{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T15:13:16Z","timestamp":1793113996497,"version":"4.5.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Fine needle aspiration (FNA) biopsy of thyroid nodules is a safe, cost-effective, and accurate diagnostic method for detecting thyroid cancer. However, about 10% of initial FNA biopsy samples from patients are non-diagnostic and require repeated FNA, which delays the diagnosis and appropriate care. On-site evaluation of the FNA sample can be performed to filter out non-diagnostic FNA samples. Unfortunately, it involves a time-consuming staining process, and a cytopathologist has to be present at the time of FNA. To bypass the staining process and expert interpretation of FNA specimens at the clinics, we developed a deep learning-based ensemble model termed FNA-Net that allows in situ screening of adequacy of unstained thyroid FNA samples smeared on a glass slide which can decrease the non-diagnostic rate in thyroid FNA. FNA-Net combines two deep learning models, a patch-based whole slide image classifier and Faster R-CNN, to detect follicular clusters with high precision. Then, FNA-Net classifies sample slides to be non-diagnostic if the total number of detected follicular clusters is less than a predetermined threshold. With bootstrapped sampling, FNA-Net achieved a 0.81 F1 score and 0.84 AUC in the precision-recall curve for detecting the non-diagnostic slides whose follicular clusters are less than six. We expect that FNA-Net can dramatically reduce the diagnostic cost associated with FNA biopsy and improve the quality of patient care.<\/jats:p>","DOI":"10.1038\/s41598-023-40652-1","type":"journal-article","created":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T08:01:26Z","timestamp":1692432086000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Screening adequacy of unstained thyroid fine needle aspiration samples using a deep learning-based classifier"],"prefix":"10.1038","volume":"13","author":[{"given":"Junbong","family":"Jang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young H.","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Westgate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caleb","family":"Hallinan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Akalin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwonmoo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"40652_CR1","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1089\/thy.2006.16.109","volume":"16","author":"DS Cooper","year":"2006","unstructured":"Cooper, D. S. et al. Management guidelines for patients with thyroid nodules and differentiated thyroid cancer: The American thyroid association guidelines taskforce. Thyroid 16, 109\u2013142. https:\/\/doi.org\/10.1089\/thy.2006.16.109 (2006).","journal-title":"Thyroid"},{"key":"40652_CR2","unstructured":"Jasim, S., Dean, D. S., Gharib, H. Fine-Needle Aspiration of the Thyroid Gland. Endotext (eds Feingold K. R. et al.) (2023)."},{"key":"40652_CR3","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1210\/er.2002-0016","volume":"24","author":"L Heged\u00fcS","year":"2003","unstructured":"Heged\u00fcS, L., Bonnema, S. J. & Bennedb\u00e6k, F. N. Management of simple nodular goiter: Current status and future perspectives. Endocr. Rev. 24, 102\u2013132. https:\/\/doi.org\/10.1210\/er.2002-0016 (2003).","journal-title":"Endocr. Rev."},{"key":"40652_CR4","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.jss.2011.11.040","volume":"172","author":"LJ Bessey","year":"2012","unstructured":"Bessey, L. J., Lai, N. K., Coorough, N. E., Chen, H. & Sippel, R. S. The incidence of thyroid cancer by FNA varies by age and gender. J. Surg. Res. 172, 188. https:\/\/doi.org\/10.1016\/j.jss.2011.11.040 (2012).","journal-title":"J. Surg. Res."},{"key":"40652_CR5","unstructured":"Hoffman, M. Fine Needle Aspiration. https:\/\/www.webmd.com\/a-to-z-guides\/fine-needle-aspiration (2020)."},{"key":"40652_CR6","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1007\/s12105-009-0104-7","volume":"3","author":"WC Faquin","year":"2009","unstructured":"Faquin, W. C. Diagnosis and reporting of follicular-patterned thyroid lesions by fine needle aspiration. Head Neck Pathol. 3, 82\u201385. https:\/\/doi.org\/10.1007\/s12105-009-0104-7 (2009).","journal-title":"Head Neck Pathol."},{"key":"40652_CR7","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1089\/thy.2012.0211","volume":"23","author":"BL Witt","year":"2013","unstructured":"Witt, B. L. & Schmidt, R. L. Rapid onsite evaluation improves the adequacy of fine-needle aspiration for thyroid lesions: A systematic review and meta-analysis. Thyroid 23, 428\u2013435. https:\/\/doi.org\/10.1089\/thy.2012.0211 (2013).","journal-title":"Thyroid"},{"key":"40652_CR8","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1309\/AJCPEGZMJKC42VUP","volume":"139","author":"RL Schmidt","year":"2013","unstructured":"Schmidt, R. L., Witt, B. L., Lopez-Calderon, L. E. & Layfield, L. J. The influence of rapid onsite evaluation on the adequacy rate of fine-needle aspiration cytology: A systematic review and meta-analysis. Am. J. Clin. Pathol. 139, 300\u2013308. https:\/\/doi.org\/10.1309\/AJCPEGZMJKC42VUP (2013).","journal-title":"Am. J. Clin. Pathol."