FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172005333> ?p ?o ?g. }

• W3172005333 endingPage "e259" @default.
• W3172005333 startingPage "e250" @default.
• W3172005333 abstract "BackgroundStrategies for integrating artificial intelligence (AI) into thyroid nodule management require additional development and testing. We developed a deep-learning AI model (ThyNet) to differentiate between malignant tumours and benign thyroid nodules and aimed to investigate how ThyNet could help radiologists improve diagnostic performance and avoid unnecessary fine needle aspiration.MethodsThyNet was developed and trained on 18 049 images of 8339 patients (training set) from two hospitals (the First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China, and Sun Yat-sen University Cancer Center, Guangzhou, China) and tested on 4305 images of 2775 patients (total test set) from seven hospitals (the First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China; the Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the Guangzhou Army General Hospital, Guangzhou, China; the Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the First Affiliated Hospital of Sun Yat-sen University; Sun Yat-sen University Cancer Center; and the First Affiliated Hospital of Guangxi Medical University, Nanning, China) in three stages. All nodules in the training and total test set were pathologically confirmed. The diagnostic performance of ThyNet was first compared with 12 radiologists (test set A); a ThyNet-assisted strategy, in which ThyNet assisted diagnoses made by radiologists, was developed to improve diagnostic performance of radiologists using images (test set B); the ThyNet assisted strategy was then tested in a real-world clinical setting (using images and videos; test set C). In a simulated scenario, the number of unnecessary fine needle aspirations avoided by ThyNet-assisted strategy was calculated.FindingsThe area under the receiver operating characteristic curve (AUROC) for accurate diagnosis of ThyNet (0·922 [95% CI 0·910–0·934]) was significantly higher than that of the radiologists (0·839 [0·834–0·844]; p<0·0001). Furthermore, ThyNet-assisted strategy improved the pooled AUROC of the radiologists from 0·837 (0·832–0·842) when diagnosing without ThyNet to 0·875 (0·871–0·880; p<0·0001) with ThyNet for reviewing images, and from 0·862 (0·851–0·872) to 0·873 (0·863–0·883; p<0·0001) in the clinical test, which used images and videos. In the simulated scenario, the number of fine needle aspirations decreased from 61·9% to 35·2% using the ThyNet-assisted strategy, while missed malignancy decreased from 18·9% to 17·0%.InterpretationThe ThyNet-assisted strategy can significantly improve the diagnostic performance of radiologists and help reduce unnecessary fine needle aspirations for thyroid nodules.FundingNational Natural Science Foundation of China and Guangzhou Science and Technology Project. Strategies for integrating artificial intelligence (AI) into thyroid nodule management require additional development and testing. We developed a deep-learning AI model (ThyNet) to differentiate between malignant tumours and benign thyroid nodules and aimed to investigate how ThyNet could help radiologists improve diagnostic performance and avoid unnecessary fine needle aspiration. ThyNet was developed and trained on 18 049 images of 8339 patients (training set) from two hospitals (the First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China, and Sun Yat-sen University Cancer Center, Guangzhou, China) and tested on 4305 images of 2775 patients (total test set) from seven hospitals (the First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China; the Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the Guangzhou Army General Hospital, Guangzhou, China; the Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the First Affiliated Hospital of Sun Yat-sen University; Sun Yat-sen University Cancer Center; and the First Affiliated Hospital of Guangxi Medical University, Nanning, China) in three stages. All nodules in the training and total test set were pathologically confirmed. The diagnostic performance of ThyNet was first compared with 12 radiologists (test set A); a ThyNet-assisted strategy, in which ThyNet assisted diagnoses made by radiologists, was developed to improve diagnostic performance of radiologists using images (test set B); the ThyNet assisted strategy was then tested in a real-world clinical setting (using images and videos; test set C). In a simulated scenario, the number of unnecessary fine needle aspirations avoided by ThyNet-assisted strategy was calculated. The area under the receiver operating characteristic curve (AUROC) for accurate diagnosis of ThyNet (0·922 [95% CI 0·910–0·934]) was significantly higher than that of the radiologists (0·839 [0·834–0·844]; p<0·0001). Furthermore, ThyNet-assisted strategy improved the pooled AUROC of the radiologists from 0·837 (0·832–0·842) when diagnosing without ThyNet to 0·875 (0·871–0·880; p<0·0001) with ThyNet for reviewing images, and from 0·862 (0·851–0·872) to 0·873 (0·863–0·883; p<0·0001) in the clinical test, which used images and videos. In the simulated scenario, the number of fine needle aspirations decreased from 61·9% to 35·2% using the ThyNet-assisted strategy, while missed malignancy decreased from 18·9% to 17·0%. The ThyNet-assisted strategy can significantly improve the diagnostic performance of radiologists and help reduce unnecessary fine needle aspirations for thyroid nodules." @default.
• W3172005333 created "2021-06-22" @default.
• W3172005333 creator A5000637143 @default.
• W3172005333 creator A5007312763 @default.
• W3172005333 creator A5013240918 @default.
• W3172005333 creator A5023526707 @default.
• W3172005333 creator A5031709547 @default.
