{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:01:05Z","timestamp":1780290065240,"version":"3.54.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020737","name":"Renji Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020737","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The management of ultrasonography (US) of thyroid nodules is often time consuming and may be inconsistent between observers. The use of deep learning (DL) can increase the speed of examinations and improve reporting consistency. To develop a novel dual attention-guided DL framework to inference histological status directly from thyroid US without expensive image-level annotations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective analysis, patients first underwent US followed by histopathological examination by fine needle aspiration or surgical histological analysis. Two datasets from the Second Affiliated Hospital of Jiaxing University, Batch 1 and Batch 2, were used in our study for training, testing and validation of the algorithm, respectively. The proposed DL framework is named ThyUS2Path and consists of two attention modules which focus on discriminative nodule patterns in different dimensions. We compare ThyUS2Path with two commonly used state-of-the-art MIL-based methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We used 6014 images from 603 patients to build the DL framework and evaluated it on 1978 external images, five-fold cross validation AUCs of 0.754 \u00b1 0.035 and 0.735 \u00b1 0.029, respectively. ThyUS2Path outperformed two commonly state-of-the-art MIL-based methods significantly, namely Maxpool and Meanpool. The algorithms also obtained good prediction performance in the external test set (AUROCs of 0.70~0.80 and AUPRCs of 0.78~0.83).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our approach gives a feasible way to link the US phenotype with histological reports and has the potential to augment clinicians\u2019 capabilities in thyroid cancer diagnosis in a non-invasive manner.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1834977","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T04:18:05Z","timestamp":1780287485000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Pathological diagnosis of thyroid nodules directly from ultrasonography by a weakly supervised deep learning framework"],"prefix":"10.3389","volume":"17","author":[{"given":"Xiao-Wen","family":"Hou","sequence":"first","affiliation":[{"name":"Ningbo Hangzhou Bay Hospital","place":["Ningbo, China"]},{"name":"Renji Hospital, School of Medicine, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei-Ling","family":"He","sequence":"additional","affiliation":[{"name":"Ningbo Hangzhou Bay Hospital","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Yue","family":"Ye","sequence":"additional","affiliation":[{"name":"Ningbo Hangzhou Bay Hospital","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Xin","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Harbin Medical University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu-Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Harbin Medical University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ultrasonography, The Second Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Neurology, The Second Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen-Zhao","family":"Sun","sequence":"additional","affiliation":[{"name":"Ningbo Hangzhou Bay Hospital","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ningbo Hangzhou Bay Hospital","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Ru","family":"Jiang","sequence":"additional","affiliation":[{"name":"Renji Hospital, School of Medicine, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Renji Hospital, School of Medicine, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji-Hong","family":"Wang","sequence":"additional","affiliation":[{"name":"Renji Hospital, School of Medicine, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan-Chao","family":"Shi","sequence":"additional","affiliation":[{"name":"Renji Hospital, School of Medicine, Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-Xin","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Ultrasonography, The Second Affiliated Hospital of Jiaxing University","place":["Jiaxing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Harbin Medical University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2006.01.013","article-title":"Quantitative analyses of sonographic images of the parotid gland in patients with Sjogren's syndrome","volume":"32","author":"Chikui","year":"2006","journal-title":"Ultrasound Med Biol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1089\/thy.2015.0020","article-title":"2015 american thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the american thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer","volume":"26","author":"Haugen","year":"2016","journal-title":"Thyroid"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1118\/1.4811156","article-title":"The essential physics of medical imaging, third edition","volume":"40","author":"Mahesh","year":"2013","journal-title":"Med Phys"},{"key":"B4","doi-asserted-by":"publisher","first-page":"277","DOI":"10.3322\/caac.20073","article-title":"Cancer statistics, 2010","volume":"60","author":"Jemal","year":"2010","journal-title":"CA Cancer J Clin"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/s20071822","article-title":"Ultrasound image-based diagnosis of Malignant thyroid nodule using artificial intelligence","volume":"20","author":"Nguyen","year":"2020","journal-title":"Sensors Bsl"},{"key":"B6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1634\/theoncologist.12-1-20","article-title":"Cancer statistics, trends, and multiple primary cancer analyses from the Surveillance, Epidemiology, and End Results (SEER) Program","volume":"12","author":"Hayat","year":"2007","journal-title":"Oncologist"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2008.0342","article-title":"A birth cohort analysis of the incidence of papillary thyroid cancer in the United States, 1973-2004","volume":"19","author":"Zhu","year":"2009","journal-title":"Thyroid"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2016.0075","article-title":"Thyroid cancer screening in South Korea increases detection of papillary cancers with no impact on other subtypes or thyroid cancer mortality","volume":"26","author":"Ahn","year":"2016","journal-title":"Thyroid"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.7863\/jum.2004.23.11.1455","article-title":"Risk for Malignancy of thyroid nodules as assessed by sonographic criteria: the need for biopsy","volume":"23","author":"Iannuccilli","year":"2004","journal-title":"J Ultrasound Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.7863\/jum.2003.22.10.1027","article-title":"Sonographic