CoChat

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

Open access
Kulkarni, Prathamesh M., Robinson, Eric J., Sarin Pradhan, Jaya, Gartrell-Corrado, Robyn D., Rohr, Bethany R., Trager, Megan H., Geskin, Larisa J., Kluger, Harriet M., Wong, Pok Fai, Acs, Balazs, Rizk, Emanuelle M., Yang, Chen, Mondal, Manas, Moore, Michael R., Osman, Iman, Phelps, Robert, Horst, Basil A., Chen, Zhe S., Ferringer, Tammie, Rimm, David L., Wang, Jing, Saenger, Yvonne M. · 2020 · Clinical Cancer Research

Published version of a preprint

Cited by 124

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Abstract

Purpose: 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. Experimental Design: 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). Results: 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). Conclusions: 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1158/1078-0432.ccr-19-1495

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 29

  1. Palmieri, 2018, Immune checkpoint inhibitor toxicity, Curr Oncol Rep, 20, 72, 10.1007/s11912-018-0718-6 · DOI
  2. Gordan, 2019, Cost differential of immuno-oncology therapy delivered at community versus hospital clinics, Am J Manag Care, 25, e66
  3. Trinidad, 2019, Update on eighth edition American Joint Committee on Cancer classification for cutaneous melanoma and overview of potential pitfalls in histological examination of staging parameters, J Clin Pathol, 72, 265, 10.1136/jclinpath-2018-205417 · DOI
  4. Taylor, 2018, Influence of variability in assessment of Breslow thickness, mitotic rate and ulceration among US pathologists interpreting invasive melanoma, for the purpose of AJCC staging, J Cutan Pathol, 45, 588, 10.1111/cup.13265 · DOI
  5. Falk Delgado, 2019, Sentinel lymph node biopsy and complete lymph node dissection for melanoma, Curr Oncol Rep, 21, 54, 10.1007/s11912-019-0798-y · DOI
  6. Ferris, 2018, Real-world performance and utility of a noninvasive gene expression assay to evaluate melanoma risk in pigmented lesions, Melanoma Res, 28, 478, 10.1097/CMR.0000000000000478 · doi:10.1097/cmr.0000000000000478
  7. Gerami, 2015, Gene expression profiling for molecular staging of cutaneous melanoma in patients undergoing sentinel lymph node biopsy, J Am Acad Dermatol, 72, 780, 10.1016/j.jaad.2015.01.009 · DOI · Paper page
  8. Gartrell, 2019, Validation of melanoma immune profile (MIP), a prognostic immune gene prediction score for stage II-III melanoma, Clin Cancer Res, 25, 2494, 10.1158/1078-0432.CCR-18-2847 · DOI
  9. Sivendran, 2014, Dissection of immune gene networks in primary melanoma tumors critical for antitumor surveillance of patients with stage II-III resectable disease, J Invest Dermatol, 134, 2202, 10.1038/jid.2014.85 · DOI
  10. Gartrell, 2018, Quantitative analysis of immune infiltrates in primary melanoma, Cancer Immunol Res, 6, 481, 10.1158/2326-6066.CIR-17-0360 · DOI · Paper page
  11. Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 · DOI · Paper page
  12. Shen, 2017, Deep learning in medical image analysis, Annu Rev Biomed Eng, 19, 221, 10.1146/annurev-bioeng-071516-044442 · DOI · Paper page
  13. Lo, 1995, Artificial convolution neural network techniques and applications for lung nodule detection, IEEE Trans Med Imaging, 14, 711, 10.1109/42.476112 · DOI · Paper page
  14. Linder, 2019, Deep learning for detecting tumour-infiltrating lymphocytes in testicular germ cell tumours, J Clin Pathol, 72, 157, 10.1136/jclinpath-2018-205328 · DOI
  15. Saltz, 2018, Spatial organization and molecular correlation of tumor-infiltrating lymphocytes using deep learning on pathology images, Cell Rep, 23, 181, 10.1016/j.celrep.2018.03.086 · DOI · Paper page
  16. Xia, 2018, Computationally-guided development of a stromal inflammation histologic biomarker in lung squamous cell carcinoma, Sci Rep, 8, 3941, 10.1038/s41598-018-22254-4 · DOI
  17. Ehteshami Bejnordi, 2018, Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies, Mod Pathol, 31, 1502, 10.1038/s41379-018-0073-z · DOI · Paper page
  18. Arvaniti, 2018, Automated Gleason grading of prostate cancer tissue microarrays via deep learning, Sci Rep, 8, 12054, 10.1038/s41598-018-30535-1 · DOI · Paper page
  19. Casanova, 2017, Morphoproteomic characterization of lung squamous cell carcinoma fragmentation, a histological marker of increased tumor invasiveness, Cancer Res, 77, 2585, 10.1158/0008-5472.CAN-16-2363 · DOI
  20. Henriques, 2018, The emerging therapeutic landscape of advanced melanoma, Curr Pharm Des, 24, 549, 10.2174/1381612824666180125093357 · doi:10.2174/1381612824666180125093357
  21. MacCormack, 2004, Local melanoma recurrence: a clarification of terminology, Dermatol Surg, 30, 1533
  22. Gonzalez, 2018, Patterns of failure following the excision of in-transit lesions in melanoma and the influence of excisional margins, J Surg Oncol, 118, 606, 10.1002/jso.25176 · doi:10.1002/jso.25176
  23. Beasley, 2017, Sentinel lymph node biopsy for recurrent melanoma: a multicenter study, Ann Surg Oncol, 24, 2728, 10.1245/s10434-017-5883-6 · doi:10.1245/s10434-017-5883-6
  24. Brown, 1995, The prognosis and treatment of true local cutaneous recurrent malignant melanoma, Dermatol Surg, 21, 285, 10.1111/j.1524-4725.1995.tb00174.x · doi:10.1111/j.1524-4725.1995.tb00174.x
  25. Srivastava N, 2014, Dropout: a simple way to prevent nerual networks from overfitting, J Mach Learn Res, 2014, 1929
  26. Ribatti, 2017, The concept of immune surveillance against tumors. The first theories, Oncotarget, 8, 7175, 10.18632/oncotarget.12739 · DOI · Paper page
  27. Clemente, 1996, Prognostic value of tumor infiltrating lymphocytes in the vertical growth phase of primary cutaneous melanoma, Cancer, 77, 1303, 10.1002/(SICI)1097-0142(19960401)77:7<1303::AID-CNCR12>3.0.CO;2-5 · DOI · Paper page
  28. Azimi, 2012, Tumor-infiltrating lymphocyte grade is an independent predictor of sentinel lymph node status and survival in patients with cutaneous melanoma, J Clin Oncol, 30, 2678, 10.1200/JCO.2011.37.8539 · DOI · Paper page
  29. Weiss, 2015, Revisiting determinants of prognosis in cutaneous melanoma, Cancer, 121, 4108, 10.1002/cncr.29634 · DOI

