Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature Extractor

TL;DR

This paper introduces MeDiVLAD, a novel AI pipeline using self-knowledge distillation and VLAD aggregation for efficient multi-level lung ultrasound severity scoring, overcoming dataset limitations.

Contribution

The paper presents a new pipeline combining self-knowledge distillation and VLAD for improved ultrasound severity scoring with minimal fine-tuning.

Findings

Outperforms conventional supervised methods in scoring accuracy.

Enables automatic identification of critical lung pathology areas.

Provides robust classification for broader medical video tasks.

Abstract

With the advent of the COVID-19 pandemic, ultrasound imaging has emerged as a promising technique for COVID-19 detection, due to its non-invasive nature, affordability, and portability. In response, researchers have focused on developing AI-based scoring systems to provide real-time diagnostic support. However, the limited size and lack of proper annotation in publicly available ultrasound datasets pose significant challenges for training a robust AI model. This paper proposes MeDiVLAD, a novel pipeline to address the above issue for multi-level lung-ultrasound (LUS) severity scoring. In particular, we leverage self-knowledge distillation to pretrain a vision transformer (ViT) without label and aggregate frame-level features via dual-level VLAD aggregation. We show that with minimal finetuning, MeDiVLAD outperforms conventional fully-supervised methods in both frame- and video-level scoring, while offering classification reasoning with exceptional quality. This superior performance enables key applications such as the automatic identification of critical lung pathology areas and provides a robust solution for broader medical video classification tasks.