1
|
Hussain A, Lee C, Hu E, Amirouche F. Deep learning automation of radiographic patterns for hallux valgus diagnosis. World J Orthop 2024; 15:105-109. [PMID: 38464350 PMCID: PMC10921175 DOI: 10.5312/wjo.v15.i2.105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Revised: 12/22/2023] [Accepted: 01/04/2024] [Indexed: 02/07/2024] Open
Abstract
Artificial intelligence (AI) and deep learning are becoming increasingly powerful tools in diagnostic and radiographic medicine. Deep learning has already been utilized for automated detection of pneumonia from chest radiographs, diabetic retinopathy, breast cancer, skin carcinoma classification, and metastatic lymphadenopathy detection, with diagnostic reliability akin to medical experts. In the World Journal of Orthopedics article, the authors apply an automated and AI-assisted technique to determine the hallux valgus angle (HVA) for assessing HV foot deformity. With the U-net neural network, the authors constructed an algorithm for pattern recognition of HV foot deformity from anteroposterior high-resolution radiographs. The performance of the deep learning algorithm was compared to expert clinician manual performance and assessed alongside clinician-clinician variability. The authors found that the AI tool was sufficient in assessing HVA and proposed the system as an instrument to augment clinical efficiency. Though further sophistication is needed to establish automated algorithms for more complicated foot pathologies, this work adds to the growing evidence supporting AI as a powerful diagnostic tool.
Collapse
Affiliation(s)
- Angela Hussain
- Department of Orthopaedic Surgery, University of Illinois College of Medicine, Chicago, IL 60612, United States
| | - Cadence Lee
- Department of Orthopaedic Surgery, University of Illinois College of Medicine, Chicago, IL 60612, United States
| | - Eric Hu
- Department of Orthopaedic Surgery, University of Illinois College of Medicine, Chicago, IL 60612, United States
| | - Farid Amirouche
- Department of Orthopaedics Surgery, University of Illinois at Chicago, Chicago, IL 60612, United States
- Department of Orthopaedic Surgery, Northshore University Health System, Skokie, IL 6007, United States
| |
Collapse
|
2
|
Li Y, Tao X, Tang K. Radiographic evaluation of congruency of the first metatarsophalangeal joint in hallux valgus. J Orthop Surg Res 2022; 17:144. [PMID: 35248093 PMCID: PMC8898459 DOI: 10.1186/s13018-022-03028-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/11/2021] [Accepted: 02/18/2022] [Indexed: 11/10/2022] Open
Abstract
Abstract
Background
Congruency of the first metatarsophalangeal (MTP) joint is extremely important for the selection of surgical methods and prognosis, while radiographic evaluation methods are relatively lacking. The purpose of this article was to explore radiographic indicators for evaluating congruency of the first MTP joint.
Methods
We selected patients with hallux valgus who had a weightbearing X-ray in the outpatient system and measured their hallux valgus angle (HVA). In total, 183 cases of 245 feet with HVA greater than 15° were selected. The distal metatarsal articular angle (DMAA), metatarsophalangeal joint angle (MTPJA), congruency index (CI) and tibial sesamoid position (TSP) were measured and statistically analysed.
Results
The higher the degree of hallux valgus was, the higher the proportion of incongruency of the first MTP joint. Significant differences were found in the DMAA, MTPJA and CI between the congruency and incongruency groups of patients with moderate-to-severe hallux valgus (P < 0.05). The areas under the curve (AUCs) of the receiver operating characteristic (ROC) curve for DMAA was 0.554 (P > 0.05). However, the MTPJA and CI were 0.906 and 0.884, the sensitivity values reached 0.791 and 0.949, the specificity values were 0.862 and 0.644, and the critical values were 10.67 and 0.765, respectively. The correlation test indicated that in the congruency group, the DMAA and HVA were positively correlated, but the MTPJA, CI and HVA had low correlation coefficients. The DMAA and HVA were not correlated in the incongruency group; however, the MTPJA and HVA were significantly positively correlated, and the CI and HVA showed a negative correlation (P < 0.05).
Conclusion
The MTPJA and CI are indicators that can be used to quantitatively evaluate the congruency of the first MTP joint, taking 10° and 0.765 as the demarcation points, respectively. Clinically, congruency of the MTP joint should be considered when choosing surgical methods for different degrees of hallux valgus, and the MTPJA and CI can be used as quantitative evaluation indicators.
Level of evidence: Level III, Retrospective Comparative Study.
