E. Fartushnyi, Yulia P. Sytch, I. Fartushnyi, K. Koshechkin, G. Lebedev
{"title":"使用卷积神经网络的迁移学习对Eu-TIRADS分类的甲状腺结节分层","authors":"E. Fartushnyi, Yulia P. Sytch, I. Fartushnyi, K. Koshechkin, G. Lebedev","doi":"10.14341/ket12724","DOIUrl":null,"url":null,"abstract":"The article describes a method for assessing the malignancy potential of thyroid nodules and their stratification according to the European Thyroid Imaging And Reporting Data System (Eu-TIRADS) scale based on ultrasound diagnostic images using an artificial intelligence system. The method is based on the use of transfer learning technology for multi-parameter models of convolutional neural networks and their subsequent fine tuning. It was shown that even on a small dataset consisting of 1129 thyroid ultrasound images classified by 5 Eu-TIRADS categories, the application of the method provides high training accuracy (Accuracy: 0.8, AUC: 0.92). This makes it possible to introduce and use this technology in clinical practice as an additional tool (‘second opinion’) for an objective assessment of the risk of malignancy in thyroid nodules for the purpose of their further selection for fine needle biopsy.","PeriodicalId":10284,"journal":{"name":"Clinical and experimental thyroidology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Stratification of thyroid nodules by Eu-TIRADS categories using transfer learning of convolutional neural networks\",\"authors\":\"E. Fartushnyi, Yulia P. Sytch, I. Fartushnyi, K. Koshechkin, G. Lebedev\",\"doi\":\"10.14341/ket12724\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The article describes a method for assessing the malignancy potential of thyroid nodules and their stratification according to the European Thyroid Imaging And Reporting Data System (Eu-TIRADS) scale based on ultrasound diagnostic images using an artificial intelligence system. The method is based on the use of transfer learning technology for multi-parameter models of convolutional neural networks and their subsequent fine tuning. It was shown that even on a small dataset consisting of 1129 thyroid ultrasound images classified by 5 Eu-TIRADS categories, the application of the method provides high training accuracy (Accuracy: 0.8, AUC: 0.92). This makes it possible to introduce and use this technology in clinical practice as an additional tool (‘second opinion’) for an objective assessment of the risk of malignancy in thyroid nodules for the purpose of their further selection for fine needle biopsy.\",\"PeriodicalId\":10284,\"journal\":{\"name\":\"Clinical and experimental thyroidology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Clinical and experimental thyroidology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.14341/ket12724\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical and experimental thyroidology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14341/ket12724","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Stratification of thyroid nodules by Eu-TIRADS categories using transfer learning of convolutional neural networks
The article describes a method for assessing the malignancy potential of thyroid nodules and their stratification according to the European Thyroid Imaging And Reporting Data System (Eu-TIRADS) scale based on ultrasound diagnostic images using an artificial intelligence system. The method is based on the use of transfer learning technology for multi-parameter models of convolutional neural networks and their subsequent fine tuning. It was shown that even on a small dataset consisting of 1129 thyroid ultrasound images classified by 5 Eu-TIRADS categories, the application of the method provides high training accuracy (Accuracy: 0.8, AUC: 0.92). This makes it possible to introduce and use this technology in clinical practice as an additional tool (‘second opinion’) for an objective assessment of the risk of malignancy in thyroid nodules for the purpose of their further selection for fine needle biopsy.