Learning to learn skill assessment for fetal ultrasound scanning

TL;DR

This paper introduces a bi-level optimization framework for fetal ultrasound skill assessment that predicts skill levels based on task performance in ultrasound images without relying on predefined ratings.

Contribution

It presents a novel joint optimization approach that evaluates ultrasound skills directly from image data, avoiding subjective or predefined skill criteria.

Findings

Successfully predicts ultrasound skills from real clinical videos.

Quantifies task performance as a skill indicator.

Demonstrates feasibility of automated skill assessment in fetal ultrasound.

Abstract

Traditionally, ultrasound skill assessment has relied on expert supervision and feedback, a process known for its subjectivity and time-intensive nature. Previous works on quantitative and automated skill assessment have predominantly employed supervised learning methods, often limiting the analysis to predetermined or assumed factors considered influential in determining skill levels. In this work, we propose a novel bi-level optimisation framework that assesses fetal ultrasound skills by how well a task is performed on the acquired fetal ultrasound images, without using manually predefined skill ratings. The framework consists of a clinical task predictor and a skill predictor, which are optimised jointly by refining the two networks simultaneously. We validate the proposed method on real-world clinical ultrasound videos of scanning the fetal head. The results demonstrate the feasibility of predicting ultrasound skills by the proposed framework, which quantifies optimised task performance as a skill indicator.