Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers
Triple-negative breast cancer (TNBC) is an aggressive and difficult-to-treat cancer type that represents approximately 15% of all breast cancers. Recently, stromal tumor-infiltrating lymphocytes (sTIL) resurfaced as a strong prognostic biomarker for overall survival (OS) for TNBC patients. Manual as...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/13/12/3050 |
| _version_ | 1797529620184039424 |
|---|---|
| author | Jeppe Thagaard Elisabeth Specht Stovgaard Line Grove Vognsen Søren Hauberg Anders Dahl Thomas Ebstrup Johan Doré Rikke Egede Vincentz Rikke Karlin Jepsen Anne Roslind Iben Kümler Dorte Nielsen Eva Balslev |
| author_facet | Jeppe Thagaard Elisabeth Specht Stovgaard Line Grove Vognsen Søren Hauberg Anders Dahl Thomas Ebstrup Johan Doré Rikke Egede Vincentz Rikke Karlin Jepsen Anne Roslind Iben Kümler Dorte Nielsen Eva Balslev |
| author_sort | Jeppe Thagaard |
| collection | DOAJ |
| description | Triple-negative breast cancer (TNBC) is an aggressive and difficult-to-treat cancer type that represents approximately 15% of all breast cancers. Recently, stromal tumor-infiltrating lymphocytes (sTIL) resurfaced as a strong prognostic biomarker for overall survival (OS) for TNBC patients. Manual assessment has innate limitations that hinder clinical adoption, and the International Immuno-Oncology Biomarker Working Group (TIL-WG) has therefore envisioned that computational assessment of sTIL could overcome these limitations and recommended that any algorithm should follow the manual guidelines where appropriate. However, no existing studies capture all the concepts of the guideline or have shown the same prognostic evidence as manual assessment. In this study, we present a fully automated digital image analysis pipeline and demonstrate that our hematoxylin and eosin (H&E)-based pipeline can provide a quantitative and interpretable score that correlates with the manual pathologist-derived sTIL status, and importantly, can stratify a retrospective cohort into two significant distinct prognostic groups. We found our score to be prognostic for OS (HR: 0.81 CI: 0.72–0.92 <i>p</i> = 0.001) independent of age, tumor size, nodal status, and tumor type in statistical modeling. While prior studies have followed fragments of the TIL-WG guideline, our approach is the first to follow all complex aspects, where appropriate, supporting the TIL-WG vision of computational assessment of sTIL in the future clinical setting. |
| first_indexed | 2024-03-10T10:16:21Z |
| format | Article |
| id | doaj.art-30e244141f494b9c91ca7436908cfb23 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T10:16:21Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-30e244141f494b9c91ca7436908cfb232023-11-22T00:46:27ZengMDPI AGCancers2072-66942021-06-011312305010.3390/cancers13123050Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast CancersJeppe Thagaard0Elisabeth Specht Stovgaard1Line Grove Vognsen2Søren Hauberg3Anders Dahl4Thomas Ebstrup5Johan Doré6Rikke Egede Vincentz7Rikke Karlin Jepsen8Anne Roslind9Iben Kümler10Dorte Nielsen11Eva Balslev12Department of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kgs. Lyngby, DenmarkDepartment of Pathology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kgs. Lyngby, DenmarkDepartment of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kgs. Lyngby, DenmarkDepartment of Applied Mathematics and Computer Science, Technical University of Denmark, 2800 Kgs. Lyngby, DenmarkVisiopharm A/S, 2970 Hørsholm, DenmarkVisiopharm A/S, 2970 Hørsholm, DenmarkDepartment of Pathology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Pathology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Pathology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Oncology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Oncology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkDepartment of Pathology, Herlev and Gentofte Hospital, 2730 Herlev, DenmarkTriple-negative breast cancer (TNBC) is an aggressive and difficult-to-treat cancer type that represents approximately 15% of all breast cancers. Recently, stromal tumor-infiltrating lymphocytes (sTIL) resurfaced as a strong prognostic biomarker for overall survival (OS) for TNBC patients. Manual assessment has innate limitations that hinder clinical adoption, and the International Immuno-Oncology Biomarker Working Group (TIL-WG) has therefore envisioned that computational assessment of sTIL could overcome these limitations and recommended that any algorithm should follow the manual guidelines where appropriate. However, no existing studies capture all the concepts of the guideline or have shown the same prognostic evidence as manual assessment. In this study, we present a fully automated digital image analysis pipeline and demonstrate that our hematoxylin and eosin (H&E)-based pipeline can provide a quantitative and interpretable score that correlates with the manual pathologist-derived sTIL status, and importantly, can stratify a retrospective cohort into two significant distinct prognostic groups. We found our score to be prognostic for OS (HR: 0.81 CI: 0.72–0.92 <i>p</i> = 0.001) independent of age, tumor size, nodal status, and tumor type in statistical modeling. While prior studies have followed fragments of the TIL-WG guideline, our approach is the first to follow all complex aspects, where appropriate, supporting the TIL-WG vision of computational assessment of sTIL in the future clinical setting.https://www.mdpi.com/2072-6694/13/12/3050deep learningdigital pathologyimage analysisprognostic biomarkersurvival analysistriple-negative breast cancer |
| spellingShingle | Jeppe Thagaard Elisabeth Specht Stovgaard Line Grove Vognsen Søren Hauberg Anders Dahl Thomas Ebstrup Johan Doré Rikke Egede Vincentz Rikke Karlin Jepsen Anne Roslind Iben Kümler Dorte Nielsen Eva Balslev Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers Cancers deep learning digital pathology image analysis prognostic biomarker survival analysis triple-negative breast cancer |
| title | Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers |
| title_full | Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers |
| title_fullStr | Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers |
| title_full_unstemmed | Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers |
| title_short | Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers |
| title_sort | automated quantification of stil density with h e based digital image analysis has prognostic potential in triple negative breast cancers |
| topic | deep learning digital pathology image analysis prognostic biomarker survival analysis triple-negative breast cancer |
| url | https://www.mdpi.com/2072-6694/13/12/3050 |
| work_keys_str_mv | AT jeppethagaard automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT elisabethspechtstovgaard automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT linegrovevognsen automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT sørenhauberg automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT andersdahl automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT thomasebstrup automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT johandore automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT rikkeegedevincentz automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT rikkekarlinjepsen automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT anneroslind automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT ibenkumler automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT dortenielsen automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers AT evabalslev automatedquantificationofstildensitywithhebaseddigitalimageanalysishasprognosticpotentialintriplenegativebreastcancers |