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

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 sta...

Full description

Saved in:
Bibliographic Details
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
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673
cites cdi_FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673
container_end_page 104644
container_issue
container_start_page 104644
container_title EBioMedicine
container_volume 93
creator 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
description 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 
doi_str_mv 10.1016/j.ebiom.2023.104644
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10363450</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2352396423002098</els_id><sourcerecordid>2824692259</sourcerecordid><originalsourceid>FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673</originalsourceid><addsrcrecordid>eNp9UdGOEyEUnRiNu1n3C0wMj75MlwGG6TwYY3bVNdlEH_SZMHBpb52BCkyT_s9-qNTWZn0xIYF7OOdcLqeqXjd00dBG3mwWMGCYFowyXhAhhXhWXTLespr3Ujx_cr6orlPaUEqbVhRw-bK64B3rWyq6y-rxDmBLRtDRo1_Vg05gSTIhlooER_I8hTnW6B2OOep8gMf9tF0Hs8-QCCayjWHlQ8poCPpS4aTjnkwwah8mTbS3BQSLJuMOSA7k213dELMG83Mb0OeiWuOAGYM_GJyFE2SdyoL0qnrh9Jjg-rRfVT8-ffx-e18_fP385fbDQ22EpLl2ujdWt641wrFlZ5dWDK4B6LTopGPS2mFouLWGdk5CL7qh19porRs7OC47flW9P_pu52ECa8CXkUd1GkkFjerfG49rtQo71VAuuWhpcXh7cojh1wwpqwmTgbGMBGFOii2ZkD1jbV-o_Eg1MaQUwZ37NFQdMlYb9SdjdchYHTMuqjdPn3jW_E20EN4dCVA-aocQVTII3pQAIpisbMD_NvgNQ3TAGw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2824692259</pqid></control><display><type>article</type><title>Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases</title><source>ScienceDirect Journals</source><source>PubMed Central</source><creator>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</creator><creatorcontrib>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</creatorcontrib><description>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 &lt; 0.0001), presence of ulceration (p = 0.0001) and eTILs ≤16.6% (p = 0.0012) were found to be significant unfavourable prognostic factors for RFS. In multiple Cox regression, eTILs ≤16.6% (p = 0.0161) remained significant and downgraded the current staging. Lower eTILs in the primary tissue was associated with unfavourable relapse-free (p = 0.0014) and distant metastasis-free survival (p = 0.0056). In multiple Cox regression adjusted for tumour thickness and ulceration, eTILs as continuous remained significant (p = 0.019). When comparing TILs in primary tissue and corresponding metastasis of the same patient, eTILs in metastases was lower than in primary melanomas (p &lt; 0.0001). In therapy-naïve metastases, an eTILs &gt;12.2% was associated with longer progression-free survival (p = 0.037) and melanoma-specific survival (p = 0.0038) in patients treated with anti-PD-1-based immunotherapy. In multiple Cox regression, lactate dehydrogenase (p &lt; 0.0001) and eTILs ≤12.2% (p = 0.0130) were significantly associated with unfavourable melanoma-specific survival. Assessment of TILs is prognostic in primary melanoma samples, and the eTILs complements staging. In therapy-naïve metastases, eTILs ≤12.2% is predictive of unfavourable survival outcomes in patients receiving anti-PD-1-based therapy. See a detailed list of funding bodies in the Acknowledgements section at the end of the manuscript.</description><identifier>ISSN: 2352-3964</identifier><identifier>EISSN: 2352-3964</identifier><identifier>DOI: 10.1016/j.ebiom.2023.104644</identifier><identifier>PMID: 37295047</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>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</subject><ispartof>EBioMedicine, 2023-07, Vol.93, p.104644-104644, Article 104644</ispartof><rights>2023 The Authors</rights><rights>Copyright © 2023 The Authors. Published by Elsevier B.V. All rights reserved.