Omni-Seg: A Single Dynamic Network for Multi-label Renal Pathology Image Segmentation using Partially Labeled Data

Ruining Deng, Quan Liu, Can Cui, Zuhayr Asad, Haichun Yang, Yuankai Huo

Keywords: Renal pathology, Image segmentation, Multi-label, Self-supervised Learning

TL;DR: In this paper, we propose a dynamic single segmentation network (OmniSeg) that learns to segment multiple tissue types at their optimal pyramid scales using partially labeled images.

Abstract: 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.

Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: methodological development

Primary Subject Area: Segmentation

Secondary Subject Area: Application: Histopathology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.

Code And Data:

The source code is available at https://github.com/ddrrnn123/Omni-Seg.
The data is available at http://haeckel.case.edu/data/KI_data/

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2112.12665/code)