},{"key":"40652_CR9","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1159\/000444917","volume":"60","author":"EJ De Koster","year":"2016","unstructured":"De Koster, E. J. et al. Thyroid ultrasound-guided fine-needle aspiration: The positive influence of on-site adequacy assessment and number of needle passes on diagnostic cytology rate. Acta Cytol. 60, 39\u201345. https:\/\/doi.org\/10.1159\/000444917 (2016).","journal-title":"Acta Cytol."},{"key":"40652_CR10","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1159\/000489550","volume":"62","author":"L Pearson","year":"2018","unstructured":"Pearson, L. et al. Rapid on-site evaluation of fine-needle aspiration by non-cytopathologists: A systematic review and meta-analysis of diagnostic accuracy studies for adequacy assessment. Acta Cytol. 62, 244\u2013252. https:\/\/doi.org\/10.1159\/000489550 (2018).","journal-title":"Acta Cytol."},{"key":"40652_CR11","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.7860\/JCDR\/2012\/4527.2642","volume":"6","author":"AL Hemalatha","year":"2012","unstructured":"Hemalatha, A. L., Umarani, M. K., Asha, U. & Gayathri, M. N. Are unstained smears, effective tools in the evaluation of the cytological sample adequacy?. J. Clin. Diagn. Res. 6, 1672\u20131674. https:\/\/doi.org\/10.7860\/JCDR\/2012\/4527.2642 (2012).","journal-title":"J. Clin. Diagn. Res."},{"key":"40652_CR12","doi-asserted-by":"publisher","first-page":"e0163045","DOI":"10.1371\/journal.pone.0163045","volume":"11","author":"HS Park","year":"2016","unstructured":"Park, H. S., Rinehart, M. T., Walzer, K. A., Chi, J.-T.A. & Wax, A. Automated Detection of P. falciparum using machine learning algorithms with quantitative phase images of unstained cells. PLoS ONE 11, e0163045. https:\/\/doi.org\/10.1371\/journal.pone.0163045 (2016).","journal-title":"PLoS ONE"},{"key":"40652_CR13","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"40652_CR14","doi-asserted-by":"publisher","first-page":"4876","DOI":"10.7150\/jca.28769","volume":"10","author":"Q Guan","year":"2019","unstructured":"Guan, Q. et al. Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: A pilot study. J. Cancer 10, 4876\u20134882. https:\/\/doi.org\/10.7150\/jca.28769 (2019).","journal-title":"J. Cancer"},{"key":"40652_CR15","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4103\/jpi.jpi_43_18","volume":"9","author":"P Sanyal","year":"2018","unstructured":"Sanyal, P., Mukherjee, T., Barui, S., Das, A. & Gangopadhyay, P. Artificial intelligence in cytopathology: A neural network to identify papillary carcinoma on thyroid fine-needle aspiration cytology smears. J. Pathol. Inform. 9, 43. https:\/\/doi.org\/10.4103\/jpi.jpi_43_18 (2018).","journal-title":"J. Pathol. Inform."},{"key":"40652_CR16","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1002\/cncy.22238","volume":"128","author":"DD Elliott Range","year":"2020","unstructured":"Elliott Range, D. D. et al. Application of a machine learning algorithm to predict malignancy in thyroid cytopathology. Cancer Cytopathol. 128, 287\u2013295. https:\/\/doi.org\/10.1002\/cncy.22238 (2020).","journal-title":"Cancer Cytopathol."},{"key":"40652_CR17","doi-asserted-by":"publisher","unstructured":"Hou, L. et al. Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification. IEEE Conference on Computer Vision and Pattern Recognition, 2424\u20132433. https:\/\/doi.org\/10.1109\/CVPR.2016.266 (2016).","DOI":"10.1109\/CVPR.2016.266"},{"key":"40652_CR18","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"40652_CR19","doi-asserted-by":"publisher","unstructured":"Deng, J. et al. ImageNet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition. https:\/\/doi.org\/10.1109\/cvpr.2009.5206848 (2009).","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"40652_CR20","doi-asserted-by":"publisher","first-page":"17003","DOI":"10.1038\/s41598-018-35274-x","volume":"8","author":"SJ Kim","year":"2018","unstructured":"Kim, S. J. et al. Deep transfer learning-based hologram classification for molecular diagnostics. Sci. Rep. 8, 17003. https:\/\/doi.org\/10.1038\/s41598-018-35274-x (2018).","journal-title":"Sci. Rep."},{"key":"40652_CR21","doi-asserted-by":"publisher","first-page":"23285","DOI":"10.1038\/s41598-021-02683-4","volume":"11","author":"K Vaidyanathan","year":"2021","unstructured":"Vaidyanathan, K. et al. A machine learning pipeline revealing heterogeneous responses to drug perturbations on vascular smooth muscle cell spheroid morphology and formation. Sci. Rep. 11, 23285. https:\/\/doi.org\/10.1038\/s41598-021-02683-4 (2021).","journal-title":"Sci. Rep."},{"key":"40652_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102548","volume":"140","author":"X Pan","year":"2023","unstructured":"Pan, X. et al. Deep cross-modal feature learning applied to predict acutely decompensated heart failure using in-home collected electrocardiography and transthoracic bioimpedance. Artif. Intell. Med. 140, 102548 (2023).","journal-title":"Artif. Intell. Med."