</rights><rights>2023 The Authors 2023</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673</citedby><cites>FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673</cites><orcidid>0000-0002-1274-2613 ; 0000-0002-6950-6929 ; 0000-0002-7843-7160 ; 0000-0003-3922-3327</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10363450/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S2352396423002098$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>230,314,725,778,782,883,3538,27907,27908,45763,53774,53776</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37295047$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Chatziioannou, Eftychia</creatorcontrib><creatorcontrib>Roßner, Jana</creatorcontrib><creatorcontrib>Aung, Thazin New</creatorcontrib><creatorcontrib>Rimm, David L.</creatorcontrib><creatorcontrib>Niessner, Heike</creatorcontrib><creatorcontrib>Keim, Ulrike</creatorcontrib><creatorcontrib>Serna-Higuita, Lina Maria</creatorcontrib><creatorcontrib>Bonzheim, Irina</creatorcontrib><creatorcontrib>Kuhn Cuellar, Luis</creatorcontrib><creatorcontrib>Westphal, Dana</creatorcontrib><creatorcontrib>Steininger, Julian</creatorcontrib><creatorcontrib>Meier, Friedegund</creatorcontrib><creatorcontrib>Pop, Oltin Tiberiu</creatorcontrib><creatorcontrib>Forchhammer, Stephan</creatorcontrib><creatorcontrib>Flatz, Lukas</creatorcontrib><creatorcontrib>Eigentler, Thomas</creatorcontrib><creatorcontrib>Garbe, Claus</creatorcontrib><creatorcontrib>Röcken, Martin</creatorcontrib><creatorcontrib>Amaral, Teresa</creatorcontrib><creatorcontrib>Sinnberg, Tobias</creatorcontrib><title>Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases</title><title>EBioMedicine</title><addtitle>EBioMedicine</addtitle><description>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 &lt; 0.0001), presence of ulceration (p = 0.0001) and eTILs ≤16.6% (p = 0.0012) were found to be significant unfavourable prognostic factors for RFS. In multiple Cox regression, eTILs ≤16.6% (p = 0.0161) remained significant and downgraded the current staging. Lower eTILs in the primary tissue was associated with unfavourable relapse-free (p = 0.0014) and distant metastasis-free survival (p = 0.0056). In multiple Cox regression adjusted for tumour thickness and ulceration, eTILs as continuous remained significant (p = 0.019). When comparing TILs in primary tissue and corresponding metastasis of the same patient, eTILs in metastases was lower than in primary melanomas (p &lt; 0.0001). In therapy-naïve metastases, an eTILs &gt;12.2% was associated with longer progression-free survival (p = 0.037) and melanoma-specific survival (p = 0.0038) in patients treated with anti-PD-1-based immunotherapy. In multiple Cox regression, lactate dehydrogenase (p &lt; 0.0001) and eTILs ≤12.2% (p = 0.0130) were significantly associated with unfavourable melanoma-specific survival. Assessment of TILs is prognostic in primary melanoma samples, and the eTILs complements staging. In therapy-naïve metastases, eTILs ≤12.2% is predictive of unfavourable survival outcomes in patients receiving anti-PD-1-based therapy. See a detailed list of funding bodies in the Acknowledgements section at the end of the manuscript.