https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/377 Fri, 24 Jul 2026 16:59:36 GMT 2026-07-24T16:59:36Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/218680 Title: Deep Learning-Based Anatomical Segmentation of the Foot and Ankle: A Multi-View Radiograph Approach Authors: Lim, Hyojin; Oh, Jaehoon; Kim, Tae Hyun; Lee, Juncheol; Chung, Jae Ho; Lee, Dong Keon Abstract: Purpose: We aimed to develop deep learning models that can identify and separate the shapes of 14 bones in the foot and ankle using multi-view radiographs and predict their masks. Materials and Methods: We retrospectively collected 273 radiographs from 99 patients with anatomically normal feet, including anteroposterior (AP), oblique (OBL), and lateral (LAT) views, obtained between January 2020 and December 2021. In each view, 14 bones were segmented using AP and OBL radiographs and 6 bones using LAT radiographs. Ground truth masks were manually annotated by two radiology technologists and reviewed by an emergency medicine physician. Two deep learning models, a fully convolutional network (FCN) with ResNet-50 and DeepLabv3 with ResNet-50, were independently fine-tuned for semantic segmentation and evaluated using five-fold cross-validation. Results: In the AP and OBL views, both models attained mean intersection over union (mIoU) values ranging from 0.899 to 0.975 and from 0.875 to 0.978, respectively. In the LAT view, mIoU values varied from 0.926 to 0.976 for FCN-ResNet-50 and from 0.872 to 0.961 for DeepLabv3. FCN-ResNet-50 achieved slightly higher mIoU values than DeepLabv3, with statistically significant differences identified between the two models in the overall OBL view and across the 14 specific bones (p<0.05). Conclusion: The FCN-ResNet-50 and DeepLabv3 models could be effective in automatically segmenting foot and ankle bone structures using multi-view radiographs. Wed, 01 Jul 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/218680 2026-07-01T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/217571 Title: 메니에르병: current approach and treatment Authors: 한상윤 Sun, 14 Jun 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/217571 2026-06-14T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/217771 Title: IONM Update and New Clinical Applications Authors: 송창면 Sat, 13 Jun 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/217771 2026-06-13T00:00:00Z https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211011 Title: Enhanced MSC spheroid adhesion on 3D-printed leaf-stacked scaffolds for functional tracheal regeneration Authors: Han, Sang-Yoon; Park, Jae Keun; Choi, Ji Suk; Jeong, Eun Ji; Eom, Min Rye; Seok, Ji Min; Kim, Min Ji; Park, Su A.; Oh, Se Heang; Kwon, Seong Keun Abstract: Reconstruction of segmental tracheal defects using three-dimensional (3D)-printed scaffolds remains a formidable challenge. While polycaprolactone (PCL) is widely utilized for its mechanical integrity, its inherent hydrophobicity limits cellular adhesion and tissue integration. In this study, we developed a 3D-printed PCL tracheal scaffold featuring a Leaf-Stacked Structure (LSS) and evaluated a spatially organized Mesenchymal Stem Cell (MSC) delivery strategy for functional regeneration. MSC spheroids were employed to overcome the limitations of monolayer cells, as their 3D configuration creates an internal hypoxic core that upregulates angiogenic and anti-inflammatory genes, thereby maximizing paracrine-mediated tissue repair. In vitro analyses, including cell adhesion assays and indirect co-culture systems, demonstrated that the LSS topography significantly enhanced the adhesion of both monolayer MSC and spheroids compared to plain PCL. Furthermore, MSC spheroids markedly promoted the proliferation and migration of human small airway epithelial cells. Based on these findings, we compared five experimental groups in a rabbit tracheal defect model: (1) Native, (2) No MSC, (3) Inner MSC (monolayer), (4) Outer spheroid, and (5) Dual group (combined inner monolayer and outer spheroids). In vivo, the Dual group exhibited the most robust mucosal regeneration, alongside an immunomodulatory shift toward increased M2/M1 macrophage ratios. Although neovascularization was prominent at MSC implantation sites, lineage analysis via β2-microglobulin tracking revealed that vessel-forming cells were primarily host-derived. This confirms that implanted MSC survived for 14 weeks and orchestrated regeneration predominantly through paracrine mechanisms.Collectively, the integration of LSS topography and spatially organized MSC represents a promising synergistic strategy for functional tracheal reconstruction. Mon, 01 Jun 2026 00:00:00 GMT https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/211011 2026-06-01T00:00:00Z