1
|
Jiang T, Lau SH, Zhang J, Chan LC, Wang W, Chan PK, Cai J, Wen C. Radiomics signature of osteoarthritis: Current status and perspective. J Orthop Translat 2024; 45:100-106. [PMID: 38524869 PMCID: PMC10958157 DOI: 10.1016/j.jot.2023.10.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Revised: 10/05/2023] [Accepted: 10/10/2023] [Indexed: 03/26/2024] Open
Abstract
Osteoarthritis (OA) is one of the fast-growing disability-related diseases worldwide, which has significantly affected the quality of patients' lives and brings about substantial socioeconomic burdens in medical expenditure. There is currently no cure for OA once the bone damage is established. Unfortunately, the existing radiological examination is limited to grading the disease's severity and is insufficient to precisely diagnose OA, detect early OA or predict OA progression. Therefore, there is a pressing need to develop novel approaches in medical image analysis to detect subtle changes for identifying early OA development and rapid progressors. Recently, radiomics has emerged as a unique approach to extracting high-dimensional imaging features that quantitatively characterise visible or hidden information from routine medical images. Radiomics data mining via machine learning has empowered precise diagnoses and prognoses of disease, mainly in oncology. Mounting evidence has shown its great potential in aiding the diagnosis and contributing to the study of musculoskeletal diseases. This paper will summarise the current development of radiomics at the crossroads between engineering and medicine and discuss the application and perspectives of radiomics analysis for OA diagnosis and prognosis. The translational potential of this article Radiomics is a novel approach used in oncology, and it may also play an essential role in the diagnosis and prognosis of OA. By transforming medical images from qualitative interpretation to quantitative data, radiomics could be the solution for precise early OA detection, progression tracking, and treatment efficacy prediction. Since the application of radiomics in OA is still in the early stages and primarily focuses on fundamental studies, this review may inspire more explorations and bring more promising diagnoses, prognoses, and management results of OA.
Collapse
Affiliation(s)
- Tianshu Jiang
- Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Sing-Hin Lau
- Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Jiang Zhang
- Department of Health Technology and Informatics, Faculty of Health and Social Sciences, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Lok-Chun Chan
- Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Wei Wang
- Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Ping-Keung Chan
- Department of Orthopaedics and Traumatology, Queen Mary Hospital, The University of Hong Kong, Hong Kong SAR, China
| | - Jing Cai
- Department of Health Technology and Informatics, Faculty of Health and Social Sciences, The Hong Kong Polytechnic University, Hong Kong SAR, China
| | - Chunyi Wen
- Department of Biomedical Engineering, Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China
| |
Collapse
|
2
|
Mohammadi S, Salehi MA, Jahanshahi A, Shahrabi Farahani M, Zakavi SS, Behrouzieh S, Gouravani M, Guermazi A. Artificial intelligence in osteoarthritis detection: A systematic review and meta-analysis. Osteoarthritis Cartilage 2024; 32:241-253. [PMID: 37863421 DOI: 10.1016/j.joca.2023.09.011] [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: 04/12/2023] [Revised: 08/11/2023] [Accepted: 09/27/2023] [Indexed: 10/22/2023]
Abstract
OBJECTIVES As an increasing number of studies apply artificial intelligence (AI) algorithms in osteoarthritis (OA) detection, we performed a systematic review and meta-analysis to pool the data on diagnostic performance metrics of AI, and to compare them with clinicians' performance. MATERIALS AND METHODS A search in PubMed and Scopus was performed to find studies published up to April 2022 that evaluated and/or validated an AI algorithm for the detection or classification of OA. We performed a meta-analysis to pool the data on the metrics of diagnostic performance. Subgroup analysis based on the involved joint and meta-regression based on multiple parameters were performed to find potential sources of heterogeneity. The risk of bias was assessed using Prediction Model Study Risk of Bias Assessment Tool reporting guidelines. RESULTS Of the 61 studies included, 27 studies with 91 contingency tables provided sufficient data to enter the meta-analysis. The pooled sensitivities for AI algorithms and clinicians on internal validation test sets were 88% (95% confidence interval [CI]: 86,91) and 80% (95% CI: 68,88) and pooled specificities were 81% (95% CI: 75,85) and 79% (95% CI: 80,85), respectively. At external validation, the pooled sensitivity and specificity for AI algorithms were 94% (95% CI: 90,97) and 91% (95% CI: 77,97), respectively. CONCLUSION Although the results of this meta-analysis should be interpreted with caution due to the potential pitfalls in the included studies, the promising role of AI as a diagnostic adjunct to radiologists is indisputable.
Collapse
Affiliation(s)
- Soheil Mohammadi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
| | | | - Ali Jahanshahi
- Faculty of Medicine, Guilan University of Medical Sciences, Rasht, Iran.
| | | | - Seyed Sina Zakavi
- Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran.
| | - Sadra Behrouzieh
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
| | - Mahdi Gouravani
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
| | - Ali Guermazi
- Department of Radiology, VA Boston Healthcare System, Boston University School of Medicine, Boston, MA, USA.
| |
Collapse
|
3
|
Miraj M. Machine Learning Models for Prediction of Progression of Knee Osteoarthritis: A Comprehensive Analysis. JOURNAL OF PHARMACY AND BIOALLIED SCIENCES 2024; 16:S764-S767. [PMID: 38595580 PMCID: PMC11000962 DOI: 10.4103/jpbs.jpbs_1000_23] [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: 10/05/2023] [Revised: 10/15/2023] [Accepted: 10/22/2023] [Indexed: 04/11/2024] Open
Abstract
Prediction of the progression of knee osteoarthritis (KOA) is a very challenging task. Early identification of risk factors plays a vital role in diagnosing KOA. Thus, machine learning models are used to predict the progression of KOA. The purpose of the present study is to find out the efficacy of various machine learning models to identify the progression of KOA. A comprehensive literature search was conducted in international databases like Google Scholar, PubMed, Web of Science, and Scopus. Studies published from the year 2010 to May 2023 on the machine learning approach to diagnose KOA were included in the study. A total of 15 studies were selected and analyzed which included machine learning as an approach to diagnose KOA. The present study found that machine learning methods are the best methods to diagnose KOA early. Various methods like deep learning, machine learning, convolutional neural network (CNN), and multi-layer perceptron showed good accuracy in diagnosing its progression. The machine learning approach has attracted significant interest from scientists and researchers and has led to a new automated approach to diagnose KOA, which will help in designing treatment approaches.
