2022/10/31 by Imaad Zaffar, Zaffar, Imaad, Guillaume Jaume +5 · 3 citations
Computer Science · #AI in cancer detection #Advanced Vision and Imaging #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #Embedding #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #I.4.0 #I.5.4 #Image (mathematics) #Machine learning #Pattern recognition (psychology) #Space (punctuation) #cs.AI #cs.CV
paper · pdf · doi:10.48550/arxiv.2210.17013
published in arXiv (Cornell University) (Cornell University) · 5 pages, 3 figures, 1 table, ISBI 2023
arxiv created 2022/10/31 · openalex publication_date 2022/10/31 · arxiv updated 2022/11/01 · openalex created_date 2022/11/06 · openalex updated_date 2026/07/28
Multiple Instance Learning (MIL) is a widely employed framework for learning on gigapixel whole-slide images (WSIs) from WSI-level annotations. In most MIL based analytical pipelines for WSI-level analysis, the WSIs are often divided into patches and deep features for patches (i.e., patch embeddings) are extracted prior to training to reduce the overall computational cost and cope with the GPUs' limited RAM. To overcome this limitation, we present EmbAugmenter, a data augmentation generative adversarial network (DA-GAN) that can synthesize data augmentations in the embedding space rather than in the pixel space, thereby significantly reducing the computational requirements. Experiments on the SICAPv2 dataset show that our approach outperforms MIL without augmentation and is on par with traditional patch-level augmentation for MIL training while being substantially faster.