SCL-WC: Cross-Slide Contrastive Learning for Weakly-Supervised Whole-Slide Image Classification

Authors: Xiyue Wang, Jinxi Xiang, Jun Zhang, Sen Yang, Zhongyi Yang, Ming-Hui Wang, Jing Zhang, Wei Yang, Junzhou Huang, Xiao Han

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate state-of-the-art performance of our method in three different classification tasks (e.g., over 2% of AUC in Camelyon16, 5% of F1 score in BRACS, and 3% of AUC in Diag Set). Our method also shows superior flexibility and scalability in weakly-supervised localization and semi-supervised classification experiments (e.g., first place in the BRIGHT challenge).
Researcher Affiliation Collaboration 1College of Biomedical Engineering, Sichuan University, Chengdu, China 610065 2College of Computer Science, Sichuan University, Chengdu, China 610065 3Tencent AI Lab, Shenzhen, China 518057
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code will be available at https://github.com/Xiyue-Wang/SCL-WC.
Open Datasets Yes In this section, we construct a series of experiments on five public histopathological image datasets. The five datasets are collected from three different organs, including prostate (PANDA [27] and Diag Set [28]), breast (Camelyon16 [29] and BRACS [30]), and colorectum (TCGA-CRC-DX), which are detailed in Table 1.
Dataset Splits Yes PANDA is the largest publicly available WSI data for 2-class prostate cancer classification, which releases a total of 10,616 WSIs (7724 Can. and 2892 Non.). We split them into training, validation, and test sets with a ratio of 7:1:2.
Hardware Specification No The paper states: "Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] See supplementary materials." However, the provided text does not contain the supplementary materials with these details.
Software Dependencies No The paper does not provide specific software dependencies with version numbers in the provided text. It mentions "The experimental setups can be seen in the supplementary material" which may contain this information, but it's not included here.
Experiment Setup No The paper states: "Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Section 4 and supplementary materials." And, "The experimental setups can be seen in the supplementary material." However, the provided text does not contain these specific details.