Abstract
Application of deep learning on histopathological whole slide images (WSIs) holds promise of improving diagnostic efficiency and reproducibility but is largely dependent on the ability to write computer code or purchase commercial solutions. We present a code-free pipeline utilizing free-to-use, open-source software (QuPath, DeepMIB, and FastPathology) for creating and deploying deep learning-based segmentation models for computational pathology. We demonstrate the pipeline on a use case of separating epithelium from stroma in colonic mucosa. A dataset of 251 annotated WSIs, comprising 140 hematoxylin-eosin (HE)-stained and 111 CD3 immunostained colon biopsy WSIs, were developed through active learning using the pipeline. On a hold-out test set of 36 HE and 21 CD3-stained WSIs a mean intersection over union score of 95.5 and 95.3% was achieved on epithelium segmentation. We demonstrate pathologist-level segmentation accuracy and clinical acceptable runtime performance and show that pathologists without programming experience can create near state-of-the-art segmentation solutions for histopathological WSIs using only free-to-use software. The study further demonstrates the strength of open-source solutions in its ability to create generalizable, open pipelines, of which trained models and predictions can seamlessly be exported in open formats and thereby used in external solutions. All scripts, trained models, a video tutorial, and the full dataset of 251 WSIs with ~31 k epithelium annotations are made openly available at https://github.com/andreped/NoCodeSeg to accelerate research in the field.
Highlights
Visual evaluation of histopathological whole slide images (WSIs) is the gold standard for diagnosing an array of medical conditions ranging from cancer subtyping and staging to inflammatory and infectious diseases
Subsequent training cycles were performed with U-Net 512 × 512 in a repetitive fashion described in Figure 1 (DeepMIB training, inference of new WSIs and import into QuPath for correction of annotations, export for new DeepMIB training, etc.) to achieve a final dataset of 111 WSIs
This allowed sorting of the patches which was in most disagreement with the U-Net predictions
Summary
Visual evaluation of histopathological whole slide images (WSIs) is the gold standard for diagnosing an array of medical conditions ranging from cancer subtyping and staging to inflammatory and infectious diseases. Application of deep learning-based methods to histopathological WSIs holds promise of improving diagnostic efficiency and reproducibility, but is largely dependent on the ability to write computer code or buy commercial solutions. Existing commercial solutions include software such as Visiopharm, Halo AI, and Aiforia, and, open-source alternatives such as MONAI-Label, H-AI-L, QuickAnnotator [9,10,11,12], and ZeroCostDL4Mic [12] These open-source solutions, either lack a full annotation, training and visualization pipeline, require some degree of programming experience, or use commercial servers. This calls for the development and use of open-source solutions that enable transparency of the image analysis pipelines, the possibility of exporting and importing results and data between applications and use of local data without the requirement of uploading restricted images to commercial serves
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.
