The proposed segmentation model with image and feature domain randomization provided automatic abdominal organ segmentation on CT and MRI scans, with high accuracy and generalization ability.

Background/Aims: Predicting treatment response to immunotherapy in hepatocellular carcinoma (HCC) is essential to improve clinical outcomes with personalized treatment strategies. This study aims to develop an AI-driven prediction model using radiomic analysis from the liver and viable HCCs on pretreatment CT to differentiate responders from non-responders. Methods: HCC patients who received immunotherapy between 2016 and 2023 with pretreatment CT scans were included. Radiomic features were extracted from the whole liver and the viable HCCs on the portal venous phase CT prior to immunotherapy. Multiple machine learning models were trained for binary classification to predict treatment response, initially using liver features (Model 1), and subsequently including both liver and tumor features (Model 2). Model performance was evaluated using three-fold cross-validation. Results: Among 55 HCC patients (median age, 69; 76.4% male) who received immunotherapy, 21 (38.2%) were responders and 34 (61.8%) non-responders by mRECIST criteria. Over 5000 radiomic features were extracted from pretreatment CT scans of the liver and viable tumors, of which approximately 100 were predictive of treatment response. Model 1 (liver) achieved an average accuracy of 77%, sensitivity of 76%, and specificity of 78%. Model 2 (liver and tumor) demonstrated improved performance, with accuracy, sensitivity, and specificity of 86%, 70%, and 94%, respectively, supporting the value of combined liver–tumor radiomics in treatment response prediction. Conclusions: This pilot study developed an AI-based model using CT-derived radiomic features to predict immunotherapy response in HCC patients. The approach may offer a non-invasive strategy to support personalized treatment planning using pretreatment CT scans.

This study presents a novel approach to improve the generalizability of pathologic complete response prediction in breast cancer by using deep learning for pharmacokinetic quantification of dynamic contrast-enhanced MRI.

Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) prediction in high-risk individuals is essential for early detection and improved outcome. While prior studies have utilized pancreatic radiomics for PDAC prediction, the added value of main pancreatic duct (MPD) features remains unclear. This study aims to assess the additional value of features of the main pancreatic duct (MPD) for predicting PDAC occurrence across different timeframes in advance. Methods: In total, 321 contrast-enhanced CT scans of the MPD and pancreas carried out across control, pre-diagnostic, and diagnostic cohorts were segmented, and radiomics were extracted. A support vector machine (SVM) classifier was used to classify the control and pre-diagnostic cohorts, with model performance assessed using area under the receiver operating characteristic (ROC) curves (AUCs) Results: The MPD diameter and volume significantly increased from the control to the pre-diagnostic and diagnostic CT scans (p < 0.05). The addition of features of the MPD to the pancreas improved the PDAC prediction AUC from 0.83 to 0.96 for subjects 6 months to 3 years in advance, from 0.81 to 0.94 for 3–6 years in advance, and 0.75 to 0.84 for 6–10 years in advance of diagnosis. Additionally, integrating MPD radiomics with diameter and volume significantly improved the AUC from 0.81 to 0.88 for subjects 6 months to 3 years in advance. Conclusions: Radiomic features from abdominal CT scans allow PDAC prediction up to 10 years in advance. Integrating MPD features, including diameter and volume, significantly improves PDAC prediction compared to using radiomics of the pancreas alone.

Background: Multiparametric MRI (mpMRI) as a non-invasive imaging tool is important in prostate cancer (PCa) detection and localization. Combined with radiomics analysis, features extracted from mpMRI have been utilized to predict PCa aggressiveness. T2 mapping provides quantitative information in PCa diagnoses but is not routinely available in clinical practice. Previous work from our group developed a deep learning-based method to estimate T2 maps from clinically acquired T1- and T2-weighted images. This study aims to evaluate the added value of the estimated T2 map by combining it with conventional T2-weighted images for detecting clinically significant PCa (csPCa). Methods: An amount of 76 peripheral zone prostate lesions, including clinically significant and insignificant cases, were retrospectively analyzed. Radiomic features were extracted from conventional T2-weighted images and deep learning-estimated T2 maps, followed by feature selection and model development using five-fold cross-validation. Logistic regression and Gaussian Process classifiers were employed to develop the prediction models, with performance evaluated by area under the curve (AUC) and accuracy metrics. Results: The model incorporating features from both T2-weighted images and estimated T2 maps achieved an AUC of 0.803, significantly outperforming the model based solely on T2-weighted image features (AUC of 0.700, p = 0.048). Conclusions: Radiomics features extracted from deep learning-estimated T2 maps provide additional quantitative information that improves the prediction of peripheral zone csPCa aggressiveness, potentially enhancing risk stratification in non-invasive PCa diagnostics.