EUVIMEDEUVIMED entdecken
Crossref

A Deep Learning Pipeline Using Prior Knowledge for Automatic Evaluation of Placenta Accreta Spectrum Disorders With MRI

Haijie Wang iD, Yida Wang, He Zhang, Xuan Yin, Chenglong Wang, Yuanyuan Lu, Yang Song iD, Hao Zhu, Guang Yang iD

Journal of Magnetic Resonance Imaging · 2024

DOI: 10.1002/jmri.28770 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2024. Verfasst von Haijie Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China. Hauptthemen laut MEDLINE: Placenta Accreta, Deep Learning. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Open Project of Shanghai Key Laboratory of Magnetic Resonance.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The diagnosis of prenatal placenta accreta spectrum (PAS) with magnetic resonance imaging (MRI) is highly dependent on radiologists' experience. A deep learning (DL) method using the prior knowledge that PAS‐related signs are generally found along the utero‐placental borderline (UPB) may help radiologists, especially those with less experience, to mitigate this issue.

Purpose

To develop a DL tool for antenatal diagnosis of PAS using T2‐weighted MR images. Study Type Retrospective. Subjects Five hundred and forty pregnant women with clinically suspected PAS disorders from two institutions, divided into training (409), internal test (103), and external test (28) datasets. Field Strength/Sequence Sagittal T2‐weighted fast spin echo sequence at 1.5 T and 3 T. Assessment An nnU‐Net was trained for placenta segmentation. The UPB straightening approach was used to extract the utero‐placental boundary region. The UPB image was then fed into DenseNet‐PAS for PAS diagnosis. DenseNet‐PP learnt placental position information to improve the PAS diagnosis performance. Three radiologists with 8, 10, and 12 years of experience independently evaluated the images. Two radiologists marked the placenta tissue. Histopathological findings were the reference standard. Statistical Tests Area under the curve (AUC) was used to evaluate the classification. Dice coefficient evaluated the segmentation between radiologists and the model performance. The Mann–Whitney U ‐test or the chi‐squared test assessed the significance of differences. Decision curve analysis was used to determine clinical effectiveness. DeLong's test was used to compare AUCs.

Results

Of the 540 patients, 170 had PAS disorders confirmed by histopathology. The DL model using UPB images and placental position yielded the highest AUC of 0.860 and 0.897 in internal test and external test cohorts, respectively, significantly exceeding the performance of three radiologists (internal test AUC, 0.737–0.770). Data Conclusion By extracting the UPB image, this fully automatic DL pipeline achieved high accuracy and may assist radiologists in PAS diagnosis using MRI. Level of Evidence 3 Technical Efficacy Stage 2

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Placenta AccretaDeep LearningFemalePregnancyHumansPlacentaRetrospective StudiesMagnetic Resonance Imaging

Stichwörter der Autor:innen

computer assisted diagnosisdeep learningplacenta accretaprenatal diagnosis

Autor:innen und Institutionen

  • Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China.
  • Department of Radiology, Obstetrics and Gynecology Hospital, Fudan University, Shanghai, China.
  • Department of Radiology, Shanghai First Maternity and Infant Health Hospital, School of Medicine, Tongji University, Shanghai, China.
  • MR Scientific Marketing, Siemens Healthineers China, Shanghai, China.
  • Department of Obstetrics, Obstetrics and Gynecology Hospital, Fudan University, Shanghai, China.

ORCID-Profile: Haijie Wang, Yang Song, Guang Yang

Förderung

  • National Natural Science Foundation of China
  • Open Project of Shanghai Key Laboratory of Magnetic Resonance

Zitieren

APA

Wang, H., Wang, Y., Zhang, H., Yin, X., Wang, C., Lu, Y., Song, Y., Zhu, H., & Yang, G. (2024). A Deep Learning Pipeline Using Prior Knowledge for Automatic Evaluation of Placenta Accreta Spectrum Disorders With MRI. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.28770

Vancouver

Wang H, Wang Y, Zhang H, Yin X, Wang C, Lu Y, et al. A Deep Learning Pipeline Using Prior Knowledge for Automatic Evaluation of Placenta Accreta Spectrum Disorders With MRI. Journal of Magnetic Resonance Imaging. 2024. doi:10.1002/jmri.28770

BibTeX
@article{Wang2024,
  author = {Wang, Haijie and Wang, Yida and Zhang, He and Yin, Xuan and Wang, Chenglong and Lu, Yuanyuan and Song, Yang and Zhu, Hao and Yang, Guang},
  title = {A Deep Learning Pipeline Using Prior Knowledge for Automatic Evaluation of Placenta Accreta Spectrum Disorders With MRI},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2024},
  doi = {10.1002/jmri.28770}
}
Kostenlos starten →