송인석 교수
In-Seok Song
고려대학교 치과 · 의학
연구실 소개
송인석 교수의 연구실은 구강·악안면 영상의학과 기반의 딥러닝 기반 진단 지원 시스템 개발에 초점을 맞추고 있습니다. 특히 흩어진 뼈 손실, 만성 치주염, 치과 CBCT 영상의 정밀 세분화 등 구강악안면 질환의 정밀 진단을 위한 AI 기반 영상 분석 기술을 연구하고 있습니다. 또한, 신경-면역 상호작용과 같은 생물학적 메커니즘과도 연계해 구강건강과 전신질환의 연관성을 탐구하고 있습니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15In this study, a deep learning-based method for developing an automated diagnostic support system that detects periodontal bone loss in the panoramic dental radiographs is proposed. The presented method called DeNTNet not only detects lesions but also provides the corresponding teeth numbers of the lesion according to dental federation notation. DeNTNet applies deep convolutional neural networks(CNNs) using transfer learning and clinical prior knowledge to overcome the morphological variation of
The objective of this retrospective study is to verify the effectiveness and safety of patient-specific titanium implants on maxillofacial bones, with a long-term follow-up. Total 16 patients with various maxillofacial defects underwent reconstruction using patient-specific titanium implants. Titanium implants, manufactured by electron beam melting, selective laser sintering, or milling, were inserted into the maxilla, mandible, or zygoma. Long-term follow-up (36.7 ± 20.1 months) was conducted a
CONTEXT: We hypothesized that insulin resistance, even with normal body weight (body mass index or waist circumference), can aggravate periodontitis severity. OBJECTIVE: We investigated the associations between diabetes, insulin resistance, and severe periodontitis. DESIGN: Among 29 235 total participants, 5690 subjects aged ≥ 30 y who had periodontal disease with community periodontal index (CPI) of 3 or 4 were selected for this study. PARTICIPANTS: Data were derived from the 2008-2010 Korea Na
The aim of this study was to segment the maxillary sinus into the maxillary bone, air, and lesion, and to evaluate its accuracy by comparing and analyzing the results performed by the experts. We randomly selected 83 cases of deep active learning. Our active learning framework consists of three steps. This framework adds new volumes per step to improve the performance of the model with limited training datasets, while inferring automatically using the model trained in the previous step. We deter
The neurological system plays an important role in modulating some inflammatory skin diseases. Neuro-cutaneous interactions may be mediated by the release of neuropeptides such as substance P (SP) which activate immunocompetent cells in the skin by binding to high affinity neurokinin receptors (NKR). Since epidermal keratinocytes produce a variety of cytokines and are intimately associated with cutaneous sensory fibers, we tested the ability of these cells to participate in the cutaneous neuroim
OBJECTIVE: To predict the hand-wrist maturation stages based on the cervical vertebrae (CV) images, and to analyse the accuracy of the proposed algorithms. SETTINGS AND POPULATION: A total of 499 pairs of hand-wrist radiographs and lateral cephalograms of 455 orthodontic patients aged 6-18 years were used for developing the prediction model for hand-wrist skeletal maturation stages. MATERIALS AND METHODS: The hand-wrist radiographs and the lateral cephalograms were collected from two university
A cDNA clone for glutaminyl cyclase was isolated from a human pituitary cDNA library and the complete DNA sequence determined. The cDNA clone had 1573 bp and contained an open reading frame of 1086 bases, coding for a protein of 361 amino acids and molecular mass of 40,876 Da. The predicted amino acid sequence of the human cDNA showed 86% sequence identity to the previously reported bovine glutaminyl cyclase sequence. A comparison of the amino acid sequences derived from the human and bovine cDN
BACKGROUND: The inferior alveolar nerve (IAN) innervates and regulates the sensation of the mandibular teeth and lower lip. The position of the IAN should be monitored prior to surgery. Therefore, a study using artificial intelligence (AI) was planned to image and track the position of the IAN automatically for a quicker and safer surgery. METHODS: A total of 138 cone-beam computed tomography datasets (Internal: 98, External: 40) collected from multiple centers (three hospitals) were used in the
OBJECTIVE: This study investigated whether obesity is linked with dental caries. This study hypothesized that obesity may influence the number or prevalence of dental caries in Korean adults. SUBJECTS AND METHODS: Data were derived from Korea National Health and Nutrition Examination Survey performed at 2008-2010. Lifestyle, sociodemographic, and biochemical variables were analyzed. Indices related to obesity, sarcopenia, and metabolic syndrome were investigated. Finally, caries index and oral h
The aim of this study was to examine the association between coffee intake and tooth loss. This study hypothesized that the intake of coffee would increase the prevalence of tooth loss in Korean adults. Subject information was obtained from the Korea National Health and Nutrition Examination Survey conducted in 2010-2011. Sociodemographic and lifestyle variables, anthropometric and biochemical status, metabolic health and glucose tolerance status, as well as oral health behaviors were evaluated.
There is growing interest in the relationship between body mass index and oral health. Previous study showed that being underweight was significantly associated with having lower masticatory performance. This study was performed to assess the relationship between an underweight body mass index lower than 18.5 and the number of natural teeth using nationally representative data. Initially, a total of 25,534 individuals were candidates in the Korean National Health and Nutrition Examination Survey
Consumption of carbonated beverages was reported to be associated with obesity and other adverse health consequences. This study was performed to assess the relationship between the consumption of carbonated beverages and periodontal disease using nationally representative data.The data from the Korea National Health and Nutrition Examination Survey conducted between 2008 and 2010 were used; the analysis in this study was confined to a total of 5517 respondents >19 years old who had no missing v
대표 연구 분야
송인석 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.