ISMRM25 - AI for Image Segmentation: Above the Neck

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

AI for Image Segmentation: Above the Neck

Digital Poster

AI & Machine Learning

Monday, 12 May 2025

Exhibition Hall

14:45 - 15:45

Session Number: D-38

No CME/CE Credit

		Computer Number: 33 1849. Deep learning segmentation of small blood vessels and vessel density mapping based on high resolution black blood MRI View Presentation Video S. Mendoza, Z. Yang, J. Lamas, K. Jann, M. Harrington, J. Ringman, Y. Shi, D. Wang USC, Los Angeles, United States Impact: A robust cerebral small vessel density estimation method can help for large-scale analysis of black blood MRI data to look for possible biomarkers of early cognitive decline. Our pipeline will be shared with the community.
		Computer Number: 34 1850. Study of the impact of registration errors on the segmentation of stroke lesion in deep learning. View Presentation Video O. Pulvéric, F. Ouadahi, T. Boutelier Olea Medical, La Ciotat, France Impact: By identifying a critical 3 mm threshold for registration errors, we established quantitative guidelines for acceptable registration accuracy in clinical workflows. This threshold helps define minimal performance requirements for registration algorithms when preprocessing images for segmentation tasks.
		Computer Number: 35 1851. Deep Learning-Driven Architecture for Automated Segmentation and High-Risk Carotid Plaque Identification in High-Resolution MRI X. Cao, Z. Zheng, Q. Yang Academy for Engineering and Technology, Fudan University, Shanghai, China Impact: This study significantly enhances the diagnostics of carotid atherosclerosis by leveraging high-resolution MRI and deep learning to accurately identify high-risk plaques, improving early intervention and potentially transforming outcomes in cardiovascular patient care.
		Computer Number: 36 1852. Improving Subcortical and Hippocampal Subfield Segmentation with a 3D Hybrid Deep Learning Solution View Presentation Video A. Cao, Z. Li, J. Jomsky, A. Laine, J. Guo University of California, Santa Barbara, San Jose, United States Impact: Our proposed novel deep learning model, MedSegMamba, reliably demonstrated state-of-the-art segmentation performance and utility across numerous datasets. It outperformed other well-established deep learning tools on the difficult tasks of subcortical and hippocampal subfield segmentation. Code is available here: https://github.com/aaroncao06/MedSegMamba.
		Computer Number: 37 1853. Improving Subcortical Segmentation in Brain MRI Using Knowledge Distillation to Enhance Robustness Against Motion Artifacts View Presentation Video C. Ryu, S. Jung, Y. Choi, D-H Kim Yonsei University, Seoul, Korea, Republic of Impact: This approach improves MRI segmentation of motion-corrupted data, supporting reliable subcortical analysis without complex preprocessing. It provides a method for cleaner, artifact-resistant segmentation, presenting significant applications both in neurodevelopmental and neurodegenerative disease research.
		Computer Number: 38 1854. A k-Space Super-Resolution and Registration-Guided Thalamic Subregions Segmentation Model for Analyzing Thalamic Iron Changes in AD J. He, D. Li, B. Fu, L. Nie, R. Wang Guizhou Provincial People’s Hospital, Guiyang, China Impact: There is currently a lack of research on quantitative iron analysis in fine-grained thalamic subregions of AD patients. This study could provide new prognostic assessments and therapeutic target references for AD research.
		Computer Number: 39 1855. Automatic Labelling of Intracranial arteries: A Comparison of UNet-based Networks View Presentation Video J. Bisbal, S. Jofré, P. Winter, A. Ponce, M. Aristova, J. Moore, O. Welin Odeback, S. Ansari, C. Tejos, S. Uribe, M. Markl, J. Sotelo, S. Schnell, D. Marlevi Pontificia Universidad Catolica de Chile, Santiago, Chile Impact: This study identifies Residual UNet as an effective tool for automated intracranial artery labeling, enabling fully automatic processing of intracranial 4D Flow MRI data.
		Computer Number: 40 1856. A Two Step Deep Learning Framework for Identifying Ischemic Stroke Core: Integration of Inception-v3 and MultiResU-Net on DWI and ADC MRI Images View Presentation Video A. Kandpal, P. Prajapati, S. Maurya, R. Gupta, A. Singh Indian Institute of Technology Delhi, New Delhi, India Impact: The proposed deep-learning framework combines DWI images and ADC maps to enable automatic, rapid ischemic core segmentation with high accuracy, supporting radiologists in the objective evaluation and planning of stroke treatment.
