TissUnet: Improved extracranial tissue and cranium segmentation for children through adulthood
Year: 2025
Type: article
Abstract: Extracranial tissues visible on brain magnetic resonance imaging (MRI) may hold significant value for characterizing health conditions and clinical decision-making, yet they are rarely quantified. Current tools have not been widely validated, particularly in settings of developing brains or underlying pathology. We present TissUnet, a deep learning model that segments skull bone, subcutaneous fat, and muscle from routine three-dimensional T1-weighted MRI, with or without contrast enhancement. The model was trained on 155 paired MRI-computed tomography (CT) scans and validated across nine datasets covering a wide age range and including individuals with brain tumors. In comparison to AI-CT-derived labels from 37 MRI-CT pairs, TissUnet achieved a median Dice coefficient of 0.79 [IQR: 0.77-0.81] in a healthy adult cohort. In a second validation using expert manual annotations, median Dice was 0.83 [IQR: 0.83-0.84] in healthy individuals and 0.81 [IQR: 0.78-0.83] in tumor cases, outperforming a previous state-of-the-art method. Acceptability testing resulted in an 89% acceptance rate after adjudication by a tie-breaker (N = 108 MRIs), and TissUnet demonstrated excellent performance in the blinded comparative review (N = 45 MRIs), including both healthy and tumor cases in pediatric populations. TissUnet enables fast, accurate, and reproducible segmentation of extracranial tissues, supporting large-scale studies on craniofacial morphology, treatment effects, and cardiometabolic risk using standard brain T1w MRI.
Source: Imaging Neuroscience
DOI: 10.1162/imag.a.1067
Authors: Markiian Mandzak, Elvira Yang, Anna Zapaishchykova, Yu-Hui Chen, Lucas Heilbroner, John Zielke, Divyanshu Tak, Reza Mojahed-Yazdi, Francesca Romana Mussa, Zezhong Ye, Sridhar Vajapeyam, Viviana Benitez, Ralph Salloum, Susan N. Chi, Houman Sotoudeh, Jakob Seidlitz, Sabine Mueller, Hugo J.W.L. Aerts, Tina Y. Poussaint, Benjamin H. Kann
Institutions: Brigham and Women's Hospital, Harvard University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center, Ukrainian Catholic University, Mass General Brigham, Ludwig-Maximilians-Universität München, Maastricht University, George Washington University, Boston Children's Hospital, The University of Texas Southwestern Medical Center, Children's Hospital of Philadelphia, University of Pennsylvania Health System, University of Pennsylvania, University of California, San Francisco
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7108446331