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

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 1 on colonoscopy tissue segmentation and classification task. The full implementation details and the trained models are available at https://github.com/Raykoooo/CAC-UNet.

Colorectal Cancer Segmentation using Atrous Convolution and Residual Enhanced UNet

“…In [13], the authors have discussed the prediction of the clinical course of patients diagnosed with colorectal cancer, while in [3], the authors have discussed estimating the patient risk score using LSTMs. Also, some work has also been done for incorporating adversarial or GAN-based approaches as in the work of [25] wherein the authors have also used concepts of attention, pyramid pooling, and atrous convolutions in their work. Another work by [7] uses adversarial approach for domain adaptation to detect the tumor in an unsupervised manner.…”