File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Computed Tomographic Radiomics in Differentiating Histologic Subtypes of Epithelial Ovarian Carcinoma

TitleComputed Tomographic Radiomics in Differentiating Histologic Subtypes of Epithelial Ovarian Carcinoma
Authors
Issue Date5-Dec-2022
PublisherAmerican Medical Association
Citation
Jama Network Open, 2022, v. 5, n. 12, p. e2245141 How to Cite?
Abstract

Importance  Epithelial ovarian carcinoma is heterogeneous and classified according to the World Health Organization Tumour Classification, which is based on histologic features and molecular alterations. Preoperative prediction of the histologic subtypes could aid in clinical management and disease prognostication.

Objective  To assess the value of radiomics based on contrast-enhanced computed tomography (CT) in differentiating histologic subtypes of epithelial ovarian carcinoma in multicenter data sets.

Design, Setting, and Participants  In this diagnostic study, 665 patients with histologically confirmed epithelial ovarian carcinoma were retrospectively recruited from 4 centers (Hong Kong, Guangdong Province of China, and Seoul, South Korea) between January 1, 2012, and February 28, 2022. The patients were randomly divided into a training cohort (n = 532) and a testing cohort (n = 133) with a ratio of 8:2. This process was repeated 100 times. Tumor segmentation was manually delineated on each section of contrast-enhanced CT images to encompass the entire tumor. The Mann-Whitney U test and voted least absolute shrinkage and selection operator were performed for feature reduction and selection. Selected features were used to build the logistic regression model for differentiating high-grade serous carcinoma and non–high-grade serous carcinoma.

Exposures  Contrast-enhanced CT-based radiomics.

Main Outcomes and Measures  Intraobserver and interobserver reproducibility of tumor segmentation were measured by Dice similarity coefficients. The diagnostic efficiency of the model was assessed by receiver operating characteristic curve and area under the curve.

Results  In this study, 665 female patients (mean [SD] age, 53.6 [10.9] years) with epithelial ovarian carcinoma were enrolled and analyzed. The Dice similarity coefficients of intraobserver and interobserver were all greater than 0.80. Twenty radiomic features were selected for modeling. The areas under the curve of the logistic regression model in differentiating high-grade serous carcinoma and non–high-grade serous carcinoma were 0.837 (95% CI, 0.835-0.838) for the training cohort and 0.836 (95% CI, 0.833-0.840) for the testing cohort.

Conclusions and Relevance  In this diagnostic study, radiomic features extracted from contrast-enhanced CT were useful in the classification of histologic subtypes in epithelial ovarian carcinoma. Intraobserver and interobserver reproducibility of tumor segmentation was excellent. The proposed logistic regression model offered excellent discriminative ability among histologic subtypes.


Persistent Identifierhttp://hdl.handle.net/10722/331420
ISSN
2023 Impact Factor: 10.5
2023 SCImago Journal Rankings: 3.478
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, MD-
dc.contributor.authorPerucho, JAU-
dc.contributor.authorHu, YL-
dc.contributor.authorChoi, MH-
dc.contributor.authorHan, LJ-
dc.contributor.authorWong, EMF-
dc.contributor.authorHo, G-
dc.contributor.authorZhang, XL-
dc.contributor.authorIp, P-
dc.contributor.authorLee, EYP-
dc.date.accessioned2023-09-21T06:55:32Z-
dc.date.available2023-09-21T06:55:32Z-
dc.date.issued2022-12-05-
dc.identifier.citationJama Network Open, 2022, v. 5, n. 12, p. e2245141-
dc.identifier.issn2574-3805-
dc.identifier.urihttp://hdl.handle.net/10722/331420-
dc.description.abstract<p><strong>Importance</strong>  Epithelial ovarian carcinoma is heterogeneous and classified according to the World Health Organization Tumour Classification, which is based on histologic features and molecular alterations. Preoperative prediction of the histologic subtypes could aid in clinical management and disease prognostication.</p><p><strong>Objective</strong>  To assess the value of radiomics based on contrast-enhanced computed tomography (CT) in differentiating histologic subtypes of epithelial ovarian carcinoma in multicenter data sets.</p><p><strong>Design, Setting, and Participants</strong>  In this diagnostic study, 665 patients with histologically confirmed epithelial ovarian carcinoma were retrospectively recruited from 4 centers (Hong Kong, Guangdong Province of China, and Seoul, South Korea) between January 1, 2012, and February 28, 2022. The patients were randomly divided into a training cohort (n = 532) and a testing cohort (n = 133) with a ratio of 8:2. This process was repeated 100 times. Tumor segmentation was manually delineated on each section of contrast-enhanced CT images to encompass the entire tumor. The Mann-Whitney <em>U</em> test and voted least absolute shrinkage and selection operator were performed for feature reduction and selection. Selected features were used to build the logistic regression model for differentiating high-grade serous carcinoma and non–high-grade serous carcinoma.</p><p><strong>Exposures</strong>  Contrast-enhanced CT-based radiomics.</p><p><strong>Main Outcomes and Measures</strong>  Intraobserver and interobserver reproducibility of tumor segmentation were measured by Dice similarity coefficients. The diagnostic efficiency of the model was assessed by receiver operating characteristic curve and area under the curve.</p><p><strong>Results</strong>  In this study, 665 female patients (mean [SD] age, 53.6 [10.9] years) with epithelial ovarian carcinoma were enrolled and analyzed. The Dice similarity coefficients of intraobserver and interobserver were all greater than 0.80. Twenty radiomic features were selected for modeling. The areas under the curve of the logistic regression model in differentiating high-grade serous carcinoma and non–high-grade serous carcinoma were 0.837 (95% CI, 0.835-0.838) for the training cohort and 0.836 (95% CI, 0.833-0.840) for the testing cohort.</p><p><strong>Conclusions and Relevance</strong>  In this diagnostic study, radiomic features extracted from contrast-enhanced CT were useful in the classification of histologic subtypes in epithelial ovarian carcinoma. Intraobserver and interobserver reproducibility of tumor segmentation was excellent. The proposed logistic regression model offered excellent discriminative ability among histologic subtypes.</p>-
dc.languageeng-
dc.publisherAmerican Medical Association-
dc.relation.ispartofJama Network Open-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleComputed Tomographic Radiomics in Differentiating Histologic Subtypes of Epithelial Ovarian Carcinoma-
dc.typeArticle-
dc.identifier.doi10.1001/jamanetworkopen.2022.45141-
dc.identifier.scopuseid_2-s2.0-85143552320-
dc.identifier.volume5-
dc.identifier.issue12-
dc.identifier.spagee2245141-
dc.identifier.eissn2574-3805-
dc.identifier.isiWOS:000937072600012-
dc.identifier.issnl2574-3805-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats