Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images
Background and aimsThe levels of M2 macrophages are significantly associated with the prognosis of hepatocellular carcinoma (HCC), however, current detection methods in clinical settings remain challenging. Our study aims to develop a weakly supervised artificial intelligence model using globally la...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-12-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2024.1474155/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850132136457142272 |
|---|---|
| author | Huiyuan Tian Yongshao Tian Dujuan Li Minfan Zhao Qiankun Luo Lingfei Kong Tao Qin |
| author_facet | Huiyuan Tian Yongshao Tian Dujuan Li Minfan Zhao Qiankun Luo Lingfei Kong Tao Qin |
| author_sort | Huiyuan Tian |
| collection | DOAJ |
| description | Background and aimsThe levels of M2 macrophages are significantly associated with the prognosis of hepatocellular carcinoma (HCC), however, current detection methods in clinical settings remain challenging. Our study aims to develop a weakly supervised artificial intelligence model using globally labeled histological images, to predict M2 macrophage levels and forecast the prognosis of HCC patients by integrating clinical features.MethodsCIBERSORTx was used to calculate M2 macrophage abundance. We developed a slide-level, weakly-supervised clustering method for Whole Slide Images (WSIs) by integrating Masked Autoencoders (MAE) with ResNet-32t to predict M2 macrophage abundance.ResultsWe developed an MAE-ResNet model to predict M2 macrophage levels using WSIs. In the testing dataset, the area under the curve (AUC) (95% CI) was 0.73 (0.59-0.87). We constructed a Cox regression model showing that the predicted probabilities of M2 macrophage abundance were negatively associated with the prognosis of HCC (HR=1.89, p=0.031). Furthermore, we incorporated clinical data, screened variables using Lasso regression, and built the comprehensive prediction model that better predicted prognosis. (HR=2.359, p=0.001).ConclusionOur models effectively predicted M2 macrophage levels and HCC prognosis. The findings suggest that our models offer a novel method for determining biomarker levels and forecasting prognosis, eliminating additional clinical tests, thereby delivering substantial clinical benefits. |
| format | Article |
| id | doaj-art-e1d6e27ce824477c9c0d1963fd5d3233 |
| institution | OA Journals |
| issn | 2234-943X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-e1d6e27ce824477c9c0d1963fd5d32332025-08-20T02:32:16ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-12-011410.3389/fonc.2024.14741551474155Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological imagesHuiyuan Tian0Yongshao Tian1Dujuan Li2Minfan Zhao3Qiankun Luo4Lingfei Kong5Tao Qin6Department of Scientific Research and Foreign Affairs, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Zhengzhou, Henan, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, ChinaDepartment of Pathology, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Zhengzhou, Henan, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, ChinaDepartment of Hepatobiliary and Pancreatic Surgery, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Zhengzhou, Henan, ChinaDepartment of Pathology, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Zhengzhou, Henan, ChinaDepartment of Hepatobiliary and Pancreatic Surgery, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Zhengzhou, Henan, ChinaBackground and aimsThe levels of M2 macrophages are significantly associated with the prognosis of hepatocellular carcinoma (HCC), however, current detection methods in clinical settings remain challenging. Our study aims to develop a weakly supervised artificial intelligence model using globally labeled histological images, to predict M2 macrophage levels and forecast the prognosis of HCC patients by integrating clinical features.MethodsCIBERSORTx was used to calculate M2 macrophage abundance. We developed a slide-level, weakly-supervised clustering method for Whole Slide Images (WSIs) by integrating Masked Autoencoders (MAE) with ResNet-32t to predict M2 macrophage abundance.ResultsWe developed an MAE-ResNet model to predict M2 macrophage levels using WSIs. In the testing dataset, the area under the curve (AUC) (95% CI) was 0.73 (0.59-0.87). We constructed a Cox regression model showing that the predicted probabilities of M2 macrophage abundance were negatively associated with the prognosis of HCC (HR=1.89, p=0.031). Furthermore, we incorporated clinical data, screened variables using Lasso regression, and built the comprehensive prediction model that better predicted prognosis. (HR=2.359, p=0.001).ConclusionOur models effectively predicted M2 macrophage levels and HCC prognosis. The findings suggest that our models offer a novel method for determining biomarker levels and forecasting prognosis, eliminating additional clinical tests, thereby delivering substantial clinical benefits.https://www.frontiersin.org/articles/10.3389/fonc.2024.1474155/fulldeep learningmasked autoencoderscomputational pathologyliver cancertumor microenvironment |
| spellingShingle | Huiyuan Tian Yongshao Tian Dujuan Li Minfan Zhao Qiankun Luo Lingfei Kong Tao Qin Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images Frontiers in Oncology deep learning masked autoencoders computational pathology liver cancer tumor microenvironment |
| title | Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images |
| title_full | Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images |
| title_fullStr | Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images |
| title_full_unstemmed | Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images |
| title_short | Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images |
| title_sort | artificial intelligence model predicts m2 macrophage levels and hcc prognosis with only globally labeled pathological images |
| topic | deep learning masked autoencoders computational pathology liver cancer tumor microenvironment |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2024.1474155/full |
| work_keys_str_mv | AT huiyuantian artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT yongshaotian artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT dujuanli artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT minfanzhao artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT qiankunluo artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT lingfeikong artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages AT taoqin artificialintelligencemodelpredictsm2macrophagelevelsandhccprognosiswithonlygloballylabeledpathologicalimages |