2021/11/01 by Andriy Myronenko, Myronenko, Andriy, Ziyue Xu +8 · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image Retrieval and Classification Techniques #Image and Video Processing (eess.IV) #Quantitative Methods (q-bio.QM) #cs.CV #eess.IV #electronic engineering #information engineering #q-bio.QM
paper · pdf · doi:10.48550/arxiv.2111.01556
MICCAI 2021
arxiv created 2021/11/01 · openalex publication_date 2021/11/01 · arxiv updated 2021/11/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational and annotation challenges. Typically, such images are divided into a set of patches (a bag of instances), where only bag-level class labels are provided. Deep learning based MIL methods calculate instance features using convolutional neural network (CNN). Our proposed approach is also deep learning based, with the following two contributions: Firstly, we propose to explicitly account for dependencies between instances during training by embedding self-attention Transformer blocks to capture dependencies between instances. For example, a tumor grade may depend on the presence of several particular patterns at different locations in WSI, which requires to account for dependencies between patches. Secondly, we propose an instance-wise loss function based on instance pseudo-labels. We compare the proposed algorithm to multiple baseline methods, evaluate it on the PANDA challenge dataset, the largest publicly available WSI dataset with over 11K images, and demonstrate state-of-the-art results.