features of benign thyroid nodules: interobserver reliability and overlap with Malignancy","volume":"22","author":"Wienke","year":"2003","journal-title":"J Ultrasound Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2017.01.046","article-title":"ACR thyroid imaging, reporting and data system (TI-RADS): white paper of the ACR TI-RADS committee","volume":"14","author":"Tessler","year":"2017","journal-title":"J Am Coll Radiol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1159\/000478927","article-title":"European thyroid association guidelines for ultrasound Malignancy risk stratification of thyroid nodules in adults: the EU-TIRADS","volume":"6","author":"Russ","year":"2017","journal-title":"Eur Thyroid J"},{"key":"B13","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1148\/radiol.2373050220","article-title":"Management of thyroid nodules detected at US: Society of Radiologists in Ultrasound consensus conference statement","volume":"237","author":"Frates","year":"2005","journal-title":"Radiology"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2014.0353","article-title":"Thyroid ultrasound features and risk of carcinoma: a systematic review and meta-analysis of observational studies","volume":"25","author":"Remonti","year":"2015","journal-title":"Thyroid"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.4132\/jptm.2017.09.20","article-title":"Thyroid fine-needle aspiration in Taiwan: The history and current practice","volume":"51","author":"Hang","year":"2017","journal-title":"J Pathol Transl Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"38","DOI":"10.12998\/wjcc.v4.i2.38","article-title":"Cytopathologic diagnosis of fine needle aspiration biopsies of thyroid nodules","volume":"4","author":"Misiakos","year":"2016","journal-title":"World J Clin cases"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2265.2012.04404.x","article-title":"What are the keys to successful thyroid FNA interpretation","volume":"77","author":"Sebo","year":"2012","journal-title":"Clin Endocrinol Oxf"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2009.0155","article-title":"The Bethesda thyroid fine-needle aspiration classification system: year 1 at an academic institution","volume":"19","author":"Theoharis","year":"2009","journal-title":"Thyroid"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1309\/AJCP4P2GCCDNHFMY","article-title":"Clinical outcome for atypia of undetermined significance in thyroid fine-needle aspirations: should repeated fna be the preferred initial approach","volume":"135","author":"VanderLaan","year":"2011","journal-title":"Am J Clin Pathol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","article-title":"Computer-aided diagnosis in medical imaging: historical review, current status and future potential","volume":"31","author":"Doi","year":"2007","journal-title":"Comput Med Imaging Graph"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.06.032","article-title":"Machine learning approaches in medical image analysis: From detection to diagnosis","volume":"33","author":"de Bruijne","year":"2016","journal-title":"Med Img Anal"},{"key":"B22","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Img Anal"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B24","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/S1470-2045(18)30762-9","article-title":"Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study","volume":"20","author":"Li","year":"2019","journal-title":"Lancet Oncol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.12659\/MSM.926096","article-title":"Ensemble deep learning model for multicenter classification of thyroid nodules on ultrasound images","volume":"26","author":"Wei","year":"2020","journal-title":"Med Sci Monit"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19992-4_46","article-title":"Multi-scale convolutional neural networks for lung nodule classification","volume":"24","author":"Shen","year":"2015","journal-title":"Inf Proc Med Imaging"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1142\/S0219720021400023","article-title":"Unsupervised multi-instance learning for protein structure determination","volume":"19","author":"Alam","year":"2021","journal-title":"J Bioinform Comput Biol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.04.006","article-title":"Multiple instance learning for classification of dementia in brain MRI","volume":"18","author":"Tong","year":"2014","journal-title":"Med Img Anal"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2900465","article-title":"Multiple instance learning for multiple diverse hyperspectral target characterizations","volume":"31","author":"Zhong","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12134","article-title":"Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images","volume":"44","author":"Ma","year":"2017","journal-title":"Med Phys"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-024-01025-4","article-title":"Thyroid nodules: diagnosis and management","volume":"20","author":"Grani","year":"2024","journal-title":"Nat Rev Endocrinol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1038\/s41746-025-01652-9","article-title":"Multimodal GPT model for assisting thyroid nodule diagnosis and management","volume":"8","author":"Yao","year":"2025","journal-title":"NPJ Dgt Med"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultras.2016.09.011","article-title":"A pre-trained convolutional neural network based method for thyroid nodule diagnosis","volume":"73","author":"Ma","year":"2017","journal-title":"Ultrasonics"},{"key":"B34","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.cmpb.2017.06.005","article-title":"Ultrasound-based differentiation of Malignant and benign thyroid nodules: An extreme learning machine approach","volume":"147","author":"Xia","year":"2017","journal-title":"Comput Methods Prog BioMed"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw252","article-title":"Classifying and segmenting microscopy images with deep multiple instance learning","volume":"32","author":"Kraus","year":"2016","journal-title":"Bioinformatics"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2021.05.038","article-title":"A comparative study of multiple instance learning methods for cancer detection using T-cell receptor sequences","volume":"19","author":"Xiong","year":"2021","journal-title":"Comput Struct Biotechnol J"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1834977\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T04:18:06Z","timestamp":1780287486000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1834977\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":36,"alternative-id":["10.3389\/fendo.2026.1834977"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1834977","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"article-number":"1834977"}}