EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

An effective and non-invasive prediction model for placenta accreta spectrum early diagnosis: Ultrasound image-based novel deep learning network

Wenyan Gao, Shuailin You, Yujiao Wu, Juan Su, Ziwei Li, Bei Shi, Xiran Jiang

Placenta and Reproductive Medicine · 31.03.2026 · 5 (1) · 16-24

DOI: 10.54844/prm.2026.1183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Placenta and Reproductive Medicine, online erschienen am 31.03.2026. Verfasst von Wenyan Gao und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The study aimed to utilize ultrasound technology to capture quantitative features of placenta accuta spectrum (PAS) and assist in its early diagnosis.

Methods

We proposed an EA-EffV2Net (an improved network combining EfficientNetV2 with an attention mechanism, where EA stands for Efficient Attention) model, trained and validated it by using ultrasound images from 468 pregnant women enrolled between July 2020 and January 2023. A clinical diagnostic model was developed based on important clinicopathological factors for comparison.

Results

Our models can improve performance in both the detection of PAS and the differential diagnosis of placenta accreta (PA) and placenta increta (PI). Compared with the clinical diagnostic model, EA-EffV2Net generated slightly higher misdiagnosis rates when diagnosing PAS and PA.

Conclusions

This study proposed a novel EA-EffV2Net model for the diagnosis of PAS and the differential diagnosis of PA and PI based on ultrasound images, which is suitable for all pregnant women is of clinical importance in individual treatment planning.

Zitieren

APA

Gao, W., You, S., Wu, Y., Su, J., Li, Z., Shi, B., & Jiang, X. (2026). An effective and non-invasive prediction model for placenta accreta spectrum early diagnosis: Ultrasound image-based novel deep learning network. Placenta and Reproductive Medicine, 5(1), 16-24. https://doi.org/10.54844/prm.2026.1183

Vancouver

Gao W, You S, Wu Y, Su J, Li Z, Shi B, et al. An effective and non-invasive prediction model for placenta accreta spectrum early diagnosis: Ultrasound image-based novel deep learning network. Placenta and Reproductive Medicine. 2026;5(1):16-24. doi:10.54844/prm.2026.1183

BibTeX
@article{Gao2026,
  author = {Gao, Wenyan and You, Shuailin and Wu, Yujiao and Su, Juan and Li, Ziwei and Shi, Bei and Jiang, Xiran},
  title = {An effective and non-invasive prediction model for placenta accreta spectrum early diagnosis: Ultrasound image-based novel deep learning network},
  journal = {Placenta and Reproductive Medicine},
  year = {2026},
  volume = {5},
  number = {1},
  pages = {16--24},
  doi = {10.54844/prm.2026.1183}
}
Kostenlos starten →