1
|
Islam MS, Rony MAT. CDK: A novel high-performance transfer feature technique for early detection of osteoarthritis. J Pathol Inform 2024; 15:100382. [PMID: 38840834 PMCID: PMC11152656 DOI: 10.1016/j.jpi.2024.100382] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2024] [Revised: 04/17/2024] [Accepted: 04/30/2024] [Indexed: 06/07/2024] Open
Abstract
Knee osteoarthritis (OA) is a prevalent condition causing significant disability, particularly among the elderly, necessitating advancements in diagnostic methodologies to facilitate early detection and treatment. Traditional OA diagnosis, relying on radiography and physical exams, faces limitations in accuracy and objectivity. This underscores the need for more advanced diagnostic methods, such as machine learning (ML) and deep learning (DL), to improve OA detection and classification. This research introduces a novel ensemble learning approach for image data feature extraction which ingeniously combines the strengths of 2 advanced (ML) models with a (DL) method to substantially improve the accuracy of OA detection from radiographic images. This innovative strategy aims to address the limitations of traditional diagnostic tools by leveraging the enhanced sensitivity and specificity of combined ML and DL models. The methodology deployed in this study encompasses the application of 10 ML models to a comprehensive publicly available Kaggle dataset with a total of 3615 samples of knee X-ray images. Through rigorous k-fold cross-validation and meticulous hyperparameter optimization, we also included evaluation metrics like accuracy, receiver operating characteristic, precision, recall, and F1-score to assess our models' performance effectively. The proposed novel CDK (convolutional neural network, decision tree, K-nearest classifier) ensemble approach for feature extraction is designed to synergize the predictive capabilities of individual models, thereby significantly improving the detection accuracy of OA indicators within radiographic images. We applied several ML and DL approaches to the newly created feature set to evaluate performance. The CDK ensemble model outperformed state-of-the-art studies with a high-performance score of 99.72% accuracy. This remarkable achievement underscores the model's exceptional capability in the early detection of OA, highlighting its superiority in comparison to existing methods.
Collapse
Affiliation(s)
- Mohammad Shariful Islam
- Department of Computer Science and Telecommunication Engineering (CSTE), Noakhali Science and Technology University, Noakhali 3814, Bangladesh
| | - Mohammad Abu Tareq Rony
- Department of Statistics, Noakhali Science and Technology University, Noakhali 3814, Bangladesh
| |
Collapse
|
2
|
Alunni Cardinali M, Govoni M, Tschon M, Brogini S, Vivarelli L, Morresi A, Fioretto D, Rocchi M, Stagni C, Fini M, Dallari D. Brillouin-Raman micro-spectroscopy and machine learning techniques to classify osteoarthritic lesions in the human articular cartilage. Sci Rep 2023; 13:1690. [PMID: 36717645 PMCID: PMC9886972 DOI: 10.1038/s41598-023-28735-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Accepted: 01/24/2023] [Indexed: 01/31/2023] Open
Abstract
In this study, Brillouin and Raman micro-Spectroscopy (BRamS) and Machine Learning were used to set-up a new diagnostic tool for Osteoarthritis (OA), potentially extendible to other musculoskeletal diseases. OA is a degenerative pathology, causing the onset of chronic pain due to cartilage disruption. Despite this, it is often diagnosed late and the radiological assessment during the routine examination may fail to recognize the threshold beyond which pharmacological treatment is no longer sufficient and prosthetic replacement is required. Here, femoral head resections of OA-affected patients were analyzed by BRamS, looking for distinctive mechanical and chemical markers of the progressive degeneration degree, and the result was compared to standard assignment via histological staining. The procedure was optimized for diagnostic prediction by using a machine learning algorithm and reducing the time required for measurements, paving the way for possible future in vivo characterization of the articular surface through endoscopic probes during arthroscopy.
Collapse
Affiliation(s)
- Martina Alunni Cardinali
- Department of Chemistry, Biology and Biotechnology, University of Perugia, 06123, Perugia, Italy
| | - Marco Govoni
- Reconstructive Orthopaedic Surgery and Innovative Techniques-Musculoskeletal Tissue Bank, IRCCS Istituto Ortopedico Rizzoli, Via G.C. Pupilli 1, 40136, Bologna, Italy.