</description><subject>Cutaneous melanoma</subject><subject>Deep Learning</subject><subject>Digital pathology</subject><subject>Humans</subject><subject>Lymphocytes, Tumor-Infiltrating - pathology</subject><subject>Melanoma - pathology</subject><subject>Melanoma, Cutaneous Malignant</subject><subject>Neoplasm Recurrence, Local - pathology</subject><subject>Predictive biomarkers</subject><subject>Prognosis</subject><subject>Prognostic biomarkers</subject><subject>Skin Neoplasms - drug therapy</subject><subject>Skin Neoplasms - pathology</subject><subject>Tumour-infiltrating lymphocytes</subject><issn>2352-3964</issn><issn>2352-3964</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9UdGOEyEUnRiNu1n3C0wMj75MlwGG6TwYY3bVNdlEH_SZMHBpb52BCkyT_s9-qNTWZn0xIYF7OOdcLqeqXjd00dBG3mwWMGCYFowyXhAhhXhWXTLespr3Ujx_cr6orlPaUEqbVhRw-bK64B3rWyq6y-rxDmBLRtDRo1_Vg05gSTIhlooER_I8hTnW6B2OOep8gMf9tF0Hs8-QCCayjWHlQ8poCPpS4aTjnkwwah8mTbS3BQSLJuMOSA7k213dELMG83Mb0OeiWuOAGYM_GJyFE2SdyoL0qnrh9Jjg-rRfVT8-ffx-e18_fP385fbDQ22EpLl2ujdWt641wrFlZ5dWDK4B6LTopGPS2mFouLWGdk5CL7qh19porRs7OC47flW9P_pu52ECa8CXkUd1GkkFjerfG49rtQo71VAuuWhpcXh7cojh1wwpqwmTgbGMBGFOii2ZkD1jbV-o_Eg1MaQUwZ37NFQdMlYb9SdjdchYHTMuqjdPn3jW_E20EN4dCVA-aocQVTII3pQAIpisbMD_NvgNQ3TAGw</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Chatziioannou, Eftychia</creator><creator>Roßner, Jana</creator><creator>Aung, Thazin New</creator><creator>Rimm, David L.</creator><creator>Niessner, Heike</creator><creator>Keim, Ulrike</creator><creator>Serna-Higuita, Lina Maria</creator><creator>Bonzheim, Irina</creator><creator>Kuhn Cuellar, Luis</creator><creator>Westphal, Dana</creator><creator>Steininger, Julian</creator><creator>Meier, Friedegund</creator><creator>Pop, Oltin Tiberiu</creator><creator>Forchhammer, Stephan</creator><creator>Flatz, Lukas</creator><creator>Eigentler, Thomas</creator><creator>Garbe, Claus</creator><creator>Röcken, Martin</creator><creator>Amaral, Teresa</creator><creator>Sinnberg, Tobias</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>6I.</scope><scope>AAFTH</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-1274-2613</orcidid><orcidid>https://orcid.org/0000-0002-6950-6929</orcidid><orcidid>https://orcid.org/0000-0002-7843-7160</orcidid><orcidid>https://orcid.org/0000-0003-3922-3327</orcidid></search><sort><creationdate>20230701</creationdate><title>Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases</title><author>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</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Cutaneous melanoma</topic><topic>Deep Learning</topic><topic>Digital pathology</topic><topic>Humans</topic><topic>Lymphocytes, Tumor-Infiltrating - pathology</topic><topic>Melanoma - pathology</topic><topic>Melanoma, Cutaneous Malignant</topic><topic>Neoplasm Recurrence, Local - pathology</topic><topic>Predictive biomarkers</topic><topic>Prognosis</topic><topic>Prognostic biomarkers</topic><topic>Skin Neoplasms - drug therapy</topic><topic>Skin Neoplasms - pathology</topic><topic>Tumour-infiltrating lymphocytes</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chatziioannou, Eftychia</creatorcontrib><creatorcontrib>Roßner, Jana</creatorcontrib><creatorcontrib>Aung, Thazin New</creatorcontrib><creatorcontrib>Rimm, David L.</creatorcontrib><creatorcontrib>Niessner, Heike</creatorcontrib><creatorcontrib>Keim, Ulrike</creatorcontrib><creatorcontrib>Serna-Higuita, Lina Maria</creatorcontrib><creatorcontrib>Bonzheim, Irina</creatorcontrib><creatorcontrib>Kuhn Cuellar, Luis</creatorcontrib><creatorcontrib>Westphal, Dana</creatorcontrib><creatorcontrib>Steininger, Julian</creatorcontrib><creatorcontrib>Meier, Friedegund</creatorcontrib><creatorcontrib>Pop, Oltin Tiberiu</creatorcontrib><creatorcontrib>Forchhammer, Stephan</creatorcontrib><creatorcontrib>Flatz, Lukas</creatorcontrib><creatorcontrib>Eigentler, Thomas</creatorcontrib><creatorcontrib>Garbe, Claus</creatorcontrib><creatorcontrib>Röcken, Martin</creatorcontrib><creatorcontrib>Amaral, Teresa</creatorcontrib><creatorcontrib>Sinnberg, Tobias</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>EBioMedicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chatziioannou, Eftychia</au><au>Roßner, Jana</au><au>Aung, Thazin New</au><au>Rimm, David L.