ISMRM25 - AI for Image Segmentation: From Head to Toe

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

AI for Image Segmentation: From Head to Toe

Digital Poster

AI & Machine Learning

Monday, 12 May 2025

Exhibition Hall

13:45 - 14:45

Session Number: D-43

No CME/CE Credit

		Computer Number: 49 1706. InvYNet: an inverted Y shape network for prostate cancer segmentation using prostate zones information Y. Liu, Z. ZHU, X. Zhang, B. Zhang The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing University, Nanjing, China Impact: InvYNet is the first model to integrate anatomical zones for prostate cancer segmentation, setting a new standard in this field.
		Computer Number: 50 1707. Enhancing Glioma Segmentation Accuracy Using Attention ResUNet F. Moodi, F. Khodadadi Shoushtari, G. Valizadeh, D. Mazinani, H. Mobarak Salari, H. Saligheh Rad Quantitative MR Imaging and Spectroscopy Group (QMISG), Tehran University of Medical Sciences, Tehran, Iran-School of Medicine, Iran University of Medical Sciences, Tehran, Iran, Tehran, Iran (Islamic Republic of) Impact: AResUNet demonstrates improved segmentation performance for glioma brain tumors, offering insights that may enhance diagnostic accuracy and treatment strategies in clinical practice. This model's architecture showcases the benefits of integrating attention mechanisms in deep learning approaches for medical image analysis.
		Computer Number: 51 1708. Clinical Evaluation of nn-UNet for Automated Segmentation of Pituitary Gland and Optic Apparatus in Brain MRI: A Multi-Database Approach View Presentation Video M. Yakubu, Q. Chen, A. Albusaidi, J. Shapey, A. King, A. Hammers King's College London, London, United Kingdom Impact: This research has the potential to improve the accuracy of MRI diagnostics for pituitary and sellar region disorders. By addressing the challenges of model performance on clinical data, it opens new avenues for optimizing deep learning applications in medical imaging.
		Computer Number: 52 1709. Deep Learning Based Tumor Segmentation on MRI of Prostate Cancer Patient-Derived Xenografts in Mouse Models View Presentation Video S. Nayak, H. Salkever, E. Diaz, A. Sinha, N. Deveshwar, M. Hess, M. Gibbons, S. Sahin, A. Rajagopal, P. Larson, R. Sriram University of California, San Francisco, San Francisco, United States Impact: This automated segmentation pipeline enhances efficiency in preclinical tumor studies, reducing manual effort and interuser variability. It provides a robust tool for evaluating treatment efficacy, potentially enabling broader use in diverse xenograft studies and informing translational research.
		Computer Number: 53 1710. Volumetric Auto-Segmentation of the Pancreaticobiliary System for Evaluating MRCP Image Quality: Efficacy Before and After Contrast-Enhanced z. zhou, C. Wang, S. Li, Z. Li Huazhong University of science and technology, Tongji College, Tongji Hospital, wuhan, China Impact: The automatic segmentation model provides a robust tool for efficient 3D pancreaticobiliary reconstruction, improving MRCP workflow. Future studies may investigate optimizing MRCP quality based on patient factors or clinical scenarios, and assess diagnostic value of quantitative parameters extracted from segmentation.
		Computer Number: 54 1711. CEST-Enhanced Dual TransUNet for Precise Segmentation of Nasopharyngeal Carcinoma View Presentation Video Z. Liyan, G. Cai, C. yingying, Y. Qian, C. Wei, L. Jianzhon, L. Zhou Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 113 Baohe Avenue, 518116, Shenzhen, China, Shenzhen, China Impact: The deep-learning model effectively utilized CEST contrast for precise NPC segmentation, enhancing radiotherapy planning by accurately targeting carcinoma and preserving healthy tissue, while advancing CEST imaging's role in clinical oncology.
		Computer Number: 55 1712. Renal corticomedullary segmentation from arterial phase volumetric T1-weighted imaging: human or machine? View Presentation Video D. Liyanage, S. Kachel, L. McKenna, E. Hornsey, C. Gillespie, B. Churilov, E. Ekinci, H. Rusinek, A. Mikheev, R. Lim Austin Health, Melbourne, Australia Impact: MRI-derived renal corticomedullary segmentation can be efficiently and reproducibly performed using automated techniques with similar results to manual segmentation. Such techniques have promise for assessment and monitoring of chronic kidney disease and have potential application for prognostication through multi-parametric approaches.
