PatchSorter: A High Throughput Deep Learning Digital Pathology Tool for Object Labeling

no code implementations • 13 Jul 2023 • Cedric Walker, Tasneem Talawalla, Robert Toth, Akhil Ambekar, Kien Rea, Oswin Chamian, Fan Fan, Sabina Berezowska, Sven Rottenberg, Anant Madabhushi, Marie Maillard, Laura Barisoni, Hugo Mark Horlings, Andrew Janowczyk

Using >100, 000 objects, we demonstrate a >7x improvement in labels per second over unaided labeling, with minimal impact on labeling accuracy, thus enabling high-throughput labeling of large datasets.

WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need

no code implementations • 13 Sep 2021 • Yoni Schirris, Mendel Engelaer, Andreas Panteli, Hugo Mark Horlings, Efstratios Gavves, Jonas Teuwen

We present WeakSTIL, an interpretable two-stage weak label deep learning pipeline for scoring the percentage of stromal tumor infiltrating lymphocytes (sTIL%) in H&E-stained whole-slide images (WSIs) of breast cancer tissue.

Decision Making Multiple Instance Learning +2

DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer

1 code implementation • 20 Jul 2021 • Yoni Schirris, Efstratios Gavves, Iris Nederlof, Hugo Mark Horlings, Jonas Teuwen

For MSI prediction in a tumor-annotated and color normalized subset of TCGA-CRC (n=360 patients), contrastive self-supervised learning improves the tile supervision baseline from 0. 77 to 0. 87 AUROC, on par with our proposed DeepSMILE method.

Classification Multiple Instance Learning +2