Yonsei University · 歯学
Professor Wonse Park's research lab specializes in the application of deep learning and artificial intelligence in oral and maxillofacial diagnostics, with a focus on improving the accuracy and efficiency of dental implant identification and classification using medical imaging. The lab conducts large-scale, multicenter studies involving panoramic and periapical radiographs to develop and validate AI algorithms that support clinical decision-making. Research also extends to the molecular biology of estrogen receptors in ovarian cancer and the diagnostic challenges of temporomandibular disorders, highlighting a multidisciplinary approach combining AI, radiology, and biomedical research. The lab is committed to translating advanced computational methods into practical clinical tools, including mobile-based emergency diagnostic systems.
Figures are computed from collected data and may differ slightly.
This study aimed to evaluate the accuracy of automated deep learning (DL) algorithm for identifying and classifying various types of dental implant systems (DIS) using a large-scale multicenter dataset. Dental implant radiographs of pos-implant surgery were collected from five college dental hospitals and 10 private dental clinics, and validated by the National Information Society Agency and the Korean Academy of Oral and Maxillofacial Implantology. The dataset contained a total of 156,965 panor
This study aimed to evaluate the efficacy of deep learning (DL) for the identification and classification of various types of dental implant systems (DISs) using a large-scale multicenter data set. We also compared the classification accuracy of DL and dental professionals. The data set, which was collected from 5 college dental hospitals and 10 private dental clinics, contained 37,442 (24.8%) periapical and 113,291 (75.2%) panoramic radiographic images and consisted of a total of 10 manufacture
By means of reverse transcription-PCR we have identified an alternatively spliced mRNA coding for a variant estrogen receptor (ER) that lacks exon 4 (ERDelta4) and is coexpressed with the wild-type ER mRNA in ovarian carcinomas. Furthermore, Western blot analysis revealed the expression of the ERDelta4 protein in normal as well as neoplastic ovarian tissues along with the wild-type ER, although the relative amounts of the wild-type ER and ERDelta4 proteins varied. The trans-activational properti
Pain and dysfunction in the temporomandibular joint (TMJ) region represent a diagnostic challenge. Temporomandibular disorders (TMD) are usually diagnosed by means of a thorough patient history and comprehensive clinical examination. However, additional diagnostic tests, such as imaging of the TMJ area, are necessary in cases where the signs do not explain the symptoms. Neoplasms and pseudotumors of the TMJ are quite uncommon, but their early recognition is necessary in order prevent the delay o
Our optimal protocol could be useful for emergency programs running on the mobile phones.
Open papers in the app to read, cite, and organize with AI.
