Edge-competing Pathological Liver Vessel Segmentation with Limited Labels

Authors: Zunlei Feng, Zhonghua Wang, Xinchao Wang, Xiuming Zhang, Lechao Cheng, Jie Lei, Yuexuan Wang, Mingli Song1325-1333

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Exhaustive experiments demonstrate that, with only limited labeled patches, EVS-Net achieves a close performance of fully supervised methods, which provides a convenient tool for the pathological liver vessel segmentation.
Researcher Affiliation Collaboration Zunlei Feng1,5#, Zhonghua Wang1#, Xinchao Wang2, Xiuming Zhang1, Lechao Cheng3, Jie Lei4, Yuexuan Wang1 , Mingli Song1,5 1Zhejiang University 2Stevens Institute of Technology 3Zhejiang Lab 4Zhejiang University of Technology 5Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies
Pseudocode Yes Algorithm 1 The Training Algorithm for EVS-Net
Open Source Code Yes Code is publicly available at https://github.com/zju-vipa/EVS-Net.
Open Datasets Yes In this paper, we first collect a pathological liver image dataset containing 522 whole slide images with labels of vessels, MVI, and hepatocellular carcinoma grades. It can readily serve as a benchmark for the research on the analysis of pathological liver images.
Dataset Splits Yes The train, validation, and test sample number are 144, 000, 18, 000, and 18, 000, respectively.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions 'Deeplab V3+' as the segmentation network but does not provide specific version numbers for software dependencies or programming languages used.
Experiment Setup Yes In the experiment, the parameters are set as follows: ζ = 1, τ = 1, η = 2, λ = 10, ncritic = 5, the batch size T = 64, Adam hyperparameters for two discriminators α = 0.0001, β1 = 0, β2 = 0.9. The radius r1 and r2 are random values between 5 and 30. The radius r3 equals to 15. The learning rate for the segmentation network and two discriminators are all set to be 1e 4.