Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study

Abstract Background 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pei Yang, Yong Pi, Tao He, Jiangming Sun, Jianan Wei, Yongzhao Xiang, Lisha Jiang, Lin Li, Zhang Yi, Zhen Zhao, Huawei Cai
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Artificial intelligence Deep convolutional neural network Thyroid scintigraphy Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/f5b6cdbeae33436189c0034d1f2daf45
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f5b6cdbeae33436189c0034d1f2daf45
record_format	dspace
spelling	oai:doaj.org-article:f5b6cdbeae33436189c0034d1f2daf452021-11-28T12:30:30ZAutomatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study10.1186/s12880-021-00710-41471-2342https://doaj.org/article/f5b6cdbeae33436189c0034d1f2daf452021-11-01T00:00:00Zhttps://doi.org/10.1186/s12880-021-00710-4https://doaj.org/toc/1471-2342Abstract Background 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. Methods We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model’s performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. Results The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for ‘diffusely increased,’ 0.997 for ‘diffusely decreased,’ 0.998 for ‘focal increased,’ and 0.945 for ‘heterogeneous uptake’ in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. Conclusions Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.Pei YangYong PiTao HeJiangming SunJianan WeiYongzhao XiangLisha JiangLin LiZhang YiZhen ZhaoHuawei CaiBMCarticleArtificial intelligenceDeep convolutional neural networkThyroid scintigraphyMedical technologyR855-855.5ENBMC Medical Imaging, Vol 21, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Artificial intelligence Deep convolutional neural network Thyroid scintigraphy Medical technology R855-855.5
spellingShingle	Artificial intelligence Deep convolutional neural network Thyroid scintigraphy Medical technology R855-855.5 Pei Yang Yong Pi Tao He Jiangming Sun Jianan Wei Yongzhao Xiang Lisha Jiang Lin Li Zhang Yi Zhen Zhao Huawei Cai Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
description	Abstract Background 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. Methods We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model’s performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. Results The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for ‘diffusely increased,’ 0.997 for ‘diffusely decreased,’ 0.998 for ‘focal increased,’ and 0.945 for ‘heterogeneous uptake’ in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. Conclusions Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.
format	article
author	Pei Yang Yong Pi Tao He Jiangming Sun Jianan Wei Yongzhao Xiang Lisha Jiang Lin Li Zhang Yi Zhen Zhao Huawei Cai
author_facet	Pei Yang Yong Pi Tao He Jiangming Sun Jianan Wei Yongzhao Xiang Lisha Jiang Lin Li Zhang Yi Zhen Zhao Huawei Cai
author_sort	Pei Yang
title	Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
title_short	Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
title_full	Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
title_fullStr	Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
title_full_unstemmed	Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
title_sort	automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study
publisher	BMC
publishDate	2021
url	https://doaj.org/article/f5b6cdbeae33436189c0034d1f2daf45
work_keys_str_mv	AT peiyang automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT yongpi automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT taohe automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT jiangmingsun automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT jiananwei automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT yongzhaoxiang automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT lishajiang automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT linli automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT zhangyi automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT zhenzhao automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy AT huaweicai automaticdifferentiationofthyroidscintigrambydeepconvolutionalneuralnetworkadualcenterstudy
_version_	1718407991217094656

Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study

Ejemplares similares