Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology
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, ope...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2021.816281/full |
| _version_ | 1818957636002906112 |
|---|---|
| author | Henrik Sahlin Pettersen Henrik Sahlin Pettersen Henrik Sahlin Pettersen Ilya Belevich Elin Synnøve Røyset Elin Synnøve Røyset Elin Synnøve Røyset Erik Smistad Erik Smistad Melanie Rae Simpson Melanie Rae Simpson Eija Jokitalo Ingerid Reinertsen Ingerid Reinertsen Ingunn Bakke Ingunn Bakke André Pedersen André Pedersen André Pedersen |
| author_facet | Henrik Sahlin Pettersen Henrik Sahlin Pettersen Henrik Sahlin Pettersen Ilya Belevich Elin Synnøve Røyset Elin Synnøve Røyset Elin Synnøve Røyset Erik Smistad Erik Smistad Melanie Rae Simpson Melanie Rae Simpson Eija Jokitalo Ingerid Reinertsen Ingerid Reinertsen Ingunn Bakke Ingunn Bakke André Pedersen André Pedersen André Pedersen |
| author_sort | Henrik Sahlin Pettersen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-20T11:13:00Z |
| format | Article |
| id | doaj.art-6ad698dcbbef4ffb9a2381ce7a518097 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-20T11:13:00Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-6ad698dcbbef4ffb9a2381ce7a5180972022-12-21T19:42:42ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2022-01-01810.3389/fmed.2021.816281816281Code-Free Development and Deployment of Deep Segmentation Models for Digital PathologyHenrik Sahlin Pettersen0Henrik Sahlin Pettersen1Henrik Sahlin Pettersen2Ilya Belevich3Elin Synnøve Røyset4Elin Synnøve Røyset5Elin Synnøve Røyset6Erik Smistad7Erik Smistad8Melanie Rae Simpson9Melanie Rae Simpson10Eija Jokitalo11Ingerid Reinertsen12Ingerid Reinertsen13Ingunn Bakke14Ingunn Bakke15André Pedersen16André Pedersen17André Pedersen18Department of Pathology, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayClinic of Laboratory Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayElectron Microscopy Unit, Institute of Biotechnology, Helsinki Institute of Life Science, University of Helsinki, Helsinki, FinlandDepartment of Pathology, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayClinic of Laboratory Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayDepartment of Health Research, SINTEF Digital, Trondheim, NorwayDepartment of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Public Health and Nursing, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayThe Clinical Research Unit for Central Norway, Trondheim, NorwayElectron Microscopy Unit, Institute of Biotechnology, Helsinki Institute of Life Science, University of Helsinki, Helsinki, FinlandDepartment of Health Research, SINTEF Digital, Trondheim, NorwayDepartment of Circulation and Medical Imaging, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayClinic of Laboratory Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayDepartment of Clinical and Molecular Medicine, Faculty of Medicine and Health Sciences, NTNU - Norwegian University of Science and Technology, Trondheim, NorwayDepartment of Health Research, SINTEF Digital, Trondheim, NorwayThe Cancer Foundation, St. Olavs Hospital, Trondheim University Hospital, Trondheim, NorwayApplication 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.https://www.frontiersin.org/articles/10.3389/fmed.2021.816281/fullcomputational pathologydeep learningcode-freesemantic segmentationU-Netopen datasets |
| spellingShingle | Henrik Sahlin Pettersen Henrik Sahlin Pettersen Henrik Sahlin Pettersen Ilya Belevich Elin Synnøve Røyset Elin Synnøve Røyset Elin Synnøve Røyset Erik Smistad Erik Smistad Melanie Rae Simpson Melanie Rae Simpson Eija Jokitalo Ingerid Reinertsen Ingerid Reinertsen Ingunn Bakke Ingunn Bakke André Pedersen André Pedersen André Pedersen Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology Frontiers in Medicine computational pathology deep learning code-free semantic segmentation U-Net open datasets |
| title | Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology |
| title_full | Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology |
| title_fullStr | Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology |
| title_full_unstemmed | Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology |
| title_short | Code-Free Development and Deployment of Deep Segmentation Models for Digital Pathology |
| title_sort | code free development and deployment of deep segmentation models for digital pathology |
| topic | computational pathology deep learning code-free semantic segmentation U-Net open datasets |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2021.816281/full |
| work_keys_str_mv | AT henriksahlinpettersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT henriksahlinpettersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT henriksahlinpettersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT ilyabelevich codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT elinsynnøverøyset codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT elinsynnøverøyset codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT elinsynnøverøyset codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT eriksmistad codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT eriksmistad codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT melanieraesimpson codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT melanieraesimpson codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT eijajokitalo codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT ingeridreinertsen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT ingeridreinertsen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT ingunnbakke codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT ingunnbakke codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT andrepedersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT andrepedersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology AT andrepedersen codefreedevelopmentanddeploymentofdeepsegmentationmodelsfordigitalpathology |