Computational analysis of whole slide images predicts PD-L1 expression and progression-free survival in immunotherapy-treated non-small cell lung cancer patients.
| Title: | Computational analysis of whole slide images predicts PD-L1 expression and progression-free survival in immunotherapy-treated non-small cell lung cancer patients. |
|---|---|
| Authors: | Dia AK; Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada.; Kolnohuz A; Quebec Heart & Lung Institute Research Center, Québec, Canada.; Université Laval, Québec, Canada.; Yolchuyeva S; Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada.; Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada.; Tonneau M; Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada.; Université de médecine de Lille, Lille, France.; Lamaze F; Quebec Heart & Lung Institute Research Center, Québec, Canada.; Orain M; Quebec Heart & Lung Institute Research Center, Québec, Canada.; Gagné A; Université Laval, Québec, Canada.; Blais F; Université Laval, Québec, Canada.; Coulombe F; Université Laval, Québec, Canada.; Malo J; Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada.; Belkaid W; Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada.; Elkrief A; Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada.; Williamson D; Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, USA.; Routy B; Centre de Recherche du Centre Hospitalier Universitaire de Montréal, Montréal, Canada.; Joubert P; Quebec Heart & Lung Institute Research Center, Québec, Canada.; Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada.; Laplante M; Quebec Heart & Lung Institute Research Center, Québec, Canada.; Université Laval, Québec, Canada.; Bilodeau S; Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada.; Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada.; Cancer Research Center, Université Laval, Québec, Canada.; Big Data Research Center, Université Laval, Québec, Canada.; Manem VS; Centre de Recherche du CHU de Québec - Université Laval, Québec, Canada. venkata.manem@crchudequebec.ulaval.ca.; Quebec Heart & Lung Institute Research Center, Québec, Canada. venkata.manem@crchudequebec.ulaval.ca.; Department of Molecular Biology, Medical Biochemistry and Pathology, Université Laval, Québec, Canada. venkata.manem@crchudequebec.ulaval.ca.; Cancer Research Center, Université Laval, Québec, Canada. venkata.manem@crchudequebec.ulaval.ca.; Big Data Research Center, Université Laval, Québec, Canada. venkata.manem@crchudequebec.ulaval.ca. |
| Source: | Journal of translational medicine [J Transl Med] 2025 May 06; Vol. 23 (1), pp. 510. Date of Electronic Publication: 2025 May 06. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: BioMed Central Country of Publication: England NLM ID: 101190741 Publication Model: Electronic Cited Medium: Internet ISSN: 1479-5876 (Electronic) Linking ISSN: 14795876 NLM ISO Abbreviation: J Transl Med Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [London] : BioMed Central, 2003- |
| MeSH Terms: | Carcinoma, Non-Small-Cell Lung*/therapy ; Carcinoma, Non-Small-Cell Lung*/pathology ; Carcinoma, Non-Small-Cell Lung*/metabolism ; Carcinoma, Non-Small-Cell Lung*/drug therapy ; B7-H1 Antigen*/metabolism ; Lung Neoplasms*/pathology ; Lung Neoplasms*/therapy ; Lung Neoplasms*/metabolism ; Lung Neoplasms*/drug therapy ; Lung Neoplasms*/immunology ; Computational Biology*/methods ; Immunotherapy* ; Image Processing, Computer-Assisted*; Humans ; Progression-Free Survival ; Male ; Female ; Machine Learning ; Middle Aged ; Aged |
| Abstract: | Background: Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment by significantly improving the efficacy of treatments and tolerability for patients with non-small cell lung cancer (NSCLC). However, even after meticulous selection based on molecular criteria, only 20-30% of the patients respond to ICIs. This highlights the urgent clinical need to develop more precise biomarkers to better identify individuals who will benefit from these expensive therapies.; Methods: Data from NSCLC patients treated with immunotherapy were collected from two institutions. From the histological images of tumors, pathomics features were extracted. We employed six machine learning models and seven feature selection methods to predict expression of the programmed death-ligand 