Literature DB >> 32045064

MRI-Based Machine Learning for Differentiating Borderline From Malignant Epithelial Ovarian Tumors: A Multicenter Study.

Yong'ai Li1, Junming Jian2,3, Perry J Pickhardt4, Fenghua Ma5, Wei Xia2, Haiming Li6, Rui Zhang2, Shuhui Zhao7, Songqi Cai8, Xingyu Zhao2,3, Jiayi Zhang2, Guofu Zhang5, Jingxuan Jiang9, Yan Zhang10, Keying Wang11, Guangwu Lin12, Feng Feng13, Jing Lu1, Lin Deng1, Xiaodong Wu2, Jinwei Qiang1, Xin Gao2.   

Abstract

BACKGROUND: Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT from MEOT) can impact surgical management. MRI has improved this assessment but subjective interpretation by radiologists may lead to inconsistent results.
PURPOSE: To develop and validate an objective MRI-based machine-learning (ML) assessment model for differentiating BEOT from MEOT, and compare the performance against radiologists' interpretation. STUDY TYPE: Retrospective study of eight clinical centers. POPULATION: In all, 501 women with histopathologically-confirmed BEOT (n = 165) or MEOT (n = 336) from 2010 to 2018 were enrolled. Three cohorts were constructed: a training cohort (n = 250), an internal validation cohort (n = 92), and an external validation cohort (n = 159). FIELD STRENGTH/SEQUENCE: Preoperative MRI within 2 weeks of surgery. Single- and multiparameter (MP) machine-learning assessment models were built utilizing the following four MRI sequences: T2 -weighted imaging (T2 WI), fat saturation (FS), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), and contrast-enhanced (CE)-T1 WI. ASSESSMENT: Diagnostic performance of the models was assessed for both whole tumor (WT) and solid tumor (ST) components. Assessment of the performance of the model in discriminating BEOT vs. early-stage MEOT was made. Six radiologists of varying experience also interpreted the MR images. STATISTICAL TESTS: Mann-Whitney U-test: significance of the clinical characteristics; chi-square test: difference of label; DeLong test: difference of receiver operating characteristic (ROC).
RESULTS: The MP-ST model performed better than the MP-WT model for both the internal validation cohort (area under the curve [AUC] = 0.932 vs. 0.917) and external validation cohort (AUC = 0.902 vs. 0.767). The model showed capability in discriminating BEOT vs. early-stage MEOT, with AUCs of 0.909 and 0.920, respectively. Radiologist performance was considerably poorer than both the internal (mean AUC = 0.792; range, 0.679-0.924) and external (mean AUC = 0.797; range, 0.744-0.867) validation cohorts. DATA
CONCLUSION: Performance of the MRI-based ML model was robust and superior to subjective assessment of radiologists. If our approach can be implemented in clinical practice, improved preoperative prediction could potentially lead to preserved ovarian function and fertility for some women. LEVEL OF EVIDENCE: Level 4. TECHNICAL EFFICACY: Stage 2. J. Magn. Reson. Imaging 2020;52:897-904.
© 2020 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  borderline epithelial ovarian tumor; machine learning; magnetic resonance imaging; malignant epithelial ovarian tumor; preoperative prediction

Mesh:

Year:  2020        PMID: 32045064     DOI: 10.1002/jmri.27084

Source DB:  PubMed          Journal:  J Magn Reson Imaging        ISSN: 1053-1807            Impact factor:   4.813


  11 in total

1.  Noninvasive prediction of residual disease for advanced high-grade serous ovarian carcinoma by MRI-based radiomic-clinical nomogram.

Authors:  Haiming Li; Rui Zhang; Ruimin Li; Wei Xia; Xiaojun Chen; Jiayi Zhang; Songqi Cai; Yong'ai Li; Shuhui Zhao; Jinwei Qiang; Weijun Peng; Yajia Gu; Xin Gao
Journal:  Eur Radiol       Date:  2021-04-16       Impact factor: 5.315

2.  Nomograms of Combining MRI Multisequences Radiomics and Clinical Factors for Differentiating High-Grade From Low-Grade Serous Ovarian Carcinoma.

