Segmenting Fetal Head with Efficient Fine-tuning Strategies in Low-resource Settings: an empirical study with U-Net

TL;DR

This study evaluates fine-tuning strategies for U-Net in fetal head segmentation from ultrasound images, demonstrating improved performance in low-resource settings and providing practical guidelines for efficient model adaptation.

Contribution

It systematically compares fine-tuning approaches for U-Net architectures, highlighting strategies that enhance segmentation accuracy with limited data and resources.

Findings

Fine-tuning U-Net outperforms training from scratch.

Decoder-focused fine-tuning yields superior results.

Lightweight architectures can match or surpass larger models.

Abstract

Accurate measurement of fetal head circumference is crucial for estimating fetal growth during routine prenatal screening. Prior to measurement, it is necessary to accurately identify and segment the region of interest, specifically the fetal head, in ultrasound images. Recent advancements in deep learning techniques have shown significant progress in segmenting the fetal head using encoder-decoder models. Among these models, U-Net has become a standard approach for accurate segmentation. However, training an encoder-decoder model can be a time-consuming process that demands substantial computational resources. Moreover, fine-tuning these models is particularly challenging when there is a limited amount of data available. There are still no "best-practice" guidelines for optimal fine-tuning of U-net for fetal ultrasound image segmentation. This work summarizes existing fine-tuning strategies with various backbone architectures, model components, and fine-tuning strategies across ultrasound data from Netherlands, Spain, Malawi, Egypt and Algeria. Our study shows that (1) fine-tuning U-Net leads to better performance than training from scratch, (2) fine-tuning strategies in decoder are superior to other strategies, (3) network architecture with less number of parameters can achieve similar or better performance. We also demonstrate the effectiveness of fine-tuning strategies in low-resource settings and further expand our experiments into few-shot learning. Lastly, we publicly released our code and specific fine-tuned weights.