Abstract
Image‐based biomarker discovery typically requires accurate segmentation of histologic structures (e.g. cell nuclei, tubules, and epithelial regions) in digital pathology whole slide images (WSIs). Unfortunately, annotating each structure of interest is laborious and often intractable even in moderately sized cohorts. Here, we present an open‐source tool, Quick Annotator (QA), designed to improve annotation efficiency of histologic structures by orders of magnitude. While the user annotates regions of interest (ROIs) via an intuitive web interface, a deep learning (DL) model is concurrently optimized using these annotations and applied to the ROI. The user iteratively reviews DL results to either (1) accept accurately annotated regions or (2) correct erroneously segmented structures to improve subsequent model suggestions, before transitioning to other ROIs. We demonstrate the effectiveness of QA over comparable manual efforts via three use cases. These include annotating (1) 337,386 nuclei in 5 pancreatic WSIs, (2) 5,692 tubules in 10 colorectal WSIs, and (3) 14,187 regions of epithelium in 10 breast WSIs. Efficiency gains in terms of annotations per second of 102×, 9×, and 39× were, respectively, witnessed while retaining f‐scores >0.95, suggesting that QA may be a valuable tool for efficiently fully annotating WSIs employed in downstream biomarker studies.
Highlights
The discovery of biomarkers associated with diagnosis, prognosis, and therapy response from digital pathology whole slide images (WSI) often requires extracting features from precise segmentations of the histologic structures contained within them[1,2,3,4]
In this work we demonstrate the utility of Quick Annotator (QA) for segmentation at three scale lengths typical in computational pathology (Table 1 and Figure S1)
Our results indicate (a) the speed efficiency improvement afforded by QA is significant, and (b) QA annotations remained highly concordant with those produced manually
Summary
The discovery of biomarkers associated with diagnosis, prognosis, and therapy response from digital pathology whole slide images (WSI) often requires extracting features from precise segmentations of the histologic structures contained within them (e.g., cell nuclei boundaries, tubule shapes, and regions of epithelium)[1,2,3,4]. This DL model makes predictions highlighting the structure, allowing the user to either accept or refine pixel-level boundaries in a rapid fashion This approach allows the DL model to provide feedback to the user, accentuating regions in the image which require additional user input to maximally improve the performance of the iteration of the supervised classifier. Through this iterative active learning based process, QA empowers the end user to spend more time efficiently verifying, as opposed to painstakingly annotating histologic structures. For the largest scale, 14,187 regions of epithelium, totaling an area of 35,844,637 pixels, were segmented in 10 WSI images
Sign-in/Register to view highlights & summary 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.
