Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer
Abstract Tumor-infiltrating lymphocytes (TIL) have been suggested as an important prognostic marker in colorectal cancer, but assessment usually requires additional tissue processing and interpretational efforts. The aim of this study is to assess the clinical significance of artificial intelligence...
Main Authors: | , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-11-01
|
Series: | npj Precision Oncology |
Online Access: | https://doi.org/10.1038/s41698-023-00470-0 |
_version_ | 1797454114579283968 |
---|---|
author | Yoojoo Lim Songji Choi Hyeon Jeong Oh Chanyoung Kim Sanghoon Song Sukjun Kim Heon Song Seonwook Park Ji-Won Kim Jin Won Kim Jee Hyun Kim Minsu Kang Sung-Bum Kang Duck-Woo Kim Heung-Kwon Oh Hye Seung Lee Keun-Wook Lee |
author_facet | Yoojoo Lim Songji Choi Hyeon Jeong Oh Chanyoung Kim Sanghoon Song Sukjun Kim Heon Song Seonwook Park Ji-Won Kim Jin Won Kim Jee Hyun Kim Minsu Kang Sung-Bum Kang Duck-Woo Kim Heung-Kwon Oh Hye Seung Lee Keun-Wook Lee |
author_sort | Yoojoo Lim |
collection | DOAJ |
description | Abstract Tumor-infiltrating lymphocytes (TIL) have been suggested as an important prognostic marker in colorectal cancer, but assessment usually requires additional tissue processing and interpretational efforts. The aim of this study is to assess the clinical significance of artificial intelligence (AI)-powered spatial TIL analysis using only a hematoxylin and eosin (H&E)-stained whole-slide image (WSI) for the prediction of prognosis in stage II–III colon cancer treated with surgery and adjuvant therapy. In this retrospective study, we used Lunit SCOPE IO, an AI-powered H&E WSI analyzer, to assess intratumoral TIL (iTIL) and tumor-related stromal TIL (sTIL) densities from WSIs of 289 patients. The patients with confirmed recurrences had significantly lower sTIL densities (mean sTIL density 630.2/mm2 in cases with confirmed recurrence vs. 1021.3/mm2 in no recurrence, p < 0.001). Additionally, significantly higher recurrence rates were observed in patients having sTIL or iTIL in the lower quartile groups. Risk groups defined as high-risk (both iTIL and sTIL in the lowest quartile groups), low-risk (sTIL higher than the median), or intermediate-risk (not high- or low-risk) were predictive of recurrence and were independently associated with clinical outcomes after adjusting for other clinical factors. AI-powered TIL analysis can provide prognostic information in stage II/III colon cancer in a practical manner. |
first_indexed | 2024-03-09T15:32:35Z |
format | Article |
id | doaj.art-d794375a19344b5aa5231f4e171e5936 |
institution | Directory Open Access Journal |
issn | 2397-768X |
language | English |
last_indexed | 2024-03-09T15:32:35Z |
publishDate | 2023-11-01 |
publisher | Nature Portfolio |
record_format | Article |
series | npj Precision Oncology |
spelling | doaj.art-d794375a19344b5aa5231f4e171e59362023-11-26T12:12:34ZengNature Portfolionpj Precision Oncology2397-768X2023-11-01711810.1038/s41698-023-00470-0Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancerYoojoo Lim0Songji Choi1Hyeon Jeong Oh2Chanyoung Kim3Sanghoon Song4Sukjun Kim5Heon Song6Seonwook Park7Ji-Won Kim8Jin Won Kim9Jee Hyun Kim10Minsu Kang11Sung-Bum Kang12Duck-Woo Kim13Heung-Kwon Oh14Hye Seung Lee15Keun-Wook Lee16LunitDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Pathology, Seoul National University Bundang HospitalDepartment of Pathology, Seoul National University Bundang HospitalLunitLunitLunitLunitDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Surgery, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Surgery, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Surgery, Seoul National University Bundang Hospital, Seoul National University College of MedicineDepartment of Pathology, Seoul National University Hospital, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of MedicineAbstract Tumor-infiltrating lymphocytes (TIL) have been suggested as an important prognostic marker in colorectal cancer, but assessment usually requires additional tissue processing and interpretational efforts. The aim of this study is to assess the clinical significance of artificial intelligence (AI)-powered spatial TIL analysis using only a hematoxylin and eosin (H&E)-stained whole-slide image (WSI) for the prediction of prognosis in stage II–III colon cancer treated with surgery and adjuvant therapy. In this retrospective study, we used Lunit SCOPE IO, an AI-powered H&E WSI analyzer, to assess intratumoral TIL (iTIL) and tumor-related stromal TIL (sTIL) densities from WSIs of 289 patients. The patients with confirmed recurrences had significantly lower sTIL densities (mean sTIL density 630.2/mm2 in cases with confirmed recurrence vs. 1021.3/mm2 in no recurrence, p < 0.001). Additionally, significantly higher recurrence rates were observed in patients having sTIL or iTIL in the lower quartile groups. Risk groups defined as high-risk (both iTIL and sTIL in the lowest quartile groups), low-risk (sTIL higher than the median), or intermediate-risk (not high- or low-risk) were predictive of recurrence and were independently associated with clinical outcomes after adjusting for other clinical factors. AI-powered TIL analysis can provide prognostic information in stage II/III colon cancer in a practical manner.https://doi.org/10.1038/s41698-023-00470-0 |
spellingShingle | Yoojoo Lim Songji Choi Hyeon Jeong Oh Chanyoung Kim Sanghoon Song Sukjun Kim Heon Song Seonwook Park Ji-Won Kim Jin Won Kim Jee Hyun Kim Minsu Kang Sung-Bum Kang Duck-Woo Kim Heung-Kwon Oh Hye Seung Lee Keun-Wook Lee Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer npj Precision Oncology |
title | Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
title_full | Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
title_fullStr | Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
title_full_unstemmed | Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
title_short | Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
title_sort | artificial intelligence powered spatial analysis of tumor infiltrating lymphocytes for prediction of prognosis in resected colon cancer |
url | https://doi.org/10.1038/s41698-023-00470-0 |
work_keys_str_mv | AT yoojoolim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT songjichoi artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT hyeonjeongoh artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT chanyoungkim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT sanghoonsong artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT sukjunkim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT heonsong artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT seonwookpark artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT jiwonkim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT jinwonkim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT jeehyunkim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT minsukang artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT sungbumkang artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT duckwookim artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT heungkwonoh artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT hyeseunglee artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer AT keunwooklee artificialintelligencepoweredspatialanalysisoftumorinfiltratinglymphocytesforpredictionofprognosisinresectedcoloncancer |