Thyroid nodule segmentation in ultrasound images using U-Net with ResNet encoder: achieving state-of-the-art performance on all public datasets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11110%2F25%3A10498128" target="_blank" >RIV/00216208:11110/25:10498128 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=6xJIFsGwII" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=6xJIFsGwII</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3934/medsci.2025009" target="_blank" >10.3934/medsci.2025009</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Thyroid nodule segmentation in ultrasound images using U-Net with ResNet encoder: achieving state-of-the-art performance on all public datasets

Popis výsledku v původním jazyce

Ultrasound imaging plays a vital role in evaluating thyroid nodules, aiding in the assessment of malignancy risk, monitoring size progression, and serving as a guiding tool for thyroid nodule biopsies. Computer-aided diagnosis (CAD) systems have emerged to assist in diagnosing thyroid lesions, reducing unnecessary biopsies, and contributing to the overall improvement of diagnostic accuracy. The segmentation process plays a crucial role in CAD systems because it marks the region of interest. If segmentation were sufficiently accurate, then it would improve the entire diagnostic process and bring CAD systems closer to routine clinical practice. As far as we know, there are currently only three publicly available datasets of ultrasound images of the thyroid gland that can be used for the purpose of thyroid nodules segmentation. The Thyroid Digital Image Database (TDID) is a long-standing benchmark dataset but faces limitations due to the data ambiguities. The TN3K dataset is more robust than TDID, and the Thyroid Ultrasound Cine-clip dataset offers recent alternatives. In this paper, we implemented a deep learning segmentation model based on UNet with a ResNet encoder. We trained this model on all available data and evaluated it on the TN3K test set. The achieved results for the Dice score, IoU score, accuracy, precision, and recall were 84.24%, 75.48%, 97.24%, 82.75%, and 88.98%, respectively. These results represent the most advanced state-of-the-art scores compared to previously published studies and demonstrate that UNet with a ResNet encoder has the capability to accurately segment thyroid nodules in ultrasound images.

Název v anglickém jazyce

Thyroid nodule segmentation in ultrasound images using U-Net with ResNet encoder: achieving state-of-the-art performance on all public datasets

Popis výsledku anglicky

Ultrasound imaging plays a vital role in evaluating thyroid nodules, aiding in the assessment of malignancy risk, monitoring size progression, and serving as a guiding tool for thyroid nodule biopsies. Computer-aided diagnosis (CAD) systems have emerged to assist in diagnosing thyroid lesions, reducing unnecessary biopsies, and contributing to the overall improvement of diagnostic accuracy. The segmentation process plays a crucial role in CAD systems because it marks the region of interest. If segmentation were sufficiently accurate, then it would improve the entire diagnostic process and bring CAD systems closer to routine clinical practice. As far as we know, there are currently only three publicly available datasets of ultrasound images of the thyroid gland that can be used for the purpose of thyroid nodules segmentation. The Thyroid Digital Image Database (TDID) is a long-standing benchmark dataset but faces limitations due to the data ambiguities. The TN3K dataset is more robust than TDID, and the Thyroid Ultrasound Cine-clip dataset offers recent alternatives. In this paper, we implemented a deep learning segmentation model based on UNet with a ResNet encoder. We trained this model on all available data and evaluated it on the TN3K test set. The achieved results for the Dice score, IoU score, accuracy, precision, and recall were 84.24%, 75.48%, 97.24%, 82.75%, and 88.98%, respectively. These results represent the most advanced state-of-the-art scores compared to previously published studies and demonstrate that UNet with a ResNet encoder has the capability to accurately segment thyroid nodules in ultrasound images.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

30224 - Radiology, nuclear medicine and medical imaging

Projekt

—

Návaznosti

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

AIMS Medical Science

ISSN

2375-1576

e-ISSN

2375-1576

Svazek periodika

12

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

124-144

Kód UT WoS článku

001460808300001

EID výsledku v databázi Scopus

—