{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T11:11:55Z","timestamp":1791544315432,"version":"4.3.4"},"reference-count":27,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T00:00:00Z","timestamp":1702080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: The purpose of this study was to develop and evaluate a deep learning model capable of autonomously detecting and segmenting radiolucent lesions in the lower jaw by utilizing You Only Look Once (YOLO) v8. Materials and Methods: This study involved the analysis of 226 lesions present in panoramic radiographs captured between 2013 and 2023 at the Clinical Hospital Dubrava and the School of Dental Medicine, University of Zagreb. Panoramic radiographs included radiolucent lesions such as radicular cysts, ameloblastomas, odontogenic keratocysts (OKC), dentigerous cysts and residual cysts. To enhance the database, we applied techniques such as translation, scaling, rotation, horizontal flipping and mosaic effects. We have employed the deep neural network to tackle our detection and segmentation objectives. Also, to improve our model\u2019s generalization capabilities, we conducted five-fold cross-validation. The assessment of the model\u2019s performance was carried out through metrics like Intersection over Union (IoU), precision, recall and mean average precision (mAP)@50 and mAP@50-95. Results: In the detection task, the precision, recall, mAP@50 and mAP@50-95 scores without augmentation were recorded at 91.8%, 57.1%, 75.8% and 47.3%, while, with augmentation, were 95.2%, 94.4%, 97.5% and 68.7%, respectively. Similarly, in the segmentation task, the precision, recall, mAP@50 and mAP@50-95 values achieved without augmentation were 76%, 75.5%, 75.1% and 48.3%, respectively. Augmentation techniques led to an improvement of these scores to 100%, 94.5%, 96.6% and 72.2%. Conclusions: Our study confirmed that the model developed using the advanced YOLOv8 has the remarkable capability to automatically detect and segment radiolucent lesions in the mandible. With its continual evolution and integration into various medical fields, the deep learning model holds the potential to revolutionize patient care.<\/jats:p>","DOI":"10.3390\/medicina59122138","type":"journal-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T06:56:00Z","timestamp":1702277760000},"page":"2138","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Detection and Segmentation of Radiolucent Lesions in the Lower Jaw on Panoramic Radiographs Using Deep Neural Networks"],"prefix":"10.3390","volume":"59","author":[{"given":"Mario","family":"Ra\u0161i\u0107","sequence":"first","affiliation":[{"name":"Clinic for Tumors, Clinical Hospital Center \u201cSisters of Mercy\u201d, Ilica 197, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Trop\u010di\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska Ulica 3, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pjetra","family":"Karlovi\u0107","sequence":"additional","affiliation":[{"name":"Department of Maxillofacial and Oral Surgery, Dubrava University Hospital, Avenija Gojka \u0160u\u0161ka 6, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0213-1170","authenticated-orcid":false,"given":"Dragana","family":"Gabri\u0107","sequence":"additional","affiliation":[{"name":"Department of Oral Surgery, School of Dental Medicine, University of Zagreb, Gunduli\u0107eva 5, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4321-4557","authenticated-orcid":false,"given":"Marko","family":"Suba\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Faculty of Electrical Engineering and Computing, University of Zagreb, Unska Ulica 3, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Predrag","family":"Kne\u017eevi\u0107","sequence":"additional","affiliation":[{"name":"Department of Maxillofacial and Oral Surgery, Dubrava University Hospital, Avenija Gojka \u0160u\u0161ka 6, 10000 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s41894-021-00111-4","article-title":"Panoramic radiography in dentistry","volume":"5","year":"2021","journal-title":"Clin. Dent. Rev."},{"key":"ref_2","unstructured":"Newman, M.G., Takei, H.H., and Carranza, F.A. (2002). Carranza\u2019s Clinical Periodontology, WB Saunders Co."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1016\/j.acra.2015.05.007","article-title":"The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload","volume":"22","author":"McDonald","year":"2015","journal-title":"Acad. Radiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/s11548-018-1876-6","article-title":"Classification of contrast-enhanced spectral mammography (CESM) images","volume":"14","author":"Perek","year":"2019","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"15415","DOI":"10.1038\/s41598-017-15720-y","article-title":"Searching for prostate cancer by fully automated magnetic resonance imaging classification: Deep learning versus non-deep learning","volume":"7","author":"Wang","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6600","DOI":"10.1038\/s41598-018-25005-7","article-title":"An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images","volume":"8","author":"Li","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fu, M., Wu, W., Hong, X., Liu, Q., Jiang, J., Ou, Y., Zhao, Y., and Gong, X. (2018). Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer images. BMC Syst. Biol., 12.","DOI":"10.1186\/s12918-018-0572-z"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Blanc-Durand, P., Van Der Gucht, A., Schaefer, N., Itti, E., and Prior, J.O. (2018). Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0195798"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2220","DOI":"10.1109\/TVLSI.2017.2688340","article-title":"Deep Convolutional Neural Network Architecture with Reconfigurable Computation Patterns","volume":"25","author":"Tu","year":"2017","journal-title":"IEEE Trans. Very Large Scale Integr. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.oooo.2019.05.014","article-title":"Automatic detection and classification of radiolucent lesions in the mandible on panoramic radiographs using a deep learning object detection technique","volume":"128","author":"Ariji","year":"2019","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yang, H., Jo, E., Kim, H.J., Cha, I.H., Jung, Y.S., Nam, W., Kim, J.Y., Kim, J.K., Kim, Y.H., and Oh, T.G. (2020). Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs. J. Clin. Med., 9.","DOI":"10.3390\/jcm9061839"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"20200185","DOI":"10.1259\/dmfr.20200185","article-title":"Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network","volume":"49","author":"Kwon","year":"2020","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lee, A., Kim, M.S., Han, S.S., Park, P., Lee, C., and Yun, J.P. (2021). Deep learning neural networks to differentiate Stafne's bone cavity from pathological radiolucent lesions of the mandible in heterogeneous panoramic radiography. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0254997"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.compbiomed.2016.11.003","article-title":"Classification of teeth in cone-beam CT using deep convolutional neural network","volume":"80","author":"Miki","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.jdent.2018.07.015","article-title":"Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm","volume":"77","author":"Lee","year":"2018","journal-title":"J. Dent."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s40902-017-0134-0","article-title":"Conservative management (marsupialization) of unicystic ameloblastoma: Literature review and a case report","volume":"39","author":"Kim","year":"2017","journal-title":"Maxillofac. Plast. Reconstr. Surg."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s40902-018-0184-y","article-title":"Volume change pattern of decompression of mandibular odontogenic keratocyst","volume":"41","author":"Park","year":"2019","journal-title":"Maxillofac. Plast. Reconstr. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"236","DOI":"10.4258\/hir.2018.24.3.236","article-title":"Application of Convolutional neural network in the diagnosis of jaw tumors","volume":"24","author":"Poedjiastoeti","year":"2018","journal-title":"Healthc. Inform. Res"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA J. Am. Med. Assoc."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.carj.2010.01.001","article-title":"Pictorial Essay: Cysts and Cyst-like Lesions of the Jaws","volume":"61","author":"Bharatha","year":"2010","journal-title":"Can. Assoc. Radiol. J."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1148\/rg.327125003","article-title":"Radiopaque jaw lesions: An approach to the differential diagnosis","volume":"32","author":"Vattoth","year":"2012","journal-title":"Radiographics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1016\/j.jds.2022.12.008","article-title":"Deep learning model for the automated evaluation of contact between the lower third molar and inferior alveolar nerve on panoramic radiography","volume":"18","author":"Takebe","year":"2023","journal-title":"J. Dent. Sci."},{"key":"ref_24","first-page":"42","article-title":"An automated technique to stage lower third molar development on panoramic radiographs for age estimation: A pilot study","volume":"2","author":"Radesh","year":"2017","journal-title":"J. Forensic Odontostomatol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"27","DOI":"10.5624\/isd.20220133","article-title":"Effect of deep transfer learning with a different kind of lesion on classification performance of pretrained model: Verification with radiolucent lesions on panoramic radiographs","volume":"53","author":"Kise","year":"2023","journal-title":"Imaging Sci. Dent."},{"key":"ref_27","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018). Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer."}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/59\/12\/2138\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:35:53Z","timestamp":1760132153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/59\/12\/2138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,9]]},"references-count":27,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["medicina59122138"],"URL":"https:\/\/doi.org\/10.3390\/medicina59122138","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,9]]}}}