File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multimodal multiphasic preoperative image-based deep-learning predicts HCC outcomes after curative surgery

TitleMultimodal multiphasic preoperative image-based deep-learning predicts HCC outcomes after curative surgery
Authors
KeywordsArtificial intelligence
Computed tomography
Deep learning
Hepatic surgery
Hepatocellular carcinoma
Issue Date2-Dec-2024
PublisherWiley
Citation
Hepatology, 2024 How to Cite?
Abstract

Background and Aims: 

HCC recurrence frequently occurs after curative surgery. Histological microvascular invasion (MVI) predicts recurrence but cannot provide preoperative prognostication, whereas clinical prediction scores have variable performances

Approach and Results: 

Recurr-NET, a multimodal multiphasic residual-network random survival forest deep-learning model incorporating preoperative CT and clinical parameters, was developed to predict HCC recurrence. Preoperative triphasic CT scans were retrieved from patients with resected histology-confirmed HCC from 4 centers in Hong Kong (internal cohort). The internal cohort was randomly divided in an 8:2 ratio into training and internal validation. External testing was performed in an independent cohort from Taiwan.

Among 1231 patients (age 62.4y, 83.1% male, 86.8% viral hepatitis, and median follow-up 65.1mo), cumulative HCC recurrence rates at years 2 and 5 were 41.8% and 56.4%, respectively. Recurr-NET achieved excellent accuracy in predicting recurrence from years 1 to 5 (internal cohort AUROC 0.770–0.857; external AUROC 0.758–0.798), significantly outperforming MVI (internal AUROC 0.518–0.590; external AUROC 0.557–0.615) and multiple clinical risk scores (ERASL-PRE, ERASL-POST, DFT, and Shim scores) (internal AUROC 0.523–0.587, external AUROC: 0.524–0.620), respectively (all p < 0.001). Recurr-NET was superior to MVI in stratifying recurrence risks at year 2 (internal: 72.5% vs. 50.0% in MVI; external: 65.3% vs. 46.6% in MVI) and year 5 (internal: 86.4% vs. 62.5% in MVI; external: 81.4% vs. 63.8% in MVI) (all p < 0.001). Recurr-NET was also superior to MVI in stratifying liver-related and all-cause mortality (all p < 0.001). The performance of Recurr-NET remained robust in subgroup analyses.

Conclusions: 

Recurr-NET accurately predicted HCC recurrence, outperforming MVI and clinical prediction scores, highlighting its potential in preoperative prognostication.


Persistent Identifierhttp://hdl.handle.net/10722/353927
ISSN
2023 Impact Factor: 12.9
2023 SCImago Journal Rankings: 5.011

 

DC FieldValueLanguage
dc.contributor.authorHui, Rex Wan-Hin-
dc.contributor.authorChiu, Keith Wan-Hang-
dc.contributor.authorLee, I-Cheng-
dc.contributor.authorWang, Chenlu-
dc.contributor.authorCheng, Ho-Ming-
dc.contributor.authorLu, Jianliang-
dc.contributor.authorMao, Xianhua-
dc.contributor.authorYu, Sarah-
dc.contributor.authorLam, Lok-Ka-
dc.contributor.authorMak, Lung-Yi-
dc.contributor.authorCheung, Tan-To-
dc.contributor.authorChia, Nam-Hung-
dc.contributor.authorCheung, Chin-Cheung-
dc.contributor.authorKan, Wai-Kuen-
dc.contributor.authorWong, Tiffany Cho-Lam-
dc.contributor.authorChan, Albert Chi-Yan-
dc.contributor.authorHuang, Yi-Hsiang-
dc.contributor.authorYuen, Man-Fung-
dc.contributor.authorYu, Philip Leung-Ho-
dc.contributor.authorSeto, Wai-Kay-
dc.date.accessioned2025-01-29T00:35:16Z-
dc.date.available2025-01-29T00:35:16Z-
dc.date.issued2024-12-02-
dc.identifier.citationHepatology, 2024-
dc.identifier.issn0270-9139-
dc.identifier.urihttp://hdl.handle.net/10722/353927-
dc.description.abstract<h3>Background and Aims: </h3><p>HCC recurrence frequently occurs after curative surgery. Histological microvascular invasion (MVI) predicts recurrence but cannot provide preoperative prognostication, whereas clinical prediction scores have variable performances</p><h3>Approach and Results: </h3><p>Recurr-NET, a multimodal multiphasic residual-network random survival forest deep-learning model incorporating preoperative CT and clinical parameters, was developed to predict HCC recurrence. Preoperative triphasic CT scans were retrieved from patients with resected histology-confirmed HCC from 4 centers in Hong Kong (internal cohort). The internal cohort was randomly divided in an 8:2 ratio into training and internal validation. External testing was performed in an independent cohort from Taiwan.</p><p>Among 1231 patients (age 62.4y, 83.1% male, 86.8% viral hepatitis, and median follow-up 65.1mo), cumulative HCC recurrence rates at years 2 and 5 were 41.8% and 56.4%, respectively. Recurr-NET achieved excellent accuracy in predicting recurrence from years 1 to 5 (internal cohort AUROC 0.770–0.857; external AUROC 0.758–0.798), significantly outperforming MVI (internal AUROC 0.518–0.590; external AUROC 0.557–0.615) and multiple clinical risk scores (ERASL-PRE, ERASL-POST, DFT, and Shim scores) (internal AUROC 0.523–0.587, external AUROC: 0.524–0.620), respectively (all p < 0.001). Recurr-NET was superior to MVI in stratifying recurrence risks at year 2 (internal: 72.5% vs. 50.0% in MVI; external: 65.3% vs. 46.6% in MVI) and year 5 (internal: 86.4% vs. 62.5% in MVI; external: 81.4% vs. 63.8% in MVI) (all p < 0.001). Recurr-NET was also superior to MVI in stratifying liver-related and all-cause mortality (all p < 0.001). The performance of Recurr-NET remained robust in subgroup analyses.</p><h3>Conclusions: </h3><p>Recurr-NET accurately predicted HCC recurrence, outperforming MVI and clinical prediction scores, highlighting its potential in preoperative prognostication.</p>-
dc.languageeng-
dc.publisherWiley-
dc.relation.ispartofHepatology-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectArtificial intelligence-
dc.subjectComputed tomography-
dc.subjectDeep learning-
dc.subjectHepatic surgery-
dc.subjectHepatocellular carcinoma-
dc.titleMultimodal multiphasic preoperative image-based deep-learning predicts HCC outcomes after curative surgery-
dc.typeArticle-
dc.identifier.doi10.1097/HEP.0000000000001180-
dc.identifier.scopuseid_2-s2.0-85211384385-
dc.identifier.eissn1527-3350-
dc.identifier.issnl0270-9139-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats