1
|
Yap MH, Cassidy B, Byra M, Liao TY, Yi H, Galdran A, Chen YH, Brüngel R, Koitka S, Friedrich CM, Lo YW, Yang CH, Li K, Lao Q, Ballester MAG, Carneiro G, Ju YJ, Huang JD, Pappachan JM, Reeves ND, Chandrabalan V, Dancey D, Kendrick C. Diabetic foot ulcers segmentation challenge report: Benchmark and analysis. Med Image Anal 2024; 94:103153. [PMID: 38569380 DOI: 10.1016/j.media.2024.103153] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 01/30/2024] [Accepted: 03/20/2024] [Indexed: 04/05/2024]
Abstract
Monitoring the healing progress of diabetic foot ulcers is a challenging process. Accurate segmentation of foot ulcers can help podiatrists to quantitatively measure the size of wound regions to assist prediction of healing status. The main challenge in this field is the lack of publicly available manual delineation, which can be time consuming and laborious. Recently, methods based on deep learning have shown excellent results in automatic segmentation of medical images, however, they require large-scale datasets for training, and there is limited consensus on which methods perform the best. The 2022 Diabetic Foot Ulcers segmentation challenge was held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention, which sought to address these issues and stimulate progress in this research domain. A training set of 2000 images exhibiting diabetic foot ulcers was released with corresponding segmentation ground truth masks. Of the 72 (approved) requests from 47 countries, 26 teams used this data to develop fully automated systems to predict the true segmentation masks on a test set of 2000 images, with the corresponding ground truth segmentation masks kept private. Predictions from participating teams were scored and ranked according to their average Dice similarity coefficient of the ground truth masks and prediction masks. The winning team achieved a Dice of 0.7287 for diabetic foot ulcer segmentation. This challenge has now entered a live leaderboard stage where it serves as a challenging benchmark for diabetic foot ulcer segmentation.
Collapse
Affiliation(s)
- Moi Hoon Yap
- Department of Computing and Mathematics, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester M1 5GD, United Kingdom; Lancashire Teaching Hospitals NHS Trust, Preston, PR2 9HT, United Kingdom.
| | - Bill Cassidy
- Department of Computing and Mathematics, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester M1 5GD, United Kingdom
| | - Michal Byra
- Institute of Fundamental Technological Research, Polish Academy of Sciences, Warsaw, Poland; RIKEN Center for Brain Science, Wako, Japan
| | - Ting-Yu Liao
- Department of Computer Science, National Tsing Hua University, No. 101, Section 2, Kuang-Fu Road, Hsinchu, Taiwan
| | - Huahui Yi
- West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China
| | - Adrian Galdran
- BCN Medtech, Universitat Pompeu Fabra, Barcelona, Spain; AIML, University of Adelaide, Australia
| | - Yung-Han Chen
- Institute of Electronics, National Yang Ming Chiao Tung University, No. 1001, University Road, Hsinchu 300, Taiwan
| | - Raphael Brüngel
- Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Str. 42, 44227 Dortmund, Germany; Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen, Zweigertstr. 37, 45130 Essen, Germany; Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstr. 2, 45131 Essen, Germany
| | - Sven Koitka
- Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, Girardetstr. 2, 45131 Essen, Germany; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstr. 55, 45147 Essen, Germany
| | - Christoph M Friedrich
- Department of Computer Science, University of Applied Sciences and Arts Dortmund (FH Dortmund), Emil-Figge-Str. 42, 44227 Dortmund, Germany; Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), University Hospital Essen, Zweigertstr. 37, 45130 Essen, Germany
| | - Yu-Wen Lo
- Department of Computer Science, National Tsing Hua University, No. 101, Section 2, Kuang-Fu Road, Hsinchu, Taiwan
| | - Ching-Hui Yang
- Department of Computer Science, National Tsing Hua University, No. 101, Section 2, Kuang-Fu Road, Hsinchu, Taiwan
| | - Kang Li
- West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China; Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | - Qicheng Lao
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China; Shanghai Artificial Intelligence Laboratory, Shanghai, China
| | | | | | - Yi-Jen Ju
- Institute of Electronics, National Yang Ming Chiao Tung University, No. 1001, University Road, Hsinchu 300, Taiwan
| | - Juinn-Dar Huang
- Institute of Electronics, National Yang Ming Chiao Tung University, No. 1001, University Road, Hsinchu 300, Taiwan
| | - Joseph M Pappachan
- Lancashire Teaching Hospitals NHS Trust, Preston, PR2 9HT, United Kingdom; Department of Life Sciences, Manchester Metropolitan University, Manchester, M1 5GD, United Kingdom
| | - Neil D Reeves
- Department of Life Sciences, Manchester Metropolitan University, Manchester, M1 5GD, United Kingdom
| | | | - Darren Dancey
