{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T21:44:50Z","timestamp":1744839890212,"version":"3.32.0"},"reference-count":0,"publisher":"SRUMB - Romanian Society for Ultrasonography in Medicine and Biology","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Med Ultrason"],"abstract":"<jats:p>Aims: This study aims to use deep learning (DL) to classify thyroid nodules as benign and malignant with ultrasonography\u00a0(US). In addition, this study investigates the impact of DL on the diagnostic success of radiologists with different experiences.\u00a0Material and methods: This study included 576 US images of thyroid nodules. The dataset was divided into 80% training\u00a0and 20% test sets. Four radiologists with different levels of experience classified the images in the test set as benign-malignant.\u00a0A DL model was then trained with the train set and predicted benign-malignant for the test set. Then, the output of the DL\u00a0model for each nodule in the test set was presented to 4 radiologists, who were asked to make a benign-malignant classification\u00a0again considering these DL results.Results: The accuracy of the DL model was 0.9391. The accuracy for junior resident\u00a0(JR) 1, JR 2, senior resident (SR), and senior radiologist (Srad) before DL-assisting were 0.7043, 0.7826, 0.8435, and 0.8522\u00a0respectively. The accuracy in DL-assisted classifications was 0.9130, 0.8696, 0.9304, and 0.9043 for JR 1, JR2, SR, and Srad,\u00a0respectively. DL assistance changed the decisions of less experienced radiologists more than more experienced radiologists.\u00a0Conclusion: The DL model has superior accuracy in classifying thyroid nodules as benign-malignant with US images than\u00a0radiologists with different levels of experience. Additionally, all radiologists, and most notably less experienced radiology\u00a0residents, increased their accuracy in DL-assisted predictions.\u00a0<\/jats:p>","DOI":"10.11152\/mu-4432","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T04:53:31Z","timestamp":1725425611000},"source":"Crossref","is-referenced-by-count":1,"title":["The impact of deep learning on diagnostic performance in the differentiation of benign and malignant thyroid nodules"],"prefix":"10.11152","author":[{"given":"Esat","family":"Kaba","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Merve","family":"Solak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ay\u015fenur Top\u00e7u","family":"Varl\u0131k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuf","family":"\u00c7ubuk\u00e7u","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L\u00fctfullah","family":"Sa\u011f\u0131r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kubilay Muhammed","family":"S\u00fcnnetci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet","family":"Alkan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasan","family":"G\u00fcndo\u011fdu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatma Beyazal","family":"\u00c7eliker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehmet","family":"Beyazal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4840","published-online":{"date-parts":[[2024,9,4]]},"container-title":["Medical Ultrasonography"],"original-title":[],"link":[{"URL":"https:\/\/www.medultrason.ro\/medultrason\/index.php\/medultrason\/article\/viewFile\/4432\/2360","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.medultrason.ro\/medultrason\/index.php\/medultrason\/article\/viewFile\/4432\/2360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T12:58:29Z","timestamp":1734613109000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medultrason.ro\/medultrason\/index.php\/medultrason\/article\/view\/4432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,4]]},"references-count":0,"URL":"https:\/\/doi.org\/10.11152\/mu-4432","relation":{},"ISSN":["2066-8643","1844-4172"],"issn-type":[{"type":"electronic","value":"2066-8643"},{"type":"print","value":"1844-4172"}],"subject":[],"published":{"date-parts":[[2024,9,4]]}}}