Cargando…

Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer

Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We emplo...

Descripción completa

Detalles Bibliográficos
Autores principales: Chan, Wai-Kin, Sun, Jui-Hung, Liou, Miaw-Jene, Li, Yan-Rong, Chou, Wei-Yu, Liu, Feng-Hsuan, Chen, Szu-Tah, Peng, Syu-Jyun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8698578/
https://www.ncbi.nlm.nih.gov/pubmed/34944587
http://dx.doi.org/10.3390/biomedicines9121771
_version_ 1784620310620798976
author Chan, Wai-Kin
Sun, Jui-Hung
Liou, Miaw-Jene
Li, Yan-Rong
Chou, Wei-Yu
Liu, Feng-Hsuan
Chen, Szu-Tah
Peng, Syu-Jyun
author_facet Chan, Wai-Kin
Sun, Jui-Hung
Liou, Miaw-Jene
Li, Yan-Rong
Chou, Wei-Yu
Liu, Feng-Hsuan
Chen, Szu-Tah
Peng, Syu-Jyun
author_sort Chan, Wai-Kin
collection PubMed
description Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We employed deep convolutional neural networks (CNNs) to facilitate the clinical diagnosis of differentiated thyroid cancers. An image dataset with thyroid ultrasound images of 421 DTCs and 391 benign patients was collected. Three CNNs (InceptionV3, ResNet101, and VGG19) were retrained and tested after undergoing transfer learning to classify malignant and benign thyroid tumors. The enrolled cases were classified as PTC, FTC, follicular variant of PTC (FVPTC), Hürthle cell carcinoma (HCC), or benign. The accuracy of the CNNs was as follows: InceptionV3 (76.5%), ResNet101 (77.6%), and VGG19 (76.1%). The sensitivity was as follows: InceptionV3 (83.7%), ResNet101 (72.5%), and VGG19 (66.2%). The specificity was as follows: InceptionV3 (83.7%), ResNet101 (81.4%), and VGG19 (76.9%). The area under the curve was as follows: Incep-tionV3 (0.82), ResNet101 (0.83), and VGG19 (0.83). A comparison between performance of physicians and CNNs was assessed and showed significantly better outcomes in the latter. Our results demonstrate that retrained deep CNNs can enhance diagnostic accuracy in most DTCs, including follicular cancers.
format Online
Article
Text
id pubmed-8698578
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86985782021-12-24 Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer Chan, Wai-Kin Sun, Jui-Hung Liou, Miaw-Jene Li, Yan-Rong Chou, Wei-Yu Liu, Feng-Hsuan Chen, Szu-Tah Peng, Syu-Jyun Biomedicines Article Differentiated thyroid cancer (DTC) from follicular epithelial cells is the most common form of thyroid cancer. Beyond the common papillary thyroid carcinoma (PTC), there are a number of rare but difficult-to-diagnose pathological classifications, such as follicular thyroid carcinoma (FTC). We employed deep convolutional neural networks (CNNs) to facilitate the clinical diagnosis of differentiated thyroid cancers. An image dataset with thyroid ultrasound images of 421 DTCs and 391 benign patients was collected. Three CNNs (InceptionV3, ResNet101, and VGG19) were retrained and tested after undergoing transfer learning to classify malignant and benign thyroid tumors. The enrolled cases were classified as PTC, FTC, follicular variant of PTC (FVPTC), Hürthle cell carcinoma (HCC), or benign. The accuracy of the CNNs was as follows: InceptionV3 (76.5%), ResNet101 (77.6%), and VGG19 (76.1%). The sensitivity was as follows: InceptionV3 (83.7%), ResNet101 (72.5%), and VGG19 (66.2%). The specificity was as follows: InceptionV3 (83.7%), ResNet101 (81.4%), and VGG19 (76.9%). The area under the curve was as follows: Incep-tionV3 (0.82), ResNet101 (0.83), and VGG19 (0.83). A comparison between performance of physicians and CNNs was assessed and showed significantly better outcomes in the latter. Our results demonstrate that retrained deep CNNs can enhance diagnostic accuracy in most DTCs, including follicular cancers. MDPI 2021-11-26 /pmc/articles/PMC8698578/ /pubmed/34944587 http://dx.doi.org/10.3390/biomedicines9121771 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chan, Wai-Kin
Sun, Jui-Hung
Liou, Miaw-Jene
Li, Yan-Rong
Chou, Wei-Yu
Liu, Feng-Hsuan
Chen, Szu-Tah
Peng, Syu-Jyun
Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title_full Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title_fullStr Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title_full_unstemmed Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title_short Using Deep Convolutional Neural Networks for Enhanced Ultrasonographic Image Diagnosis of Differentiated Thyroid Cancer
title_sort using deep convolutional neural networks for enhanced ultrasonographic image diagnosis of differentiated thyroid cancer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8698578/
https://www.ncbi.nlm.nih.gov/pubmed/34944587
http://dx.doi.org/10.3390/biomedicines9121771
work_keys_str_mv AT chanwaikin usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT sunjuihung usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT lioumiawjene usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT liyanrong usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT chouweiyu usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT liufenghsuan usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT chenszutah usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer
AT pengsyujyun usingdeepconvolutionalneuralnetworksforenhancedultrasonographicimagediagnosisofdifferentiatedthyroidcancer