Automated quantification of stromal tumour infiltrating lymphocytes is associated with prognosis in breast cancer
© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature..
Stromal tumour infiltrating lymphocytes (sTIL) in haematoxylin and eosin (H&E) stained sections has been linked to better outcomes and better responses to neoadjuvant therapy in triple-negative and HER2-positive breast cancer (TNBC and HER2 +). However, the infiltrate includes different cell populations that have specific roles in the tumour immune microenvironment. Various studies have found high concordance between sTIL visual quantification and computational assessment, but specific data on the individual prognostic impact of plasma cells or lymphocytes within sTIL on patient prognosis is still unknown. In this study, we validated a deep-learning breast cancer sTIL scoring model (smsTIL) based on the segmentation of tumour cells, benign ductal cells, lymphocytes, plasma cells, necrosis, and 'other' cells in whole slide images (WSI). Focusing on HER2 + and TNBC patient samples, we assessed the concordance between sTIL visual scoring and the smsTIL in 130 WSI. Furthermore, we analysed 175 WSI to correlate smsTIL with clinical data and patient outcomes. We found a high correlation between sTIL values scored visually and semi-automatically (R = 0.76; P = 2.2e-16). Patients with higher smsTIL had better overall survival (OS) in TNBC (P = 0.0021). In the TNBC cohort, smsTIL was as an independent prognostic factor for OS. As part of this work, we introduce a new segmentation dataset of H&E-stained WSI.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:483 |
|---|---|
| Enthalten in: |
Virchows Archiv : an international journal of pathology - 483(2023), 5 vom: 28. Nov., Seite 655-663 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Gonzàlez-Farré, Mònica [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Biomarkers, Tumor |
|---|
| Anmerkungen: |
Date Completed 27.11.2023 Date Revised 05.12.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1007/s00428-023-03608-4 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM360007570 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM360007570 | ||
| 003 | DE-627 | ||
| 005 | 20231226082103.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00428-023-03608-4 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1199.xml |
| 035 | |a (DE-627)NLM360007570 | ||
| 035 | |a (NLM)37500796 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Gonzàlez-Farré, Mònica |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Automated quantification of stromal tumour infiltrating lymphocytes is associated with prognosis in breast cancer |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 27.11.2023 | ||
| 500 | |a Date Revised 05.12.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature. | ||
| 520 | |a Stromal tumour infiltrating lymphocytes (sTIL) in haematoxylin and eosin (H&E) stained sections has been linked to better outcomes and better responses to neoadjuvant therapy in triple-negative and HER2-positive breast cancer (TNBC and HER2 +). However, the infiltrate includes different cell populations that have specific roles in the tumour immune microenvironment. Various studies have found high concordance between sTIL visual quantification and computational assessment, but specific data on the individual prognostic impact of plasma cells or lymphocytes within sTIL on patient prognosis is still unknown. In this study, we validated a deep-learning breast cancer sTIL scoring model (smsTIL) based on the segmentation of tumour cells, benign ductal cells, lymphocytes, plasma cells, necrosis, and 'other' cells in whole slide images (WSI). Focusing on HER2 + and TNBC patient samples, we assessed the concordance between sTIL visual scoring and the smsTIL in 130 WSI. Furthermore, we analysed 175 WSI to correlate smsTIL with clinical data and patient outcomes. We found a high correlation between sTIL values scored visually and semi-automatically (R = 0.76; P = 2.2e-16). Patients with higher smsTIL had better overall survival (OS) in TNBC (P = 0.0021). In the TNBC cohort, smsTIL was as an independent prognostic factor for OS. As part of this work, we introduce a new segmentation dataset of H&E-stained WSI | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Digital pathology | |
| 650 | 4 | |a HER2 + | |
| 650 | 4 | |a Segmentation model | |
| 650 | 4 | |a Stromal tumour infiltrating lymphocytes | |
| 650 | 4 | |a Triple negative breast carcinoma | |
| 650 | 7 | |a Biomarkers, Tumor |2 NLM | |
| 700 | 1 | |a Gibert, Joan |e verfasserin |4 aut | |
| 700 | 1 | |a Santiago-Díaz, Pablo |e verfasserin |4 aut | |
| 700 | 1 | |a Santos, Jordina |e verfasserin |4 aut | |
| 700 | 1 | |a García, Pilar |e verfasserin |4 aut | |
| 700 | 1 | |a Massó, Jordi |e verfasserin |4 aut | |
| 700 | 1 | |a Bellosillo, Beatriz |e verfasserin |4 aut | |
| 700 | 1 | |a Lloveras, Belén |e verfasserin |4 aut | |
| 700 | 1 | |a Albanell, Joan |e verfasserin |4 aut | |
| 700 | 1 | |a Vázquez, Ivonne |e verfasserin |4 aut | |
| 700 | 1 | |a Comerma, Laura |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Virchows Archiv : an international journal of pathology |d 1997 |g 483(2023), 5 vom: 28. Nov., Seite 655-663 |w (DE-627)NLM074732579 |x 1432-2307 |7 nnns |
| 773 | 1 | 8 | |g volume:483 |g year:2023 |g number:5 |g day:28 |g month:11 |g pages:655-663 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/s00428-023-03608-4 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 483 |j 2023 |e 5 |b 28 |c 11 |h 655-663 | ||