A Deep Learning Model for Molecular Label Transfer that Enables Cancer Cell Identification from Histopathology Images

• Published in: bioRxiv
• Main Authors: Su, Andrew, Lee, Hojoon, Tan, Xiao, Suarez, Carlos J, Andor, Noemi, Nguyen, Quan, Ji, Hanlee P
• Format: Paper
• Language: English
• Published: Cold Spring Harbor Cold Spring Harbor Laboratory Press 19.03.2021; Cold Spring Harbor Laboratory
• Edition: 1.1
• Subjects: Bioinformatics; Cancer; Classification systems; Colorectal carcinoma; Computer applications; Deep learning; Histopathology; Immunohistochemistry; Neural networks; Tumors; deep learning; computer-assisted tools; molecular label; digital pathology; Colorectal cancer; histopathological images; cancer diagnosis; label transferring
• ISSN: 2692-8205; 2692-8205
• DOI: 10.1101/2021.03.18.436004

ABSTRACT Deep learning cancer classification systems have the potential to improve cancer diagnosis. However, development of these computational approaches depends on prior annotation through a pathologist. This initial step relying on a manual, low-resolution, time-consuming process is highly variable and subject to observer variance. To address this issue, we developed a novel method, H&E Molecular neural network (HEMnet). This two-step process utilises immunohistochemistry as an initial molecular label for cancer cells on a H&E image and then we train a cancer classifier on the overlapping clinical histopathological images. Using this molecular transfer method, we show that HEMnet accurately distinguishes colorectal cancer from normal tissue at high resolution without the need for an initial manual histopathologic evaluation. Our validation study using histopathology images from TCGA samples accurately estimates tumour purity. Overall, our method provides a path towards a fully automated delineation of any type of tumor so long as there is a cancer-oriented molecular stain available for subsequent learning. Software, tutorials and interactive tools are available at: https://github.com/BiomedicalMachineLearning/HEMnet Competing Interest Statement The authors have declared no competing interest. Footnotes * https://github.com/BiomedicalMachineLearning/HEMnet