| | - Matilde Tschon
- Surgical Sciences and Technologies, IRCCS Istituto Ortopedico Rizzoli, Via Di Barbiano 1/10, 40136, Bologna, Italy
| | - Silvia Brogini
- Surgical Sciences and Technologies, IRCCS Istituto Ortopedico Rizzoli, Via Di Barbiano 1/10, 40136, Bologna, Italy
| | - Leonardo Vivarelli
- Reconstructive Orthopaedic Surgery and Innovative Techniques-Musculoskeletal Tissue Bank, IRCCS Istituto Ortopedico Rizzoli, Via G.C. Pupilli 1, 40136, Bologna, Italy
| | - Assunta Morresi
- Department of Chemistry, Biology and Biotechnology, University of Perugia, 06123, Perugia, Italy
| | - Daniele Fioretto
- Department of Physics and Geology, University of Perugia, Via A. Pascoli, 06123, Perugia, Italy.,CEMIN-Center of Excellence for Innovative Nanostructured Material, 06123, Perugia, Italy
| | - Martina Rocchi
- Reconstructive Orthopaedic Surgery and Innovative Techniques-Musculoskeletal Tissue Bank, IRCCS Istituto Ortopedico Rizzoli, Via G.C. Pupilli 1, 40136, Bologna, Italy
| | - Cesare Stagni
- Reconstructive Orthopaedic Surgery and Innovative Techniques-Musculoskeletal Tissue Bank, IRCCS Istituto Ortopedico Rizzoli, Via G.C. Pupilli 1, 40136, Bologna, Italy
| | - Milena Fini
- Scientific Director, IRCCS Istituto Ortopedico Rizzoli, Via Di Barbiano 1/10, 40136, Bologna, Italy
| | - Dante Dallari
- Reconstructive Orthopaedic Surgery and Innovative Techniques-Musculoskeletal Tissue Bank, IRCCS Istituto Ortopedico Rizzoli, Via G.C. Pupilli 1, 40136, Bologna, Italy
| |
Collapse
|
3
|
Biological Targets of Multimolecular Therapies in Middle-Age Osteoarthritis. Sports Med Arthrosc Rev 2022; 30:141-146. [PMID: 35921596 DOI: 10.1097/jsa.0000000000000349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
Knee osteoarthritis (OA) is a common condition, prevalent in middle-agedness, associated with chronic pain and impaired quality of life. Two interrelated biological processes fuel early OA progression: inflammation and structural tissues catabolism. Procatabolic and proinflammatory mediators are interconnected and form part of a self-perpetuating loop. They leverage OA research complexity because of the impossibility to discern certain spatiotemporal tissues' changes from others. Both are shared targets of versatile regenerative multimolecular therapies. In particular, platelet-rich plasma can interfere with inflammation and inflammatory pain. The therapeutic approach is to alter the vicious inflammatory loop by modifying the molecular composition of the synovial fluid, thereby paracrine cellular cross talk. Intra-articular injections of platelet-rich plasma can provide key factors balancing proinflammatory and anti-inflammatory factors, targeting macrophage dysfunction and modulating immune mechanisms within the knee.
Collapse
|
4
|
Khalil NFW, El-sherif S, El Hamid MMA, Elnemr R, Taleb RSZ. Role of global femoral cartilage in assessing severity of primary knee osteoarthritis. EGYPTIAN RHEUMATOLOGY AND REHABILITATION 2022. [DOI: 10.1186/s43166-022-00115-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
Abstract
Background/objective
Osteoarthritis is a degenerative joint disease marked by structural changes in the joint. Radiological evaluation can be used to assess structural changes. Pain, inflammation, and stiffness are common clinical symptoms, leading to limitations in daily activities. Ultrasound, unlike traditional radiography, allows for a direct examination of changes in soft tissues. In addition, it is sensitive in detecting osteophytes as well as identifying early OA changes in femoral cartilage associated with clinical manifestations and function.
Results
A cross- sectional study of 40 patients with primary KOA diagnosed according to the American College of Rheumatology (ACR) criteria. After radiographic evaluation using Kellgren-Lawrence (K-L) scale and US examination assessing global femoral hyaline cartilage (GFC), osteophytes, meniscal extrusion, effusion, and Baker’s cyst of the most symptomatic knee, there was significant correlation between (K-L) grading and (GFC) ultrasonographic grading (p = < 0.001). After assessment of pain and functional disability using Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) scale, there was significant correlation between KL and GFC grading with age (p = < 0.001 for both), disease duration (p = < 0.001 for both) as well as WOMAC total scores (p = < 0.001 for both). GFC grading was the only independent predictor relative to other ultrasonographic variables for WOMAC total score (p = < 0.001).
Conclusions
US is a valid tool to evaluate knee joint space and is well correlated with radiographic images. KOA severity assessed by KL grading and GFC ultrasonographic grading showed good correlation with age, duration of the disease, pain intensity, and functional disability.