Authors:  Cuiping Li; Hongfei Wang; Yulan Chen; Chao Zhu; Yankun Gao; Xia Wang; Jiangning Dong; Xingwang Wu
Journal:  Front Oncol       Date:  2022-06-07       Impact factor: 5.738

3.  A Nomogram Combining MRI Multisequence Radiomics and Clinical Factors for Predicting Recurrence of High-Grade Serous Ovarian Carcinoma.

Authors:  Cuiping Li; Hongfei Wang; Yulan Chen; Mengshi Fang; Chao Zhu; Yankun Gao; Jianying Li; Jiangning Dong; Xingwang Wu
Journal:  J Oncol       Date:  2022-05-04       Impact factor: 4.501

4.  Bi-parametric magnetic resonance imaging based radiomics for the identification of benign and malignant prostate lesions: cross-vendor validation.

Authors:  Xuefu Ji; Jiayi Zhang; Yuguo Tang; Wei Xia; Wei Shi; Dong He; Jie Bao; Xuedong Wei; Yuhua Huang; Yangchuan Liu; Jyh-Cheng Chen; Xin Gao
Journal:  Phys Eng Sci Med       Date:  2021-06-01

5.  Radiomics Model Based on MR Images to Discriminate Pancreatic Ductal Adenocarcinoma and Mass-Forming Chronic Pancreatitis Lesions.

Authors:  Yan Deng; Bing Ming; Ting Zhou; Jia-Long Wu; Yong Chen; Pei Liu; Ju Zhang; Shi-Yong Zhang; Tian-Wu Chen; Xiao-Ming Zhang
Journal:  Front Oncol       Date:  2021-03-24       Impact factor: 6.244

6.  MR-based radiomics-clinical nomogram in epithelial ovarian tumor prognosis prediction: tumor body texture analysis across various acquisition protocols.

Authors:  Tianping Wang; Haijie Wang; Yida Wang; Xuefen Liu; Lei Ling; Guofu Zhang; Guang Yang; He Zhang
Journal:  J Ovarian Res       Date:  2022-01-12       Impact factor: 4.234

7.  Radiomics Based on Contrast-Enhanced MRI in Differentiation Between Fat-Poor Angiomyolipoma and Hepatocellular Carcinoma in Noncirrhotic Liver: A Multicenter Analysis.

Authors:  Xiangtian Zhao; Yukun Zhou; Yuan Zhang; Lujun Han; Li Mao; Yizhou Yu; Xiuli Li; Mengsu Zeng; Mingliang Wang; Zaiyi Liu
Journal:  Front Oncol       Date:  2021-10-13       Impact factor: 6.244

8.  Diagnosing Ovarian Cancer on MRI: A Preliminary Study Comparing Deep Learning and Radiologist Assessments.

Authors:  Tsukasa Saida; Kensaku Mori; Sodai Hoshiai; Masafumi Sakai; Aiko Urushibara; Toshitaka Ishiguro; Manabu Minami; Toyomi Satoh; Takahito Nakajima
Journal:  Cancers (Basel)       Date:  2022-02-16       Impact factor: 6.639

9.  T2-weighted MRI-based radiomics for discriminating between benign and borderline epithelial ovarian tumors: a multicenter study.

Authors:  Mingxiang Wei; Yu Zhang; Genji Bai; Cong Ding; Haimin Xu; Yao Dai; Shuangqing Chen; Hong Wang
Journal:  Insights Imaging       Date:  2022-08-09

10.  Artificial intelligence performance in image-based ovarian cancer identification: A systematic review and meta-analysis.

Authors:  He-Li Xu; Ting-Ting Gong; Fang-Hua Liu; Hong-Yu Chen; Qian Xiao; Yang Hou; Ying Huang; Hong-Zan Sun; Yu Shi; Song Gao; Yan Lou; Qing Chang; Yu-Hong Zhao; Qing-Lei Gao; Qi-Jun Wu
Journal:  EClinicalMedicine       Date:  2022-09-17
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.