},{"key":"40652_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2021.100105","volume":"1","author":"J Jang","year":"2021","unstructured":"Jang, J. et al. A deep learning-based segmentation pipeline for profiling cellular morphodynamics using multiple types of live cell microscopy. Cell Rep. Methods 1, 100105 (2021).","journal-title":"Cell Rep. Methods"},{"key":"40652_CR24","doi-asserted-by":"publisher","DOI":"10.1101\/2021.05.25.445699","author":"C Wang","year":"2021","unstructured":"Wang, C., Choi, H. J., Woodbury, L. & Lee, K. Deep learning-based subcellular phenotyping of protrusion dynamics reveals fine differential drug responses at subcellular and single-cell levels. Biophys. J. https:\/\/doi.org\/10.1101\/2021.05.25.445699 (2021).","journal-title":"Biophys. J."},{"key":"40652_CR25","doi-asserted-by":"publisher","DOI":"10.1101\/2021.05.29.446284","author":"TH Song","year":"2021","unstructured":"Song, T. H. et al. Deep learning-based phenotyping of breast cancer cells using lens-free digital in-line holography. Biophys. J. https:\/\/doi.org\/10.1101\/2021.05.29.446284 (2021).","journal-title":"Biophys. J."},{"key":"40652_CR26","doi-asserted-by":"publisher","unstructured":"Cipolla, R., Gal, Y. & Kendall, A. Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/cvpr.2018.00781 (2018).","DOI":"10.1109\/cvpr.2018.00781"},{"key":"40652_CR27","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 234\u2013241 (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"40652_CR28","unstructured":"Lee, G., Yang, E. & Hwang, S. J. Asymmetric multi-task learning based on task relatedness and loss. Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, 230\u2013238 (2016)."},{"key":"40652_CR29","doi-asserted-by":"publisher","first-page":"38","DOI":"10.12998\/wjcc.v4.i2.38","volume":"4","author":"EP Misiakos","year":"2016","unstructured":"Misiakos, E. P. et al. Cytopathologic diagnosis of fine needle aspiration biopsies of thyroid nodules. World J. Clin. Cases 4, 38\u201348. https:\/\/doi.org\/10.12998\/wjcc.v4.i2.38 (2016).","journal-title":"World J. Clin. Cases"},{"key":"40652_CR30","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1089\/thy.2017.0500","volume":"27","author":"ES Cibas","year":"2017","unstructured":"Cibas, E. S. & Ali, S. Z. The 2017 bethesda system for reporting thyroid cytopathology. Thyroid 27, 1341\u20131346. https:\/\/doi.org\/10.1089\/thy.2017.0500 (2017).","journal-title":"Thyroid"},{"key":"40652_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.632","author":"P Isola","year":"2017","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T. & Efros, A. A. Image-to-image translation with conditional adversarial\u00a0Networks.\u00a0IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/cvpr.2017.632 (2017).","journal-title":"Networks"},{"key":"40652_CR32","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1038\/s41379-019-0205-0","volume":"32","author":"MG Hanna","year":"2019","unstructured":"Hanna, M. G. et al. Whole slide imaging equivalency and efficiency study: Experience at a large academic center. Mod. Pathol. 32, 916\u2013928. https:\/\/doi.org\/10.1038\/s41379-019-0205-0 (2019).","journal-title":"Mod. Pathol."},{"key":"40652_CR33","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/cvpr.2016.91 (2016).","DOI":"10.1109\/cvpr.2016.91"},{"key":"40652_CR34","doi-asserted-by":"publisher","unstructured":"Huang, J. et al. Speed\/accuracy trade-offs for modern convolutional object detectors. IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2017.351 (2017).","DOI":"10.1109\/CVPR.2017.351"},{"key":"40652_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V. & Alemi, A. A. Inception-v4, inception-ResNet and the impact of residual connections on learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4278\u20134284 (2017).","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"40652_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.xpro.2022.101469","volume":"3","author":"J Jang","year":"2022","unstructured":"Jang, J., Hallinan, C. & Lee, K. Protocol for live cell image segmentation to profile cellular morphodynamics using MARS-Net. STAR Protoc. 3, 101469 (2022).","journal-title":"STAR Protoc."}],"updated-by":[{"DOI":"10.1038\/s41598-023-42267-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000}}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-40652-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-40652-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-40652-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T08:06:16Z","timestamp":1700294776000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-40652-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,19]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["40652"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-40652-1","relation":{"correction":[{"id-type":"doi","id":"10.1038\/s41598-023-42267-y","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,19]]},"assertion":[{"value":"1 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41598-023-42267-y","URL":"https:\/\/doi.org\/10.1038\/s41598-023-42267-y","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Y.K., A.A., and K.L. filed a US patent application, 63\/117,254, \u201cWet Read Apparatus and Method to Confirm On-site FNA Biopsy Specimen Adequacy\u201d. The other authors declare no competing financial or non-financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"13525"}}