American Association for Cancer Research
Browse
10780432ccr191495-sup-221905_2_supp_5798792_pz839j.xlsx (17.12 kB)

Supplementary Data from Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death

Download (17.12 kB)
dataset
posted on 2023-03-31, 21:23 authored by Prathamesh M. Kulkarni, Eric J. Robinson, Jaya Sarin Pradhan, Robyn D. Gartrell-Corrado, Bethany R. Rohr, Megan H. Trager, Larisa J. Geskin, Harriet M. Kluger, Pok Fai Wong, Balazs Acs, Emanuelle M. Rizk, Chen Yang, Manas Mondal, Michael R. Moore, Iman Osman, Robert Phelps, Basil A. Horst, Zhe S. Chen, Tammie Ferringer, David L. Rimm, Jing Wang, Yvonne M. Saenger
Supplementary Data from Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death

Funding

NIH

Melanoma Research Alliance

Columbia University's Irving Institute for Clinical and Translational Research

Swim Across America

Yale SPORE in Lung Cancer

Yale Cancer Center

NYU Melanoma SPORE

National Cancer Institute

Find out more...

History

ARTICLE ABSTRACT

Biomarkers for disease-specific survival (DSS) in early-stage melanoma are needed to select patients for adjuvant immunotherapy and accelerate clinical trial design. We present a pathology-based computational method using a deep neural network architecture for DSS prediction. The model was trained on 108 patients from four institutions and tested on 104 patients from Yale School of Medicine (YSM, New Haven, CT). A receiver operating characteristic (ROC) curve was generated on the basis of vote aggregation of individual image sequences, an optimized cutoff was selected, and the computational model was tested on a third independent population of 51 patients from Geisinger Health Systems (GHS). Area under the curve (AUC) in the YSM patients was 0.905 (P < 0.0001). AUC in the GHS patients was 0.880 (P < 0.0001). Using the cutoff selected in the YSM cohort, the computational model predicted DSS in the GHS cohort based on Kaplan–Meier (KM) analysis (P < 0.0001). The novel method presented is applicable to digital images, obviating the need for sample shipment and manipulation and representing a practical advance over current genetic and IHC-based methods.

Usage metrics

    Clinical Cancer Research

    Categories

    Keywords

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC