Key-frame Guided Network for Thyroid Nodule Recognition using Ultrasound Videos

TL;DR

This paper introduces a novel ultrasound video analysis framework for thyroid nodule recognition that leverages key-frame detection and motion attention to improve diagnostic accuracy over static image-based methods.

Contribution

It proposes a detection-localization framework for key-frame identification and a key-frame guided classification model with motion attention, integrating temporal information for better diagnosis.

Findings

Outperforms existing static image-based methods

Accurately identifies clinical key-frames in ultrasound videos

Demonstrates superior performance on real clinical data

Abstract

Ultrasound examination is widely used in the clinical diagnosis of thyroid nodules (benign/malignant). However, the accuracy relies heavily on radiologist experience. Although deep learning techniques have been investigated for thyroid nodules recognition. Current solutions are mainly based on static ultrasound images, with limited temporal information used and inconsistent with clinical diagnosis. This paper proposes a novel method for the automated recognition of thyroid nodules through an exhaustive exploration of ultrasound videos and key-frames. We first propose a detection-localization framework to automatically identify the clinical key-frame with a typical nodule in each ultrasound video. Based on the localized key-frame, we develop a key-frame guided video classification model for thyroid nodule recognition. Besides, we introduce a motion attention module to help the network focus on significant frames in an ultrasound video, which is consistent with clinical diagnosis. The proposed thyroid nodule recognition framework is validated on clinically collected ultrasound videos, demonstrating superior performance compared with other state-of-the-art methods.