1
|
Huang Z, Li H, Shao S, Zhu H, Hu H, Cheng Z, Wang J, Kevin Zhou S. PELE scores: pelvic X-ray landmark detection with pelvis extraction and enhancement. Int J Comput Assist Radiol Surg 2024:10.1007/s11548-024-03089-z. [PMID: 38491244 DOI: 10.1007/s11548-024-03089-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2023] [Accepted: 02/27/2024] [Indexed: 03/18/2024]
Abstract
PURPOSE Pelvic X-ray (PXR) is widely utilized in clinical decision-making associated with the pelvis, the lower part of the trunk that supports and balances the trunk. In particular, PXR-based landmark detection facilitates downstream analysis and computer-assisted diagnosis and treatment of pelvic diseases. Although PXR has the advantages of low radiation and reduced cost compared to computed tomography (CT), it characterizes the 2D pelvis-tissue superposition of 3D structures, which may affect the accuracy of landmark detection in some cases. However, the superposition nature of PXR is implicitly handled by existing deep learning-based landmark detection methods, which mainly design the deep network structures for better detection performances. Explicit handling of the superposition nature of PXR is rarely done. METHODS In this paper, we explicitly focus on the superposition of X-ray images. Specifically, we propose a pelvis extraction (PELE) module that consists of a decomposition network, a domain adaptation network, and an enhancement module, which utilizes 3D prior anatomical knowledge in CT to guide and well isolate the pelvis from PXR, thereby eliminating the influence of soft tissue for landmark detection. The extracted pelvis image, after enhancement, is then used for landmark detection. RESULTS We conduct an extensive evaluation based on two public and one private dataset, totaling 850 PXRs. The experimental results show that the proposed PELE module significantly improves the accuracy of PXRs landmark detection and achieves state-of-the-art performances in several benchmark metrics. CONCLUSION The design of PELE module can improve the accuracy of different pelvic landmark detection baselines, which we believe is obviously conducive to the positioning and inspection of clinical landmarks and critical structures, thus better serving downstream tasks. Our project has been open-sourced at https://github.com/ECNUACRush/PELEscores .
Collapse
Affiliation(s)
- Zhen Huang
- Computer Science Department, University of Science and Technology of China (USTC), Hefei, 230026, China
- Center for Medical Imaging, Robotics, Analytic Computing and Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, 215123, China
| | - Han Li
- School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC, Hefei, 230026, China
- Center for Medical Imaging, Robotics, Analytic Computing and Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, 215123, China
| | | | - Heqin Zhu
- School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC, Hefei, 230026, China
- Center for Medical Imaging, Robotics, Analytic Computing and Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, 215123, China
| | - Huijie Hu
- Computer Science Department, University of Science and Technology of China (USTC), Hefei, 230026, China
- Center for Medical Imaging, Robotics, Analytic Computing and Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, 215123, China
| | | | - Jianji Wang
- Affiliated Hospital of Guizhou Medical University, Guiyang, 550000, China
| | - S Kevin Zhou
- School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC, Hefei, 230026, China.
- Center for Medical Imaging, Robotics, Analytic Computing and Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, 215123, China.
- Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, 100190, China.
| |
Collapse
|
2
|
Dawod MS, Alswerki MN, Abuqudiri AZ, Albadaineh AA, Mahmoud LM, Altarawneh DJ, Rbeihat NH, Alkhanazreh RM. The Impact of Maternal Age and Educational Level on Developmental Dysplasia of the Hip Diagnosis and Screening: A Descriptive Comparative Study. Adv Orthop 2023; 2023:6793645. [PMID: 37275323 PMCID: PMC10234724 DOI: 10.1155/2023/6793645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Revised: 05/05/2023] [Accepted: 05/18/2023] [Indexed: 06/07/2023] Open
Abstract
Background Early and proper screening for developmental dysplasia of the hip (DDH) is very critical to prevent catastrophic complication on the developing hip joint. Many factors (either maternal or child-related) that hinder timely DDH screening have been previously investigated. Methods A cross-sectional descriptive study design was adopted. 175 babies presented for DDH screening coming with their mothers were investigated. Maternal age, age group, and educational level were recorded. In addition, multiple child-related variables such as age of screening, gender, positive family history, preterm delivery, and mode of delivery were recorded as well. Analysis for association between delayed vs. early screening was made against the maternal and the child-related variables. Results A total number of 175 children with their mothers were investigated. The mean maternal age was 27.9 years, about one third of the mothers had a graduate level of education (36.3%), while 41.1% had high school education, and 22.3% had middle school education. On the other hand, 40.0% of the investigated babies were first born and two thirds of our sample babies were females (66.9%). Of the included babies, 100 (57.1%) were screened at the appropriate 4-month age, while 75 (42.9%) missed the 4-month screening. Chi-square analysis showed that delayed DDH screening was associated with a lower maternal educational level (P ≤ 0.001), younger maternal age (P ≤ 0.001), and first born baby (P ≤ 0.001). Positive family history was protective against delayed DDH screening (P = 0.032). Conclusion The lower maternal educational level, younger maternal age group, and first born babies are risk factors for delayed DDH screening.
