New Productive Force: The Preliminary Report of First Craniofacial Surgical Robot IST Multicenter Clinical Trial in China DOI
Li Li,

Li Lin,

Haisong Xu

et al.

Journal of Craniofacial Surgery, Journal Year: 2024, Volume and Issue: 36(1), P. 21 - 25

Published: Dec. 27, 2024

Background: This paper presents the authors' team’s research on a craniofacial surgical robot developed in China. Initiated 2011 with government funding, project was officially launched Shanghai, jointly by Ninth People’s Hospital affiliated Shanghai Jiao Tong University School of Medicine and medical-engineering team. Currently, based multiple rounds model surgeries, animal experiments, clinical trials, our team is applying for approval as Class III medical device from National Medical Products Administration (NMPA). As an innovative tool field surgery, it fills technological gap within country. Methods: study multicenter cohort patient data 2019 to 2024. Inclusion criteria included patients who underwent surgery complete follow-up data, primary variable being use robotic assistance surgery. Data analysis involved descriptive statistics, t tests, multivariable regression, significance level set at P <0.05. Results: The has been widely explored fields congenital deformities, tumor reconstruction, esthetic In trials discussed this article, which experiments both deformity correction surgeries total 39 were enrolled. mandibular osteotomy robotic-assisted procedures can reduce length error average 2.2 mm angle 9.09 degrees, while also decreasing time 10.43 minutes. hemifacial microsomia distraction osteogenesis 4.6 shorten 60 group showed better perioperative outcomes patients. precision improved there significant reduction postoperative complications. Conclusion: completed first robots China, demonstrating that significantly enhances precision, reduces operation time, improves indicators. These findings indicate highly effective assisting surgeons complex procedures. suggests that, future, likely be adopted advancing efficiency bringing transformative progress practice.

Language: Английский

mBRSET: A Portable Retina Fundus Photos Benchmark Dataset for Clinical and Demographic Prediction DOI Creative Commons
Chenwei Wu, David Restrepo, Luis Filipe Nakayama

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 12, 2024

Abstract This paper introduces mBRSET, the first publicly available retina dataset captured using handheld retinal cameras in real-life, high-burden scenarios, comprising 5,164 images from 1,291 patients of diverse backgrounds. addresses lack ophthalmological data low- and middle-income countries (LMICs) by providing a cost-effective accessible solution for ocular screening management. Portable enable applications outside traditional hospital settings, such as community health screenings telemedicine consultations, thereby democratizing healthcare. Extensive metadata that are typically unavailable other datasets, including age, sex, diabetes duration, treatments, comorbidities, also recorded. To validate utility state-of-the-art deep models, ConvNeXt V2, Dino SwinV2, were trained benchmarking, achieving high accuracy clinical tasks diagnosing diabetic retinopathy, macular edema; fairness predicting education insurance status. The mBRSET serves resource developing AI algorithms investigating real-world applications, enhancing care resource-constrained environments .

Language: Английский

Citations

4
Impact of Mydriasis on Image Gradability and Automated Diabetic Retinopathy Screening with a Handheld Camera in Real-World Settings DOI

Iago Diogenes,

David Restrepo, Lucas Zago Ribeiro

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 2, 2025

Abstract Purpose Diabetic retinopathy (DR) screening in low- and middle-income countries (LMICs) faces challenges due to limited access specialized care. Portable retinal cameras provide a practical alternative, but image quality, influenced by mydriasis, affects artificial intelligence (AI) model performance. This study examines the role of mydriasis improving quality AI-based DR detection resource-limited settings. Methods We compared proportion gradable images between mydriatic non-mydriatic groups used logistic regression identify factors influencing gradability, including age, gender, race, diabetes duration, systemic hypertension. A ResNet-200d algorithm was trained on mBRSET dataset validated images. Performance metrics, such as accuracy, F1 score, AUC, were evaluated. Results The group had higher (82.1% vs. 55.6%, P < 0.001). Factors hypertension, older male longer duration associated with lower gradability Mydriatic achieved better AI performance, accuracy (82.91% 79.23%), score (0.83 0.79), AUC (0.94 0.93). Among images, performance difference not statistically significant. Conclusion Mydriasis improves enhances screening. However, optimizing for imaging is critical LMICs where agents may be unavailable. Refining models consistent across conditions essential support broader implementation AI-driven resource-constrained

Language: Английский

Citations

0
A portable retina fundus photos dataset for clinical, demographic, and diabetic retinopathy prediction DOI Creative Commons
Chenwei Wu, David Restrepo, Luis Filipe Nakayama

et al.

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Feb. 22, 2025

Language: Английский

Citations

0
New Productive Force: The Preliminary Report of First Craniofacial Surgical Robot IST Multicenter Clinical Trial in China DOI
Li Li,

Li Lin,

Haisong Xu

et al.

Journal of Craniofacial Surgery, Journal Year: 2024, Volume and Issue: 36(1), P. 21 - 25

Published: Dec. 27, 2024

Background: This paper presents the authors' team’s research on a craniofacial surgical robot developed in China. Initiated 2011 with government funding, project was officially launched Shanghai, jointly by Ninth People’s Hospital affiliated Shanghai Jiao Tong University School of Medicine and medical-engineering team. Currently, based multiple rounds model surgeries, animal experiments, clinical trials, our team is applying for approval as Class III medical device from National Medical Products Administration (NMPA). As an innovative tool field surgery, it fills technological gap within country. Methods: study multicenter cohort patient data 2019 to 2024. Inclusion criteria included patients who underwent surgery complete follow-up data, primary variable being use robotic assistance surgery. Data analysis involved descriptive statistics, t tests, multivariable regression, significance level set at P <0.05. Results: The has been widely explored fields congenital deformities, tumor reconstruction, esthetic In trials discussed this article, which experiments both deformity correction surgeries total 39 were enrolled. mandibular osteotomy robotic-assisted procedures can reduce length error average 2.2 mm angle 9.09 degrees, while also decreasing time 10.43 minutes. hemifacial microsomia distraction osteogenesis 4.6 shorten 60 group showed better perioperative outcomes patients. precision improved there significant reduction postoperative complications. Conclusion: completed first robots China, demonstrating that significantly enhances precision, reduces operation time, improves indicators. These findings indicate highly effective assisting surgeons complex procedures. suggests that, future, likely be adopted advancing efficiency bringing transformative progress practice.

Language: Английский

Citations

0