{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T12:42:27Z","timestamp":1792672947186,"version":"4.5.0"},"reference-count":40,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T00:00:00Z","timestamp":1792281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Ultrason Imaging"],"abstract":"<jats:p>\n                    Ultrasound assessment of cervical lymph node metastasis in papillary thyroid carcinoma is crucial but suffers from inter-observer variability. Existing deep learning solutions typically use separate single-task pipelines, resulting in parameter redundancy. We propose MTL-LymphNet, a lightweight, backbone-agnostic multi-task learning framework that simultaneously segments lymph nodes and classifies metastasis within a single forward pass, evaluated across 3 backbones and 4 loss weighting strategies. On 338 images from 2 independent clinical centers, MTL-LymphNet achieved an internal cross-validation Dice coefficient of 0.891\u2009\u00b1\u20090.022 and AUC of 0.948\u2009\u00b1\u20090.027. Bidirectional external validation revealed substantial domain shift, with cross-center Dice of 0.865 and 0.779, and AUC of 0.733 and 0.830. The multi-task configuration offered a favorable efficiency\u2013performance trade-off (\u2206Dice\u2009=\u2009\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mi>\u0394<\/mml:mi>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    ,\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mo>\u2212<\/mml:mo>\n                          <mml:mn>0<\/mml:mn>\n                          <mml:mo>.<\/mml:mo>\n                          <mml:mn>014<\/mml:mn>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    , P &lt; .0001) for 40% fewer parameters than separate models. No backbone or weighting strategy consistently dominated, and calibration degraded substantially under domain shift (ECE: 0.049 internally vs 0.178-0.304 externally), requiring center-specific recalibration before clinical use. To our knowledge, this is the first MTL framework for cervical lymph node analysis with bidirectional multi-center validation and systematic ablation. With a compact size of 22.6 to 29.1\u2009MB and CPU inference of 81 to 131\u2009ms, MTL-LymphNet demonstrates technical feasibility as a CAD tool warranting prospective validation.\n                  <\/jats:p>","DOI":"10.1177\/01617346261488317","type":"journal-article","created":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T05:14:06Z","timestamp":1792386846000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["MTL-LymphNet: A Lightweight Multi-Task Learning Framework for Simultaneous Lymph Node Segmentation and Metastasis Classification in Thyroid Cancer Ultrasound"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9047-9171","authenticated-orcid":false,"given":"Muhammad","family":"Thahiruddin","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Universitas Annuqayah, Sumenep, Jawa Timur, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imam","family":"Wahyudi","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Universitas Annuqayah, Sumenep, Jawa Timur, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfie Nuril","family":"Mustofa","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Universitas Annuqayah, Sumenep, Jawa Timur, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,10,18]]},"reference":[{"key":"e_1_3_5_2_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21820"},{"key":"e_1_3_5_3_2","doi-asserted-by":"publisher","DOI":"10.1177\/10507256251363120"},{"key":"e_1_3_5_4_2","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2012.0043"},{"key":"e_1_3_5_5_2","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2013.0367"},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.1159\/000354537"},{"key":"e_1_3_5_7_2","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2007.0269"},{"key":"e_1_3_5_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/lary.21227"},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_3_5_10_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng-071516-044442"},{"key":"e_1_3_5_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_5_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24144668"},{"key":"e_1_3_5_13_2","unstructured":"Oktay O Schlemper J Folgoc LL et al. Attention U-net: learning where to look for the pancreas. Medical Imaging with Deep Learning https:\/\/openreview.net\/forum?id=Skft7cijM (2022 accessed 15 August 2026)."},{"key":"e_1_3_5_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"e_1_3_5_15_2","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1204987"},{"key":"e_1_3_5_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/jum.16131"},{"key":"e_1_3_5_17_2","doi-asserted-by":"publisher","DOI":"10.1023\/a:1007379606734"},{"key":"e_1_3_5_18_2","doi-asserted-by":"publisher","unstructured":"Ruder S. An overview of multi-task learning in deep neural networks. Pre-print. Posted online June 15 2017. arXiv:1706.05098. doi:10.48550\/ARXIV.1706.05098","DOI":"10.48550\/ARXIV.1706.05098"},{"key":"e_1_3_5_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47157-0_20"},{"key":"e_1_3_5_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00218"},{"key":"e_1_3_5_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108319"},{"key":"e_1_3_5_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108540"},{"key":"e_1_3_5_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3236693"},{"key":"e_1_3_5_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102633"},{"key":"e_1_3_5_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104616"},{"key":"e_1_3_5_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/icsps66615.2025.11347670"},{"key":"e_1_3_5_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asjsur.2024.02.140"},{"key":"e_1_3_5_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62042-z"},{"key":"e_1_3_5_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3575454"},{"key":"e_1_3_5_30_2","first-page":"3","volume-title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","author":"Zhou Z","year":"2018","unstructured":"Zhou Z, Rahman Siddiquee MM, Tajbakhsh N, et al. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. Springer International Publishing; 2018. pp.3-11."},{"key":"e_1_3_5_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280"},{"key":"e_1_3_5_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00781"},{"key":"e_1_3_5_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00197"},{"key":"e_1_3_5_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2026.112694"},{"key":"e_1_3_5_35_2","unstructured":"Wightman R. Pytorch image models https:\/\/github.com\/rwightman\/pytorch-image-models (2019 accessed 15 August 2026)."},{"key":"e_1_3_5_36_2","first-page":"68","volume-title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","author":"Wu K","unstructured":"Wu K, Zhang J, Peng H, et al. TinyViT: Fast Pretraining Distillation for Small Vision Transformers. Springer Nature Switzerland; 2022:68-85."},{"key":"e_1_3_5_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00140"},{"key":"e_1_3_5_38_2","unstructured":"Tan M Le Q. EfficientNet: rethinking model scaling for convolutional neural networks. In Chaudhuri K Salakhutdinov R (eds.) Proceedings of the 36th International Conference on Machine Learning Proceedings of Machine Learning Research volume 97. PMLR 2019:6105-6114. https:\/\/proceedings.mlr.press\/v97\/tan19a.html (accessed 15 August 2026)."},{"key":"e_1_3_5_39_2","unstructured":"Iakubovskii P. Segmentation models pytorch https:\/\/github.com\/qubvel\/segmentation_models.pytorch (2019 accessed 15 August 2026)."},{"key":"e_1_3_5_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"e_1_3_5_41_2","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"}],"container-title":["Ultrasonic Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261488317","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01617346261488317","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261488317","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T11:46:17Z","timestamp":1792669577000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01617346261488317"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,18]]},"references-count":40,"alternative-id":["10.1177\/01617346261488317"],"URL":"https:\/\/doi.org\/10.1177\/01617346261488317","relation":{},"ISSN":["0161-7346","1096-0910"],"issn-type":[{"value":"0161-7346","type":"print"},{"value":"1096-0910","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,18]]},"article-number":"01617346261488317"}}