		Computer Number: 41 1857. Diffusion MRI spherical mean improves deep cerebellar nuclei segmentation View Presentation Video J. H. Legarreta, Z. Lan, Y. Chen, F. Zhang, E. Yeterian, N. Makris, J. Rushmore, Y. Rathi, L. O’Donnell Brigham and Women's Hospital, Mass General Brigham/Harvard Medical School, Boston, United States Impact: Diffusion MRI spherical mean should be considered as a relevant image contrast for cerebellar structure segmentation using deep neural networks towards an increasingly accurate connectivity analysis.
		Computer Number: 42 1858. Deep-THOMAS: a robust deep learning network for fast and accurate thalamic nuclei segmentation View Presentation Video A. Barat, R. Ramesh, A. Cacciola, A. Banerjee, M. Saranathan University of Massachusetts Amherst, Amherst, United States Impact: This robust thalamic nuclei segmentation tool can be integral for clinical neuroimaging, offering fast, reliable segmentation, opening the door for analysis of large public databases to study the role of thalamic nuclei in a variety of neurodegenerative and neuropsychiatric conditions.
		Computer Number: 43 1859. Comparative Analysis of Deep Learning Models for Brain Tumor Segmentation in MRI Scans Using BraTS and Experimental Datasets View Presentation Video S. Misra, S. Bera, S. Basak, S. Sarkar, A. Rajan, S. Mohan, H. Poptani, S. Chawla, S. Bhaduri TCG Centres for Research & Education in Science & Technology, Kolkata, India Impact: It highlights potential of deep-learning models, particularly nnU-Net to improve accuracy and efficiency in brain-tumor segmentation, reducing reliance on labor-intensive methods like RANO and iRANO. Addressing dataset-specific limitations through transfer-learning, the findings aids in consistent tumor-volume assessment, enhancing treatment monitoring.
		Computer Number: 44 1860. Contrastive Mutual Learning: A Semi-Supervised Method for 3D Fetal Brain Segmentation View Presentation Video S. Li, L. Jia, W. Cai, C. Wang, H. Wang, H. Li Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, China, Shanghai, China Impact: This study implemented a semi-supervised learning approach to address the challenges of limited labeled data and high annotation costs in 3D fetal brain segmentation. The performance demonstrates the proposed algorithm's robust potential.
		Computer Number: 45 1861. Improving Brain Tumor Segmentation with a Clinically-Informed Multi-Decoder U-Net View Presentation Video A. Rezk, A. Al-Fakih, A. Shazly, K. Ryu, M. A. Al-masni Sejong University, Seoul, Korea, Republic of Impact: Our clinically guided, multi-decoder U-Net demonstrates improved segmentation accuracy, particularly in diverse and non-standard datasets. This innovation paves the way for more reliable, adaptable, and interpretable brain tumor imaging, enhancing diagnostic confidence and treatment planning.
		Computer Number: 46 1862. MR-Eye atlas: a large-scale atlas of the eye based on T1-weighted MR imaging View Presentation Video J. Barranco, A. Luyken, P. Stachs, O. Esteban, Y. Aleman, S. Langner, O. Stachs, B. Franceschiello, M. Bach Cuadra CIBM Center for Biomedical Imaging, Lausanne, Switzerland Impact: The publicly provided large-scale unbiased T1w MR-Eye atlases will facilitate spatial normalization and quantitative analysis in the field of ophthalmic imaging, helping clinicians in the diagnosis of multiple ocular diseases, and enhancing our understanding in sex-specific eye anatomy and physiology.
		Computer Number: 47 1863. Automated Pipeline Development for Multi-Compartmental Volumetric Glioblastoma Segmentation and Advanced MRI Parameter Extraction View Presentation Video E. Lotan, A. Saulnier, J. Nguyen, E. Hammon, A. Davis, M. Lee NYU Grossman School of Medicine, New York, United States Impact: This automated pipeline can enhance clinical decision-making and personalized treatment for glioblastoma patients. Its development will facilitate new research on imaging biomarkers, ultimately improving patient outcomes and advancing neuroimaging practices.
		Computer Number: 48 1864. A Comprehensive Deep Learning Approach for Multi-type Central Nervous System Tumor Segmentation Based on the 2021 WHO Classification View Presentation Video S. Li, L. Guo, Y. Tian, G. Ju, S. Zhang, Y. Jin, X. Su, S. Tang, A. Zeng, Y. Luo, X. Yang, L. Wang, L. Wang, H. Zhang, W. Yang, X. Liang, Q. Yue West China Hospital of Sichuan University, Chengdu, China Impact: This work advances automated, multi-tumor segmentation tools, enhancing clinical workflows and supporting consistent, efficient CNS tumor analysis.

Similar Session(s)