Multi-Center Study on Deep Learning-Assisted Detection and Classification of Fetal Central Nervous System Anomalies Using Ultrasound Imaging

TL;DR

This study develops a deep learning model that accurately detects and classifies fetal CNS anomalies from ultrasound images, improving diagnostic accuracy and efficiency across multiple centers and gestational stages.

Contribution

The paper introduces a multi-center deep learning system for fetal CNS anomaly detection that enhances diagnosis accuracy and provides visual interpretability to assist radiologists.

Findings

Patient-level prediction accuracy of 94.5%

AUROC value of 99.3% for anomaly classification

Effective across all gestational periods

Abstract

Prenatal ultrasound evaluates fetal growth and detects congenital abnormalities during pregnancy, but the examination of ultrasound images by radiologists requires expertise and sophisticated equipment, which would otherwise fail to improve the rate of identifying specific types of fetal central nervous system (CNS) abnormalities and result in unnecessary patient examinations. We construct a deep learning model to improve the overall accuracy of the diagnosis of fetal cranial anomalies to aid prenatal diagnosis. In our collected multi-center dataset of fetal craniocerebral anomalies covering four typical anomalies of the fetal central nervous system (CNS): anencephaly, encephalocele (including meningocele), holoprosencephaly, and rachischisis, patient-level prediction accuracy reaches 94.5%, with an AUROC value of 99.3%. In the subgroup analyzes, our model is applicable to the entire gestational period, with good identification of fetal anomaly types for any gestational period. Heatmaps superimposed on the ultrasound images not only provide a visual interpretation for the algorithm but also provide an intuitive visual aid to the physician by highlighting key areas that need to be reviewed, helping the physician to quickly identify and validate key areas. Finally, the retrospective reader study demonstrates that by combining the automatic prediction of the DL system with the professional judgment of the radiologist, the diagnostic accuracy and efficiency can be effectively improved and the misdiagnosis rate can be reduced, which has an important clinical application prospect.