ISMRM25 - AI for Diagnosis/Prognosis: Body III

ISMRM & ISMRT Annual Meeting & Exhibition • 10-15 May 2025 • Honolulu, Hawai'i

AI for Diagnosis/Prognosis: Body III

Digital Poster

AI & Machine Learning

Monday, 12 May 2025

Exhibition Hall

09:15 - 10:15

Session Number: D-44

No CME/CE Credit

		Computer Number: 17 1546. An MR breast auto prescription on-site learning system to adapt different scan plan preferences: a proof-of-concept study View Presentation Video C. Wang, H. Yang, L. Zhang Canon Medical Systems (China), Beijing, China Impact: The proof-of-concept study verifies the proposed on-site learning system's feasibility by in-house simulation. The system could automatically train auto prescription models adapting to different scan orientation preferences, and it is expected to be extended to other scan ROI parameters.
		Computer Number: 18 1547. Promoting LLMs for Breast Cancer TNM Staging Using Radiology Reports: Comparing Different Prompts and Models W. Xu, Z. Ding, Q. Shen, Y. Shan, S. Pan, Z. Li, L. Cao, M. Ruan Hangzhou First People's Hospital Affiliated of Westlake University School of Medicine, Hangzhou, China Impact: This study demonstrates the potential of LLMs, especially ChatGPT 4.0, in automating breast cancer TNM staging from DCE-MRI reports. The effectiveness of few-shot learning suggests a pathway for rapid adaptation of AI in radiology, potentially enhancing diagnostic efficiency and accuracy.
		Computer Number: 19 1548. Fully automatic lesion segmentation and deep myometrial invasion prediction method for endometrial cancer based on MRI K. Gao, H. Wu, W. Wang the Affiliated Hospital of Inner Mongolia Medical University, Hohhot, Inner Mongolia, China Impact: NnU-Net has the potential to automatically identify and segment endometrial cancer lesions. The combined model integrating radiomics features and clinical risk factors has a better ability to identify deep myometrial invasion.
		Computer Number: 20 1549. Automated Deep Learning Method for Whole-Breast Segmentation in Synthetic MRI W. Gao, Y. Zhang, Y. Xia, Y. Xiong The Second Affiliated Hospital of Xi 'an Jiaotong University, Xi'an, China Impact: The nnU-Net exhibited exceptional segmentation performance for fully automated breast segmentation of contrast-free quantitative images.
		Computer Number: 21 1550. Research on Predicting the Efficacy of NAC in Breast Cancer Based on a Multisequence MRI Intratumoral Combined Peritumoral Radiomics Model View Presentation Video X. Liu, Y. Cao, A. Yang, M. Cao Qinghai University Affiliated Hospital, Xining, China Impact: This study contributes to improving the level of breast cancer diagnosis and treatment.
		Computer Number: 22 1551. Potential time and recall benefits for adaptive AI breast MRI screening View Presentation Video L. Balkenende, J. Brunekreef, J. Teuwen, R. Mann Netherlands Cancer Institute (NKI), Amsterdam, Netherlands Impact: The AI-based hybrid protocol could improve MRI screening by reducing acquisition time and recall rates, enhancing patient-centric care, improving MRI availability and achieving better breast cancer screening.
		Computer Number: 23 1552. MRI subregion Radiomics for Predicting Recurrence Risk in ER+/HER2- Breast Cancer Y. Chen, W. Peng, J. Shi Fudan University Shanghai Cancer Center, Shanghai, China Impact: This study first identified radiomics signatures using intratumoral subregional features to predict RS accurately and cost-effectively in ER+/HER2- breast cancer.
		Computer Number: 24 1553. CNN-Certainty-Directed Utilization of Deep Learning in Radiological Assessment of Adnexal Masses on Pelvic MRI View Presentation Video D. Bonekamp, T. Mokry, N. Netzer, T. Hielscher, C. Flechtenmacher, L. K. Nees, O. Zivanovic, H-U Kauczor, H-P Schlemmer DKFZ, Heidelberg, Germany Impact: CNN-based triage of multi-parametric pelvic MRI for assessment of adnexal masses has potential to support radiological decision making.
