biostudies-literatureMillward JAustin Medical Research FoundationAustralian National Health and Medical Research Council298https://www.ebi.ac.uk/biostudies/studies/S-EPMC11892243biostudies-literatureUnknown23(1)<h4>Background</h4>The presence of tumour-infiltrating lymphocytes (TILs) is a well-established prognostic biomarker across multiple cancer types, with higher TIL counts being associated with lower recurrence rates and improved patient survival. We aimed to examine whether an automated intraepithelial TIL (iTIL) assessment could stratify patients by risk, with the ability to generalise across independent patient cohorts, using routine H&E slides of colorectal cancer (CRC). To our knowledge, no other existing fully automated iTIL system has demonstrated this capability.<h4>Methods</h4>An automated method employing deep neural networks was developed to enumerate iTILs in H&E slides of CRC. The method was applied to a Stage III discovery cohort (n = 353) to identify an optimal threshold of 17Journal of translational medicineAutomated deep learning-based assessment of tumour-infiltrating lymphocyte density determines prognosis in colorectal cancer.PMC11892243Austin Medical Research Foundation1185513Williams DSSieber OMMouradov DHe ZNibali AWard RLMillward JHawkins NJMielke LATran KGill AJChou AfalseAutomated deep learning-based assessment of tumour-infiltrating lymphocyte density determines prognosis in colorectal cancer.<h4>Background</h4>The presence of tumour-infiltrating lymphocytes (TILs) is a well-established prognostic biomarker across multiple cancer types, with higher TIL counts being associated with lower recurrence rates and improved patient survival. We aimed to examine whether an automated intraepithelial TIL (iTIL) assessment could stratify patients by risk, with the ability to generalise across independent patient cohorts, using routine H&E slides of colorectal cancer (CRC). To our knowledge, no other existing fully automated iTIL system has demonstrated this capability.<h4>Methods</h4>An automated method employing deep neural networks was developed to enumerate iTILs in H&E slides of CRC. The method was applied to a Stage III discovery cohort (n = 353) to identify an optimal threshold of 172025-01-01T00:00:00Z2025 Mar2025-04-26T02:53:20.485Z2025-04-06T10:35:47.023ZS-EPMC118922434006535410.1186/s12967-025-06254-3