Computed tomography-based texture assessment for the differentiation of benign, borderline, and early-stage malignant ovarian neoplasms

Sep 24, 2026

Computed tomography-based texture assessment evaluates imaging heterogeneity to distinguish ovarian tumor categories across the benign, borderline, and early-stage malignant spectrum. A retrospective cohort of 225 patients with histopathologically confirmed tumors after surgical resection was analyzed using thick 5-mm slices from regular and portal venous phases. Raw data analysis, principal and linear/nonlinear discriminant approaches were used for classification; radiologist errors were compared with MaZda texture outputs and performance was validated using a neural network classifier and ROC curves. Nonlinear discriminant analysis showed the lowest misclassification, with distinct texture parameters supporting reliable separation.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Objective

Methods

Results

Conclusions

Keywords

Introduction

Computed tomography-based texture assessment for the differentiation of benign, borderline, and early-stage malignant ovarian neoplasms Ziying He 1,*, Jia Chen2,*, Fei Yang3, Xinwei Pan 1 and Chanzhen Liu 1 Journal of International Medical Research 2023, Vol. 51(1) 1–14! The Author(s) 2023 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/03000605221150139](DOI: 10.1177/03000605221150139)[ ](DOI: 10.1177/03000605221150139)[journals.sagepub.com/home/imr](journals.sagepub.com/home/imr) Abstract Objective: This study was performed to examine the value of computed tomography-based texture assessment for characterizing different types of ovarian neoplasms. Methods: This retrospective study involved 225 patients with histopathologically confirmed ovarian tumors after surgical resection. Two different data sets of thick (5-mm) slices (during regular and portal venous phases) were analyzed. Raw data analysis, principal component analysis, linear discriminant analysis, and nonlinear discriminant analysis were performed to classify ovarian tumors. The radiologist’s misclassification rate was compared with the MaZda (texture analysis software) findings. The results were validated with the neural network classifier. Receiver operating characteristic curves were analyzed to determine the performances of different parameters. Results: Nonlinear discriminant analysis had a lower misclassification rate than the other analyses. Thirty texture parameters significantly differed between the two groups. In the training set, WavEnLH_s-3 and WavEnHL_s-3 were the optimal texture features during the regular phase, while WavEnHH_s-4 and Kurtosis seemed to be the most discriminative features during the portal venous phase. In the validation test, benign versus malignant tumors and benign versus borderline lesions were well-distinguished. Conclusions: Computed tomography-based texture features provide a useful imaging signature that may assist in differentiating benign, borderline, and early-stage ovarian cancer. 1 Department of Gynecologic Oncology, Guangxi Medical University Cancer Hospital, Nanning, China 2Department of Radiology, Guangxi Medical University Cancer Hospital, Nanning, China 3Department of Clinical Medical, Guangxi Medical University, Nanning, China *These authors contributed equally to this work. Corresponding author: Chanzhen Liu, Department of Gynecologic Oncology, Guangxi Medical University Cancer Hospital, 71 Hedi Road, Qingxiu District, Nanning 530021, China. Email: [liuchanzhen@gxmu.edu.cn](liuchanzhen@gxmu.edu.cn) Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License ([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages ([https://us.sagepub.com/en-us/nam/open-access-at-sage](https://us.sagepub.com/en-us/nam/open-access-at-sage)). Keywords Ovarian neoplasm, software, machine learning, tomography, texture, histopathology Date received: 8 October 2022; accepted: 20 December 2022 Introduction Ovarian neoplasms include benign, borderline, and cancerous lesions based on histopathology.1 Among them, borderline ovarian tumors (BOTs) show mild nuclear atypia and cell proliferation without stromal invasion, and their biological behavior falls between that of cancerous and benign tumors.2 Early-stage ovarian cancer (OC)(International Federation of Gynecology and Obstetrics [FIGO] stage I–II) has a significantly higher 5-year survival rate than other types of epithelial OC,3 and it accounts for approximately 25% of all ovarian neoplasms.4,5 Ovarian tumors are usually treated surgica

FAQs

What is the main objective of the study?

To examine the value of computed tomography-based texture assessment for characterizing different types of ovarian neoplasms.

How were the tumors classified in the study?

Thick (5-mm) CT slice data from regular and portal venous phases were analyzed using raw data analysis, principal component analysis, and linear and nonlinear discriminant analyses, with results validated by a neural network classifier.

Which analysis method achieved the best classification performance?

Nonlinear discriminant analysis produced a lower misclassification rate than the other analyses, and multiple texture parameters differed significantly between groups.

Sep 24, 2026

Uploaded by mieayamfan