Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases
Chatziioannou E, Roßner J, Aung T, Rimm D, Niessner H, Keim U, Serna-Higuita L, Bonzheim I, Cuellar L, Westphal D, Steininger J, Meier F, Pop O, Forchhammer S, Flatz L, Eigentler T, Garbe C, Röcken M, Amaral T, Sinnberg T. Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases. EBioMedicine 2023, 93: 104644. PMID: 37295047, PMCID: PMC10363450, DOI: 10.1016/j.ebiom.2023.104644.Peer-Reviewed Original ResearchConceptsTumor-infiltrating lymphocytesMultiple Cox regressionMelanoma-specific survivalCox regressionTumor thicknessCutaneous melanomaPrimary melanomaAssessment of TILsPD-1 checkpoint inhibitionSignificant unfavourable prognostic factorLonger progression-free survivalDistant metastasis-free survivalSimple Cox regressionUnfavourable survival outcomeFirst-line therapyProgression-free survivalUnfavourable prognostic factorCutaneous melanoma patientsMetastasis-free survivalPresence of ulcerationPrimary cutaneous melanomaCox regression modelPrimary melanoma samplesPrimary tissuesOverall survival