Collapse
|
3
|
Heineman N, Liu G, Pacicco T, Dessouky R, Wukich DK, Chhabra A. Clinical and imaging assessment and treatment of hallux valgus. Acta Radiol 2020; 61:56-66. [PMID: 31084192 DOI: 10.1177/0284185119847675] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
Hallux valgus is a common condition estimated to affect as many as 23% of adults. The condition is associated with a variety of debilitating symptoms leading to significant morbidity and quality of life issues. Proper evaluation of this deformity and the timely management of its symptoms can improve hallux valgus-related symptomatology and quality of life. The most commonly used and readily reproduced measurements for assessing hallux valgus are the inter-metatarsal angle and the hallux valgus angle. These angles are helpful for choosing and planning surgical intervention for patients who fail initial conservative measures with distal osteotomies reserved for mild or moderate hallux valgus and proximal osteotomies indicated for more moderate to severe deformities. After reading this review article, readers will gain knowledge of the etiopathogenesis of hallux valgus, measurement parameters, and treatment strategies with representative case examples.
Collapse
Affiliation(s)
- Nathan Heineman
- Department of Radiology, UT Southwestern Medical Center, Dallas, TX, USA
- Department of Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| | - George Liu
- Department of Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| | - Thomas Pacicco
- Department of Radiology, UT Southwestern Medical Center, Dallas, TX, USA
| | - Riham Dessouky
- Department of Radiology, Faculty of Medicine, Zagazig University, Zagazig, Egypt
| | - Dane K Wukich
- Department of Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| | - Avneesh Chhabra
- Department of Radiology, UT Southwestern Medical Center, Dallas, TX, USA
| |
Collapse
|
4
|
Hummel J, Skweres J, Heineman N, Dessouky R, Xi Y, Zhang L, Wukich DK, Chhabra A. Hallux valgus assessment on X-ray and Magnetic resonance Imaging (MRI): Correlation with qualitative soft tissue and internal derangement findings on MRI. Eur J Radiol 2019; 113:24-31. [PMID: 30927954 DOI: 10.1016/j.ejrad.2019.01.035] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2018] [Revised: 11/30/2018] [Accepted: 01/30/2019] [Indexed: 10/27/2022]
Abstract
AIM Radiographs (X-rays) are used for the preoperative assessment of hallux valgus (HV). Our purpose was to determine how well quantitative measurements of HV on radiographs and MRI correlate with the qualitative soft tissue and internal derangement findings on MRI. MATERIALS AND METHODS After IRB approval, 56 consecutive patients with MRI and radiographs of the foot were retrospectively reviewed. Two trained readers independently evaluated radiographs, measuring hallux valgus angle (HVA) and intermetatarsal angle (IMA). Two separate readers assessed qualitative MRI data by evaluating 21 different soft tissue and bony features. Statistical analysis included inter-reader reliability (IRR) and correlation of quantitative and qualitative findings. RESULTS Excellent IRR (ICC = 0.89-0.96) was observed for radiograph and MRI measurements of the hallux valgus severity. For qualitative assessments on MRI, IRR was good to excellent for all features (ICC = 0.63-0.9). No significant difference was found for HVA or IMA between normal and abnormal qualitative MRI features. No statistically significant correlation between the severity of hallux valgus and injury to hallux joints and supporting structures was found. CONCLUSION Hallux valgus measurements are reliable on x-rays and MRI and qualitative findings of 1st MTP joint show good to excellent inter-reader agreement on MRI. No statistically significant correlations exist between the severity of hallux valgus and qualitative MRI findings.
Collapse
Affiliation(s)
- Jed Hummel
- Radiology, UT Southwestern Medical Center, Dallas, TX, USA
| | - Justin Skweres
- Radiology, UT Southwestern Medical Center, Dallas, TX, USA
| | - Nathan Heineman
- Radiology, UT Southwestern Medical Center, Dallas, TX, USA; Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| | - Riham Dessouky
- Radiology, Faculty of Medicine, Zagazig University, Zagazig, Egypt
| | - Yin Xi
- Radiology, UT Southwestern Medical Center, Dallas, TX, USA
| | | | - Dane K Wukich
- Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| | - Avneesh Chhabra
- Radiology, UT Southwestern Medical Center, Dallas, TX, USA; Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA.