		Computer Number: 25 1554. Assessment of machine learning model performance to differentiate benign and malignant breast lesion: Finding best radiomic features on MDME MRI View Presentation Video H. HAQUE, T. Matsuda, M. Matsuda, S. Fuchibe, T. Kido GE HealthCare, Tokyo, Japan Impact: Comparing with BI_RADS, post contrast MDME derived radiomics-based machine learning shows promising potential in differentiating malignant breast lesion. Which may simplify of breast image scanning protocols and pulse-sequence-design for malignancy check.
		Computer Number: 26 1555. Value of predicting HER-2 and Ki-67 expression status in breast cancer based on multiparametric MRI intratumor combined with peritumor radiomics View Presentation Video M. Cao, Y. cao, X. Liu, A. Yang Affiliated Hospital of Qinghai University, Xining, China Impact: Accurate preoperative prediction of HER-2 and Ki-67 expression status in breast cancer is expected to provide a reference for precise and personalized treatment decisions in later stages of clinical practice.
		Computer Number: 27 1556. Deep learning-based prediction of response to neoadjuvant immunochemotherapy in triple-negative breast cancer based on pretreatment DCE-MRI View Presentation Video Z. Fu, Y. Liu, Z. Xu, J. B. Son, X. Huo, T. Moseley, B. Adrada, C. Yam, J. Ma, G. Rauch The University of Texas MD Anderson Cancer Center, Houston, United States Impact: A deep learning model has the potential to predict TNBC response to NICT before treatment and to help with the clinical management.
		Computer Number: 28 1557. The Role of Multiparametric MRI Radiomics in Predicting Axillary Lymph Node Metastasis in Invasive Breast Cancer Patients: A Comparative Study Y. Chen, Y. Guo, W. Tang, S. Chen, Q. Kong, Y. Xu, X. Jiang Guangzhou First People's Hospital, Guangzhou, China Impact: The comparative analysis identified the optimal combination of MRI sequences that can enhance the accuracy of preoperative ALNM status prediction in invasive breast cancer patients, potentially enabling the personalization of axillary treatment strategies.
		Computer Number: 29 1558. Prediction of LVSI Status in Pre-treatment Cervical Cancer Using a Tumor Ecological Model Based on DCE-MRI Quantitative Parameter Mapping F. Li, G. Huang, K. Ai Gansu Provincial People's Hospital, lanzhou, China Impact: By utilizing tumor habitat imaging and ecological analysis methods, we quantify the differences in spatial heterogeneity within tumors to predict the LVSI status of patients with cervical cancer and provide biological interpretability for the behavior that gives rise to LVSI.
		Computer Number: 30 1559. Automated classification of intervertebral disc degeneration using Pyradiomics features: XGBoost versus OnevsRest View Presentation Video L. T. Muftuler, A. Drobek Medical College of Wisconsin, Milwaukee, United States Impact: Lack of objective measures of disc degeneration may cause uncertainties in treatment decisions. Automated evaluation of disc degeneration streamlines the physician’s workflow and reduce uncertainties. Using radiomics features enables explainability and provides simple and robust training for machine learning approaches.
		Computer Number: 31 1560. Breast Cancer Detection Using Synthetic Post-Contrast MRI in Breast Cancer Patients View Presentation Video S. M. Ha, Y. Lee, H. Yoen, W. K. Moon Seoul national University Hospital, Seoul, Korea, Republic of Impact: With increased demand for non-contrast breast MRI due to gadolinium concerns, synthetic post-contrast MRI offers a promising alternative, enhancing breast cancer detection and making MRI more accessible.
		Computer Number: 32 1561. Based on Multiparameter-MRI radiomic features: differential diagnosis of BI-RADS 4 Breast lesions with DCE-TIC type II y. li, l. zhang, s. zhao, y. wu, M. Zhang, H. Guan The First Affiliated Hospital of Dalian Medical University, Dalian, China Impact: This study’s multi-parameter MRI radiomics model enhances diagnostic accuracy for BI-RADS 4 breast lesions, offering radiologists a reliable tool for distinguishing benign from malignant cases, reducing unnecessary biopsies, and improving patient management in breast cancer diagnostics.

Similar Session(s)