Collapse
Affiliation(s)
- Mohammad Miraj
- Department of Physical Therapy and Health Rehabilitation, College of Applied Medical Sciences, Majmaah University, AlMajmaah, Saudi Arabia
| |
Collapse
|
4
|
Fayed AM, Mansur NSB, de Carvalho KA, Behrens A, D'Hooghe P, de Cesar Netto C. Artificial intelligence and ChatGPT in Orthopaedics and sports medicine. J Exp Orthop 2023; 10:74. [PMID: 37493985 PMCID: PMC10371934 DOI: 10.1186/s40634-023-00642-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/13/2023] [Accepted: 07/18/2023] [Indexed: 07/27/2023] Open
Abstract
Artificial intelligence (AI) is looked upon nowadays as the potential major catalyst for the fourth industrial revolution. In the last decade, AI use in Orthopaedics increased approximately tenfold. Artificial intelligence helps with tracking activities, evaluating diagnostic images, predicting injury risk, and several other uses. Chat Generated Pre-trained Transformer (ChatGPT), which is an AI-chatbot, represents an extremely controversial topic in the academic community. The aim of this review article is to simplify the concept of AI and study the extent of AI use in Orthopaedics and sports medicine literature. Additionally, the article will also evaluate the role of ChatGPT in scientific research and publications.Level of evidence: Level V, letter to review.
Collapse
Affiliation(s)
- Aly M Fayed
- Department of Orthopaedics and Rehabilitation, University of Iowa Hospitals and Clinics, Iowa City, IA, USA.
| | | | - Kepler Alencar de Carvalho
- Department of Orthopaedics and Rehabilitation, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
| | - Andrew Behrens
- Department of Orthopaedics and Rehabilitation, University of Iowa Hospitals and Clinics, Iowa City, IA, USA
| | - Pieter D'Hooghe
- Aspetar Orthopedic and Sports Medicine Hospital, Doha, Qatar
| | | |
Collapse
|
5
|
Vertebral trabecular bone texture analysis in opportunistic MRI and CT scan can distinguish patients with and without osteoporotic vertebral fracture: A preliminary study. Eur J Radiol 2023; 158:110642. [PMID: 36527774 DOI: 10.1016/j.ejrad.2022.110642] [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: 07/21/2022] [Revised: 11/29/2022] [Accepted: 11/30/2022] [Indexed: 12/12/2022]
Abstract
PURPOSE To investigate the potential of texture parameters from opportunistic MRI and CT for the detection of patients with vertebral fragility fracture, to design a decision tree and to compute a Random Forest analysis for the prediction of fracture risk. METHODS One hundred and eighty vertebrae of sixty patients with at least one (30) or without (30) a fragility fracture were retrospectively assessed. Patients had a DXA, an MRI and a CT scan from the three first lumbar vertebrae. Vertebrae texture analysis was performed in routine abdominal or lumbar CT and lumbar MRI using 1st and 2nd order texture parameters. Hounsfield Unit Bone density (HU BD) was also measured on CT-scan images. RESULTS Twelve texture parameters, Z-score and HU BD were significantly different between the two groups whereas T score and BMD were not. The inter observer reproducibility was good to excellent. Decision tree showed that age and HU BD were the most relevant factors to predict the fracture risk with a 93 % sensitivity and 56 % specificity. AUC was 0.91 in MRI and 0.92 in CT-scan using the Random Forest analysis. The corresponding sensitivity and specificity were 72 % and 93 % in MRI and 83 and 89 % in CT. CONCLUSIONS This study is the first to compare texture indices computed from opportunistic CT and MR images. Age and HU-BD together with selected texture parameters could be used to assess risk fracture. Machine learning algorithm can detect fracture risk in opportunistic CT and MR imaging and might be of high interest for the diagnosis of osteoporosis.
Collapse
|
6
|
Xuan A, Chen H, Chen T, Li J, Lu S, Fan T, Zeng D, Wen Z, Ma J, Hunter D, Ding C, Zhu Z. The application of machine learning in early diagnosis of osteoarthritis: a narrative review. Ther Adv Musculoskelet Dis 2023; 15:1759720X231158198. [PMID: 36937823 PMCID: PMC10017946 DOI: 10.1177/1759720x231158198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 02/01/2023] [Indexed: 03/16/2023] Open
Abstract
Osteoarthritis (OA) is the commonest musculoskeletal disease worldwide, with an increasing prevalence due to aging. It causes joint pain and disability, decreased quality of life, and a huge burden on healthcare services for society. However, the current main diagnostic methods are not suitable for early diagnosing patients of OA. The use of machine learning (ML) in OA diagnosis has increased dramatically in the past few years. Hence, in this review article, we describe the research progress in the application of ML in the early diagnosis of OA, discuss the current trends and limitations of ML approaches, and propose future research priorities to apply the tools in the field of OA. Accurate ML-based predictive models with imaging techniques that are sensitive to early changes in OA ahead of the emergence of clinical features are expected to address the current dilemma. The diagnostic ability of the fusion model that combines multidimensional information makes patient-specific early diagnosis and prognosis estimation of OA possible in the future.
Collapse
Affiliation(s)
| | | | - Tianyu Chen
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Jia Li
- Division of Orthopaedic Surgery, Department of Orthopaedics, Nafang Hospital, Southern Medical University, Guangzhou, China
| | - Shilong Lu
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Tianxiang Fan
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Dong Zeng
- College of Automation Science and Engineering, South China University of Technology, Guangzhou, China
| | - Zhibo Wen
- Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou, China
| | - Jianhua Ma
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - David Hunter
- Clinical Research Centre, Zhujiang Hospital, Southern Medical University, Guangzhou, China
- Department of Rheumatology, Royal North Shore Hospital and Institute of Bone and Joint Research, Kolling Institute, University of Sydney, Sydney, NSW, Australia
| | | | | |
Collapse
|
7
|
Pishgar F, Ashraf-ganjouei A, Dolatshahi M, Guermazi A, Zikria B, Cao X, Wan M, Roemer FW, Dam E, Demehri S. Conventional MRI-derived subchondral trabecular biomarkers and their association with knee cartilage volume loss as early as 1 year: a longitudinal analysis from Osteoarthritis Initiative. Skeletal Radiol 2022; 51:1959-1966. [PMID: 35366094 PMCID: PMC9414671 DOI: 10.1007/s00256-022-04042-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Revised: 02/13/2022] [Accepted: 02/13/2022] [Indexed: 02/02/2023]
Abstract
OBJECTIVE To study associations between MRI-derived subchondral trabecular biomarkers obtained from conventional MRI sequences and knee cartilage loss over 12 and 24 months, using the FNIH osteoarthritis (OA) biomarkers consortium. MATERIALS AND METHODS Data of the 600 subjects in the FNIH OA biomarkers consortium (a nested case-control study within Osteoarthritis Initiative [OAI]) were extracted from the online database. Baseline knee MRI (intermediate-weighted (IW) sequences) were evaluated to determine conventional MRI-derived trabecular thickness (cTbTh) and bone-to-total ratio (cBV/TV). The measurements for medial and lateral volumes of cartilages using baseline, 12-, and 24-month knee MRI were extracted from the OAI database, and cartilage volume loss over 12 and 24 months of follow-up were determined using Relative Change Index. The association between conventional MRI-based subchondral trabecular biomarkers and cartilage volume loss were studied using logistic regression models, adjusted for relevant confounders including age, sex, body mass index (BMI), vitamin D use, Kellgren Lawrence grade (KLG), and tibiofemoral alignment. RESULTS Higher medial cTbTh and cBV/TV at baseline were associated with increased odds of medial tibial cartilage volume loss over 12 months (ORs: 1.01 [1.00-1.02] and 1.24 [1.10-1.39] per 1-SD change) and 24 months (ORs: 1.01 [1.00-1.02] and 1.22 [1.08-1.37], per 1-SD change). No significant association was observed between medial subchondral trabecular biomarkers and lateral tibial or femoral (medial or lateral) cartilage volume loss over the first and second follow-up years. CONCLUSIONS Conventional MRI-derived subchondral trabecular biomarkers (higher medial cTbTh and cBV/TV) may be associated with increased medial tibial cartilage volume loss as early as 1 year.
Collapse
Affiliation(s)
- Farhad Pishgar
- Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 601 N Caroline St, JHOC 4240, Baltimore, MD 21287, USA
| | - Amir Ashraf-ganjouei
- Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Science Institute, Tehran University of Medical Sciences, Tehran, Iran
| | - Mahsa Dolatshahi
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| | - Ali Guermazi
- Department of Radiology, VA Boston Healthcare System, Boston University School of Medicine, Boston, MA, USA
| | - Bashir Zikria
- Department of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Xu Cao
- Department of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Mei Wan
- Department of Orthopaedic Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Frank W. Roemer
- Department of Radiology, VA Boston Healthcare System, Boston University School of Medicine, Boston, MA, USA,Department of Radiology, University of Erlangen-Nuremberg, Erlangen, Germany
| | - Erik Dam
- Machine Learning Section, Department of Computer Science, University of Copenhagen, Kobenhavns, Denmark
| | - Shadpour Demehri
- Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 601 N Caroline St, JHOC 4240, Baltimore, MD 21287, USA
| |
Collapse
|
8
|
Binvignat M, Pedoia V, Butte AJ, Louati K, Klatzmann D, Berenbaum F, Mariotti-Ferrandiz E, Sellam J. Use of machine learning in osteoarthritis research: a systematic literature review. RMD Open 2022; 8:rmdopen-2021-001998. [PMID: 35296530 PMCID: PMC8928401 DOI: 10.1136/rmdopen-2021-001998] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Accepted: 02/16/2022] [Indexed: 11/21/2022] Open
Abstract
Objective The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA). Methods A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected. Results From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles. Conclusion This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.
Collapse
Affiliation(s)
- Marie Binvignat
- Department of Rheumatology, Hôpital Saint-Antoine, Assistance Publique - Hôpitaux de Paris (AP-HP), Centre de Recherche Saint-Antoine, Inserm UMRS_938, Assistance Publique - Hôpitaux de Paris (AP-HP), Sorbonne Universite, Paris, France.,Bakar Computational Health Science Institute, University of California, San Francisco, California, USA.,Immunology Immunopathology Immunotherapy UMRS_959, Sorbonne Universite, Paris, France
| | - Valentina Pedoia
- Center for Intelligent Imaging (CI2), Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA
| | - Atul J Butte
- Bakar Computational Health Science Institute, University of California, San Francisco, California, USA
| | - Karine Louati
- Department of Rheumatology, Hôpital Saint-Antoine, Assistance Publique - Hôpitaux de Paris (AP-HP), Centre de Recherche Saint-Antoine, Inserm UMRS_938, Assistance Publique - Hôpitaux de Paris (AP-HP), Sorbonne Universite, Paris, France
| | - David Klatzmann
- Immunology Immunopathology Immunotherapy UMRS_959, Sorbonne Universite, Paris, France.,Biotherapy (CIC-BTi) and Inflammation Immunopathology-Biotherapy Department (i2B), Hôpital Pitié-Salpêtrière, AP-HP, Paris, France
| | - Francis Berenbaum
- Department of Rheumatology, Hôpital Saint-Antoine, Assistance Publique - Hôpitaux de Paris (AP-HP), Centre de Recherche Saint-Antoine, Inserm UMRS_938, Assistance Publique - Hôpitaux de Paris (AP-HP), Sorbonne Universite, Paris, France
| | | | - Jérémie Sellam
- Department of Rheumatology, Hôpital Saint-Antoine, Assistance Publique - Hôpitaux de Paris (AP-HP), Centre de Recherche Saint-Antoine, Inserm UMRS_938, Assistance Publique - Hôpitaux de Paris (AP-HP), Sorbonne Universite, Paris, France
| |
Collapse
|
9
|
Ningrum DNA, Kung WM, Tzeng IS, Yuan SP, Wu CC, Huang CY, Muhtar MS, Nguyen PA, Li JYC, Wang YC. A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record. J Multidiscip Healthc 2021; 14:2477-2485. [PMID: 34539180 PMCID: PMC8445097 DOI: 10.2147/jmdh.s325179] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2021] [Accepted: 08/27/2021] [Indexed: 02/05/2023] Open
Abstract
PURPOSE To develop deep learning model (Deep-KOA) that can predict the risk of knee osteoarthritis (KOA) within the next year by using the previous three years nonimage-based electronic medical record (EMR) data. PATIENTS AND METHODS We randomly selected information of two million patients from the Taiwan National Health Insurance Research Database (NHIRD) from January 1, 1999 to December 31, 2013. During the study period, 132,594 patients were diagnosed with KOA, while 1,068,464 patients without KOA were chosen randomly as control. We constructed a feature matrix by using the three-year history of sequential diagnoses, drug prescriptions, age, and sex. Deep learning methods of convolutional neural network (CNN) and artificial neural network (ANN) were used together to develop a risk prediction model. We used the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and precision to evaluate the performance of Deep-KOA. Then, we explored the important features using stepwise feature selection. RESULTS This study included 132,594 KOA patients, 83,111 females (62.68%), 49,483 males (37.32%), mean age 64.2 years, and 1,068,464 non-KOA patients, 545,902 females (51.09%), 522,562 males (48.91%), mean age 51.00 years. The Deep-KOA achieved an overall AUROC, sensitivity, specificity, and precision of 0.97, 0.89, 0.93, and 0.80 respectively. The discriminative analysis of Deep-KOA showed important features from several diseases such as disorders of the eye and adnexa, acute respiratory infection, other metabolic and immunity disorders, and diseases of the musculoskeletal and connective tissue. Age and sex were not found as the most discriminative features, with AUROC of 0.9593 (-0.76% loss) and 0.9644 (-0.25% loss) respectively. Whereas medications including antacid, cough suppressant, and expectorants were identified as discriminative features. CONCLUSION Deep-KOA was developed to predict the risk of KOA within one year earlier, which may provide clues for clinical decision support systems to target patients with high risk of KOA to get precision prevention program.
Collapse
Affiliation(s)
- Dina Nur Anggraini Ningrum
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan
- International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan
- Public Health Department, Faculty of Sport Science, Universitas Negeri Semarang, Semarang City, Indonesia
| | - Woon-Man Kung
- Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan
| | - I-Shiang Tzeng
- Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan
- Department of Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan
- Department of Statistics, National Taipei University, Taipei, Taiwan
| | - Sheng-Po Yuan
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan
- Department of Otorhinolaryngology, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan
| | - Chieh-Chen Wu
- Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan
| | - Chu-Ya Huang
- Taiwan College of Healthcare Executives, Taipei, Taiwan
| | - Muhammad Solihuddin Muhtar
- International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan
| | - Phung-Anh Nguyen
- International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan, Taiwan
| | - Jack Yu-Chuan Li
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan
- International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan
- Department of Dermatology, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
- TMU Research Center of Cancer Translational Medicine, Taipei Medical University, Taipei, Taiwan
| | - Yao-Chin Wang
- Graduate Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei, Taiwan
- Department of Emergency Medicine, Min-Sheng General Hospital, Taoyuan, Taiwan
| |
Collapse
|
10
|
Conventional MRI-based subchondral trabecular biomarkers as predictors of knee osteoarthritis progression: data from the Osteoarthritis Initiative. Eur Radiol 2020; 31:3564-3573. [PMID: 33241511 DOI: 10.1007/s00330-020-07512-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2020] [Revised: 10/08/2020] [Accepted: 11/11/2020] [Indexed: 02/07/2023]
Abstract
OBJECTIVES To evaluate the reliability and validity of measuring subchondral trabecular biomarkers in "conventional" intermediate-weighted (IW) MRI sequences and to assess the predictive value of biomarker changes for predicting near-term symptomatic and structural progressions in knee osteoarthritis (OA). METHODS For this study, a framework for measuring trabecular biomarkers in the proximal medial tibia in the "conventional" IW MRI sequence was developed. The reliability of measuring these biomarkers (trabecular thickness [cTbTh], spacing [cTbSp], connectivity density [cConnD], and bone-to-total volume ratio [cBV/TV]) was evaluated in the Bone Ancillary Study (within the Osteoarthritis Initiative [OAI]). The validity of these measurements was assessed by comparing to "apparent" biomarkers (from high-resolution steady-state MRI sequence) and peri-articular bone marrow density (BMD, from dual-energy X-ray absorptiometry). The association of these biomarker changes from baseline to 24 months (using the Reliable Change Index) with knee OA progression was studied in the FNIH OA Biomarkers Consortium (within the OAI). Pain and radiographic progression were evaluated by comparing baseline WOMAC pain score and radiographic joint space width with the 24-to-48-month scores/measurements. Associations between biomarker changes and these outcomes were studied using logistic regression adjusted for the relevant covariates. RESULTS With acceptable reliability, the cTbTh and cBV/TV, but not cTbSp or cConnD, were modestly associated with the "apparent" biomarkers and peri-articular BMD (β: 1.10 [95% CI: 0.45-1.75], p value: 0.001 and β: 3.69 [95% CI: 2.56-4.83], p value: < 0.001, respectively). Knees with increased cTbTh had higher (OR: 1.44 [95% CI: 1.03-2.02], p value: 0.035) and knees with decreased cTbTh (OR: 0.69 [95% CI: 0.49-0.95], p value: 0.026) or decreased cBV/TV (OR: 0.67 [95% CI: 0.48-0.93], p value: 0.018) had lower odds of experiencing OA pain progression over the follow-ups. CONCLUSIONS Measurement of certain "conventional" MRI-based subchondral trabecular biomarkers has high reliability and modest validity. Though modest, there are significant associations between these biomarker changes and knee OA pain progression up to 48-month follow-up. KEY POINTS • Despite the lower spatial resolution than what is required to accurately study the subchondral trabecular microstructures, the "conventional" IW MRI sequences may retain adequate information that allows quantification of trabecular microstructure biomarkers. • Subchondral trabecular biomarkers obtained from "conventional" IW MRI sequences (i.e., cTbTh, cTbSp, and cBV/TV) are reliable and valid measures of trabecular microstructure changes compared to those from "apparent" trabecular biomarkers (from the FISP MRI sequence) and peri-articular BMD (from DXA). • Increased trabecular thickness and bone-to-total ratio (cTbTh and cBV/TV, obtained from "conventional" IW MRI sequences) from baseline to 24-month visits may be associated with higher odds of knee OA pain progression over 48 months of follow-up.
Collapse
|
11
|
Peña-Solórzano CA, Albrecht DW, Bassed RB, Burke MD, Dimmock MR. Findings from machine learning in clinical medical imaging applications - Lessons for translation to the forensic setting. Forensic Sci Int 2020; 316:110538. [PMID: 33120319 PMCID: PMC7568766 DOI: 10.1016/j.forsciint.2020.110538] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2019] [Revised: 04/28/2020] [Accepted: 10/04/2020] [Indexed: 12/18/2022]
Abstract
Machine learning (ML) techniques are increasingly being used in clinical medical imaging to automate distinct processing tasks. In post-mortem forensic radiology, the use of these algorithms presents significant challenges due to variability in organ position, structural changes from decomposition, inconsistent body placement in the scanner, and the presence of foreign bodies. Existing ML approaches in clinical imaging can likely be transferred to the forensic setting with careful consideration to account for the increased variability and temporal factors that affect the data used to train these algorithms. Additional steps are required to deal with these issues, by incorporating the possible variability into the training data through data augmentation, or by using atlases as a pre-processing step to account for death-related factors. A key application of ML would be then to highlight anatomical and gross pathological features of interest, or present information to help optimally determine the cause of death. In this review, we highlight results and limitations of applications in clinical medical imaging that use ML to determine key implications for their application in the forensic setting.
Collapse
Affiliation(s)
- Carlos A Peña-Solórzano
- Department of Medical Imaging and Radiation Sciences, Monash University, Wellington Rd, Clayton, Melbourne, VIC 3800, Australia.
| | - David W Albrecht
- Clayton School of Information Technology, Monash University, Wellington Rd, Clayton, Melbourne, VIC 3800, Australia.
| | - Richard B Bassed
- Victorian Institute of Forensic Medicine, 57-83 Kavanagh St., Southbank, Melbourne, VIC 3006, Australia; Department of Forensic Medicine, Monash University, Wellington Rd, Clayton, Melbourne, VIC 3800, Australia.
| | - Michael D Burke
- Victorian Institute of Forensic Medicine, 57-83 Kavanagh St., Southbank, Melbourne, VIC 3006, Australia; Department of Forensic Medicine, Monash University, Wellington Rd, Clayton, Melbourne, VIC 3800, Australia.
| | - Matthew R Dimmock
- Department of Medical Imaging and Radiation Sciences, Monash University, Wellington Rd, Clayton, Melbourne, VIC 3800, Australia.
| |
Collapse
|
12
|
Identification of Risk Factors and Machine Learning-Based Prediction Models for Knee Osteoarthritis Patients. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10196797] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/16/2023]
Abstract
Knee Osteoarthritis (KOA) is a multifactorial disease that causes low quality of life, poor psychology and resignation from life. Furthermore, KOA is a big data problem in terms of data complexity, heterogeneity and size as it has been commonly considered in the literature with most of the reported studies being limited in the amount of information they can adequately process. The aim of this paper is: (i) To provide a robust feature selection (FS) approach that could identify important risk factors which contribute to the prediction of KOA and (ii) to develop machine learning (ML) prediction models for KOA. The current study considers multidisciplinary data from the osteoarthritis initiative (OAI) database, the available features of which come from heterogeneous sources such as questionnaire data, physical activity indexes, self-reported data about joint symptoms, disability and function as well as general health and physical exams’ data. The novelty of the proposed FS methodology lies on the combination of different well-known approaches including filter, wrapper and embedded techniques, whereas feature ranking is decided on the basis of a majority vote scheme to avoid bias. The validation of the selected factors was performed in data subgroups employing seven well-known classifiers in five different approaches. A 74.07% classification accuracy was achieved by SVM on the group of the first fifty-five selected risk factors. The effectiveness of the proposed approach was evaluated in a comparative analysis with respect to classification errors and confusion matrices to confirm its clinical relevance. The results are the basis for the development of reliable tools for the prediction of KOA progression.
Collapse
|
13
|
Machine learning in knee osteoarthritis: A review. OSTEOARTHRITIS AND CARTILAGE OPEN 2020; 2:100069. [DOI: 10.1016/j.ocarto.2020.100069] [Citation(s) in RCA: 35] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2019] [Revised: 04/15/2020] [Accepted: 04/17/2020] [Indexed: 12/15/2022] Open
|
14
|
Cabitza F, Locoro A, Banfi G. Machine Learning in Orthopedics: A Literature Review. Front Bioeng Biotechnol 2018; 6:75. [PMID: 29998104 PMCID: PMC6030383 DOI: 10.3389/fbioe.2018.00075] [Citation(s) in RCA: 105] [Impact Index Per Article: 17.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2018] [Accepted: 05/23/2018] [Indexed: 12/12/2022] Open
Abstract
In this paper we present the findings of a systematic literature review covering the articles published in the last two decades in which the authors described the application of a machine learning technique and method to an orthopedic problem or purpose. By searching both in the Scopus and Medline databases, we retrieved, screened and analyzed the content of 70 journal articles, and coded these resources following an iterative method within a Grounded Theory approach. We report the survey findings by outlining the articles' content in terms of the main machine learning techniques mentioned therein, the orthopedic application domains, the source data and the quality of their predictive performance.
Collapse
Affiliation(s)
- Federico Cabitza
- Dipartimento di Informatica, Sistemistica e Comunicazione, Universitá degli Studi di Milano-Bicocca, Milan, Italy
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
| | | | - Giuseppe Banfi
- Dipartimento di Informatica, Sistemistica e Comunicazione, Universitá degli Studi di Milano-Bicocca, Milan, Italy
| |
Collapse
|
15
|
An open 8-channel parallel transmission coil for static and dynamic 7T MRI of the knee and ankle joints at multiple postures. Magn Reson Med 2017. [DOI: 10.1002/mrm.26804] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
|
16
|
MacKay JW, Murray PJ, Kasmai B, Johnson G, Donell ST, Toms AP. Subchondral bone in osteoarthritis: association between MRI texture analysis and histomorphometry. Osteoarthritis Cartilage 2017; 25:700-707. [PMID: 27986620 DOI: 10.1016/j.joca.2016.12.011] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/01/2016] [Revised: 11/14/2016] [Accepted: 12/07/2016] [Indexed: 02/02/2023]
Abstract
OBJECTIVE Magnetic resonance imaging (MRI) texture analysis is a method of analyzing subchondral bone alterations in osteoarthritis (OA). The objective of this study was to evaluate the association between MR texture analysis and ground-truth subchondral bone histomorphometry at the tibial plateau. DESIGN The local research ethics committee approved the study. All subjects provided written, informed consent. This was a cross-sectional study carried out at our institution between February and August 2014. Ten participants aged 57-84 with knee OA scheduled for total knee arthroplasty (TKA) underwent pre-operative MRI of the symptomatic knee at 3T using a high spatial-resolution coronal T1 weighted sequence. Tibial plateau explants obtained at the time of TKA underwent histological preparation to allow calculation of bone volume fraction (BV.TV), trabecular thickness (Tb.Th), trabecular separation (Tb.Sp) and trabecular number (Tb.N). Texture analysis was performed on the tibial subchondral bone of MRI images matched to the histological sections. Regression models were created to assess the association of texture analysis features with BV.TV, Tb.Th, Tb.Sp and Tb.N. RESULTS MRI texture features were significantly associated with BV.TV (R2 = 0.76), Tb.Th (R2 = 0.47), Tb.Sp (R2 = 0.75) and Tb.N (R2 = 0.60, all P < 0.001). Simple gray-value histogram based texture features demonstrated the highest standardized regression coefficients for each model. CONCLUSION MRI texture analysis features were significantly associated with ground-truth subchondral bone histomorphometry at the tibial plateau.
Collapse
Affiliation(s)
- J W MacKay
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, UK; Department of Radiology, University of Cambridge, Cambridge, UK.
| | - P J Murray
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, UK.
| | - B Kasmai
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, UK.
| | - G Johnson
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, UK; Norwich Medical School, University of East Anglia, Norwich, UK.
| | - S T Donell
- Norwich Medical School, University of East Anglia, Norwich, UK; Department of Trauma & Orthopaedics, Norfolk & Norwich University Hospital, Norwich, UK.
| | - A P Toms
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, UK; Norwich Medical School, University of East Anglia, Norwich, UK.
| |
Collapse
|
17
|
Łuczkiewicz P, Daszkiewicz K, Chróścielewski J, Witkowski W, Winklewski PJ. The Influence of Articular Cartilage Thickness Reduction on Meniscus Biomechanics. PLoS One 2016; 11:e0167733. [PMID: 27936066 PMCID: PMC5147969 DOI: 10.1371/journal.pone.0167733] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2016] [Accepted: 11/18/2016] [Indexed: 11/18/2022] Open
Abstract
OBJECTIVE Evaluation of the biomechanical interaction between meniscus and cartilage in medial compartment knee osteoarthritis. METHODS The finite element method was used to simulate knee joint contact mechanics. Three knee models were created on the basis of knee geometry from the Open Knee project. We reduced the thickness of medial cartilages in the intact knee model by approximately 50% to obtain a medial knee osteoarthritis (OA) model. Two variants of medial knee OA model with congruent and incongruent contact surfaces were analysed to investigate the influence of congruency. A nonlinear static analysis for one compressive load case was performed. The focus of the study was the influence of cartilage degeneration on meniscal extrusion and the values of the contact forces and contact areas. RESULTS In the model with incongruent contact surfaces, we observed maximal compressive stress on the tibial plateau. In this model, the value of medial meniscus external shift was 95.3% greater, while the contact area between the tibial cartilage and medial meniscus was 50% lower than in the congruent contact surfaces model. After the non-uniform reduction of cartilage thickness, the medial meniscus carried only 48.4% of load in the medial compartment in comparison to 71.2% in the healthy knee model. CONCLUSIONS We have shown that the change in articular cartilage geometry may significantly reduce the role of meniscus in load transmission and the contact area between the meniscus and cartilage. Additionally, medial knee OA may increase the risk of meniscal extrusion in the medial compartment of the knee joint.
Collapse
Affiliation(s)
- Piotr Łuczkiewicz
- II Clinic of Orthopaedics and Kinetic Organ Traumatology, Medical University of Gdańsk, Gdańsk, Poland
- * E-mail:
| | - Karol Daszkiewicz
- Department of Mechanics of Materials, Faculty of Civil and Environmental Engineering, Gdańsk University of Technology, Gdańsk, Poland
| | - Jacek Chróścielewski
- Department of Mechanics of Materials, Faculty of Civil and Environmental Engineering, Gdańsk University of Technology, Gdańsk, Poland
| | - Wojciech Witkowski
- Department of Mechanics of Materials, Faculty of Civil and Environmental Engineering, Gdańsk University of Technology, Gdańsk, Poland
| | - Pawel J. Winklewski
- Institute of Human Physiology, Medical University of Gdańsk, Gdańsk, Poland
- Institute of Health Sciences, Pomeranian University of Słupsk, Słupsk, Poland
| |
Collapse
|
18
|
Sørensen L, Igel C, Liv Hansen N, Osler M, Lauritzen M, Rostrup E, Nielsen M. Early detection of Alzheimer's disease using MRI hippocampal texture. Hum Brain Mapp 2015; 37:1148-61. [PMID: 26686837 DOI: 10.1002/hbm.23091] [Citation(s) in RCA: 109] [Impact Index Per Article: 12.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2015] [Revised: 11/06/2015] [Accepted: 12/06/2015] [Indexed: 11/08/2022] Open
Abstract
Cognitive impairment in patients with Alzheimer's disease (AD) is associated with reduction in hippocampal volume in magnetic resonance imaging (MRI). However, it is unknown whether hippocampal texture changes in persons with mild cognitive impairment (MCI) that does not have a change in hippocampal volume. We tested the hypothesis that hippocampal texture has association to early cognitive loss beyond that of volumetric changes. The texture marker was trained and evaluated using T1-weighted MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and subsequently applied to score independent data sets from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL) and the Metropolit 1953 Danish Male Birth Cohort (Metropolit). Hippocampal texture was superior to volume reduction as predictor of MCI-to-AD conversion in ADNI (area under the receiver operating characteristic curve [AUC] 0.74 vs. 0.67; DeLong test, p = 0.005), and provided even better prognostic results in AIBL (AUC 0.83). Hippocampal texture, but not volume, correlated with Addenbrooke's cognitive examination score (Pearson correlation, r = -0.25, p < 0.001) in the Metropolit cohort. The hippocampal texture marker correlated with hippocampal glucose metabolism as indicated by fluorodeoxyglucose-positron emission tomography (Pearson correlation, r = -0.57, p < 0.001). Texture statistics remained significant after adjustment for volume in all cases, and the combination of texture and volume did not improve diagnostic or prognostic AUCs significantly. Our study highlights the presence of hippocampal texture abnormalities in MCI, and the possibility that texture may serve as a prognostic neuroimaging biomarker of early cognitive impairment.
Collapse
Affiliation(s)
- Lauge Sørensen
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark.,Biomediq A/S, Denmark
| | - Christian Igel
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark
| | - Naja Liv Hansen
- Functional Imaging Unit, Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Denmark.,Center for Healthy Aging, University of Copenhagen, Denmark
| | - Merete Osler
- Center for Healthy Aging, University of Copenhagen, Denmark.,Research Centre for Prevention and Health, Rigshospitalet-Glostrup, Denmark
| | - Martin Lauritzen
- Center for Healthy Aging, University of Copenhagen, Denmark.,Department of Neuroscience and Pharmacology, University of Copenhagen, Denmark.,Department of Clinical Neurophysiology, Rigshospitalet, Denmark
| | - Egill Rostrup
- Functional Imaging Unit, Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, Denmark.,Center for Healthy Aging, University of Copenhagen, Denmark
| | - Mads Nielsen
- The Image Group, Department of Computer Science, University of Copenhagen, Denmark.,Biomediq A/S, Denmark
| | | |
Collapse
|
19
|
MacKay JW, Murray PJ, Low SBL, Kasmai B, Johnson G, Donell ST, Toms AP. Quantitative analysis of tibial subchondral bone: Texture analysis outperforms conventional trabecular microarchitecture analysis. J Magn Reson Imaging 2015; 43:1159-70. [PMID: 26606692 DOI: 10.1002/jmri.25088] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2015] [Accepted: 10/26/2015] [Indexed: 11/07/2022] Open
Abstract
BACKGROUND The aim of this study was to compare two different methods of quantitative assessment of tibial subchondral bone in osteoarthritis (OA): statistical texture analysis (sTA) and trabecular microarchitecture analysis (tMA). METHODS Asymptomatic controls aged 20-30 (n = 10), patients aged 40-50 with chronic knee pain but without established OA (n = 10) and patients aged 55-85 with advanced OA scheduled for knee replacement (n = 10) underwent knee MR imaging at 3 Tesla with a three-dimensional gradient echo sequence to allow sTA and tMA. tMA and sTA features were calculated using region of interest creation in the medial (MT) and lateral (LT) tibial subchondral bone. Features were compared between groups using one-way analysis of variance. The two most discriminating tMA and sTA features were used to construct exploratory discriminant functions to assess the ability of the two methods to classify participants. RESULTS No tMA features were significantly different between groups at either MT or LT. 17/20 and 11/20 sTA features were significantly different between groups at the MT/LT, respectively (P < 0.001). Discriminant functions created using tMA features classified 12/30 participants correctly (40% accuracy; 95% confidence interval [CI], 22-58%) based on MT data and 9/30 correctly (30%,; 95% CI, 14-46) based on LT data. Discriminant functions using sTA features classified 16/30 participants correctly (53%; 95% CI, 35-71) based on MT data and 14/30 correctly (47%; 95% CI, 29-65) based on LT data. CONCLUSION sTA features showed more significant differences between the three study groups and improved classification accuracy compared with tMA features.
