File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Article: Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma

TitleComputed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma
Authors
KeywordsEsophageal squamous cell carcinoma
Neoadjuvant chemoradiotherapy
Deep learning
Radiomics
Computed tomography
Issue Date2021
PublisherElsevier Ireland Ltd. The Journal's web site is located at http://www.elsevier.com/locate/radonc
Citation
Radiotherapy & Oncology, 2021, v. 154, p. 6-13 How to Cite?
AbstractBackground: Deep learning is promising to predict treatment response. We aimed to evaluate and validate the predictive performance of the CT-based model using deep learning features for predicting pathologic complete response to neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC). Materials and methods: Patients were retrospectively enrolled between April 2007 and December 2018 from two institutions. We extracted deep learning features of six pre-trained convolutional neural networks, respectively, from pretreatment CT images in the training cohort (n = 161). Support vector machine was adopted as the classifier. Validation was performed in an external testing cohort (n = 70). We assessed the performance using the area under the receiver operating characteristics curve (AUC) and selected an optimal model, which was compared with a radiomics model developed from the training cohort. A clinical model consisting of clinical factors only was also built for baseline comparison. We further conducted a radiogenomics analysis using gene expression profiles to reveal underlying biology associated with radiological prediction. Results: The optimal model with features extracted from ResNet50 achieved an AUC and accuracy of 0.805 (95% CI, 0.696–0.913) and 77.1% (65.6%-86.3%) in the testing cohort, compared with 0.725 (0.605–0.846)) and 67.1% (54.9%-77.9%) for the radiomics model. All the radiological models showed better predictive performance than the clinical model. Radiogenomics analysis suggested a potential association mainly with WNT signaling pathway and tumor microenvironment. Conclusions: The novel and noninvasive deep learning approach could provide efficient and accurate prediction of treatment response to nCRT in ESCC, and benefit clinical decision making of therapeutic strategy.
Persistent Identifierhttp://hdl.handle.net/10722/287952
ISSN
2023 Impact Factor: 4.9
2023 SCImago Journal Rankings: 1.702
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHu, Y-
dc.contributor.authorXIE, C-
dc.contributor.authorYang, H-
dc.contributor.authorHo, JWK-
dc.contributor.authorWen, J-
dc.contributor.authorHan, L-
dc.contributor.authorLam, KO-
dc.contributor.authorWong, IYH-
dc.contributor.authorLaw, SYK-
dc.contributor.authorChiu, KWH-
dc.contributor.authorVardhanabhuti, V-
dc.contributor.authorFu, J-
dc.date.accessioned2020-10-05T12:05:39Z-
dc.date.available2020-10-05T12:05:39Z-
dc.date.issued2021-
dc.identifier.citationRadiotherapy & Oncology, 2021, v. 154, p. 6-13-
dc.identifier.issn0167-8140-
dc.identifier.urihttp://hdl.handle.net/10722/287952-
dc.description.abstractBackground: Deep learning is promising to predict treatment response. We aimed to evaluate and validate the predictive performance of the CT-based model using deep learning features for predicting pathologic complete response to neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC). Materials and methods: Patients were retrospectively enrolled between April 2007 and December 2018 from two institutions. We extracted deep learning features of six pre-trained convolutional neural networks, respectively, from pretreatment CT images in the training cohort (n = 161). Support vector machine was adopted as the classifier. Validation was performed in an external testing cohort (n = 70). We assessed the performance using the area under the receiver operating characteristics curve (AUC) and selected an optimal model, which was compared with a radiomics model developed from the training cohort. A clinical model consisting of clinical factors only was also built for baseline comparison. We further conducted a radiogenomics analysis using gene expression profiles to reveal underlying biology associated with radiological prediction. Results: The optimal model with features extracted from ResNet50 achieved an AUC and accuracy of 0.805 (95% CI, 0.696–0.913) and 77.1% (65.6%-86.3%) in the testing cohort, compared with 0.725 (0.605–0.846)) and 67.1% (54.9%-77.9%) for the radiomics model. All the radiological models showed better predictive performance than the clinical model. Radiogenomics analysis suggested a potential association mainly with WNT signaling pathway and tumor microenvironment. Conclusions: The novel and noninvasive deep learning approach could provide efficient and accurate prediction of treatment response to nCRT in ESCC, and benefit clinical decision making of therapeutic strategy. -
dc.languageeng-
dc.publisherElsevier Ireland Ltd. The Journal's web site is located at http://www.elsevier.com/locate/radonc-
dc.relation.ispartofRadiotherapy & Oncology-
dc.subjectEsophageal squamous cell carcinoma-
dc.subjectNeoadjuvant chemoradiotherapy-
dc.subjectDeep learning-
dc.subjectRadiomics-
dc.subjectComputed tomography-
dc.titleComputed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma-
dc.typeArticle-
dc.identifier.emailHo, JWK: jwkho@hku.hk-
dc.identifier.emailLam, KO: lamkaon@hku.hk-
dc.identifier.emailWong, IYH: iyhwong@hku.hk-
dc.identifier.emailLaw, SYK: slaw@hku.hk-
dc.identifier.emailChiu, KWH: kwhchiu@hku.hk-
dc.identifier.emailVardhanabhuti, V: varv@hku.hk-
dc.identifier.authorityHo, JWK=rp02436-
dc.identifier.authorityLam, KO=rp01501-
dc.identifier.authorityWong, IYH=rp02293-
dc.identifier.authorityLaw, SYK=rp00437-
dc.identifier.authorityChiu, KWH=rp02074-
dc.identifier.authorityVardhanabhuti, V=rp01900-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.radonc.2020.09.014-
dc.identifier.pmid32941954-
dc.identifier.scopuseid_2-s2.0-85091670770-
dc.identifier.hkuros315268-
dc.identifier.volume154-
dc.identifier.spage6-
dc.identifier.epage13-
dc.identifier.isiWOS:000629914800019-
dc.publisher.placeIreland-
dc.identifier.issnl0167-8140-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats