Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images

Mahmudul Hasan, Xiaoling Hu, Shahira Abousamra, Prateek Prasanna, Joel Saltz +1 more
10/2/2024
eess.IVcs.CV

Official code: Shauqi/SS-cVAE (5 stars, MIT, last commit 2024-07-08).

Abstract

Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE.

View on arXivView PDF

Code Implementations(1)

Shauqi/SS-cVAEOfficial100%
MIT

Code Repository for Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images

50Shell, PythonJul 3, 20242 years agoMIT

Similar Papers

ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalization

84% match1 repo22024

Continual Learning for Tumor Classification in Histopathology Images

82% match2022

Enhancing Deep Learning Model Explainability in Brain Tumor Datasets using Post-Heuristic Approaches

82% match2024

Disentangled PET Lesion Segmentation

82% match1 repo12024

Image Data collection and implementation of deep learning-based model in detecting Monkeypox disease using modified VGG16

82% match1 repo212022

Efficient Brain Tumor Classification with Lightweight CNN Architecture: A Novel Approach

82% match2025

Cite this paper

@article{hasan2024semisupervised,
  title  = {Semi-Supervised Contrastive VAE for Disentanglement of Digital Pathology Images},
  author = {Mahmudul Hasan and Xiaoling Hu and Shahira Abousamra and Prateek Prasanna and Joel Saltz and Chao Chen},
  year   = {2024},
  eprint = {2410.02012},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.02012v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.02012.svg)](https://codeofpaper.com/paper/2410.02012)

Discussion