1 (PD-L1), a current biomarker used to select patients for immunotherapy, and progression-free survival (PFS). The association between pathomics features and biological pathways was explored to validate pathomics-based signatures. We performed gene set enrichment analysis to identify the pathways enriched with the predictive signatures.; Results: Handcrafted histological features were extracted from the whole slide images (WSI). The Support Vector Machines model with the SurfStar feature selection method, offered the best results, with an area under the curve (AUC) of around 0.66 for both the training and validation sets to predict PD-L1. For the prediction of PFS, the most effective model was linear discriminant analysis using the Multi Surf feature selection method with an AUC of 0.71 for the training set and 0.62 for the validation set. We found immune pathways to be upregulated in the high PD-L1 and high PFS groups, confirming the utility of image analysis for predicting clinical endpoints in patients treated with immunotherapy.; Conclusion: Our models, based on the analysis of histological images, can serve as predictive biomarkers for PD-L1 and PFS. This approach, focused on histological images, enables the distinction of patients based on treatment response, thus providing clinicians with a valuable tool for patient management. With further validation on external cohorts, these models could enhance clinical decision-making through analysis of routine medical images.; (© 2025. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The study was approved by the Institutional Review Boards at the two academic institutions where the data was collected (MP-10-2020-3397 / CÉR CHUM: 19.397). Informed consent was obtained from all the study participants. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | Insights Imaging. 2021 Nov 24;12(1):172. (PMID: 34817740); Sci Rep. 2018 Mar 2;8(1):3941. (PMID: 29500362); JTO Clin Res Rep. 2023 Nov 18;4(12):100602. (PMID: 38124790); Ann Transl Med. 2023 Aug 30;11(10):354. (PMID: 37675322); J Biomed Inform. 2018 Sep;85:168-188. (PMID: 30030120); J Thorac Oncol. 2019 Jan;14(1):25-36. (PMID: 30253973); PLoS One. 2019 Feb 22;14(2):e0212110. (PMID: 30794577); Front Oncol. 2022 Oct 06;12:1005805. (PMID: 36276163); Mol Cancer Ther. 2015 Apr;14(4):847-56. (PMID: 25695955); Cell Syst. 2015 Dec 23;1(6):417-425. (PMID: 26771021); J Pathol Inform. 2019 Jul 23;10:24. (PMID: 31523482); Nat Cancer. 2022 Oct;3(10):1151-1164. (PMID: 36038778); Ann Oncol. 2019 Jun 1;30(6):998-1004. (PMID: 30895304); J Transl Med. 2024 Jan 10;22(1):42. (PMID: 38200511); NPJ Precis Oncol. 2022 Jun 3;6(1):33. (PMID: 35661148); J Thorac Oncol. 2021 Dec;16(12):2109-2120. (PMID: 34358724); Am Soc Clin Oncol Educ Book. 2016;35:e450-8. (PMID: 27249753); Cancers (Basel). 2024 Jan 13;16(2):. (PMID: 38254838); Sci Rep. 2018 Nov 26;8(1):17343. (PMID: 30478349); Nat Rev Clin Oncol. 2023 Mar;20(3):143-159. (PMID: 36639452); PLoS One. 2021 Nov 29;16(11):e0260500. (PMID: 34843570); Nat Rev Clin Oncol. 2019 Nov;16(11):703-715. (PMID: 31399699); J Clin Oncol. 2012 Apr 1;30(10):1030-3. (PMID: 22370321); Clin Cancer Res. 2013 May 15;19(10):2607-12. (PMID: 23669420); ESMO Open. 2022 Jun;7(3):100465. (PMID: 35427835); Sci Rep. 2021 Mar 23;11(1):6633. (PMID: 33758304); J Pathol. 2022 Jul;257(4):413-429. (PMID: 35579955); Nat Biotechnol. 2016 Aug 9;34(8):888. (PMID: 27504780); J Clin Oncol. 2023 May 10;41(14):2458-2466. (PMID: 37146426); Am J Cancer Res. 2020 Mar 01;10(3):727-742. (PMID: 32266087); Sci Rep. 2023 Jul 8;13(1):11065. (PMID: 37422576); JACC CardioOncol. 2022 Dec 20;4(5):579-597. (PMID: 36636451); N Engl J Med. 2015 Jul 9;373(2):123-35. (PMID: 26028407); Sci Adv. 2022 Jun 3;8(22):eabn3966. (PMID: 35648850); Cancers (Basel). 2020 Dec 07;12(12):. (PMID: 33297357); PLoS One. 2014 Feb 19;9(2):e87357. (PMID: 24586270) |
| Grant Information: | Fonds de Recherche du Québec - Santé Fonds de Recherche du Québec - Santé; IVADO IVADO |
| Substance Nomenclature: | 0 (B7-H1 Antigen); 0 (CD274 protein, human) |
| Entry Date(s): | Date Created: 20250506 Date Completed: 20250507 Latest Revision: 20250509 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC12056990 |
| DOI: | 10.1186/s12967-025-06487-2 |
| PMID: | 40329352 |
| Database: | MEDLINE |
Journal Article