Collapse
Affiliation(s)
- James W MacKay
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
| | - Philip J Murray
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
| | - Samantha B L Low
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
| | - Bahman Kasmai
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
| | - Glyn Johnson
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
- Norwich Medical School, University of East Anglia, Norwich, United Kingdom
| | - Simon T Donell
- Norwich Medical School, University of East Anglia, Norwich, United Kingdom
- Department of Trauma & Orthopaedics, Norfolk & Norwich University Hospital, Norwich, United Kingdom
| | - Andoni P Toms
- Department of Radiology, Norfolk & Norwich University Hospital, Norwich, United Kingdom
- Norwich Medical School, University of East Anglia, Norwich, United Kingdom
| |
Collapse
|
20
|
Yang Z, Fripp J, Chandra SS, Neubert A, Xia Y, Strudwick M, Paproki A, Engstrom C, Crozier S. Automatic bone segmentation and bone-cartilage interface extraction for the shoulder joint from magnetic resonance images. Phys Med Biol 2015; 60:1441-59. [PMID: 25611124 DOI: 10.1088/0031-9155/60/4/1441] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
We present a statistical shape model approach for automated segmentation of the proximal humerus and scapula with subsequent bone-cartilage interface (BCI) extraction from 3D magnetic resonance (MR) images of the shoulder region. Manual and automated bone segmentations from shoulder MR examinations from 25 healthy subjects acquired using steady-state free precession sequences were compared with the Dice similarity coefficient (DSC). The mean DSC scores between the manual and automated segmentations of the humerus and scapula bone volumes surrounding the BCI region were 0.926 ± 0.050 and 0.837 ± 0.059, respectively. The mean DSC values obtained for BCI extraction were 0.806 ± 0.133 for the humerus and 0.795 ± 0.117 for the scapula. The current model-based approach successfully provided automated bone segmentation and BCI extraction from MR images of the shoulder. In future work, this framework appears to provide a promising avenue for automated segmentation and quantitative analysis of cartilage in the glenohumeral joint.
Collapse
Affiliation(s)
- Zhengyi Yang
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia
| | | | | | | | | | | | | | | | | |
Collapse
|
21
|
Lowitz T, Museyko O, Bousson V, Kalender WA, Laredo JD, Engelke K. Characterization of knee osteoarthritis-related changes in trabecular bone using texture parameters at various levels of spatial resolution-a simulation study. BONEKEY REPORTS 2014; 3:615. [PMID: 25512855 DOI: 10.1038/bonekey.2014.110] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/22/2014] [Accepted: 10/24/2014] [Indexed: 12/21/2022]
Abstract
Articular cartilage and subchondral bone are the key tissues in osteoarthritis (OA). The role of the cancellous bone increasingly attracts attention in OA research. Because of its fast adaptation to changes in the loading distribution across joints, its quantification is expected to improve the diagnosis and monitoring of OA. In this study, we simulated OA progression-related changes of trabecular structure in a series of digital bone models and then characterized the potential of texture parameters and bone mineral density (BMD) as surrogate measures to quantify trabecular bone structure. Five texture parameters were studied: entropy, global and local inhomogeneity, anisotropy and variogram slope. Their dependence on OA relevant structural changes was investigated for three spatial resolutions typically used in micro computed tomography (CT; 10 μm), high-resolution peripheral quantitative CT (HR-pQCT) (90 μm) and clinical whole-body CT equipment (250 μm). At all resolutions, OA-related changes in trabecular bone architecture can be quantified using a specific (resolution dependent) combination of three texture parameters. BMD alone is inadequate for this purpose but if available reduces the required texture parameter combination to anisotropy and global inhomogeneity. The results are summarized in a comprehensive analysis guide for the detection of structural changes in OA knees. In conclusion, texture parameters can be used to characterize trabecular bone architecture even at spatial resolutions below the dimensions of a single trabecula and are essential for a detailed classification of relevant OA changes that cannot be achieved with a measurement of BMD alone.
Collapse
Affiliation(s)
- Torsten Lowitz
- Institute of Medical Physics, University of Erlangen-Nürnberg , Erlangen, Germany
| | - Oleg Museyko
- Institute of Medical Physics, University of Erlangen-Nürnberg , Erlangen, Germany
| | - Valerie Bousson
- Service de Radiologie Ostéo-Articulaire - Assistance Publique-Hopitaux de Paris, Hôpital Lariboisière , Paris, France ; Univ Paris Diderot, Sorbonne Paris Cité, CNRS UMR 7052 , Paris, France
| | - Willi A Kalender
- Institute of Medical Physics, University of Erlangen-Nürnberg , Erlangen, Germany
| | - Jean Denis Laredo
- Service de Radiologie Ostéo-Articulaire - Assistance Publique-Hopitaux de Paris, Hôpital Lariboisière , Paris, France ; Univ Paris Diderot, Sorbonne Paris Cité, CNRS UMR 7052 , Paris, France
| | - Klaus Engelke
- Institute of Medical Physics, University of Erlangen-Nürnberg , Erlangen, Germany
| |
Collapse
|