3D Segmentation of Subcortical Brain Structure with Few Labeled Data using 2D Diffusion Models
Ji‐Hoon Cho, Hyungjoon Bae, Xiaofeng Liu, Fangxu Xing, Kyung‐Eun Lee, Georges El Fakhri, Van Jay Wedeen, Jinah Park, Jonghye Woo · Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition · 2024
Motivation: Deep learning-based segmentation methods have shown promising results; however, they require a large number of segmentation labels for training, which is very costly to obtain, especially for 3D labels. Goal(s): Our goal is to achieve promising 3D segmentation results with few labels by exploiting the ability to capture semantic information from 2D diffusion models trained without labels. Approach: We train simple pixel classifiers using features extracted from 2D diffusion models that have been trained with slices from three orthogonal orientations. Results: In our experiments on the Human Connectome Project database, our proposed method outperformed conventional segmentation methods in a few labeled scenarios. Impact: Our proposed method for segmenting subcortical brain structures can be readily applied to pre-trained diffusion models with only a few labeled data, while also generating paired segmentation labels for the images produced by diffusion models.