Slideflow: deep learning for digital histopathology with real-time whole-slide visualization
Abstract Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with diffe...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-024-05758-x |
| _version_ | 1827300856436883456 |
|---|---|
| author | James M. Dolezal Sara Kochanny Emma Dyer Siddhi Ramesh Andrew Srisuwananukorn Matteo Sacco Frederick M. Howard Anran Li Prajval Mohan Alexander T. Pearson |
| author_facet | James M. Dolezal Sara Kochanny Emma Dyer Siddhi Ramesh Andrew Srisuwananukorn Matteo Sacco Frederick M. Howard Anran Li Prajval Mohan Alexander T. Pearson |
| author_sort | James M. Dolezal |
| collection | DOAJ |
| description | Abstract Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi. |
| first_indexed | 2024-04-24T16:12:08Z |
| format | Article |
| id | doaj.art-6bb82f18fca04a3bb0dda2cd9c996a9f |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-24T16:12:08Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-6bb82f18fca04a3bb0dda2cd9c996a9f2024-03-31T11:37:09ZengBMCBMC Bioinformatics1471-21052024-03-0125112910.1186/s12859-024-05758-xSlideflow: deep learning for digital histopathology with real-time whole-slide visualizationJames M. Dolezal0Sara Kochanny1Emma Dyer2Siddhi Ramesh3Andrew Srisuwananukorn4Matteo Sacco5Frederick M. Howard6Anran Li7Prajval Mohan8Alexander T. Pearson9Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterDivision of Hematology, Department of Internal Medicine, The Ohio State University Comprehensive Cancer CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterDepartment of Computer Science, University of ChicagoSection of Hematology/Oncology, Department of Medicine, University of Chicago Medical CenterAbstract Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi.https://doi.org/10.1186/s12859-024-05758-xDigital pathologyComputational pathologySoftware toolkitWhole-slide imagingExplainable AISelf-supervised learning |
| spellingShingle | James M. Dolezal Sara Kochanny Emma Dyer Siddhi Ramesh Andrew Srisuwananukorn Matteo Sacco Frederick M. Howard Anran Li Prajval Mohan Alexander T. Pearson Slideflow: deep learning for digital histopathology with real-time whole-slide visualization BMC Bioinformatics Digital pathology Computational pathology Software toolkit Whole-slide imaging Explainable AI Self-supervised learning |
| title | Slideflow: deep learning for digital histopathology with real-time whole-slide visualization |
| title_full | Slideflow: deep learning for digital histopathology with real-time whole-slide visualization |
| title_fullStr | Slideflow: deep learning for digital histopathology with real-time whole-slide visualization |
| title_full_unstemmed | Slideflow: deep learning for digital histopathology with real-time whole-slide visualization |
| title_short | Slideflow: deep learning for digital histopathology with real-time whole-slide visualization |
| title_sort | slideflow deep learning for digital histopathology with real time whole slide visualization |
| topic | Digital pathology Computational pathology Software toolkit Whole-slide imaging Explainable AI Self-supervised learning |
| url | https://doi.org/10.1186/s12859-024-05758-x |
| work_keys_str_mv | AT jamesmdolezal slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT sarakochanny slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT emmadyer slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT siddhiramesh slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT andrewsrisuwananukorn slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT matteosacco slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT frederickmhoward slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT anranli slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT prajvalmohan slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization AT alexandertpearson slideflowdeeplearningfordigitalhistopathologywithrealtimewholeslidevisualization |