CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
This work addresses the challenge of analyzing histopathology images for cancer classification, which is incremental as it builds on existing multi-resolution and self-supervised learning approaches.
The paper tackled the problem of extracting rich phenotype information from whole slide histology images by jointly leveraging complementary information from multiple resolutions, and presented CD-Net, a novel transformer-based Pyramidal Context-Detail Network that achieved classification of Lung Adenocarcinoma from Squamous cell carcinoma.
Extracting rich phenotype information, such as cell density and arrangement, from whole slide histology images (WSIs), requires analysis of large field of view, i.e more contexual information. This can be achieved through analyzing the digital slides at lower resolution. A potential drawback is missing out on details present at a higher resolution. To jointly leverage complementary information from multiple resolutions, we present a novel transformer based Pyramidal Context-Detail Network (CD-Net). CD-Net exploits the WSI pyramidal structure through co-training of proposed Context and Detail Modules, which operate on inputs from multiple resolutions. The residual connections between the modules enable the joint training paradigm while learning self-supervised representation for WSIs. The efficacy of CD-Net is demonstrated in classifying Lung Adenocarcinoma from Squamous cell carcinoma.