File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: CT texture analysis in histological classification of epithelial ovarian carcinoma

TitleCT texture analysis in histological classification of epithelial ovarian carcinoma
Authors
KeywordsX-ray computed tomography
Epithelial ovarian carcinoma
Female
Issue Date2021
PublisherSpringer Verlag. The Journal's web site is located at http://link.springer.de/link/service/journals/00330/index.htm
Citation
European Radiology, 2021, v. 31 n. 7, p. 5050-5058 How to Cite?
AbstractObjectives: The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC). Methods: Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features’ reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson’s correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features. Results: HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464). Conclusion: CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features.
Persistent Identifierhttp://hdl.handle.net/10722/301480
ISSN
2023 Impact Factor: 4.7
2023 SCImago Journal Rankings: 1.656
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorAn, H-
dc.contributor.authorWANG, Y-
dc.contributor.authorWong, EMF-
dc.contributor.authorLyu, S-
dc.contributor.authorHan, L-
dc.contributor.authorPerucho, JAU-
dc.contributor.authorCao, P-
dc.contributor.authorLee, EYP-
dc.date.accessioned2021-07-27T08:11:42Z-
dc.date.available2021-07-27T08:11:42Z-
dc.date.issued2021-
dc.identifier.citationEuropean Radiology, 2021, v. 31 n. 7, p. 5050-5058-
dc.identifier.issn0938-7994-
dc.identifier.urihttp://hdl.handle.net/10722/301480-
dc.description.abstractObjectives: The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC). Methods: Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features’ reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson’s correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features. Results: HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464). Conclusion: CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features.-
dc.languageeng-
dc.publisherSpringer Verlag. The Journal's web site is located at http://link.springer.de/link/service/journals/00330/index.htm-
dc.relation.ispartofEuropean Radiology-
dc.rightsThis is a post-peer-review, pre-copyedit version of an article published in [insert journal title]. The final authenticated version is available online at: https://doi.org/[insert DOI]-
dc.subjectX-ray computed tomography-
dc.subjectEpithelial ovarian carcinoma-
dc.subjectFemale-
dc.titleCT texture analysis in histological classification of epithelial ovarian carcinoma-
dc.typeArticle-
dc.identifier.emailPerucho, JAU: peruchoj@hku.hk-
dc.identifier.emailCao, P: caopeng1@hku.hk-
dc.identifier.emailLee, EYP: eyplee77@hku.hk-
dc.identifier.authorityCao, P=rp02474-
dc.identifier.authorityLee, EYP=rp01456-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/s00330-020-07565-3-
dc.identifier.pmid33409777-
dc.identifier.scopuseid_2-s2.0-85099019239-
dc.identifier.hkuros323361-
dc.identifier.volume31-
dc.identifier.issue7-
dc.identifier.spage5050-
dc.identifier.epage5058-
dc.identifier.isiWOS:000605578600028-
dc.publisher.placeGermany-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats