{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T04:26:56Z","timestamp":1793939216449,"version":"4.8.0"},"reference-count":39,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"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":["Journal of X-Ray Science and Technology"],"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>\n                      Automatic detection and segmentation of dental diseases from panoramic x-ray images have been a difficult task to achieve due to the problems of class imbalance and varying sizes of lesions, as well as the inconspicuous nature of early caries. This paper introduces SwinDent-Seg, which is a hybrid architecture of Swin Transformer-CNN that includes CSFF module, ECMA attention, and high-resolution P\n                      <jats:sub>2<\/jats:sub>\n                      detection head.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>The proposed model was trained and evaluated on a dataset of 1018 annotated panoramic radiographs comprising seven dental pathology classes. Model development and hyperparameter optimization were performed using a validation set (220 images). SwinDent-Seg was compared with multiple CNN- and Transformer-based baselines, including YOLOv8, YOLO11 and RT-DETR-L. A confidence-weighted ensemble combining SwinDent-Seg and YOLOv8m-seg was subsequently evaluated on an independent test set (81 images).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>On the validation set, SwinDent-Seg achieved the best single-model performance, with an mAP50 of 0.8947, outperforming all baseline models, including YOLOv8m-seg (mAP50\u2009=\u20090.6770). The proposed architecture markedly improved caries detection, increasing AP50 from 0.134 to 0.8953. On the independent test set, the confidence-weighted ensemble (SwinDent-Seg\u2009+\u2009YOLOv8m-seg) achieved the best overall performance, with an mAP50 of 0.9289 and a macro-AUC of 0.9515, exceeding the performance of either individual model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>SwinDent-Seg demonstrates superior single-model validation performance, while the confidence-weighted ensemble provides the highest independent test-set performance. These findings indicate that combining Transformer-based global contextual representation with CNN-based localization improves robust multi-class dental pathology segmentation and supports the development of reliable computer-aided diagnostic systems for panoramic radiographs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/08953996261478470","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T13:08:28Z","timestamp":1786972108000},"page":"723-739","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["SwinDent-Seg: Hybrid Swin transformer-CNN with cross-scale feature fusion for automated detection and segmentation of dental pathologies in panoramic radiographs"],"prefix":"10.1177","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9894-0630","authenticated-orcid":false,"given":"SI","family":"Mahizha","sequence":"first","affiliation":[{"name":"St Xavier's Catholic College of Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-393X","authenticated-orcid":false,"given":"J","family":"Annrose","sequence":"additional","affiliation":[{"name":"St Xavier's Catholic College of Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6081-3227","authenticated-orcid":false,"given":"J","family":"Mano Christaine Angelo","sequence":"additional","affiliation":[{"name":"Sree Mookambika Institute of Dental Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22197370"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3389\/froh.2022.764479"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6029245"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13020202"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14202336"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2023.104607"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11030347"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92121-2"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15151961"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gmod.2025.101302"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-026-11939-x"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1051\/mbcb\/2025008"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.3390\/medicina59122138"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-33391-y"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3556523"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15030244"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2018.00058"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105829"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.5624\/isd.20220105"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.0151225"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2024.104891"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01338-w"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14040805"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15131693"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2022.0131230"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3150358"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.48084\/etasr.13101"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.53555\/jptcp.v31i6.6983"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.58496\/MJCS\/2024\/022"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24082483"},{"key":"e_1_3_2_32_2","article-title":"MHAF-YOLO: multi-branch heterogeneous auxiliary fusion YOLO for accurate object detection","volume":"2502","author":"Yang Z","year":"2025","unstructured":"Yang Z, et al. MHAF-YOLO: multi-branch heterogeneous auxiliary fusion YOLO for accurate object detection. ArXiv 2025; {abs\/2502.04656}. Available at: http:\/\/arxiv.org\/abs\/2502.04656","journal-title":"ArXiv"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41432-025-01134-7"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.prosdent.2025.09.040"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.22514\/jocpd.2024.136"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01763-5"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.109784"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2025.105668"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.70019"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90386-1"}],"container-title":["Journal of X-Ray Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08953996261478470","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/08953996261478470","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08953996261478470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T03:50:23Z","timestamp":1793937023000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/08953996261478470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1177\/08953996261478470"],"URL":"https:\/\/doi.org\/10.1177\/08953996261478470","relation":{},"ISSN":["0895-3996","1095-9114"],"issn-type":[{"value":"0895-3996","type":"print"},{"value":"1095-9114","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]}}}