A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning

TL;DR

This paper investigates transfer learning techniques for ultrasound image segmentation of multiple anatomical structures, aiming to improve domain generalization across different scanners and settings for robot-guided procedures.

Contribution

It introduces a systematic study of fine-tuning strategies within transfer learning to enhance ultrasound segmentation across diverse datasets, proposing a method to predict generalization performance.

Findings

Fine-tuning different model blocks yields significant performance differences.

A simple method can predict generalization to unseen datasets.

Transfer learning improves robustness across varied ultrasound data.

Abstract

Identifying landmarks in the femoral area is crucial for ultrasound (US) -based robot-guided catheter insertion, and their presentation varies when imaged with different scanners. As such, the performance of past deep learning-based approaches is also narrowly limited to the training data distribution; this can be circumvented by fine-tuning all or part of the model, yet the effects of fine-tuning are seldom discussed. In this work, we study the US-based segmentation of multiple classes through transfer learning by fine-tuning different contiguous blocks within the model, and evaluating on a gamut of US data from different scanners and settings. We propose a simple method for predicting generalization on unseen datasets and observe statistically significant differences between the fine-tuning methods while working towards domain generalization.