Thinking Twice: Clinical-Inspired Thyroid Ultrasound Lesion Detection Based on Feature Feedback

TL;DR

This paper introduces a novel thyroid ultrasound lesion detection network inspired by clinical diagnosis, utilizing a feature feedback mechanism to improve feature extraction and fusion, achieving high accuracy and real-time performance.

Contribution

The study proposes a new detection network with a feature feedback mechanism, including a feedback feature selection module and a feature feedback pyramid, enhancing feature extraction and fusion.

Findings

Achieved 70.3% AP and 99.0% AP50 on thyroid ultrasound dataset.

The method meets real-time detection requirements.

Outperforms existing methods in feature robustness against noise.

Abstract

Accurate detection of thyroid lesions is a critical aspect of computer-aided diagnosis. However, most existing detection methods perform only one feature extraction process and then fuse multi-scale features, which can be affected by noise and blurred features in ultrasound images. In this study, we propose a novel detection network based on a feature feedback mechanism inspired by clinical diagnosis. The mechanism involves first roughly observing the overall picture and then focusing on the details of interest. It comprises two parts: a feedback feature selection module and a feature feedback pyramid. The feedback feature selection module efficiently selects the features extracted in the first phase in both space and channel dimensions to generate high semantic prior knowledge, which is similar to coarse observation. The feature feedback pyramid then uses this high semantic prior knowledge to enhance feature extraction in the second phase and adaptively fuses the two features, similar to fine observation. Additionally, since radiologists often focus on the shape and size of lesions for diagnosis, we propose an adaptive detection head strategy to aggregate multi-scale features. Our proposed method achieves an AP of 70.3% and AP50 of 99.0% on the thyroid ultrasound dataset and meets the real-time requirement. The code is available at https://github.com/HIT-wanglingtao/Thinking-Twice.