Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition

Radiomics: Body

Digital Poster

Analysis Methods

Monday, 11 May 2026

Digital Posters Row G

13:50 - 14:45

Session Number: 366-03

No CME/CE Credit

Similar Sessions

This is a digital poster section about applications of radiomics outside neuro.

Skill Level: Intermediate

		366-03-001. Intratumoral Habitat and Peritumor Radiomics for Progression Risk Stratification of Patients with Soft Tissue Sarcoma Haoyu Liang, Mengxiao Liu, Yang Song Huashan Hospital, Fudan University, China Impact: Combining radiomics features derived from the intratumoral habitat and peritumoral region resulted in superior performance for predicting progression-free-survival in patients with STS, which is helpful for clinical decision making.
		366-03-002. LASSO informed textural changes are more sensitive than volumetry of amygdala in cocaine use disorder patients Shounak Nandi, Sairam Geethanath Albert Einstein College of Medicine, Bronx, United States of America Impact: This framework improves reproducibility and interpretability in longitudinal MRI studies by integrating penalized regression and mixed-effects modeling, revealing texture features as temporally sensitive biomarkers of amygdalar microstructure and treatment-related plasticity beyond conventional volumetric measures in cocaine-use-disorder patients undergoing treatment.
		366-03-003. DWI, Motion-Corrected T2W, & Free-Breathing 3D-GRE Radiomics for Predicting Neoadjuvant Chemotherapy Efficacy in ESCC Bingmei Bai, Funing Chu, Yue Wu, Jinrong Qu The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China Impact: A non-invasive multimodal MR radiomics model integrating features from pre- and post-NAC imaging accurately predicts pathologic response in ESCC patients. This tool can potentially identify non-responders early, enabling timely treatment modification and facilitating personalized therapeutic strategies before invasive surgery.
		366-03-004. 2.5D deep learning based on multimodal and multi-view MRI predicts recurrence-free survival after radical resection of HCC Jiayi Li, Nanyun Lin, Hui Ma, Yueming Li The First Affiliated Hospital of Fujian Medical University, Fuzhou, China Impact: This study aids clinicians in stratifying post-HCC-resection recurrence risk and formulating personalized treatment plans, advances the clinical translation of deep learning, guides researchers in exploring multimodal 2.5D models, and enables further research focusing on the model’s applicability in multicenter data.
		366-03-005. Can AI help radiologists with prostate MRI interpretation? Donald Chan, Cynthia Li, Richard Fan, Simon Soerensen, Jessica Chong, Sunny Rishi, Terrence Jao, Andreas Loening, Pejman Ghanouni, Geoffrey Sonn, Mirabela Rusu Stanford Medicine, Stanford, United States of America Impact: AI may help improve the interpretation of prostate MRI. This study will evaluate the effect of AI on inter-reader variability and reader accuracy. Future directions include further development of AI models and radiologist education about AI.
		366-03-006. Preoperative phenotypic stratification of primary central nervous system lymphoma using multiparametric MRI-based radiomics Lingxu Chen Beijing Tiantan Hospital, Capital Medical University, Beijing, China Impact: An automated multiparametric MRI–based radiomics approach predicts double-expression and germinal center B-cell–like phenotypes of primary central nervous system lymphoma, providing a practical, noninvasive tool for preoperative risk stratification and to inform therapeutic decision-making.
		366-03-007. Prediction of Neoadjuvant Response of Breast Cancer using Pharmacokinetic Quantification of Pre-treatment DCE MRI Haoyan Ding, Chaowei Wu, Lixia Wang, Linda Azab, Yuan Yuan, Debiao Li Cedars-Sinai Medical Center, Los Angeles, United States of America Impact: This framework enables more accurate prediction of breast cancer treatment response by integrating pharmacokinetic quantification in deep learning and multi-scale radiomics. It may assist clinicians in early therapy evaluation, optimize treatment decisions, and inspire broader use of temporal-spatial analysis.
		366-03-008. Distinguishing Atypical Nasopharyngeal Lymphoid Hyperplasia from Early Nasopharyngeal Carcinoma Using MR Habitat Radiomics Zhenhuan Huang, Zhaoxue Tu, Peng Wu, Tingyu Yu, Dandan Lin, Jing Qiu, Qikui You, Hui Ma, Wanrong Huang, Yueming Li Longyan First Affiliated Hospital of Fujian Medical University, Longyan, China Impact: This habitat radiomics tool could reduce unnecessary biopsies for patients and improve diagnostic consistency for clinicians. It also enables new research into how spatial tumor heterogeneity influences early cancer detection.
		366-03-009. Spatiotemporal Delta Radiomics for Predicting Axillary Lymph Node Metastasis in Breast Cancer Hui Yang, Shuluan Chen, Xuetong Tao, Xuanle Li, Kexin Chen, Ya Ren, Meng Wang, Lin Li, Jie Wen, wei cui, Xin Liu, Dong Liang, Hairong Zheng, Zhanli Hu, Zhou Liu, Na Zhang Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China Impact: Delta-radiomics features from DCE-MRI wash-in and wash-out dynamics serve as promising biomarkers for noninvasive ALNM prediction.
		366-03-010. Development of MRI-based radiomics model for age-adjusted detection of disease in a preclinical blood cancer models Ana Gomes, Algernon Bloom mPixl Technologies Ltd, London, United Kingdom Impact: We demonstrate that incorporating age-adjusted radiomic feature selection significantly mitigates demographic bias in AI-based AML classification while preserving diagnostic-grade performance, thereby addressing key fairness considerations for the clinical deployment of medical imaging AI across diverse patient populations.