CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Code

• github.com/ThoroughImages/CAMEL
  OfficialIn papernone★ 0
• github.com/tuhinmallick/Seminar-
  none★ 3
• github.com/tuhinmallick/Weakly-Supervised-Learning-for-Digital-Pathology
  none★ 3

Abstract

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixel-level labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.

Tasks

Reproductions