PDF icon Download PDF
Am J Perinatol 2024; 41(S 01): e2174-e2183
DOI: 10.1055/a-2099-3809
Original Article

Magnetic Resonance Imaging–Based Radiomics Nomogram to Predict Intraoperative Hemorrhage of Placenta Previa

Yanli Lu
1   Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Liping Zhou
2   Department of Obstetrics and Gynecology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Xiaoyan Wang
2   Department of Obstetrics and Gynecology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Yongmei Li
2   Department of Obstetrics and Gynecology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Dali Chen
2   Department of Obstetrics and Gynecology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Yidong Gu
3   Department of Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
,
Yongfei Yue
2   Department of Obstetrics and Gynecology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou, Jiangsu, People's Republic of China
› Author Affiliations
Funding This study was supported by Maternal and children's health research project of Jiangsu Province (grant number: F202108), Clinical Medical Expert Team Project of Suzhou (grant number: SZYJTD201709), Suzhou Science and Technology Plan Research Project (grant number: SKJYD2021222), and Suzhou Science and Technology Plan Research Project (grant number: SYSD2020133).
› Further Information
Also available ateRefHebammen
   Permissions and Reprints
Preview

Abstract

Objective Placenta previa (PP) is associated with intraoperative and postpartum hemorrhage, increased maternal morbidity and mortality. We aimed to develop a magnetic resonance imaging (MRI)-based nomogram to preoperative prediction of intraoperative hemorrhage (IPH) for PP.

Study Design A total of 125 PP pregnant women were divided into a training set (n = 80) and a validation set (n = 45). An MRI-based model was built for the classification of patients into IPH and non-IPH groups in a training set and a validation set. Multivariate nomograms were built according to radiomics features. Receiver operating characteristic (ROC) curve was used to assess the model. Predictive accuracy of nomogram were assessed by calibration plots and decision curve analysis.

Results In multivariate analysis, placenta position, placenta thickness, cervical blood sinus, and placental signals in the cervix were significantly independent predictors for IPH (all ps < 0.05). The MRI-based nomogram showed favorable discrimination between IPH and non-IPH groups. The calibration curve showed good agreement between the estimated and the actual probability of IPH. Decision curve analysis also showed a high clinical benefit across a wide range of probability thresholds. Area under the ROC curve was 0.918 (95% confidence interval [CI]: 0.857–0.979) in the training set and 0.866 (95% CI: 0.748–0.985) in the validation set by the combination of four MRI features.

Conclusion The MRI-based nomograms might be a useful tool for the preoperative prediction of IPH outcomes for PP. Our study enables obstetricians to perform adequate preoperative evaluation to reduce blood loss and cesarean hysterectomy.

Key Points

  • MRI is an important method for preoperative assessment of the risk of placenta previa.

  • MRI-based nomogram can assess the risk of intraoperative bleeding of placenta previa.

  • MRI is helpful for more comprehensive evaluation of placenta previa and adequate preoperative preparation.

Keywords

placenta previa - magnetic resonance imaging - intraoperative hemorrhage - nomogram


Publication History

Received: 14 April 2022

Accepted: 22 May 2023

Accepted Manuscript online:
24 May 2023

Article published online:
04 July 2023

© 2023. Thieme. All rights reserved.

Thieme Medical Publishers, Inc.
333 Seventh Avenue, 18th Floor, New York, NY 10001, USA