| |
Collapse
|
5
|
Heineman N, Chhabra A, Zhang L, Dessouky R, Wukich D. Point vs. traditional method evaluation of hallux valgus: interreader reliability and intermethod performance using X-ray and MRI. Skeletal Radiol 2019; 48:251-257. [PMID: 30003279 DOI: 10.1007/s00256-018-3022-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/27/2018] [Revised: 06/17/2018] [Accepted: 06/24/2018] [Indexed: 02/02/2023]
Abstract
BACKGROUND The two most widely used measurements for diagnosing and assessing the severity of hallux valgus are the hallux valgus angle (HVA) and the intermetatarsal angle (IMA). Traditionally, these have been measured by using the midaxial lines approximating the axis of each bone. A new simpler point method has been recently suggested for measuring these angles by connecting points along the medial corners of each bone. Interreader reliability of these measurements on X-ray and MRI as well as intermethod and intermodality differences have not been assessed. METHODS A series of 56 consecutive patients between 18 and 100 years old with no history of foot trauma or orthopedic hardware in their feet were included. All had AP and lateral X-rays and MRI performed on the same foot between April 27, 2015 and March 9, 2016. Two readers measured HVA and IMA using both the traditional midaxial and new point methods. ICC correlations were obtained. RESULTS The interreader reliability for HVA was similar on point method (0.92) and traditional method (0.94). For the IMA, the ICC was 0.77 on point method versus 0.76 on traditional method. The intermodality agreement (between X-ray and MRI) was higher for HVA (ICC = 0.85, 0.88) as compared to IMA (0.58, 0.74), respectively on both methods. The mean difference between the methods was larger on traditional method = 5.5 for HVA and 2.5° for IMA. CONCLUSIONS HVA is more reliable than IMA on both methods and modalities and a significant difference exists between the magnitudes of values obtained using the two methods. LEVEL OF CLINICAL EVIDENCE 3.
Collapse
Affiliation(s)
- Nathan Heineman
- Radiology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9178, USA
| | - Avneesh Chhabra
- Radiology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9178, USA. .,Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA. .,Adjunct Faculty, Johns Hopkins University, Baltimore, MD, USA.
| | - Lihua Zhang
- Radiology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9178, USA
| | - Riham Dessouky
- Radiology, UT Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9178, USA.,Radiology, Faculty of Medicine, Zagazig University, Zagazig, Egypt
| | - Dane Wukich
- Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX, USA
| |
Collapse
|
6
|
Heineman N, Xi Y, Zhang L, Dessouky R, Hummel J, Skweres J, Wukich D, Chhabra A. Hallux Valgus Evaluation on MRI: Can Measurements Validated on Radiographs Be Used? J Foot Ankle Surg 2018; 57:305-308. [PMID: 29331288 DOI: 10.1053/j.jfas.2017.10.009] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/28/2017] [Indexed: 02/03/2023]
Abstract
Hallux valgus (HV) is a common deformity of the great toe affecting >23% of adults in the United States. The severity of the deformity is traditionally analyzed using radiographs to determine measurements such as the HV and intermetatarsal angles. We sought to determine the relationship between the radiographic and magnetic resonance imaging (MRI) measurements because this is not yet known. Two of us analyzed a series of 56 consecutive patients who had had radiographs and MRI performed on the same foot between April 27, 2015 and March 9, 2016 and who satisfied all other inclusion and exclusion criteria (age 18 to 100 years, no history of recent foot trauma, and no metal hardware in the foot). We found excellent interreader reliability (intraclass correlation 0.89 to 0.96) and intermodality agreement (intraclass correlation 0.83 to 0.91). The HV angle measured 15.0° ± 8.8° on the MRI scans and 13.8° ± 8.7° on the radiographs (mean difference -1.15° ± 3.89°), and the intermetatarsal angle was 9.0° ± 3.1° on the MRI scans and 8.8° ± 2.9° on the radiographs (mean difference -0.22° ± 2.10°). The HV measurements were reliable on both radiographs and MRI for the range of values tested. Small intermodality statistically significant differences in HV angle measurements were found; however, these might not be enough to be clinically significant.
Collapse
Affiliation(s)
- Nathan Heineman
- Medical Student, Department of Radiology, UT Southwestern Medical Center, Dallas, TX
| | - Yin Xi
- Assistant Professor, Department of Radiology, UT Southwestern Medical Center, Dallas, TX
| | - Lihua Zhang
- Associate Professor, Department of Radiology, Peking University Third Hospital, Beijing, China
| | - Riham Dessouky
- Assistant Professor, Department of Radiology, Faculty of Medicine, Zagazig University, Zagazig, Egypt
| | - Jed Hummel
- Fellow, Department of Radiology, UT Southwestern Medical Center, Dallas, TX
| | - Justin Skweres
- Fellow, Department of Radiology, UT Southwestern Medical Center, Dallas, TX
| | - Dane Wukich
- Professor and Chairman, Department of Orthopaedic Surgery, UT Southwestern Medical Center, Dallas, TX
| | - Avneesh Chhabra
- Associate Professor and Musculoskeletal Division Chief, Department of Radiology, UT Southwestern Medical Center, Dallas, TX.
| |
Collapse
|