Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet

TL;DR

This paper introduces a novel adversarial CAC-UNet model for multi-level detection of malignant tissues in colonoscopy images, improving segmentation accuracy and reducing false positives in early cancer diagnosis.

Contribution

The paper presents a new adversarial CAC-UNet architecture with a pre-prediction strategy and a malignancy-guided label smoothing for robust tissue segmentation.

Findings

Achieved top performance in MICCAI DigestPath2019 challenge

Reduced false positives in malignant tissue detection

Enhanced segmentation robustness with adversarial training

Abstract

The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate. In this paper, we propose a highly efficient multi-level malignant tissue detection through the designed adversarial CAC-UNet. A patch-level model with a pre-prediction strategy and a malignancy area guided label smoothing is adopted to remove the negative WSIs, with which to lower the risk of false positive detection. For the selected key patches by multi-model ensemble, an adversarial context-aware and appearance consistency UNet (CAC-UNet) is designed to achieve robust segmentation. In CAC-UNet, mirror designed discriminators are able to seamlessly fuse the whole feature maps of the skillfully designed powerful backbone network without any information loss. Besides, a mask prior is further added to guide the accurate segmentation mask prediction through an extra mask-domain discriminator. The proposed scheme achieves the best results in MICCAI DigestPath2019 challenge on colonoscopy tissue segmentation and classification task. The full implementation details and the trained models are available at https://github.com/Raykoooo/CAC-UNet.