Enhancing thyroid nodule assessment with deep learning and ultrasound imaging

The thyroid is a tiny, butterfly-shaped gland in the neck which produces hormones that are essential for controlling the body's various metabolic processes. Thyroid nodules, which are abnormal growths or lumps in the thyroid gland, are common thyroid illnesses, as are hypothyroidism, hyperthyro...

Full description

Saved in:
Bibliographic Details
Main Authors: Jatinder Kumar, Surya Narayan Panda, Devi Dayal, Manish Sharma
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:e-Prime: Advances in Electrical Engineering, Electronics and Energy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772671125000014
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590922191208448
author Jatinder Kumar
Surya Narayan Panda
Devi Dayal
Manish Sharma
author_facet Jatinder Kumar
Surya Narayan Panda
Devi Dayal
Manish Sharma
author_sort Jatinder Kumar
collection DOAJ
description The thyroid is a tiny, butterfly-shaped gland in the neck which produces hormones that are essential for controlling the body's various metabolic processes. Thyroid nodules, which are abnormal growths or lumps in the thyroid gland, are common thyroid illnesses, as are hypothyroidism, hyperthyroidism, and both. Thyroid issues are most commonly identified and categorised using thyroid ultrasonography (USG) images. They can have a range of effects on the body's metabolism and overall health. Developments in artificial intelligence (AI), particularly deep learning (DL), are helping to identify and measure patterns in clinical images because of DL's capacity towards pull out hierarchical attribute representations from images without the need for annotated images. Minimizing unnecessary fine needle aspiration (FNA) requires the essential identification of as many malignant thyroid nodules as possible, distinguishing them from benign ones. This research work introduces a technique for thyroid nodule identification in USGs, employing DL to extract relevant features. Three pre-trained DL models, namely ResNet-18, VGG-19 and AlexNet were fine-tuned before using for classification of thyroid USG images. The models' testing and training were done with Digital Database of Thyroid Ultrasound Images (DDTI) which is gold standard dataset. The results demonstrate a classification accuracy of 97.13%, 90.31% and 83.59% with ResNet-18, VGG-19 and AlexNet, respectively. The experimental findings affirm that the pre-trained network model ResNet-18 achieves superior classification performance compared to VGG-19 and AlexNet.
format Article
id doaj-art-e311a531e7344c1eb7f7202cc9a29a0f
institution Kabale University
issn 2772-6711
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series e-Prime: Advances in Electrical Engineering, Electronics and Energy
spelling doaj-art-e311a531e7344c1eb7f7202cc9a29a0f2025-01-23T05:28:01ZengElseviere-Prime: Advances in Electrical Engineering, Electronics and Energy2772-67112025-03-0111100894Enhancing thyroid nodule assessment with deep learning and ultrasound imagingJatinder Kumar0Surya Narayan Panda1Devi Dayal2Manish Sharma3Computer Section, F Block, Nehru Hospital, Sector-12, PGIMER, Chandigarh, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India; Corresponding author.Endocrinology and Diabetes Unit, Department of Paediatrics, PGIMER, Chandigarh, IndiaChitkara University Institute of Engineering and Technology, Chitkara University, Punjab, IndiaThe thyroid is a tiny, butterfly-shaped gland in the neck which produces hormones that are essential for controlling the body's various metabolic processes. Thyroid nodules, which are abnormal growths or lumps in the thyroid gland, are common thyroid illnesses, as are hypothyroidism, hyperthyroidism, and both. Thyroid issues are most commonly identified and categorised using thyroid ultrasonography (USG) images. They can have a range of effects on the body's metabolism and overall health. Developments in artificial intelligence (AI), particularly deep learning (DL), are helping to identify and measure patterns in clinical images because of DL's capacity towards pull out hierarchical attribute representations from images without the need for annotated images. Minimizing unnecessary fine needle aspiration (FNA) requires the essential identification of as many malignant thyroid nodules as possible, distinguishing them from benign ones. This research work introduces a technique for thyroid nodule identification in USGs, employing DL to extract relevant features. Three pre-trained DL models, namely ResNet-18, VGG-19 and AlexNet were fine-tuned before using for classification of thyroid USG images. The models' testing and training were done with Digital Database of Thyroid Ultrasound Images (DDTI) which is gold standard dataset. The results demonstrate a classification accuracy of 97.13%, 90.31% and 83.59% with ResNet-18, VGG-19 and AlexNet, respectively. The experimental findings affirm that the pre-trained network model ResNet-18 achieves superior classification performance compared to VGG-19 and AlexNet.http://www.sciencedirect.com/science/article/pii/S2772671125000014Deep learningMalignantBenignAlexNetVGG-19ResNet-18
spellingShingle Jatinder Kumar
Surya Narayan Panda
Devi Dayal
Manish Sharma
Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
e-Prime: Advances in Electrical Engineering, Electronics and Energy
Deep learning
Malignant
Benign
AlexNet
VGG-19
ResNet-18
title Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
title_full Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
title_fullStr Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
title_full_unstemmed Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
title_short Enhancing thyroid nodule assessment with deep learning and ultrasound imaging
title_sort enhancing thyroid nodule assessment with deep learning and ultrasound imaging
topic Deep learning
Malignant
Benign
AlexNet
VGG-19
ResNet-18
url http://www.sciencedirect.com/science/article/pii/S2772671125000014
work_keys_str_mv AT jatinderkumar enhancingthyroidnoduleassessmentwithdeeplearningandultrasoundimaging
AT suryanarayanpanda enhancingthyroidnoduleassessmentwithdeeplearningandultrasoundimaging
AT devidayal enhancingthyroidnoduleassessmentwithdeeplearningandultrasoundimaging
AT manishsharma enhancingthyroidnoduleassessmentwithdeeplearningandultrasoundimaging