Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 2;11(1):2809.
doi: 10.1038/s41598-021-82305-1.

Automated digital TIL analysis (ADTA) adds prognostic value to standard assessment of depth and ulceration in primary melanoma

Michael R Moore #  1 , Isabel D Friesner #  2 , Emanuelle M Rizk #  1 , Benjamin T Fullerton  1 , Manas Mondal  1 , Megan H Trager  3 , Karen Mendelson  4 , Ijeuru Chikeka  5 , Tahsin Kurc  6 , Rajarsi Gupta  6 , Bethany R Rohr  7 , Eric J Robinson  8 , Balazs Acs  9   10 , Rui Chang  11 , Harriet Kluger  12 , Bret Taback  13 , Larisa J Geskin  5 , Basil Horst  14 , Kevin Gardner  15 , George Niedt  5 , Julide T Celebi  4 , Robyn D Gartrell-Corrado  16 , Jane Messina  17 , Tammie Ferringer  18 , David L Rimm  9 , Joel Saltz  6 , Jing Wang #  19   20 , Rami Vanguri #  21 , Yvonne M Saenger #  22
Affiliations

Automated digital TIL analysis (ADTA) adds prognostic value to standard assessment of depth and ulceration in primary melanoma

Michael R Moore et al. Sci Rep. .

Abstract

Accurate prognostic biomarkers in early-stage melanoma are urgently needed to stratify patients for clinical trials of adjuvant therapy. We applied a previously developed open source deep learning algorithm to detect tumor-infiltrating lymphocytes (TILs) in hematoxylin and eosin (H&E) images of early-stage melanomas. We tested whether automated digital (TIL) analysis (ADTA) improved accuracy of prediction of disease specific survival (DSS) based on current pathology standards. ADTA was applied to a training cohort (n = 80) and a cutoff value was defined based on a Receiver Operating Curve. ADTA was then applied to a validation cohort (n = 145) and the previously determined cutoff value was used to stratify high and low risk patients, as demonstrated by Kaplan-Meier analysis (p ≤ 0.001). Multivariable Cox proportional hazards analysis was performed using ADTA, depth, and ulceration as co-variables and showed that ADTA contributed to DSS prediction (HR: 4.18, CI 1.51-11.58, p = 0.006). ADTA provides an effective and attainable assessment of TILs and should be further evaluated in larger studies for inclusion in staging algorithms.

PubMed Disclaimer

Conflict of interest statement

Dr. Saenger has received research funding from Amgen and Regeneron. In addition, she is co-founder of a small biomarkers start-up company, Wasaba. All other authors declare no competing interests.

Figures

Figure 1
Figure 1
A detailed view of our approach. (a) Workflow for ADTA, based on Saltz et al. (QuPath v0.1.2: https://qupath.github.io/; QuIP: https://sbu-bmi.github.io/quip_distro/; TIL identification: https://github.com/SBU-BMI/quip_classification). Representative H&Es of (b) high-risk (low lymphocytic infiltrate) and (c) low-risk (high lymphocytic infiltrate) patients, as defined by the algorithm.
Figure 2
Figure 2
ADTA performance on training cohort. (a) ADTA score correlates with pathologist TIL grading defined as absent, non-brisk, or brisk (ρ = 0.515, p ≤ 0.001 using Spearman’s rank correlation coefficient). (b) KM curve for DSS created using ROC-defined cutoff (p = 0.0220 using log rank (Mantel Cox) test).
Figure 3
Figure 3
ADTA performance on validation cohort. (a) Correlation between ADTA score and pathologist TIL grading defined as absent, non-brisk, or brisk (ρ = 0.211, p = 0.011 using Spearman’s rank correlation coefficient). (b) KM curve for DSS created using pre-defined cutoff (p < 0.001 using log rank (Mantel Cox) test).
Figure 4
Figure 4
Cox regression analysis of validation cohort. (a) Univariable Cox regression analysis of disease-specific survival on validation cohort including ADTA, depth, ulceration, T-stage, and TIL grade. (b) Multivariable Cox regression analysis of disease-specific survival on validation cohort including ADTA, depth, and ulceration. (c) Multivariable Cox regression analysis of disease-specific survival on validation cohort including ADTA and T-stage.
See this image and copyright information in PMC

References

    1. Weber J, et al. A randomized, double-blind, placebo-controlled, phase II study comparing the tolerability and efficacy of ipilimumab administered with or without prophylactic budesonide in patients with unresectable stage III or IV melanoma. Clin. Cancer Res. 2009;15:5591–5598. doi: 10.1158/1078-0432.CCR-09-1024. - DOI - PubMed
    1. O'Day SJ, et al. Efficacy and safety of ipilimumab monotherapy in patients with pretreated advanced melanoma: A multicenter single-arm phase II study. Ann. Oncol. 2010;21:1712–1717. doi: 10.1093/annonc/mdq013. - DOI - PubMed
    1. Hodi FS, et al. Improved survival with ipilimumab in patients with metastatic melanoma. N. Engl. J. Med. 2010;363:711–723. doi: 10.1056/NEJMoa1003466. - DOI - PMC - PubMed
    1. Weber J, et al. Adjuvant Nivolumab versus Ipilimumab in resected stage III or IV melanoma. N. Engl. J. Med. 2017;377:1824–1835. doi: 10.1056/NEJMoa1709030. - DOI - PubMed
    1. Eggermont AMM, et al. Adjuvant pembrolizumab versus placebo in resected stage III melanoma. N. Engl. J. Med. 2018;378:1789–1801. doi: 10.1056/NEJMoa1802357. - DOI - PubMed

Publication types

MeSH terms