</au><au>Niessner, Heike</au><au>Keim, Ulrike</au><au>Serna-Higuita, Lina Maria</au><au>Bonzheim, Irina</au><au>Kuhn Cuellar, Luis</au><au>Westphal, Dana</au><au>Steininger, Julian</au><au>Meier, Friedegund</au><au>Pop, Oltin Tiberiu</au><au>Forchhammer, Stephan</au><au>Flatz, Lukas</au><au>Eigentler, Thomas</au><au>Garbe, Claus</au><au>Röcken, Martin</au><au>Amaral, Teresa</au><au>Sinnberg, Tobias</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases</atitle><jtitle>EBioMedicine</jtitle><addtitle>EBioMedicine</addtitle><date>2023-07-01</date><risdate>2023</risdate><volume>93</volume><spage>104644</spage><epage>104644</epage><pages>104644-104644</pages><artnum>104644</artnum><issn>2352-3964</issn><eissn>2352-3964</eissn><abstract>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 &lt; 0.0001), presence of ulceration (p = 0.0001) and eTILs ≤16.6% (p = 0.0012) were found to be significant unfavourable prognostic factors for RFS. In multiple Cox regression, eTILs ≤16.6% (p = 0.0161) remained significant and downgraded the current staging. Lower eTILs in the primary tissue was associated with unfavourable relapse-free (p = 0.0014) and distant metastasis-free survival (p = 0.0056). In multiple Cox regression adjusted for tumour thickness and ulceration, eTILs as continuous remained significant (p = 0.019). When comparing TILs in primary tissue and corresponding metastasis of the same patient, eTILs in metastases was lower than in primary melanomas (p &lt; 0.0001). In therapy-naïve metastases, an eTILs &gt;12.2% was associated with longer progression-free survival (p = 0.037) and melanoma-specific survival (p = 0.0038) in patients treated with anti-PD-1-based immunotherapy. In multiple Cox regression, lactate dehydrogenase (p &lt; 0.0001) and eTILs ≤12.2% (p = 0.0130) were significantly associated with unfavourable melanoma-specific survival. Assessment of TILs is prognostic in primary melanoma samples, and the eTILs complements staging. In therapy-naïve metastases, eTILs ≤12.2% is predictive of unfavourable survival outcomes in patients receiving anti-PD-1-based therapy. See a detailed list of funding bodies in the Acknowledgements section at the end of the manuscript.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>37295047</pmid><doi>10.1016/j.ebiom.2023.104644</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-1274-2613</orcidid><orcidid>https://orcid.org/0000-0002-6950-6929</orcidid><orcidid>https://orcid.org/0000-0002-7843-7160</orcidid><orcidid>https://orcid.org/0000-0003-3922-3327</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2352-3964
ispartof EBioMedicine, 2023-07, Vol.93, p.104644-104644, Article 104644
issn 2352-3964
2352-3964
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_10363450
source ScienceDirect Journals; PubMed Central
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
title Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T05%3A26%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20learning-based%20scoring%20of%20tumour-infiltrating%20lymphocytes%20is%20prognostic%20in%20primary%20melanoma%20and%20predictive%20to%20PD-1%20checkpoint%20inhibition%20in%20melanoma%20metastases&rft.jtitle=EBioMedicine&rft.au=Chatziioannou,%20Eftychia&rft.date=2023-07-01&rft.volume=93&rft.spage=104644&rft.epage=104644&rft.pages=104644-104644&rft.artnum=104644&rft.issn=2352-3964&rft.eissn=2352-3964&rft_id=info:doi/10.1016/j.ebiom.2023.104644&rft_dat=%3Cproquest_pubme%3E2824692259%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c460t-fa9cda5f5c4f287d8d4bf1ee7a476f26ddbb13ddc07f6e947b9aacaaa1dbf3673%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2824692259&rft_id=info:pmid/37295047&rfr_iscdi=true