Evaluate Fine-tuning Strategies for Fetal Head Ultrasound Image Segmentation with U-Net

TL;DR

This paper evaluates transfer learning strategies using a lightweight U-Net with MobileNet encoder for fetal head ultrasound segmentation, demonstrating reduced model size with maintained accuracy, beneficial for AI applications in medical imaging.

Contribution

It introduces a transfer learning fine-tuning approach with a lightweight U-Net for fetal head segmentation, reducing model size while maintaining performance.

Findings

Achieved segmentation with 85.8% fewer parameters.

Outperformed other strategies with models under 4.4 million parameters.

Highlighted the trade-off between model size and segmentation accuracy.

Abstract

Fetal head segmentation is a crucial step in measuring the fetal head circumference (HC) during gestation, an important biometric in obstetrics for monitoring fetal growth. However, manual biometry generation is time-consuming and results in inconsistent accuracy. To address this issue, convolutional neural network (CNN) models have been utilized to improve the efficiency of medical biometry. But training a CNN network from scratch is a challenging task, we proposed a Transfer Learning (TL) method. Our approach involves fine-tuning (FT) a U-Net network with a lightweight MobileNet as the encoder to perform segmentation on a set of fetal head ultrasound (US) images with limited effort. This method addresses the challenges associated with training a CNN network from scratch. It suggests that our proposed FT strategy yields segmentation performance that is comparable when trained with a reduced number of parameters by 85.8%. And our proposed FT strategy outperforms other strategies with smaller trainable parameter sizes below 4.4 million. Thus, we contend that it can serve as a dependable FT approach for reducing the size of models in medical image analysis. Our key findings highlight the importance of the balance between model performance and size in developing Artificial Intelligence (AI) applications by TL methods. Code is available at https://github.com/13204942/FT_Methods_for_Fetal_Head_Segmentation.