DOI 10.1016/j.placenta.2026.05.005
Development of a simplified MRI model for diagnosing placenta accreta spectrum disorders.
Аннотация
INTRODUCTION
Accurate prenatal diagnosis of placenta accreta spectrum (PAS) disorders is crucial for reducing the risk of severe maternal morbidities. This study aims to develop and evaluate a simplified MRI model for PAS, assessing its performance across radiologists with varying levels of experience.
METHODS
We conducted a retrospective study of surgically or pathologically confirmed PAS cases at our institution from 2016 to 2024. Two senior and two junior radiologists independently and blindly reviewed MRI images, focusing on two key categories: (1) uteroplacental interface abnormalities and (2) uteroplacental circulatory abnormalities. A simplified MRI model incorporating these 2 categories was developed for PAS diagnosis.
RESULTS
The intraclass correlation coefficient (ICC) for the agreement regarding uteroplacental interface abnormalities (0.848 vs 0.736) and uteroplacental circulatory abnormalities (0.806 vs 0.675) were higher than those of conventional MRI features for both senior and junior readers. The combined MRI model demonstrated strong performance, with an AUC of 0.84, sensitivity of 90.40%, specificity of 73.90% for senior readers, and AUC of 0.795, sensitivity of 81%, specificity of 66.7% for junior readers, which was significantly better than AUC of the 2 principal categories or the single MRI features (all p < 0.05).
DISCUSSION: The proposed simplified MRI model showed high diagnostic accuracy for PAS and was particularly beneficial for junior radiologists, suggesting its potential as a practical clinical tool.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.