File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Article: Radiomics Model to Predict Early Progression of Nonmetastatic Nasopharyngeal Carcinoma after Intensity Modulation Radiation Therapy: A Multicenter Study

TitleRadiomics Model to Predict Early Progression of Nonmetastatic Nasopharyngeal Carcinoma after Intensity Modulation Radiation Therapy: A Multicenter Study
Authors
Issue Date2019
PublisherRadiological Society of North America, Inc.. The Journal's web site is located at https://pubs.rsna.org/artificial-intelligence
Citation
Radiology: Artificial Intelligence, 2019, v. 1 n. 4, p. e180075 How to Cite?
AbstractA machine-learning radiomic model based on pretreatment MRI findings has potential in the identification of patients with nonmetastatic nasopharyngeal carcinoma who are at risk for early disease progression after primary treatment. Purpose To examine the prognostic value of a machine learning model trained with pretreatment MRI radiomic features in the assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC) who are at risk for 3-year disease progression after intensity-modulated radiation therapy and to explain the radiomics features in the model. Materials and Methods A total of 277 patients with nonmetastatic NPC admitted between March 2008 and December 2014 at two imaging centers were retrospectively reviewed. Patients were allocated to a discovery or validation cohort based on where they underwent MRI (discovery cohort, n = 217; validation cohort, n = 60). A total of 525 radiomics features extracted from contrast material–enhanced T1- or T2-weighted MRI studies and five clinical features were subjected to radiomic machine learning modeling to predict 3-year disease progression. Feature selection was performed by analyzing robustness to resampling, reproducibility between observers, and redundancy. Features for the final model were selected with Kaplan-Meier analysis and the log-rank test. A support vector machine was used as the classifier for the model. To interpret the pattern learned from the model, Shapley additive explanations (SHAP) was applied. Results The final model yielded an area under the receiver operating characteristic curve of 0.80 in both the discovery (95% bootstrap confidence interval: 0.80, 0.81) and independent validation (95% bootstrap confidence interval: 0.73, 0.89) cohorts. Analysis with SHAP revealed that tumor shape sphericity, first-order mean absolute deviation, T stage, and overall stage were important factors in 3-year disease progression. Conclusion These results add to the growing evidence of the role of radiomics in the assessment of NPC. By using explanatory techniques, such as SHAP, the complex interaction of features learned by the model may be understood.
Persistent Identifierhttp://hdl.handle.net/10722/276138
ISSN

 

DC FieldValueLanguage
dc.contributor.authorDu, R-
dc.contributor.authorLee, VHF-
dc.contributor.authorYuan, H-
dc.contributor.authorLam, KO-
dc.contributor.authorPang, HMH-
dc.contributor.authorChen, Y-
dc.contributor.authorLam, EYM-
dc.contributor.authorKhong, PL-
dc.contributor.authorLee, WMA-
dc.contributor.authorKwong, DLW-
dc.contributor.authorVardhanabhuti, V-
dc.date.accessioned2019-09-10T02:56:43Z-
dc.date.available2019-09-10T02:56:43Z-
dc.date.issued2019-
dc.identifier.citationRadiology: Artificial Intelligence, 2019, v. 1 n. 4, p. e180075-
dc.identifier.issn2638-6100-
dc.identifier.urihttp://hdl.handle.net/10722/276138-
dc.description.abstractA machine-learning radiomic model based on pretreatment MRI findings has potential in the identification of patients with nonmetastatic nasopharyngeal carcinoma who are at risk for early disease progression after primary treatment. Purpose To examine the prognostic value of a machine learning model trained with pretreatment MRI radiomic features in the assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC) who are at risk for 3-year disease progression after intensity-modulated radiation therapy and to explain the radiomics features in the model. Materials and Methods A total of 277 patients with nonmetastatic NPC admitted between March 2008 and December 2014 at two imaging centers were retrospectively reviewed. Patients were allocated to a discovery or validation cohort based on where they underwent MRI (discovery cohort, n = 217; validation cohort, n = 60). A total of 525 radiomics features extracted from contrast material–enhanced T1- or T2-weighted MRI studies and five clinical features were subjected to radiomic machine learning modeling to predict 3-year disease progression. Feature selection was performed by analyzing robustness to resampling, reproducibility between observers, and redundancy. Features for the final model were selected with Kaplan-Meier analysis and the log-rank test. A support vector machine was used as the classifier for the model. To interpret the pattern learned from the model, Shapley additive explanations (SHAP) was applied. Results The final model yielded an area under the receiver operating characteristic curve of 0.80 in both the discovery (95% bootstrap confidence interval: 0.80, 0.81) and independent validation (95% bootstrap confidence interval: 0.73, 0.89) cohorts. Analysis with SHAP revealed that tumor shape sphericity, first-order mean absolute deviation, T stage, and overall stage were important factors in 3-year disease progression. Conclusion These results add to the growing evidence of the role of radiomics in the assessment of NPC. By using explanatory techniques, such as SHAP, the complex interaction of features learned by the model may be understood.-
dc.languageeng-
dc.publisherRadiological Society of North America, Inc.. The Journal's web site is located at https://pubs.rsna.org/artificial-intelligence-
dc.relation.ispartofRadiology: Artificial Intelligence-
dc.titleRadiomics Model to Predict Early Progression of Nonmetastatic Nasopharyngeal Carcinoma after Intensity Modulation Radiation Therapy: A Multicenter Study-
dc.typeArticle-
dc.identifier.emailLee, VHF: vhflee@hku.hk-
dc.identifier.emailLam, KO: lamkaon@hku.hk-
dc.identifier.emailPang, HMH: herbpang@hku.hk-
dc.identifier.emailLam, EYM: elam@eee.hku.hk-
dc.identifier.emailKhong, PL: plkhong@hku.hk-
dc.identifier.emailLee, WMA: awmlee@hkucc.hku.hk-
dc.identifier.emailKwong, DLW: dlwkwong@hku.hk-
dc.identifier.emailVardhanabhuti, V: varv@hku.hk-
dc.identifier.authorityLee, VHF=rp00264-
dc.identifier.authorityLam, KO=rp01501-
dc.identifier.authorityPang, HMH=rp01857-
dc.identifier.authorityLam, EYM=rp00131-
dc.identifier.authorityKhong, PL=rp00467-
dc.identifier.authorityLee, WMA=rp02056-
dc.identifier.authorityKwong, DLW=rp00414-
dc.identifier.authorityVardhanabhuti, V=rp01900-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1148/ryai.2019180075-
dc.identifier.hkuros302995-
dc.identifier.volume1-
dc.identifier.issue4-
dc.identifier.spagee180075-
dc.identifier.epagee180075-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats