Generalising multistain immunohistochemistry tissue segmentation using end‐to‐end colour deconvolution deep neural networks. Issue 7 (25th April 2019)

• Record Type: Journal Article
• Authors: Lahiani, Amal; Gildenblat, Jacob; Klaman, Irina; Navab, Nassir; Klaiman, Eldad
• Is Part Of: IET image processing. Volume 13:Issue 7(2019)
• Page Start: 1066
• Page End: 1073
• Publication Date: 2019-04-25
• Subjects: image segmentation -- biomedical optical imaging -- cancer -- tumours -- medical image processing -- learning (artificial intelligence) -- convolutional neural nets -- drugs; annotation process -- deep learning method -- segment digitised slide images -- fully convolutional neural network -- colour deconvolution segment -- drug development -- image populations -- cancer immunotherapy biomarker research -- microscopic whole slide images -- tumour biopsies -- biomarkers -- colour deconvolution deep neural networks -- multistain immunohistochemistry tissue segmentation; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6513
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : A key challenge in cancer immunotherapy biomarker research is quantification of pattern changes in microscopic whole slide images of tumour biopsies. Drug development requires a correlative analysis of various biomarkers. To enable that, tissue slides are manually annotated by pathologists, which is a tedious and error‐prone task. Automation of this annotation process can improve accuracy and consistency while reducing workload and cost. The authors present a deep learning method to automatically segment digitised slide images with multiple stainings into compartments of tumour, healthy tissue, necrosis, and background. The method is based on using a fully convolutional neural network including a colour deconvolution segment learned end‐to‐end and helping the network to converge faster and deal with the dataset staining variability. They evaluate the performance of the proposed method using the F1 score, which is the harmonic mean between precision and recall. They report a testing F1 score of 0.88, 0.9, 0.8, and 0.99 for tumour, tissue, necrosis, and background, respectively. They address the task in the context of drug development where multiple stains exist and look into solutions for generalisations over these image populations. They also apply visualisation techniques to help understand the network decisions and gain more trust from pathologists.