• W3172005333 creator A5035519525 @default.
• W3172005333 creator A5035863523 @default.
• W3172005333 creator A5037951010 @default.
• W3172005333 creator A5039238883 @default.
• W3172005333 creator A5040205022 @default.
• W3172005333 creator A5041388103 @default.
• W3172005333 creator A5045498363 @default.
• W3172005333 creator A5046958855 @default.
• W3172005333 creator A5050508395 @default.
• W3172005333 creator A5053015958 @default.
• W3172005333 creator A5055693358 @default.
• W3172005333 creator A5061788165 @default.
• W3172005333 creator A5061892970 @default.
• W3172005333 creator A5065787822 @default.
• W3172005333 creator A5066559595 @default.
• W3172005333 creator A5068252474 @default.
• W3172005333 creator A5073844365 @default.
• W3172005333 creator A5077410670 @default.
• W3172005333 creator A5085787908 @default.
• W3172005333 creator A5087337734 @default.
• W3172005333 creator A5089114785 @default.
• W3172005333 date "2021-04-01" @default.
• W3172005333 modified "2023-10-15" @default.
• W3172005333 title "Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study" @default.
• W3172005333 cites W1484128005 @default.
• W3172005333 cites W2031898975 @default.
• W3172005333 cites W2045658574 @default.
• W3172005333 cites W2054679703 @default.
• W3172005333 cites W2077963729 @default.
• W3172005333 cites W2087132831 @default.
• W3172005333 cites W2089588713 @default.
• W3172005333 cites W2091586716 @default.
• W3172005333 cites W2111010188 @default.
• W3172005333 cites W2137591261 @default.
• W3172005333 cites W2142775760 @default.
• W3172005333 cites W2144678115 @default.
• W3172005333 cites W2145150141 @default.
• W3172005333 cites W2152446218 @default.
• W3172005333 cites W2581082771 @default.
• W3172005333 cites W2603963723 @default.
• W3172005333 cites W2772246530 @default.
• W3172005333 cites W2788633781 @default.
• W3172005333 cites W2807852823 @default.
• W3172005333 cites W2886281300 @default.
• W3172005333 cites W2896561890 @default.
• W3172005333 cites W2901702315 @default.
• W3172005333 cites W2905949064 @default.
• W3172005333 cites W2911378287 @default.
• W3172005333 cites W2956423933 @default.
• W3172005333 cites W2963446712 @default.
• W3172005333 cites W3005273854 @default.
• W3172005333 cites W3036242295 @default.
• W3172005333 cites W3081164189 @default.
• W3172005333 doi "https://doi.org/10.1016/s2589-7500(21)00041-8" @default.
• W3172005333 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33766289" @default.
• W3172005333 hasPublicationYear "2021" @default.
• W3172005333 type Work @default.
• W3172005333 sameAs 3172005333 @default.
• W3172005333 citedByCount "101" @default.
• W3172005333 countsByYear W31720053332021 @default.
• W3172005333 countsByYear W31720053332022 @default.
• W3172005333 countsByYear W31720053332023 @default.
• W3172005333 crossrefType "journal-article" @default.
• W3172005333 hasAuthorship W3172005333A5000637143 @default.
• W3172005333 hasAuthorship W3172005333A5007312763 @default.
• W3172005333 hasAuthorship W3172005333A5013240918 @default.
• W3172005333 hasAuthorship W3172005333A5023526707 @default.
• W3172005333 hasAuthorship W3172005333A5031709547 @default.
• W3172005333 hasAuthorship W3172005333A5035519525 @default.
• W3172005333 hasAuthorship W3172005333A5035863523 @default.
• W3172005333 hasAuthorship W3172005333A5037951010 @default.
• W3172005333 hasAuthorship W3172005333A5039238883 @default.
• W3172005333 hasAuthorship W3172005333A5040205022 @default.
• W3172005333 hasAuthorship W3172005333A5041388103 @default.
• W3172005333 hasAuthorship W3172005333A5045498363 @default.
• W3172005333 hasAuthorship W3172005333A5046958855 @default.
• W3172005333 hasAuthorship W3172005333A5050508395 @default.
• W3172005333 hasAuthorship W3172005333A5053015958 @default.
• W3172005333 hasAuthorship W3172005333A5055693358 @default.
• W3172005333 hasAuthorship W3172005333A5061788165 @default.
• W3172005333 hasAuthorship W3172005333A5061892970 @default.
• W3172005333 hasAuthorship W3172005333A5065787822 @default.
• W3172005333 hasAuthorship W3172005333A5066559595 @default.
• W3172005333 hasAuthorship W3172005333A5068252474 @default.
• W3172005333 hasAuthorship W3172005333A5073844365 @default.
• W3172005333 hasAuthorship W3172005333A5077410670 @default.
• W3172005333 hasAuthorship W3172005333A5085787908 @default.
• W3172005333 hasAuthorship W3172005333A5087337734 @default.
• W3172005333 hasAuthorship W3172005333A5089114785 @default.
• W3172005333 hasBestOaLocation W31720053331 @default.
• W3172005333 hasConcept C126322002 @default.

• next