Abstract
Current histopathological diagnosis involves human expert interpretation of stained images for diagnosis. This process is prone to inter-observer variability, often leading to low concordance rates amongst pathologists across many types of tissues. Further, since structural features are mostly just defined for epithelial alterations during tumor progression, the use of associated stromal changes is limited. Here we sought to examine whether digital analysis of commonly used hematoxylin and eosin-stained images could provide precise and quantitative metrics of disease from both epithelial and stromal cells. We developed a convolutional neural network approach to identify epithelial breast cells from their microenvironment. Second, we analyzed the microenvironment to further observe different constituent cells using unsupervised clustering. Finally, we categorized breast cancer by the combined effects of stromal and epithelial inertia. Together, the work provides insight and evidence of cancer association for interpretable features from deep learning methods that provide new opportunities for comprehensive analysis of standard pathology images.
Highlights
The current clinical pipeline for cancer diagnosis involves human expert evaluation of large sections of tissue stained with dyes or a variety of specialized molecular markers (Kiernan, 1999)
We tested our methods on tissue microarrays (TMA), which provide the opportunity for a large number of highly diverse samples but recognize that the potential to examine many components of the tumor and microenvironment in each sample may be limited
This paper presents a deep learning scheme for digital tissue segmentation using stained images which can further be used to extract sophisticated spatial features for cancer diagnosis in an automated, fast and accurate manner
Summary
The current clinical pipeline for cancer diagnosis involves human expert evaluation of large sections of tissue stained with dyes or a variety of specialized molecular markers (Kiernan, 1999). Increasing cancer incidence rates put an increased burden on pathologists worldwide (Williams et al, 2017), as limited resources and limited growth of trained medical personnel (Robboy et al, 2015) are subjected to greater strains. With the advent of whole slide imaging (Pantanowitz et al, 2011; Ghaznavi et al, 2013), digitized versions of stained slides are available and advanced computational analysis can be readily applied (Gurcan et al, 2009).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
