Automatic Quality Assessment of First Trimester Crown-Rump-Length Ultrasound Images

TL;DR

This work addresses the challenge of ensuring correct CRL view quality for accurate gestational age estimation by combining fetal structure segmentation with a clinically guided mapping to seven CRL-view criteria. The proposed pipeline uses a CNN+Transformer network (Fetal TransUNet) for segmentation and a rule-based mapping to assess adherence, providing explainable outputs and outperforming traditional CNN classifiers on several criteria. Results indicate improved segmentation quality and meaningful criterion-level decisions, though the dataset is small and imbalanced, limiting universal generalization. The approach offers real-time feedback potential for sonographers and GA estimation, with future work focusing on larger, multi-reader datasets to enhance robustness.

Abstract

Fetal gestational age (GA) is vital clinical information that is estimated during pregnancy in order to assess fetal growth. This is usually performed by measuring the crown-rump-length (CRL) on an ultrasound image in the Dating scan which is then correlated with fetal age and growth trajectory. A major issue when performing the CRL measurement is ensuring that the image is acquired at the correct view, otherwise it could be misleading. Although clinical guidelines specify the criteria for the correct CRL view, sonographers may not regularly adhere to such rules. In this paper, we propose a new deep learning-based solution that is able to verify the adherence of a CRL image to clinical guidelines in order to assess image quality and facilitate accurate estimation of GA. We first segment out important fetal structures then use the localized structures to perform a clinically-guided mapping that verifies the adherence of criteria. The segmentation method combines the benefits of Convolutional Neural Network (CNN) and the Vision Transformer (ViT) to segment fetal structures in ultrasound images and localize important fetal landmarks. For segmentation purposes, we compare our proposed work with UNet and show that our CNN/ViT-based method outperforms an optimized version of UNet. Furthermore, we compare the output of the mapping with classification CNNs when assessing the clinical criteria and the overall acceptability of CRL images. We show that the proposed mapping is not only explainable but also more accurate than the best performing classification CNNs.

Figures (1)

• Figure 1: Flowchart of the proposed method with Fetal TransUNet to verify the adherence to clinical guidelines of the fetal ultrasound images.