Deep Learning Based on Standard H&E Images of Primary Melanoma Tumors Identifies Patients at Risk for Visceral Recurrence and Death
Open accessPublished version of a preprint
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.
Integrity signals
Registry
Cites
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.
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
QuPath: Open source software for digital pathology image analysis
Bankhead, P., Loughrey, M. B., Fernández, J. A., Dombrowski, Y., McArt, D. G., Dunne, P. D., McQuaid, S., Gray, R. T., Murray, L. J., Coleman, H. G., et al. (2017) · Scientific Reports · doi:10.1038/s41598-017-17204-5 · Cited by 8,908 · cited 1×
“Identification of regions of interest To isolate tumor and immune regions for RNN sequence generation, we usedQuPath digital pathology software (22) to buildmodules for nuclear segmentation and cell classification.”
MethodEhteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293
Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyö, D., Moreira, A. L., Razavian, N., & Tsirigos, A. (2018) · Nature Medicine · doi:10.1038/s41591-018-0177-5 · Cited by 2,930 · cited 1×
“While standard methods for processing histopathologic images with neural networks (21, 30) involve dividing the image into smaller (i.”
MethodAdjuvant nivolumab versus ipilimumab in resected stage III or IV melanoma
Weber, J., Mandala, M., Del Vecchio, M., Gogas, H. J., Arance, A. M., Cowey, C. L., Dalle, S., Schenker, M., Chiarion-Sileni, V., Marquez-Rodas, I., et al. (2017) · New England Journal of Medicine · doi:10.1056/nejmoa1709030 · Cited by 2,246 · cited 1×
“Effective adjuvant therapy, however, was not introduced into general practice until 2017 with the FDA approval of nivolumab for resected stage III melanoma (24).”
BackgroundDeep learning based tissue analysis predicts outcome in colorectal cancer
Bychkov, D., Linder, N., Turkki, R., Nordling, S., Kovanen, P. E., Verrill, C., Walliander, M., Lundin, M., Haglund, C., & Lundin, J. (2018) · Scientific Reports · doi:10.1038/s41598-018-21758-3 · Cited by 644 · cited 1×
“While standard methods for processing histopathologic images with neural networks (21, 30) involve dividing the image into smaller (i.e., 512 (cid”
Method
Research works printed but not linked: 29
- Palmieri, 2018, Immune checkpoint inhibitor toxicity, Curr Oncol Rep, 20, 72, 10.1007/s11912-018-0718-6 · DOI
- Gordan, 2019, Cost differential of immuno-oncology therapy delivered at community versus hospital clinics, Am J Manag Care, 25, e66
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- Esteva, 2017, Dermatologist-level classification of skin cancer with deep neural networks, Nature, 542, 115, 10.1038/nature21056 · DOI · Paper page
- Shen, 2017, Deep learning in medical image analysis, Annu Rev Biomed Eng, 19, 221, 10.1146/annurev-bioeng-071516-044442 · DOI · Paper page
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- Henriques, 2018, The emerging therapeutic landscape of advanced melanoma, Curr Pharm Des, 24, 549, 10.2174/1381612824666180125093357 · doi:10.2174/1381612824666180125093357
- MacCormack, 2004, Local melanoma recurrence: a clarification of terminology, Dermatol Surg, 30, 1533
- 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
- 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
- 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
- Srivastava N, 2014, Dropout: a simple way to prevent nerual networks from overfitting, J Mach Learn Res, 2014, 1929
- Ribatti, 2017, The concept of immune surveillance against tumors. The first theories, Oncotarget, 8, 7175, 10.18632/oncotarget.12739 · DOI · Paper page
- 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
- 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
- Weiss, 2015, Revisiting determinants of prognosis in cutaneous melanoma, Cancer, 121, 4108, 10.1002/cncr.29634 · DOI
Cited by
Deep learning in histopathology: the path to the clinic
van der Laak, J., Litjens, G., & Ciompi, F. (2021) · Nature Medicine · doi:10.1038/s41591-021-01343-4 · Cited by 902
Deep learning in cancer pathology: a new generation of clinical biomarkers
Echle, A., Rindtorff, N. T., Brinker, T. J., Luedde, T., Pearson, A. T., & Kather, J. N. (2021) · British Journal of Cancer · doi:10.1038/s41416-020-01122-x · Cited by 667
“49 This is a prime example showing that it is possible to train DL networks on clinical endpoints directly from histology.”
BackgroundPan-cancer integrative histology-genomic analysis via multimodal deep learning
Chen, R. J., Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Noor, Z., Shaban, M., Shady, M., Williams, M., Joo, B., et al. (2022) · Cancer Cell · doi:10.1016/j.ccell.2022.07.004 · Cited by 660
Digital pathology and artificial intelligence in translational medicine and clinical practice
Baxi, V., Edwards, R., Montalto, M., & Saha, S. (2022) · Modern Pathology · doi:10.1038/s41379-021-00919-2 · Cited by 592
Artificial intelligence as the next step towards precision pathology
Acs, B., Rantalainen, M., & Hartman, J. (2020) · Journal of Internal Medicine · doi:10.1111/joim.13030 · Cited by 450
Self-citation
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.