SEGMENTATION OF THYROID NODULES ON ULTRASOUND IMAGES

Abstract

The increasing prevalence of thyroid cancer in our country and globally has led to the development of various computer-aided studies for its detection, contributing significantly to the literature. Artificial intelligence and image processing are particularly prominent methods in this field due to their non-invasive nature, accessibility, and ability to provide valuable information about the morphological characteristics of nodules. In recent years, segmentation algorithms in medical imaging have garnered substantial interest for their potential to enhance diagnostic accuracy. Accurate segmentation of thyroid nodules is a critical first step in the development of AI-assisted clinical decision support systems for the detection and diagnosis of thyroid cancer. In this study, innovative methods were employed to detect thyroid nodules. A dice score of 79% was achieved in instance segmentation using the YOLOv5-Small algorithm when doppler images were excluded, while a dice score of 91% was obtained using the YOLOv5-Large algorithm on a dataset that included doppler images. In semantic segmentation, the Attention Unet++ and Manet algorithms achieved a dice score of 89% when doppler images were excluded, and 91% when they were included. These results demonstrate that images typically excluded by physicians could potentially offer better outcomes in computerized image processing.