Doppler-Enhanced Deep Learning: Improving Thyroid Nodule Segmentation with YOLOv5 Instance Segmentation

TL;DR

This study enhances thyroid nodule segmentation in ultrasound images using YOLOv5, showing that incorporating Doppler images significantly improves accuracy, with the YOLOv5-Large model achieving a dice score of 91%.

Contribution

It demonstrates the effectiveness of YOLOv5 for thyroid nodule instance segmentation and highlights the benefit of including Doppler images, which are usually excluded.

Findings

YOLOv5-Large achieved 91% dice score with Doppler images.

Including Doppler images improves segmentation performance across models.

YOLOv5 provides a real-time solution for thyroid nodule detection.

Abstract

The increasing prevalence of thyroid cancer globally has led to the development of various computer-aided detection methods. Accurate segmentation of thyroid nodules is a critical first step in the development of AI-assisted clinical decision support systems. This study focuses on instance segmentation of thyroid nodules using YOLOv5 algorithms on ultrasound images. We evaluated multiple YOLOv5 variants (Nano, Small, Medium, Large, and XLarge) across two dataset versions, with and without doppler images. The YOLOv5-Large algorithm achieved the highest performance with a dice score of 91\% and mAP of 0.87 on the dataset including doppler images. Notably, our results demonstrate that doppler images, typically excluded by physicians, can significantly improve segmentation performance. The YOLOv5-Small model achieved 79\% dice score when doppler images were excluded, while including them improved performance across all model variants. These findings suggest that instance segmentation with YOLOv5 provides an effective real-time approach for thyroid nodule detection, with potential clinical applications in automated diagnostic systems.