Sam-Sun Lee

Cross-vendor robustness of a hybrid deep learning framework for 4-stage periodontitis classification on panoramic radiographs

Sang-Jeong Lee, Ji Yong Han, Kyung‐Hoe Huh, Min-Suk Heo et autres

OBJECTIVES: Although deep learning for periodontitis diagnosis on panoramic radiographs has advanced rapidly, most studies use single-vendor data and cross-vendor generalization is rarely evaluated. Therefore, we evaluate the cross-vendor robustness of a hybrid CNN-CAD framework for automated four-stage periodontitis classification. METHODS: Five …

kr (code pays fourni par la source)

SinusNet+: deep condition-label-free segmentation of maxillary sinus conditions in cone-beam CT images

D M Kim, Su Yang, Ji Yong Han, Jo-Eun Kim et autres

BACKGROUND: Segmentation of maxillary sinus conditions (MSC) in cone-beam computed tomography (CBCT) images may support preoperative assessment in the posterior maxilla, including implant planning and sinus floor augmentation. Supervised deep learning methods for MSC segmentation typically rely on labor-intensive manual annotation of …

kr (code pays fourni par la source)

Three-dimensional CT imaging features of impacted first permanent molars and their correlation with prognosis

Jinwoo Kim, Jong Woo Kim, Kyung‐Hoe Huh, Won-Jin Yi et autres

OBJECTIVES: Impaction of first permanent molars is uncommon but may affect oral function and craniofacial development. Although various etiologic factors have been proposed, three-dimensional imaging features associated with impacted first permanent molars-particularly, furcation area root resorption-have not been well investigated. The objective …

kr (code pays fourni par la source)

Automatic multi-class classification of 3D relationships between the mandibular third molar and canal on cone-beam computed tomography using a geometry-aware network

Hyomin Kim, Ji Yong Han, Su Yang, Jo‐Eun Kim et autres

OBJECTIVES: Accurate 3D evaluation of the spatial relationship between the mandibular third molar (M3) and the mandibular canal (MC) is critical for assessing the risk of nerve injury during M3 extraction. The purpose of this study was to automatically classify the diverse …

kr (code pays fourni par la source)

Expert consensus-based review and refinement of dental radiographic quality management and radiation safety criteria in oral and maxillofacial radiography in Korea: A Delphi study

Hyun Jin Cho, Sam-Sun Lee, Ju-Hee Kang, Jo‐Eun Kim et autres

Purpose: This study aimed to establish expert consensus on dental radiographic quality management and radiation safety evaluation items published by the Korean Academy of Oral and Maxillofacial Radiology that lacked formal consensusbased validation, while improving terminological precision and ensuring consistency across evaluation …

kr (code pays fourni par la source)

A novel cross-attentive network for classifying cervical metastatic lymph nodes on B- and D-mode ultrasound images in oral squamous cell carcinoma

Yong-Tae Kim, Ji Yong Han, Su Yang, Jong Woo Kim et autres

OBJECTIVES: This study proposes a deep convolutional neural network model that integrates B-mode and D-mode ultrasound images to classify metastatic lymph nodes in patients with oral squamous cell carcinoma. METHODS: A shared backbone network incorporating a cross-attention mechanism was employed to enhance …

kr, us (code pays fourni par la source)

Peritumoral bone changes in mandibular gingival squamous cell carcinoma: A prospective radiologic-histopathologic correlation study

Gyu-Dong Jo, Kyu‐Young Oh, Jo‐Eun Kim, Won-Jin Yi et autres

Accurate differentiation between tumor invasion and reactive bone response is essential for surgical planning in squamous cell carcinoma (SCC). This prospective study investigated the radiologic-histopathologic correlation of peritumoral bone changes to distinguish malignant invasion from reactive alterations. Twenty-four patients with SCC involving …

kr (code pays fourni par la source)

Diagnostic performance of quantitative parameters derived from twin-beam dual-energy CT for differentiating benign and malignant salivary gland tumors of the palate

Gyu-Dong Jo, Kyung‐Hoe Huh, Won-Jin Yi, Min-Suk Heo et autres

OBJECTIVES: To evaluate the diagnostic performance of quantitative parameters derived from twin-beam dual-energy computed tomography (TB-DECT) in distinguishing benign from malignant palatal salivary gland tumours. METHODS: This retrospective study included 45 patients with pathologically confirmed palatal salivary gland tumours (23 benign, 22 …

kr (code pays fourni par la source)

0599 Plastic associated endocrine disruptors reduce nicastrin protein and potentiate inflammation in hidradenitis suppurativa

K.L. Williams, Beita Badiei, John P. Reilly, William J. Andrews et autres

us (code pays fourni par la source)

0847 The addition of collagen scaffolds to human cell therapy to modify skin identity

Sam-Sun Lee, Yingchao Xue, A. Li, Elizabeth Winnicki et autres

us (code pays fourni par la source)

Development of 10 principles of radiation protection in oral and maxillofacial radiology

Sam-Sun Lee, Ju-Hee Kang, Jo‐Eun Kim, Kyung‐Hoe Huh et autres

Purpose: This study aimed to establish an expert consensus on a set of principles for radiation protection in oral and maxillofacial radiology in Korea. Although national and international guidelines exist, their practical application to dental radiology remains limited, with key clinical components …

kr (code pays fourni par la source)

Can deep learning identify humans by automatically constructing a database with dental panoramic radiographs?

Hye-Ran Choi, Thomhert Suprapto Siadari, Dong-Yub Ko, Jo‐Eun Kim et autres

The aim of this study was to propose a novel method to identify individuals by recognizing dentition change, along with human identification process using deep learning. Recent and past images of adults aged 20-49 years with more than two dental panoramic radiographs …

kr (code pays fourni par la source)