Collapse
|
3
|
Sari AS, Karakus O, Gultekin MZ, Senaran H. Acetabular index and acetabular depth ratio in newborns and infants aged 6 months or less with the healthy development of hips: A retrospective cross-sectional study. Medicine (Baltimore) 2023; 102:e33631. [PMID: 37083764 PMCID: PMC10118329 DOI: 10.1097/md.0000000000033631] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/21/2023] [Accepted: 04/06/2023] [Indexed: 04/22/2023] Open
Abstract
Radiographic assessment of the hip may render critical in the diagnosis of developmental dysplasia of the hip (DDH) in newborns and infants aged ≤6 months. There is no complete dataset on the acetabular index (AI) and acetabular depth ratio (ADR) values in this age group. The objective of this study was to assess the AI and ADR values in newborns and infants aged ≤6 months with healthy development. A retrospective analysis was performed on pelvic radiographs of newborns and infants (≤6 months) between August 2020 and September 2021. There were 3000 children with pelvic radiographic imaging. Normal sonographic findings and radiographs without any structural deformity of the hip were inclusion criteria. A total of 1132 newborns and infants (2264 hips) were analyzed. Measurements of AI and ADR (ischium and pubic bone as landmarks for acetabular depth ratio A [ADR-A] and acetabular depth ratio B [ADR-B]) were performed. Correlation and intraclass correlation coefficient (ICC) values were calculated. Left-sided AI values were significantly higher than the right-sided AI values, except in infants aged 4 to ≤5 months (P < .05). ADR-B values differed significantly between male and female newborns and infants both in terms of the side of the hip measured and age (P < .05). AI values were fairly correlated with age (r = -0.286 for left and r = -0.254 for right) in the negative direction and with ADR-A (r = 0.449 and r = 0.469 for left and right) and ADR-B (r = 0.545 and r = 0.592 for left and right) in the positive direction. Inter-observer ICC was 0.845 to 0.989 (excellent) for AI, 0.534 and 0.904 (moderate to excellent) for ADR-A, and -0.014 and 0.774 (slightly good to good) for ADR-B. Intra-observer ICC was 0.811 to 0.996 (excellent) for AI, 0.575 to 0.98 (moderate to excellent) for ADR-A, and 0.023 to 0.954 (slightly good to excellent) for ADR-B. This study features the first complete data set of AI and ADR measurements, which are essential for pelvic radiographic imaging of hip dysplasia, in newborns and infants aged ≤6 months.
Collapse
Affiliation(s)
- Ahmet Sinan Sari
- Konya City Hospital, Department of Orthopedics and Traumatology, Konya, Turkey
- Fier Memorial Regional Hospital, Department of Orthopedics and Traumatology, Fier, Albania
| | - Ozgun Karakus
- Balikesir City Hospital, Department of Orthopedics and Traumatology, Balikesir, Turkey
| | | | - Hakan Senaran
- Bezmialem Vakif University Faculty of Medicine, Department of Orthopedics and Traumatology, Istanbul, Turkey
| |
Collapse
|
4
|
Aroojis A, Mehta R. Hip and Happening: Current Concepts in the Diagnosis and Management of Developmental Dysplasia of the Hip in 2022. Indian J Orthop 2021; 55:1351-1354. [PMID: 35003530 PMCID: PMC8688597 DOI: 10.1007/s43465-021-00587-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Affiliation(s)
- Alaric Aroojis
- Department of Paediatric Orthopaedics, Bai Jerbai Wadia Hospital for Children, Acharya Donde Marg, Mumbai, 400012 Maharashtra India
| | - Rujuta Mehta
- Bai Jerbai Wadia Hospital for Children, Nanavati Max Superspecialty Hospital, Jaslok Hospital, Mumbai, India
| |
Collapse
|