- Department of Computing and Mathematics, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester M1 5GD, United Kingdom
| | - Connah Kendrick
- Department of Computing and Mathematics, Manchester Metropolitan University, John Dalton Building, Chester Street, Manchester M1 5GD, United Kingdom
| |
Collapse
|
2
|
Ju YJ, Lee JE, Lee SY. Associations between Chewing Difficulty, Subjective Cognitive Decline, and Related Functional Difficulties among Older People without Dementia: Focus on Body Mass Index. J Nutr Health Aging 2021; 25:347-355. [PMID: 33575727 DOI: 10.1007/s12603-020-1521-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
OBJECTIVE This study aimed to determine whether chewing difficulty is associated with subjective cognitive decline (SCD) and related functional difficulties by body mass index. DESIGN A population-based cross-sectional study. SETTING AND PARTICIPANTS A nationwide sample of 54,004 individuals aged ≥65 years from the 2018 Korea Community Health Survey. MEASUREMENTS SCD and SCD-related functional difficulties were measured using the cognitive decline module of the Behavioral Risk Factor Surveillance System. Chewing difficulty was assessed based on a self-report questionnaire from an oral health-related behaviors interview survey. BMI was calculated from objective values by measuring height and weight through a physical meter. RESULTS Among the 54,004 individuals, the prevalence of SCD in underweight, overweight, and obesity group was 33.6% (n = 806), 30.3% (n = 9,691), and 28.7% (n=5,632) respectively. Chewing difficulty was associated with SCD and SCD-related functional difficulties. This association was more pronounced in underweight (BMI: <18.5 kg/m2) people [underweight: (odds ratio [OR] = 1.68, 95% confidence interval [CI] 1.48-1.92); normal weight: OR = 1.13, 95% CI 1.04-1.22; obese: OR = 1.15, 95% CI 1.05-1.27]. Similar trends were demonstrated for SCD-related functional difficulties (underweight: OR = 1.53, 95% CI 1.17-2.01; normal weight: OR = 1.36, 95% CI 1.15-1.63; obese: OR = 1.50, 95% CI 1.22-1.86). CONCLUSIONS Chewing difficulty was associated with SCD and SCD-related functional difficulties in older people. Our results suggest that underweight status may play roles in the associations between chewing difficulty and SCD and SCD-related functional difficulties.
Collapse
Affiliation(s)
- Y J Ju
- Soon Young Lee, MD, PhD, Department of Preventive Medicine and Public Health, Ajou University School of Medicine 206 World cup-ro, Yeongtong-gu, Suwon-si Gyeonggi-do 16499, Republic of Korea, T: 82-31-219-5301, F: 82-31-219-5084, E:
| | | | | |
Collapse
|
3
|
Abstract
Background In many countries, including South Korea, labour market changes have led to an increase in unstable, temporary jobs. There is evidence that workers in such jobs may experience poorer mental health than those in more stable employment. Aims To investigate the association between temporary employment and depressive symptoms in South Korean workers. Methods We analysed data from the 2010-2014 Korean Welfare Panel Study (KOWEPS). Employment type was categorized into workers paid per day of labour (day labourers), those on short-term contracts (fixed-term workers) and permanent workers. The association between employment type and depressive symptoms, measured using the Center for Epidemiological Studies Depression scale (CES-D 11), was examined using the generalized estimating equation model. Results A total of 3756 workers aged 20-59 were included in the 2010 baseline population. Day labourers had the highest mean CES-D 11 score, followed by fixed-term workers and permanent workers. With the day labourer group as reference, fixed-term workers (β: -1.5027, P < 0.001) and permanent workers (β: -2.1848, P < 0.001) showed statistically significant decreases in depression scores. Conclusions Compared with day labourers, fixed-term workers and permanent workers had progressively lower depression scores. The findings of this study suggest that mental health inequalities based on employment type exist in South Korea.
Collapse
Affiliation(s)
- W Kim
- Department of Public Health, Graduate School, Yonsei University, Seoul 03722, Republic of Korea.,Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea
| | - T-H Kim
- Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea.,Graduate School of Public Heath, Yonsei University, Seoul 03722, Republic of Korea
| | - T-H Lee
- Department of Public Health, Graduate School, Yonsei University, Seoul 03722, Republic of Korea.,Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea
| | - Y J Ju
- Department of Public Health, Graduate School, Yonsei University, Seoul 03722, Republic of Korea.,Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea
| | - S Y Chun
- Department of Public Health, Graduate School, Yonsei University, Seoul 03722, Republic of Korea.,Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea
| | - E-C Park
- Institute of Health Services Research, Yonsei University, Seoul 03722, Republic of Korea.,Department of Preventive Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea
| |
Collapse
|