		Computer Number: 56 1713. Cartilage Auto-Segmentation of 3D T2* GRE Sequence in 7T High-Resolution 3D MRI View Presentation Video E. Hedayati, A. W. Kajabi, K. Knutsen, C. Steinberger, A. Lamba, L. Tollefson, G. Metzger, R. LaPrade, J. Ellermann University of Minnesota, Minneapolis, United States Impact: This method accelerates cartilage segmentation in 3D T2*-weighted MRI, reducing manual correction, speeding ground truth creation, potentially supporting quantitative analysis, and enhancing efficiency in cartilage assessment for knee osteoarthritis.
		Computer Number: 57 1714. A Shape Attentive Convolutional Neural Network for Improving the Generalizability of CMR Image Segmentation View Presentation Video X. Wang, S. Lloyd, H. Gupta, L. Dell’Italia, T. Denney Auburn University, Auburn, United States Impact: Our network can be trained and validated on CMR data from one site and can accurately segment CMR data from other sites.
		Computer Number: 58 1715. Spatial-Temporal Mamba Network for Accurate Breast Tumor Segmentation in DCE-MRI View Presentation Video H. Zhang, M. Wang, Y. Ren, J. Wen, W. Cui, B. Han, D. Luo, Z. Liu, N. Zhang Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China Impact: Our results show that the proposed model can significantly improve tumor segmentation accuracy in DCE-MRI by utilizing both spatial and temporal features. This advancement holds promise for more accurate breast cancer diagnosis and better-informed treatment planning.
		Computer Number: 59 1716. Automated MRI-Based Quantification of Forearm Muscle Health and Associations with Hand Function View Presentation Video J. Fundaun, V. Oliva, S. Bédard, E. Wesselink, B. Lynn, A. Pai S, D. Pfyffer, M. Kaptan, N. Berhe, J. Ratliff, S. Hu, Z. Smith, T. Hastie, S. Mackey, M. McKay, J. Elliott, S. Delp, G. Glover, A. Chaudhari, C. Law, A. Smith, K. Weber II Stanford University, Palo Alto, United States Impact: We developed an accurate, reliable computer-vision model to automatically segment forearm muscles, which will be made openly available. This method can improve clinical assessment of forearm muscle health leading to more efficient evaluation and management of conditions affecting hand function.
		Computer Number: 60 1717. DG-Net：A Semi-Supervised Fetal Brain Segmentation Method Based on Diffusion Model and Guided Consistency View Presentation Video K. Qi, C. Yan, D. Niu, B. Zhang, D. Liang, X. Long Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China , Shenzhen, China Impact: This study introduces a semi-supervised fetal brain tissue segmentation method leveraging the diffusion model and guided consistency. It achieves comparable performance with fewer labeled samples, reducing manual marking time and advancing fetal brain diagnosis.
		Computer Number: 61 1718. Automated Multi-Organ Segmentation in Fetal MRI View Presentation Video A. Lim, M. Wagner, B. Ertl-Wagner, L. Vidarsson, D. Sussman Toronto Metropolitan University, Toronto, Canada Impact: The Fetal MRI Segmentation Network (FetSegNet) enables precise fetal body, amniotic fluid, and placenta segmentation, enhancing clinical efficiency and supporting more accurate pregnancy monitoring, paving the way for improved maternal-fetal health diagnostics and a deeper understanding of fetal development.
		Computer Number: 62 1719. Validation of fully-automated whole liver segmentation for measurement of hepatic fat fraction View Presentation Video N. Mahalingam, D. Bachu, C. Crabtree, K. Binzel, A. M. Castillo, J. Volek, Y. Han, O. Simonetti The Ohio State University, Columbus, United States Impact: Hepatic fat fraction from MRI can non-invasively stage the degree of hepatic steatosis for NAFLD evaluation. Automatic fat fraction measurement is more efficient than manual approaches, making it more suitable for clinical workflows.
		Computer Number: 63 1720. Validation of an Automated Open Source Pipeline for Comprehensive Knee MRI Segmentation and Measurement of Quantitative Outcomes View Presentation Video F. Belibi, V. Sahani, Y. Vainberg, A. Goyal, A. Williams, C. Chu, R. Pedersen, B. Haddock, A. Chaudhari, F. Kogan, A. Gatti Stanford University, Stanford, United States Impact: Automated segmentation and analysis of bone and cartilage have the potential to greatly improve the translation potential of quantitative MSK MRI biomarkers.
		Computer Number: 64 1721. Data Augmentation with Generative Deep Learning for Automatic Bone Segmentation from Fat Fraction MRI View Presentation Video N. Dwork, P. Elangovan, D. Connor, A. McManus, R. Krug, G. Kazakia, C. Jankowski, J. Carballido-Gamio University of Colorado Anschutz, Aurora, United States Impact: With an automatic bone segmentation algorithm from fat fraction MR images, future work will conduct a thorough investigation into how bone marrow adiposity affects bone fragility.

Similar Session(s)