Deep learning-based quantification of tumor-infiltrating lymphocytes as a prognostic indicator in nasopharyngeal carcinoma: multicohort findings

T Lu; F Xie; Y Hu; S Zhan; F Zhong; J Chen; J Pan; X Gong; Z Liu; C Huang; C Xie; Q Guo; M L K Chua; J Li

doi:10.1016/j.esmoop.2025.105494

Deep learning-based quantification of tumor-infiltrating lymphocytes as a prognostic indicator in nasopharyngeal carcinoma: multicohort findings

ESMO Open. 2025 Jul 3;10(7):105494. doi: 10.1016/j.esmoop.2025.105494. Online ahead of print.

Authors

T Lu¹, F Xie², Y Hu³, S Zhan⁴, F Zhong⁵, J Chen⁶, J Pan⁷, X Gong⁸, Z Liu⁹, C Huang⁹, C Xie³, Q Guo¹⁰, M L K Chua¹¹, J Li¹²

Affiliations

¹ NHC Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Medical College, Nanchang University, Nanchang, China; JXHC Key Laboratory of Tumour Metastasis, Jiangxi Cancer Hospital, Nanchang, China; JXHC Key Laboratory of Tumor Microenvironment and Immunoregulation, Jiangxi Cancer Hospital, Nanchang, China.
² Department of Radiology, Ganzhou Cancer Hospital, Ganzhou, China.
³ State Key Laboratory of Oncology in South China, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China; Department of Radiation Oncology, Sun Yat-sen University Cancer Center, Guangzhou, China.
⁴ Department of Radiation Oncology, Fujian Medical University Cancer Hospital & Fujian Cancer Hospital, Fuzhou, China; Department of Radiation Oncology, Fuqing City Hospital Affiliated to Fujian Medical University, Fuzhou, China.
⁵ NHC Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Medical College, Nanchang University, Nanchang, China.
⁶ NHC Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Department of Pharmacology, School of Pharmacy, Jiangxi Medical College, Nanchang University, Nanchang, China.
⁷ Department of Radiation Oncology, Fujian Medical University Cancer Hospital & Fujian Cancer Hospital, Fuzhou, China.
⁸ NHC Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Medical College, Nanchang University, Nanchang, China; JXHC Key Laboratory of Tumour Metastasis, Jiangxi Cancer Hospital, Nanchang, China.
⁹ Department of Pathology, Jiangxi Clinical Research Center for Cancer, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China.
¹⁰ Department of Radiation Oncology, Fujian Medical University Cancer Hospital & Fujian Cancer Hospital, Fuzhou, China. Electronic address: guoqiaojuan@163.com.
¹¹ Department of Head and Neck and Thoracic Cancers, Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore; Division of Medical Sciences, National Cancer Centre Singapore, Singapore, Singapore; Oncology Academic Programme, Duke-NUS Medical School, Singapore, Singapore. Electronic address: gmsclkm@nus.edu.sg.
¹² NHC Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma, Jiangxi Cancer Hospital, The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Medical College, Nanchang University, Nanchang, China; JXHC Key Laboratory of Tumour Metastasis, Jiangxi Cancer Hospital, Nanchang, China. Electronic address: lijingao@hotmail.com.

PMID: 40614660
DOI: 10.1016/j.esmoop.2025.105494

Abstract

Background: Nasopharyngeal carcinoma (NPC) features a tumor-immune microenvironment rich in tumor-infiltrating lymphocytes (TILs), important for prognosis but labor-intensive to quantify. This study evaluates a deep learning model to quantify TILs (TIL_DL) in hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) of NPC and explores the association of TIL_DL percentage with patient outcomes and response to immune checkpoint blockade (ICB).

Methods: We retrospectively analyzed 435 nonmetastatic NPC patients from two centers, divided into a training cohort (n = 220) and a validation cohort (n = 215). An additional cohort of de novo metastatic NPC patients receiving ICB therapy (n = 63) was included. The deep learning model calculated TIL_DL percentages from H&E-stained WSIs. Correlations between TIL_DL percentages and immunohistochemistry (IHC)-derived TIL densities were assessed. Survival analyses evaluated their prognostic significance.

Results: TIL_DL percentages showed strong correlations with IHC-derived TIL densities (CD3+ T cells R = 0.46, CD8+ T cells R = 0.33, CD20+ B cells R = 0.57; all P < 0.001). Higher TIL_DL percentages (median ≥45.7%) were associated with better 5-year disease-free survival (DFS) and overall survival (OS) in both training (DFS: 80.6% versus 62.5%, P = 0.016; OS: 84.4% versus 71.8%, P = 0.025) and validation cohorts (DFS: 87.3% versus 74.3%, P = 0.016; OS: 93.7% versus 82.6%, P = 0.010). In the ICB-treated metastatic cohort, higher TIL_DL percentages predicted better 3-year progression-free survival (PFS: 40.5% versus 25.0%, P = 0.022). Multivariate analyses confirmed TIL_DL percentage as an independent prognostic factor in both settings.

Conclusions: The TIL_DL percentage derived from H&E-stained WSIs effectively stratifies risk in nonmetastatic NPC and may serve as a biomarker in metastatic NPC treated with ICB, aiding in patient selection for individualized treatment.

Keywords: deep learning; digital pathology images; nasopharyngeal carcinoma; prognosis; tumor-infiltrating lymphocytes.