaluate the stability of the model. Among the four machine learning models, the SVM model had the best predictive performance, with an area under the ROC (AUC) of 0.813, 0.724, and 0.721 for the training set, internal testing set, and external testing set, respectively. The clinical model, radiomics model, and combined model had an AUC of 0.823, 0.813, 0.817, 0.508, 0.724, 0.751, 0.582, 0.721, and 0.744 in the training set, internal testing set, and external testing set, respectively. In conclusion, the combined model performed significantly better than the clinical model (p = 0.017, 0.038), but there was no significant difference between the radiomics model and the combined model (p = 0.556, 0.614).

BACKGROUND. Habitat imaging provides a novel approach to capture spatial heterogeneity within lesions. OBJECTIVE. The purpose of this study was to develop a ternary-classification habitat model to characterize lung adenocarcinoma presenting as a subsolid nodule (SSN) on CT and to test the model's diagnostic performance compared with 2D and radiomic models. METHODS. This retrospective study included 747 patients (median age, 56 years; 241 men, 506 women) with 834 resected lung adenocarcinomas that presented as SSNs on low-dose CT between July 2018 and July 2023. Adenocarcinomas from one center were divided into training (n = 440) and internal test (n = 189) sets; adenocarcinomas from three other centers formed an external test set (n = 205). Adenocarcinomas were classified as noninvasive adenocarcinoma, grade 1 invasive adenocarcinoma (IAC), or grade 2 or 3 (hereafter, grade 2/3) IAC. Ternary-classification models were built in the training set using multivariable multinomial logistic regression analyses (2D model: diameter and consolidation-to-tumor ratio; habitat model: volume and volume ratio of attenuation-based subregions; radiomic model: extracted radiomic features; combined model: habitat and radiomic features). Performance was evaluated using macroaveraged and class-specific AUCs. RESULTS. The optimal number of habitats was four. The 2D, habitat, radiomic, and combined models had macroaveraged AUCs in the internal test set of 0.857, 0.909, 0.914, and 0.912 and in the external test set of 0.871, 0.919, 0.924, and 0.926, respectively. Those four models had class-specific AUCs in the external test set for noninvasive adenocarcinoma of 0.945, 0.956, 0.961, and 0.955; for grade 1 IAC of 0.792, 0.858, 0.857, and 0.862; and for grade 2/3 IAC of 0.875, 0.940, 0.952, and 0.961, respectively. In the external test set, macroaveraged AUCs and class-specific AUCs for grades 1 and 2/3 IAC were significantly higher for habitat, radiomic, and combined models versus the 2D model, but not for other model comparisons; class-specific AUCs for noninvasive adenocarcinoma were not significantly different for any model comparisons. CONCLUSION. The habitat model performed significantly better than the 2D model in ternary adenocarcinoma classification; its performance was not significantly different from the radiomic and combined models. CLINICAL IMPACT. The habitat model's combination of interpretability and diagnostic performance supports its utility for noninvasive risk stratification of SSNs encountered during lung cancer screening.

BackgroundRadiomics and artificial intelligence have shown strong predictive capabilities in urinary stone research, particularly concerning stone composition, characteristics, and treatment outcomes. However, the association of stone radiomics and recurrence has not been well studied. This study aims to develop a machine learning model that combines radiomic features and clinical variables to pre-operatively predict kidney stones recurrence.MethodsA total of 540 patients with kidney stones from the First Affiliated Hospital of Guangzhou Medical University were randomly divided into an internal training set (n = 378) and an internal test set (n = 162) in a 7:3 ratio. Additionally, 141 patients from Zhongda Hospital Southeast University served as an external test set. Clinical data were collected from all patients, and both univariate and multivariate analyses were performed to identify clinical predictors of kidney stone recurrence. Radiomic features were extracted from non-contrast CT scans to construct the optimal radiomic model. A radiomic scoring nomogram, integrating both independent clinical predictors and the radiomic model, was then developed to assess the risk of kidney stone recurrence. Time-to-recurrence analyses, including Kaplan–Meier estimation of stone-free survival, time-dependent ROC curves at 3, 5, and 7 years, and multivariable Cox regression, were performed to evaluate long-term predictive performance.ResultsAmong the enrolled patients, 558 (81.9%) experienced recurrence, with 150 cases (26.9%,150/558) being symptomatic. Meanwhile, 123 patients (18.1%) did not experience recurrence. Median recurrence time was 3, 4, and 6 years in the internal training, internal test, and external test sets, respectively. The clinical model identified lower calyx stones and a history of stone disease as independent predictors of kidney stone recurrence. Of the 1688 radiomic features extracted from the kidney stones, 20 features were selected for the final model through the maximum relevance minimum redundancy and least absolute shrinkage and selection operator regression. The radiomic model demonstrated the area under the curve values of 0.797, 0.786, and 0.760 in the internal training, internal testing, and external testing, respectively, showing superior predictive performance compared to the clinical model alone. The combined nomogram model, integrating clinical predictors and radiomic features, further enhanced predictive accuracy with AUC values of 0.820, 0.824, and 0.786 in the respective cohorts. Kaplan–Meier analysis confirmed that patients stratified as high-risk by the nomogram had significantly lower stone-free survival of follow-up (log-rank P < 0.05), and the nomogram maintained robust discriminative performance at 3, 5, and 7 years across all cohorts.ConclusionsThe nomogram, which combines clinical variables and radiomic features, appears to demonstrate potential as a predictive tool for assessing kidney stone recurrence during patient follow-up in this study.Clinical trial numberNot applicable.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12880-025-02043-y.

Background Macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC) is an aggressive variant associated with angiogenesis and immunosuppressive tumor microenvironment, which is expected to be noninvasively identified using radiomics approaches. Purpose To construct a CT radiomics model to predict the MTM subtype and to investigate the underlying immune infiltration patterns. Materials and Methods This study included five retrospective data sets and one prospective data set from three academic medical centers between January 2015 and December 2021. The preoperative liver contrast-enhanced CT studies of 365 adult patients with resected HCC were evaluated. The Third Xiangya Hospital of Central South University provided the training set and internal test set, while Yueyang Central Hospital and Hunan Cancer Hospital provided the external test sets. Radiomic features were extracted and used to develop a radiomics model with machine learning in the training set, and the performance was verified in the two test sets. The outcomes cohort, including 58 adult patients with advanced HCC undergoing transarterial chemoembolization and antiangiogenic therapy, was used to evaluate the predictive value of the radiomics model for progression-free survival (PFS). Bulk RNA sequencing of tumors from 41 patients in The Cancer Genome Atlas (TCGA) and single-cell RNA sequencing from seven prospectively enrolled participants were used to investigate the radiomics-related immune infiltration patterns. Area under the receiver operating characteristics curve of the radiomics model was calculated, and Cox proportional regression was performed to identify predictors of PFS. Results Among 365 patients (mean age, 55 years ± 10 [SD]; 319 men) used for radiomics modeling, 122 (33%) were confirmed to have the MTM subtype. The radiomics model included 11 radiomic features and showed good performance for predicting the MTM subtype, with AUCs of 0.84, 0.80, and 0.74 in the training set, internal test set, and external test set, respectively. A low radiomics model score relative to the median value in the outcomes cohort was independently associated with PFS (hazard ratio, 0.4; 95% CI: 0.2, 0.8; P = .01). The radiomics model was associated with dysregulated humoral immunity involving B-cell infiltration and immunoglobulin synthesis. Conclusion Accurate prediction of the macrotrabecular-massive subtype in patients with hepatocellular carcinoma was achieved using a CT radiomics model, which was also associated with defective humoral immunity. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Yoon and Kim in this issue.