Learning to segment anatomy and lesions from disparately labeled sources in brain MRI
This addresses the problem of accurate brain MRI segmentation for medical imaging applications, but it is incremental as it builds on prior work with specific enhancements.
The paper tackles the challenge of segmenting both healthy tissues and lesions in brain MRI without requiring jointly labeled training datasets, by proposing a method that decouples segmentation paths and uses meta-learning and co-training, resulting in improved performance on a glioblastoma dataset compared to state-of-the-art methods.
Segmenting healthy tissue structures alongside lesions in brain Magnetic Resonance Images (MRI) remains a challenge for today's algorithms due to lesion-caused disruption of the anatomy and lack of jointly labeled training datasets, where both healthy tissues and lesions are labeled on the same images. In this paper, we propose a method that is robust to lesion-caused disruptions and can be trained from disparately labeled training sets, i.e., without requiring jointly labeled samples, to automatically segment both. In contrast to prior work, we decouple healthy tissue and lesion segmentation in two paths to leverage multi-sequence acquisitions and merge information with an attention mechanism. During inference, an image-specific adaptation reduces adverse influences of lesion regions on healthy tissue predictions. During training, the adaptation is taken into account through meta-learning and co-training is used to learn from disparately labeled training images. Our model shows an improved performance on several anatomical structures and lesions on a publicly available brain glioblastoma dataset compared to the state-of-the-art segmentation methods.