Omni-Seg: A Single Dynamic Network for Multi-label Renal Pathology Image Segmentation using Partially Labeled Data
This work addresses the challenge of comprehensive tissue analysis in non-cancer renal pathology, offering a more efficient solution for medical image segmentation, though it is incremental in improving existing multi-label segmentation approaches.
The paper tackles multi-label segmentation of renal pathology images with partially labeled data, proposing Omni-Seg, a single dynamic network that achieves superior accuracy and reduces resource consumption compared to prior multi-network methods, as demonstrated on ~150,000 patch-wise images across six tissue types.
Computer-assisted quantitative analysis on Giga-pixel pathology images has provided a new avenue in histology examination. The innovations have been largely focused on cancer pathology (i.e., tumor segmentation and characterization). In non-cancer pathology, the learning algorithms can be asked to examine more comprehensive tissue types simultaneously, as a multi-label setting. The prior arts typically needed to train multiple segmentation networks in order to match the domain-specific knowledge for heterogeneous tissue types (e.g., glomerular tuft, glomerular unit, proximal tubular, distal tubular, peritubular capillaries, and arteries). In this paper, we propose a dynamic single segmentation network (Omni-Seg) that learns to segment multiple tissue types using partially labeled images (i.e., only one tissue type is labeled for each training image) for renal pathology. By learning from ~150,000 patch-wise pathological images from six tissue types, the proposed Omni-Seg network achieved superior segmentation accuracy and less resource consumption when compared to the previous the multiple-network and multi-head design. In the testing stage, the proposed method obtains "completely labeled" tissue segmentation results using only "partially labeled" training images. The source code is available at https://github.com/ddrrnn123/Omni-Seg