A machine learning based algorithm accurately stages liver disease by quantification of arteries
Abstract A major histologic feature of cirrhosis is the loss of liver architecture with collapse of tissue and vascular changes per unit. We developed qVessel to quantify the arterial density (AD) in liver biopsies with chronic disease of varied etiology and stage. 46 needle liver biopsy samples wit...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87427-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585782989160448 |
|---|---|
| author | Zhengxin Li Xin Sun Zhimin Zhao Qiang Yang Yayun Ren Xiao Teng Dean C. S. Tai Ian R. Wanless Jörn M. Schattenberg Chenghai Liu |
| author_facet | Zhengxin Li Xin Sun Zhimin Zhao Qiang Yang Yayun Ren Xiao Teng Dean C. S. Tai Ian R. Wanless Jörn M. Schattenberg Chenghai Liu |
| author_sort | Zhengxin Li |
| collection | DOAJ |
| description | Abstract A major histologic feature of cirrhosis is the loss of liver architecture with collapse of tissue and vascular changes per unit. We developed qVessel to quantify the arterial density (AD) in liver biopsies with chronic disease of varied etiology and stage. 46 needle liver biopsy samples with chronic hepatitis B (CHB), 48 with primary biliary cholangitis (PBC) and 43 with metabolic dysfunction-associated steatotic liver disease (MASLD) were collected at the Shuguang Hospital. The METAVIR system was used to assess stage. The second harmonic generation (SHG)/two-photon images were generated from unstained slides. Collagen proportionate area (CPA) using SHG. AD was counted using qVessel (previously trained on manually labeled vessels by stained slides (CD34/a-SMA/CK19) and developed by a decision tree algorithm). As liver fibrosis progressed from F1 to F4, we observed that both AD and CPA gradually increases among the three etiologies (P < 0.05). However, at each stage of liver fibrosis, there was no significant difference in AD or CPA between CHB and PBC compared to MASLD (P > 0.05). AD and CPA performed similar diagnostic efficacy in liver cirrhosis (P > 0.05). Using the qVessel algorithm, we discovered a significant correlation between AD, CPA and METAVIR stages in all three etiologies. This suggests that AD could underpin a novel staging system. |
| format | Article |
| id | doaj-art-78d0e26b43ef47549925f8d125891ba7 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-78d0e26b43ef47549925f8d125891ba72025-01-26T12:30:54ZengNature PortfolioScientific Reports2045-23222025-01-011511810.1038/s41598-025-87427-4A machine learning based algorithm accurately stages liver disease by quantification of arteriesZhengxin Li0Xin Sun1Zhimin Zhao2Qiang Yang3Yayun Ren4Xiao Teng5Dean C. S. Tai6Ian R. Wanless7Jörn M. Schattenberg8Chenghai Liu9Gongli Hospital of Shanghai Pudong New AreaShuguang Hospital, Shanghai University of Traditional Chinese MedicineShuguang Hospital, Shanghai University of Traditional Chinese MedicineHangzhou Choutu Tech. Co., Ltd.Hangzhou Choutu Tech. Co., Ltd.Histoindex Pte. LtdHistoindex Pte. LtdDepartment of Pathology, Queen Elizabeth II Health Sciences Centre, Dalhousie UniversityDepartment of Internal Medicine II, Saarland University Medical CenterShuguang Hospital, Shanghai University of Traditional Chinese MedicineAbstract A major histologic feature of cirrhosis is the loss of liver architecture with collapse of tissue and vascular changes per unit. We developed qVessel to quantify the arterial density (AD) in liver biopsies with chronic disease of varied etiology and stage. 46 needle liver biopsy samples with chronic hepatitis B (CHB), 48 with primary biliary cholangitis (PBC) and 43 with metabolic dysfunction-associated steatotic liver disease (MASLD) were collected at the Shuguang Hospital. The METAVIR system was used to assess stage. The second harmonic generation (SHG)/two-photon images were generated from unstained slides. Collagen proportionate area (CPA) using SHG. AD was counted using qVessel (previously trained on manually labeled vessels by stained slides (CD34/a-SMA/CK19) and developed by a decision tree algorithm). As liver fibrosis progressed from F1 to F4, we observed that both AD and CPA gradually increases among the three etiologies (P < 0.05). However, at each stage of liver fibrosis, there was no significant difference in AD or CPA between CHB and PBC compared to MASLD (P > 0.05). AD and CPA performed similar diagnostic efficacy in liver cirrhosis (P > 0.05). Using the qVessel algorithm, we discovered a significant correlation between AD, CPA and METAVIR stages in all three etiologies. This suggests that AD could underpin a novel staging system.https://doi.org/10.1038/s41598-025-87427-4Machine learningArterial densityLiver fibrosisChronic liver disease. |
| spellingShingle | Zhengxin Li Xin Sun Zhimin Zhao Qiang Yang Yayun Ren Xiao Teng Dean C. S. Tai Ian R. Wanless Jörn M. Schattenberg Chenghai Liu A machine learning based algorithm accurately stages liver disease by quantification of arteries Scientific Reports Machine learning Arterial density Liver fibrosis Chronic liver disease. |
| title | A machine learning based algorithm accurately stages liver disease by quantification of arteries |
| title_full | A machine learning based algorithm accurately stages liver disease by quantification of arteries |
| title_fullStr | A machine learning based algorithm accurately stages liver disease by quantification of arteries |
| title_full_unstemmed | A machine learning based algorithm accurately stages liver disease by quantification of arteries |
| title_short | A machine learning based algorithm accurately stages liver disease by quantification of arteries |
| title_sort | machine learning based algorithm accurately stages liver disease by quantification of arteries |
| topic | Machine learning Arterial density Liver fibrosis Chronic liver disease. |
| url | https://doi.org/10.1038/s41598-025-87427-4 |
| work_keys_str_mv | AT zhengxinli amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT xinsun amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT zhiminzhao amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT qiangyang amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT yayunren amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT xiaoteng amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT deancstai amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT ianrwanless amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT jornmschattenberg amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT chenghailiu amachinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT zhengxinli machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT xinsun machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT zhiminzhao machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT qiangyang machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT yayunren machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT xiaoteng machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT deancstai machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT ianrwanless machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT jornmschattenberg machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries AT chenghailiu machinelearningbasedalgorithmaccuratelystagesliverdiseasebyquantificationofarteries |