Development and validation of a combined model based on MRI radiomics for predicting placenta accreta spectrum and adverse pregnancy outcomes: a multicenter retrospective study
Zhongjie Zhou, Huaizhi Ge, Pinfa Zou, Tianyi Ye, Ting Zou, Qin Fang, Yan Zeng, Yu Wang, Xiaofen Zhang, Zhangye Xu, Xianping Huang · 2026
Read Development and validation of a combined model based on MRI radiomics for predicting placenta accreta spectrum and adverse pregnancy outcomes: a multicenter retrospective study by Zhongjie Zhou, Huaizhi Ge, Pinfa Zou, Tianyi Ye, Ting Zou, Qin Fang, Yan Zeng, Yu Wang, Xiaofen Zhang, Zhangye Xu, Xianping Huang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13224454.txt.
Description
When the placenta grows too deeply into the womb, delivery can turn dangerous, and spotting the condition before birth matters. Zhongjie Zhou and ten co-authors build prediction models from MRI scans of 610 pregnancies across several centers, 292 with the condition and 318 without. They split cases into training, validation, and external test groups, and combine image-derived radiomics features with clinical facts.
The combined model beat both the image-only and clinical-only models at every stage, reaching areas under the curve near 0.79 for diagnosis. For predicting pregnancy outcomes in affected women it did better still, up to 0.907 on external testing. The authors present the tool as decision support for the teams managing these high-risk pregnancies. The study appears in 2026.
Catalog record
| CREATOR | Zhongjie Zhou, Huaizhi Ge, Pinfa Zou, Tianyi Ye, Ting Zou, Qin Fang, Yan Zeng, Yu Wang, Xiaofen Zhang, Zhangye Xu, Xianping Huang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |