Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases

• Published in: EBioMedicine 2023-07, Vol.93, p.104644-104644, Article 104644
• Main Authors: Chatziioannou, Eftychia, Roßner, Jana, Aung, Thazin New, Rimm, David L., Niessner, Heike, Keim, Ulrike, Serna-Higuita, Lina Maria, Bonzheim, Irina, Kuhn Cuellar, Luis, Westphal, Dana, Steininger, Julian, Meier, Friedegund, Pop, Oltin Tiberiu, Forchhammer, Stephan, Flatz, Lukas, Eigentler, Thomas, Garbe, Claus, Röcken, Martin, Amaral, Teresa, Sinnberg, Tobias
• Format: Article
• Language: English
• Subjects: Cutaneous melanoma; Deep Learning; Digital pathology; Humans; Lymphocytes, Tumor-Infiltrating - pathology; Melanoma - pathology; Melanoma, Cutaneous Malignant; Neoplasm Recurrence, Local - pathology; Predictive biomarkers; Prognosis; Prognostic biomarkers; Skin Neoplasms - drug therapy; Skin Neoplasms - pathology; Tumour-infiltrating lymphocytes
• ISSN: 2352-3964; 2352-3964
• DOI: 10.1016/j.ebiom.2023.104644

Recent advances in digital pathology have enabled accurate and standardised enumeration of tumour-infiltrating lymphocytes (TILs). Here, we aim to evaluate TILs as a percentage electronic TIL score (eTILs) and investigate its prognostic and predictive relevance in cutaneous melanoma. We included stage I to IV cutaneous melanoma patients and used hematoxylin-eosin-stained slides for TIL analysis. We assessed eTILs as a continuous and categorical variable using the published cut-off of 16.6% and applied Cox regression models to evaluate associations of eTILs with relapse-free, distant metastasis-free, and overall survival. We compared eTILs of the primaries with matched metastasis. Moreover, we assessed the predictive relevance of eTILs in therapy-naïve metastases according to the first-line therapy. We analysed 321 primary cutaneous melanomas and 191 metastatic samples. In simple Cox regression, tumour thickness (p