Spine-GFlow: A hybrid learning framework for robust multi-tissue segmentation in lumbar MRI without manual annotation. (July 2022)

• Record Type: Journal Article
• Authors: Kuang, Xihe; Cheung, Jason Pui Yin; Wong, Kwan-Yee K.; Lam, Wai Yi; Lam, Chak Hei; Choy, Richard W.; Cheng, Christopher P.; Wu, Honghan; Yang, Cao; Wang, Kun; Li, Yang; Zhang, Teng
• Is Part Of: Computerized medical imaging and graphics. Volume 99(2022)
• Publication Date: 2022-07
• Subjects: Multi-tissue segmentation -- Auto-annotation -- Weakly-supervised segmentation -- Spine; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102091
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract: Most learning-based magnetic resonance image (MRI) segmentation methods rely on the manual annotation to provide supervision, which is extremely tedious, especially when multiple anatomical structures are required. In this work, we aim to develop a hybrid framework named Spine-GFlow that combines the image features learned by a CNN model and anatomical priors for multi-tissue segmentation in a sagittal lumbar MRI. Our framework does not require any manual annotation and is robust against image feature variation caused by different image settings and/or underlying pathology. Our contributions include: 1) a rule-based method that automatically generates the weak annotation (initial seed area), 2) a novel proposal generation method that integrates the multi-scale image features and anatomical prior, 3) a comprehensive loss for CNN training that optimizes the pixel classification and feature distribution simultaneously. Our Spine-GFlow has been validated on 2 independent datasets: HKDDC (containing images obtained from 3 different machines) and IVDM3Seg. The segmentation results of vertebral bodies (VB), intervertebral discs (IVD), and spinal canal (SC) are evaluated quantitatively using intersection over union (IoU) and the Dice coefficient. Results show that our method, without requiring manual annotation, has achieved a segmentation performance comparable to a model trained with full supervision (mean Dice 0.914 vs 0.916). Highlights: Multi-tissue segmentation is provided. No manual annotation is required. The method is robust to unpredictable image feature variation. The method is generalizable for different imaging equipment.