He An1, Yiang Wang1, Esther M F Wong2, Shanshan Lyu3, Lujun Han4, Jose A U Perucho1, Peng Cao1, Elaine Y P Lee5. 1. Department of Diagnostic Radiology, Queen Mary Hospital, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, Hong Kong SAR. 2. Department of Radiology, Pamela Youde Nethersole Eastern Hospital, Hong Kong, Hong Kong SAR. 3. Department of Pathology, Guangdong Provincial People's Hospital/Guangdong Academy of Medical Sciences, Guangzhou, China. 4. Department of Diagnostic Radiology, Sun Yat-sen University Cancer Center, Guangzhou, China. 5. Department of Diagnostic Radiology, Queen Mary Hospital, Li Ka Shing Faculty of Medicine, University of Hong Kong, Hong Kong, Hong Kong SAR. eyplee77@hku.hk.
Abstract
OBJECTIVES: 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. KEY POINTS: • A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.
OBJECTIVES: 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. KEY POINTS: • A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.
Authors: Robert J Morgan; Deborah K Armstrong; Ronald D Alvarez; Jamie N Bakkum-Gamez; Kian Behbakht; Lee-May Chen; Larry Copeland; Marta Ann Crispens; Maria DeRosa; Oliver Dorigo; David M Gershenson; Heidi J Gray; Ardeshir Hakam; Laura J Havrilesky; Carolyn Johnston; Shashikant Lele; Lainie Martin; Ursula A Matulonis; David M O'Malley; Richard T Penson; Sanja Percac-Lima; Mario Pineda; Steven C Plaxe; Matthew A Powell; Elena Ratner; Steven W Remmenga; Peter G Rose; Paul Sabbatini; Joseph T Santoso; Theresa L Werner; Jennifer Burns; Miranda Hughes Journal: J Natl Compr Canc Netw Date: 2016-09 Impact factor: 11.908
Authors: Hebert Alberto Vargas; Harini Veeraraghavan; Maura Micco; Stephanie Nougaret; Yulia Lakhman; Andreas A Meier; Ramon Sosa; Robert A Soslow; Douglas A Levine; Britta Weigelt; Carol Aghajanian; Hedvig Hricak; Joseph Deasy; Alexandra Snyder; Evis Sala Journal: Eur Radiol Date: 2017-03-13 Impact factor: 5.315
Authors: Lien N Hoang; Susanna Zachara; Anita Soma; Martin Köbel; Cheng-Han Lee; Jessica N McAlpine; David Huntsman; Thomas Thomson; Dirk van Niekerk; Naveena Singh; C Blake Gilks Journal: Int J Gynecol Pathol Date: 2015-11 Impact factor: 2.762
Authors: T Sugiyama; T Kamura; J Kigawa; N Terakawa; Y Kikuchi; T Kita; M Suzuki; I Sato; K Taguchi Journal: Cancer Date: 2000-06-01 Impact factor: 6.860
Authors: Viviane Hess; Roger A'Hern; Nazar Nasiri; D Michael King; Peter R Blake; Desmond P J Barton; John H Shepherd; T Ind; J Bridges; K Harrington; Stanley B Kaye; Martin E Gore Journal: J Clin Oncol Date: 2004-03-15 Impact factor: 44.544