Collapse
|
5
|
Zhang S, Guo G, Li X, Yao F, Wu Z, Zhu Q, Fang M. The Effectiveness of Traditional Chinese Yijinjing Qigong Exercise for the Patients With Knee Osteoarthritis on the Pain, Dysfunction, and Mood Disorder: A Pilot Randomized Controlled Trial. Front Med (Lausanne) 2022; 8:792436. [PMID: 35087846 PMCID: PMC8787110 DOI: 10.3389/fmed.2021.792436] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2021] [Accepted: 11/29/2021] [Indexed: 11/23/2022] Open
Abstract
Background: Although traditional Chinese Yijinjing Qigong Exercise (YJJQE) is popularly used in China, to alleviate symptoms of people with knee osteoarthritis (KOA), no randomized controlled trials (RCTs) are available to evaluate the effects of YJJQE in patients with KOA. The purpose of this trial is to assess the clinical efficacy of YJJQE for patients with KOA. Methods: A total of 50 participants clinically diagnosed with KOA are randomly (1:1) assigned to the YJJQE group (n = 25) and to the stretching training exercise (STE) group (n = 25), for a 40-min exercise session twice a week for 12 weeks. All outcome measures are collected at baseline and at 12-week ending intervention, which includes the primary outcomes of Western Ontario and McMaster Universities Osteoarthritis Index Scale (WOMAC), the secondary outcomes of visual analog scale (VAS), mental component summary (MCS), physical component summary (PCS), Beck depression inventory (BDI), perceived stress scale (PSS), Berg balance scale (BBS), and the Gait functional mobility data. Results: The YJJQE group did not have any significant changes compared to the control group on the WOMAC score after the 12-week intervention (P > 0.05), though the YJJQE group demonstrated better performance in MCS, BDI, and PSS (P = 0.002, P = 0.001, and P = 0.026, respectively) than the control group. No serious adverse events occurred in either group, and only mild muscle soreness was reported during both exercise treatments. Conclusion: Because no difference between both groups was shown, with regards to the primary outcome measurement (WOMAC), it can hardly explain that the YJJQE had an advantageous effect on patients experiencing the pain and dysfunction of knee osteoarthritis. However, compared to the control group, YJJQE appeared to be associated with improvements in psychological well-being including reduced stress, anxiety, depression, and mood disturbance to manage KOA. Further trials with larger sample sizes and follow-up studies will be required. Clinical Trial Registration:https://www.chictr.org.cn/edit.aspx?pid=60357&htm=4, ChiCTR2000037256.
Collapse
Affiliation(s)
- Shuaipan Zhang
- School of Acupuncture-Moxibustion and Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Yue Yang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Guangxin Guo
- School of Acupuncture-Moxibustion and Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Yue Yang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Xing Li
- Department of Integrated Traditional Chinese and Western Medicine, Institute of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Fei Yao
- School of Acupuncture-Moxibustion and Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Zhiwei Wu
- Tuina Department, Yue Yang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Institute of Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Qingguang Zhu
- Tuina Department, Yue Yang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Institute of Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Min Fang
- School of Acupuncture-Moxibustion and Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Yue Yang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China.,Tuina Department, Institute of Tuina, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| |
Collapse
|
6
|
Andia I, Atilano L, Maffulli N. Moving toward targeting the right phenotype with the right platelet-rich plasma (PRP) formulation for knee osteoarthritis. Ther Adv Musculoskelet Dis 2021; 13:1759720X211004336. [PMID: 33854574 PMCID: PMC8010808 DOI: 10.1177/1759720x211004336] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2021] [Accepted: 03/03/2021] [Indexed: 12/14/2022] Open
Abstract
Intra-articular injections of platelet-rich plasma (PRP) and other novel blood-derived products developed specifically for osteoarthritis (OA) can provide pain relief and potential benefits in disease progression. Meta-analyses show the clinical superiority of PRP compared with other intra-articular injections, but results are modest and the effect sizes are small. PRP injections in knee OA are performed indiscriminately, but the clinical response varies enormously between patients because of an array of mixed OA phenotypes. Subgroup analyses are scarce; some studies stratify patients according to radiographic severity and found better results in early OA, without consensus for more advanced stages of the condition. Parallel identification of soluble and imaging biomarkers is essential to personalise and leverage PRP therapies. The inflammatory phenotype is most interesting from the PRP perspective because PRPs modulate inflammation by releasing a large pool of chemokines and cytokines, which interact with synovial fibroblasts and macrophages; in addition, they can modulate the innate immune response. No soluble biomarkers have been discovered that have implications for OA research and PRP interventions. Clinical examination of patients based on their inflammatory phenotype and imaging identification of pain sources and structural alterations could help discern who will respond to PRP. Synovial inflammation and bone marrow lesions are sources of pain, and intra-articular injections of PRP combined with subchondral bone injection can enhance clinical outcomes. Further refining ultrasound phenotypes may aid in personalising PRP therapies. Intra-articular delivery combined with injections in altered ligamentous structures, medial and coronal ligaments or premeniscal pes anserinus showed positive clinical outcomes. Although the evidence supporting these approaches are weak, they merit further consideration to refine PRP protocols and target the right OA phenotypes.
Collapse
Affiliation(s)
- Isabel Andia
- Regenerative Therapies, Biocruces Bizkaia Health Research Institute, Cruces University Hospital, Plaza Cruces 12, Barakaldo, Bizkaia, 48903, Spain
| | - Leire Atilano
- Regenerative Therapies, Biocruces Bizkaia Health Research Institute, Interventionist Radiology Unit, Department of Radiology, Cruces University Hospital, Barakaldo, Bizkaia, 48903, Spain
| | - Nicola Maffulli
- Department of Musculoskeletal Disorders, University of Salerno School of Medicine and Dentristry, Salerno, Italy
- Queen Mary University of London, Barts and the London School of Medicine and Dentistry, London, UK
| |
Collapse
|