Unsupervised Brain Lesion Segmentation Using Posterior Distributions Learned by Subspace-based Generative Model

• Published in: IEEE transactions on medical imaging Vol. PP; p. 1
• Main Authors: Zhuang, Huixiang, Guan, Yue, Ding, Yi, Xu, Chang, Cheng, Zijun, Ma, Yuhao, Liu, Ruihao, Meng, Ziyu, Li, Cao, Li, Yao, Liang, Zhi-Pei
• Format: Journal Article
• Language: English
• Published: United States IEEE 08.08.2025
• Subjects: Accuracy; Bayes methods; Brain; Brain modeling; Generative adversarial networks; Image segmentation; intensity subspace; Lesions; Multiple sclerosis; posterior distributions; Random variables; structure subspace; subspace-based generative model; Training; unsupervised brain lesion segmentation

Unsupervised brain lesion segmentation, focusing on learning normative distributions from images of healthy subjects, are less dependent on lesion-labeled data, thus exhibiting better generalization capabilities. A fundamental challenge in learning normative distributions of images lies in the high...