Semi-automatic muscle segmentation in MR images using deep registration-based label propagation

• Published in: Pattern recognition Vol. 140; no. August 2023; p. 109529
• Main Authors: Decaux, Nathan, Conze, Pierre-Henri, Ropars, Juliette, He, Xinyan, Sheehan, Frances T., Pons, Christelle, Ben Salem, Douraied, Brochard, Sylvain, Rousseau, François
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.08.2023; Elsevier
• Subjects: Computer Science; Computer Vision and Pattern Recognition; Deep registration; Label propagation; Musculoskeletal system; Semi-automatic segmentation; Semi-automatic segmentation; Musculoskeletal system; Deep registration; Label propagation; deep registration; label propagation; musculoskeletal system; few-shot segmentation; semi-automatic segmentation
• ISSN: 0031-3203; 1873-5142; 1873-5142
• DOI: 10.1016/j.patcog.2023.109529

•Registration-based label propagation is used for intra-subject muscle MR segmentation.•3D few-shot segmentation is reached by propagating 2D labels using deep registration.•Propagation is guided by image intensity, muscle shape and registration consistency.•Bidirectional propagation uses registration quality estimation as weighting guidance.•An unsupervised pre-training stage initializes the deep registration framework. Fully automated approaches based on convolutional neural networks have shown promising performances on muscle segmentation from magnetic resonance (MR) images, but still rely on an extensive amount of training data to achieve valuable results. Muscle segmentation for pediatric and rare diseases cohorts is therefore still often done manually. Producing dense delineations over 3D volumes remains a time-consuming and tedious task, with significant redundancy between successive slices. In this work, we propose a segmentation method relying on registration-based label propagation, which provides 3D muscle delineations from a limited number of annotated 2D slices. Based on an unsupervised deep registration scheme, our approach ensures the preservation of anatomical structures by penalizing deformation compositions that do not produce consistent segmentation from one annotated slice to another. Evaluation is performed on MR data from lower leg and shoulder joints. Results demonstrate that the proposed semi-automatic multi-label segmentation model outperforms state-of-the-art techniques.