TY - GEN
T1 - Representation learning of histopathology images using graph neural networks
AU - Adnan, Mohammed
AU - Kalra, Shivam
AU - Tizhoosh, Hamid R.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - Representation learning for Whole Slide Images (WSIs) is pivotal in developing image-based systems to achieve higher precision in diagnostic pathology. We propose a two-stage framework for WSI representation learning. We sample relevant patches using a color-based method and use graph neural networks to learn relations among sampled patches to aggregate the image information into a single vector representation. We introduce attention via graph pooling to automatically infer patches with higher relevance. We demonstrate the performance of our approach for discriminating two sub-types of lung cancers, Lung Adenocarcinoma (LUAD) & Lung Squamous Cell Carcinoma (LUSC). We collected 1, 026 lung cancer WSIs with the 40× magnification from The Cancer Genome Atlas (TCGA) dataset, the largest public repository of histopathology images and achieved state-of-the-art accuracy of 88.8% and AUC of 0.89 on lung cancer sub-type classification by extracting features from a pre-trained DenseNet model.
AB - Representation learning for Whole Slide Images (WSIs) is pivotal in developing image-based systems to achieve higher precision in diagnostic pathology. We propose a two-stage framework for WSI representation learning. We sample relevant patches using a color-based method and use graph neural networks to learn relations among sampled patches to aggregate the image information into a single vector representation. We introduce attention via graph pooling to automatically infer patches with higher relevance. We demonstrate the performance of our approach for discriminating two sub-types of lung cancers, Lung Adenocarcinoma (LUAD) & Lung Squamous Cell Carcinoma (LUSC). We collected 1, 026 lung cancer WSIs with the 40× magnification from The Cancer Genome Atlas (TCGA) dataset, the largest public repository of histopathology images and achieved state-of-the-art accuracy of 88.8% and AUC of 0.89 on lung cancer sub-type classification by extracting features from a pre-trained DenseNet model.
UR - http://www.scopus.com/inward/record.url?scp=85090164869&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090164869&partnerID=8YFLogxK
U2 - 10.1109/CVPRW50498.2020.00502
DO - 10.1109/CVPRW50498.2020.00502
M3 - Conference contribution
AN - SCOPUS:85090164869
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 4254
EP - 4261
BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PB - IEEE Computer Society
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Y2 - 14 June 2020 through 19 June 2020
ER -