Cited by

See all 124

Metadata

Authors
Kulkarni, P. M., Robinson, E. J., Sarin Pradhan, J., Gartrell-Corrado, R. D., Rohr, B. R., Trager, M. H., Geskin, L. J., Kluger, H. M., Wong, P. F., Acs, B., Rizk, E. M., Yang, C., Mondal, M., Moore, M. R., Osman, I., Phelps, R., Horst, B. A., Chen, Z. S., Ferringer, T., Rimm, D. L., Wang, J., & Saenger, Y. M.
Venue
Clinical Cancer Research
Published
2019-10-21
Volume
26
Issue
5
Pages
1126-1134
ISSN
  • 1078-0432 (ISSN-L)
  • 1557-3265
OpenAlex
W2981358604
Cited by
124
References
5
FWCI
5.76
Type
journal article
Language
en
Open access
green
Funders
  • NIH (R01FD006108, UH2CA218149, KL2TR001874)
  • Melanoma Research Alliance
  • Columbia University's Irving Institute for Clinical and Translational Research
  • Swim Across America
  • Yale SPORE in Lung Cancer (P50CA196530)
  • Yale Cancer Center (P30CA016359)
  • NYU Melanoma SPORE (P50CA225450)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death. https://app.cochat.ai/papers/10.1158/1078-0432.ccr-19-1495
The paper
Kulkarni, P. M., Robinson, E. J., Sarin Pradhan, J., Gartrell-Corrado, R. D., Rohr, B. R., Trager, M. H., Geskin, L. J., Kluger, H. M., Wong, P. F., Acs, B., Rizk, E. M., Yang, C., Mondal, M., Moore, M. R., Osman, I., Phelps, R., Horst, B. A., Chen, Z. S., Ferringer, T., . . . Saenger, Y. M. (2020). Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death. Clinical Cancer Research. https://doi.org/10.1158/1078-0432.ccr-19-1495

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.