Democratizing Pathological Image Segmentation with Lay Annotators via Molecular-empowered Learning.

Journal: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Published Date: Oct 1, 2023

Abstract

Multi-class cell segmentation in high-resolution Giga-pixel whole slide images (WSI) is critical for various clinical applications. Training such an AI model typically requires labor-intensive pixel-wise manual annotation from experienced domain experts (e.g., pathologists). Moreover, such annotation is error-prone when differentiating fine-grained cell types (e.g., podocyte and mesangial cells) via the naked human eye. In this study, we assess the feasibility of democratizing pathological AI deployment by only using lay annotators (annotators without medical domain knowledge). The contribution of this paper is threefold: (1) We proposed a molecular-empowered learning scheme for multi-class cell segmentation using partial labels from lay annotators; (2) The proposed method integrated Giga-pixel level molecular-morphology cross-modality registration, molecular-informed annotation, and molecular-oriented segmentation model, so as to achieve significantly superior performance via 3 lay annotators as compared with 2 experienced pathologists; (3) A deep corrective learning (learning with imperfect label) method is proposed to further improve the segmentation performance using partially annotated noisy data. From the experimental results, our learning method achieved F1 = 0.8496 using molecular-informed annotations from lay annotators, which is better than conventional morphology-based annotations (F1 = 0.7015) from experienced pathologists. Our method democratizes the development of a pathological segmentation deep model to the lay annotator level, which consequently scales up the learning process similar to a non-medical computer vision task. The official implementation and cell annotations are publicly available at https://github.com/hrlblab/MolecularEL.

Authors

  • Ruining Deng
    Vanderbilt University, Nashville TN 37215, USA.
  • Yanwei Li
    Vanderbilt University, Nashville TN 37215, USA.
  • Peize Li
    Vanderbilt University, Nashville TN 37215, USA.
  • Jiacheng Wang
    Vanderbilt University, Nashville TN 37215, USA.
  • Lucas W Remedios
    Vanderbilt University, Nashville TN 37215, USA.
  • Saydolimkhon Agzamkhodjaev
    Vanderbilt University, Nashville TN 37215, USA.
  • Zuhayr Asad
    Vanderbilt University, Nashville, TN 37212, USA.
  • Quan Liu
    Vanderbilt University, Nashville, TN 37212, USA.
  • Can Cui
    Vanderbilt University, Nashville TN 37215, USA.
  • Yaohong Wang
    Vanderbilt University Medical Center, Nashville TN 37232, USA.
  • Yihan Wang
    Vanderbilt University Medical Center, Nashville TN 37232, USA.
  • Yucheng Tang
    NVIDIA Corporation, Santa Clara and Bethesda, USA.
  • Haichun Yang
    Vanderbilt University Medical Center, Nashville TN 37232, USA.
  • Yuankai Huo
    Vanderbilt University, Nashville, TN 37212, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals