Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H E-stained slides

by   Miriam Hägele, et al.

In this paper, we present a deep learning segmentation approach to classify and quantify the two most prevalent primary liver cancers - hepatocellular carcinoma and intrahepatic cholangiocarcinoma - from hematoxylin and eosin (H E) stained whole slide images. While semantic segmentation of medical images typically requires costly pixel-level annotations by domain experts, there often exists additional information which is routinely obtained in clinical diagnostics but rarely utilized for model training. We propose to leverage such weak information from patient diagnoses by deriving complementary labels that indicate to which class a sample cannot belong to. To integrate these labels, we formulate a complementary loss for segmentation. Motivated by the medical application, we demonstrate for general segmentation tasks that including additional patches with solely weak complementary labels during model training can significantly improve the predictive performance and robustness of a model. On the task of diagnostic differentiation between hepatocellular carcinoma and intrahepatic cholangiocarcinoma, we achieve a balanced accuracy of 0.91 (CI 95 show that leveraging complementary labels improves the robustness of segmentation and increases performance at case level.


page 3

page 5

page 6

page 7

page 9


Learning Semantic Segmentation with Diverse Supervision

Models based on deep convolutional neural networks (CNN) have significan...

Weak-shot Semantic Segmentation via Dual Similarity Transfer

Semantic segmentation is an important and prevalent task, but severely s...

On Boosting Semantic Street Scene Segmentation with Weak Supervision

Training convolutional networks for semantic segmentation requires per-p...

Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation

With the increase in the number of image data and the lack of correspond...

Boosting segmentation with weak supervision from image-to-image translation

In many cases, especially with medical images, it is prohibitively chall...

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

Domain adaptive semantic segmentation aims to learn a model with the sup...

Please sign up or login with your details

Forgot password? Click here to reset