Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning

EBioMedicine, vol. 107, pp. 105276

Abstract

BACKGROUND: Deployment and access to state-of-the-art precision medicine technologies remains a fundamental challenge in providing equitable global cancer care in low-resource settings. The expansion of digital pathology in recent years and its potential interface with diagnostic artificial intelligence algorithms provides an opportunity to democratize access to personalized medicine. Current digital pathology workstations, however, cost thousands to hundreds of thousands of dollars. As cancer incidence rises in many low- and middle-income countries, the validation and implementation of low-cost automated diagnostic tools will be crucial to helping healthcare providers manage the growing burden of cancer. METHODS: Here we describe a low-cost ($230) workstation for digital slide capture and computational analysis composed of open-source components. We analyze the predictive performance of deep learning models when they are used to evaluate pathology images captured using this open-source workstation versus images captured using common, significantly more expensive hardware. Validation studies assessed model performance on three distinct datasets and predictive models: head and neck squamous cell carcinoma (HPV positive versus HPV negative), lung cancer (adenocarcinoma versus squamous cell carcinoma), and breast cancer (invasive ductal carcinoma versus invasive lobular carcinoma). FINDINGS: When compared to traditional pathology image capture methods, low-cost digital slide capture and analysis with the open-source workstation, including the low-cost microscope device, was associated with model performance of comparable accuracy for breast, lung, and HNSCC classification. At the patient level of analysis, AUROC was 0.84 for HNSCC HPV status prediction, 1.0 for lung cancer subtype prediction, and 0.80 for breast cancer classification. INTERPRETATION: Our ability to maintain model performance despite decreased image quality and low-power computational hardware demonstrates that it is feasible to massively reduce costs associated with deploying deep learning models for digital pathology applications. Improving access to cutting-edge diagnostic tools may provide an avenue for reducing disparities in cancer care between high- and low-income regions. FUNDING: Funding for this project including personnel support was provided via grants from NIH/NCIR25-CA240134, NIH/NCIU01-CA243075, NIH/NIDCRR56-DE030958, NIH/NCIR01-CA276652, NIH/NCIK08-CA283261, NIH/NCI-SOAR25CA240134, SU2C (Stand Up to Cancer) Fanconi Anemia Research Fund - Farrah Fawcett Foundation Head and Neck Cancer Research Team Grant, and the European UnionHorizon Program (I3LUNG).

Authors 12

1. Divya Choudhury

   University of Chicago

   Affiliation as printed

   Pritzker School of Medicine, University of Chicago, Chicago, IL, USA

2. James M. Dolezal

   Geisinger Medical Center

   Affiliation as printed

   Geisinger Cancer Institute, Danville, PA, USA

3. Emma Dyer

   University of Chicago Medical Center

   Affiliation as printed

   Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA

4. Sara E. Kochanny

   University of Chicago Medical Center

   Affiliation as printed

   Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA

5. Siddhi Ramesh

   University of Chicago

   Affiliation as printed

   Pritzker School of Medicine, University of Chicago, Chicago, IL, USA

6. Frederick Matthew Howard

   University of Chicago Medical Center

   Affiliation as printed

   Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA

7. Jayson R. Margalus

   DePaul University

   Affiliation as printed

   DePaul University, Idea Realization Lab, Chicago, IL, USA

8. Amelia R. Schroeder

   DePaul University

   Affiliation as printed

   DePaul University, Idea Realization Lab, Chicago, IL, USA

9. Jefree J. Schulte

   University of Wisconsin–Madison

   Affiliation as printed

   Department of Pathology and Laboratory Medicine, University of Wisconsin School of Medicine and Public Health, USA

10. Marina Chiara Garassino

    University of Chicago Medical Center

    Affiliation as printed

    Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA

11. Jakob Nikolas Kather Aachen Department of Medicine III

    German Cancer Research Center · Universitätsklinikum Aachen · Deutsches Konsortium für Translationale Krebsforschung · RWTH Aachen University

    Affiliation as printed

    Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany; German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany; Applied Tumor Immunity, German Cancer Research Center (DKFZ), Heidelberg, Germany

12. Alexander T. Pearson corresponding

    University of Chicago · University of Chicago Medical Center

    Affiliation as printed

    Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, USA. Electronic address: apearson5@uchicago.edu