Literature DB >> 36094660

Prediction of placenta accreta spectrum by combining deep learning and radiomics using T2WI: a multicenter study.

Zhengjie Ye1, Rongrong Xuan2, Menglin Ouyang2, Yutao Wang2, Jian Xu3, Wei Jin4.   

Abstract

PURPOSE: To achieve prenatal prediction of placenta accreta spectrum (PAS) by combining clinical model, radiomics model, and deep learning model using T2-weighted images (T2WI), and to objectively evaluate the performance of the prediction through multicenter validation.
METHODS: A total of 407 pregnant women from two centers undergoing preoperative magnetic resonance imaging (MRI) were retrospectively recruited. The patients from institution I were divided into a training cohort (n = 298) and a validation cohort (n = 75), while patients from institution II served as the external test cohort (n = 34). In this study, we built a clinical prediction model using patient clinical data, a radiomics model based on selected key features, and a deep learning model by mining deep semantic features. Based on this, we developed a combined model by ensembling the prediction results of the three models mentioned above to achieve prenatal prediction of PAS. The performance of these predictive models was evaluated with respect to discrimination, calibration, and clinical usefulness.
RESULTS: The combined model achieved AUCs of 0.872 (95% confidence interval, 0.843 to 0.908) in the validation cohort and 0.857 (0.808 to 0.894) in the external test cohort, both of which outperformed the other models. The calibration curves demonstrated excellent consistency in the validation cohort and the external test cohort, and the decision curves indicated high clinical usefulness.
CONCLUSION: By using preoperative clinical information and MRI images, the combined model can accurately predict PAS by ensembling clinical model, radiomics model, and deep learning model.
© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Entities:  

Keywords:  Deep learning; Ensemble learning; Magnetic resonance imaging; Placenta accreta spectrum; Radiomics

Year:  2022        PMID: 36094660     DOI: 10.1007/s00261-022-03673-4

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  14 in total

1.  Novel MRI finding for diagnosis of invasive placenta praevia: evaluation of findings for 65 patients using clinical and histopathological correlations.

Authors:  Yoshiko Ueno; Kazuhiro Kitajima; Fumi Kawakami; Tetsuo Maeda; Yuko Suenaga; Satoru Takahashi; Shozo Matsuoka; Kenji Tanimura; Hideto Yamada; Yoshiharu Ohno; Kazuro Sugimura
Journal:  Eur Radiol       Date:  2013-11-22       Impact factor: 5.315

2.  How and why should the radiologist look at the placenta?

Authors:  N Siauve
Journal:  Eur Radiol       Date:  2019-08-07       Impact factor: 5.315

3.  Identification of suspicious invasive placentation based on clinical MRI data using textural features and automated machine learning.

Authors:  Huaiqiang Sun; Haibo Qu; Lu Chen; Wei Wang; Yi Liao; Ling Zou; Ziyi Zhou; Xiaodong Wang; Shu Zhou
Journal:  Eur Radiol       Date:  2019-08-23       Impact factor: 5.315

4.  Conventional MRI features for predicting the clinical outcome of patients with invasive placenta.

Authors:  Ting Chen; Xiao Quan Xu; Hai Bin Shi; Zheng Qiang Yang; Xin Zhou; Yi Pan
Journal:  Diagn Interv Radiol       Date:  2017 May-Jun       Impact factor: 2.630

5.  Evaluation of interobserver variability and diagnostic performance of developed MRI-based radiological scoring system for invasive placenta previa.

Authors:  Yoshiko Ueno; Tetsuo Maeda; Utaru Tanaka; Kenji Tanimura; Kazuhiro Kitajima; Yuko Suenaga; Satoru Takahashi; Hideto Yamada; Kazuro Sugimura
Journal:  J Magn Reson Imaging       Date:  2016-02-21       Impact factor: 4.813

6.  Deep learning predicts epidermal growth factor receptor mutation subtypes in lung adenocarcinoma.

Authors:  Jiangdian Song; Changwei Ding; Qinlai Huang; Ting Luo; Xiaoman Xu; Zongjian Chen; Shu Li
Journal:  Med Phys       Date:  2021-11-07       Impact factor: 4.071

7.  Deep learning-based radiomics predicts response to chemotherapy in colorectal liver metastases.

Authors:  Jingwei Wei; Jin Cheng; Dongsheng Gu; Fan Chai; Nan Hong; Yi Wang; Jie Tian
Journal:  Med Phys       Date:  2020-11-30       Impact factor: 4.071

Review 8.  Review of MRI imaging for placenta accreta spectrum: Pathophysiologic insights, imaging signs, and recent developments.

Authors:  Harit Kapoor; Mauro Hanaoka; Adrian Dawkins; Aman Khurana
Journal:  Placenta       Date:  2020-11-13       Impact factor: 3.481

9.  Prediction of placenta accreta spectrum using texture analysis on coronal and sagittal T2-weighted imaging.

Authors:  Hainan Ren; Naoko Mori; Shunji Mugikura; Hiroaki Shimizu; Sakiko Kageyama; Masatoshi Saito; Kei Takase
Journal:  Abdom Radiol (NY)       Date:  2021-07-30

10.  Radiomics analysis of placenta on T2WI facilitates prediction of postpartum haemorrhage: A multicentre study.

Authors:  Qingxia Wu; Kuan Yao; Zhenyu Liu; Longfei Li; Xin Zhao; Shuo Wang; Honglei Shang; Yusong Lin; Zejun Wen; Xiaoan Zhang; Jie Tian; Meiyun Wang
Journal:  EBioMedicine       Date:  2019-11-22       Impact factor: 8.143

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.