scholarly journals Interpretable and parameter optimized ensemble model for knee osteoarthritis assessment using radiographs

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mohammed Bany Muhammad ◽  
Mohammed Yeasin

AbstractKnee osteoarthritis (KOA) is an orthopedic disorder with a substantial impact on mobility and quality of life. An accurate assessment of the KOA levels is imperative in prioritizing meaningful patient care. Quantifying osteoarthritis features such as osteophytes and joint space narrowing (JSN) from low-resolution images (i.e., X-ray images) are mostly subjective. We implement an objective assessment and quantification of KOA to aid practitioners. In particular, we developed an interpretable ensemble of convolutional neural network (CNN) models consisting of three modules. First, we developed a scale-invariant and aspect ratio preserving model to localize Knee joints. Second, we created multiple instances of "hyperparameter optimized" CNN models with diversity and build an ensemble scoring system to assess the severity of KOA according to the Kellgren–Lawrence grading (KL) scale. Third, we provided visual explanations of the predictions by the ensemble model. We tested our models using a collection of 37,996 Knee joints from the Osteoarthritis Initiative (OAI) dataset. Our results show a superior (13–27%) performance improvement compared to the state-of-the-art methods.

2021 ◽  
Author(s):  
Gary H Chang ◽  
Lisa K Park ◽  
Nina A Le ◽  
Ray S Jhun ◽  
Tejus Surendran ◽  
...  

Objective: Develop a bone shape measure that reflects the extent of cartilage loss and bone flattening in knee osteoarthritis (OA) and test it against estimates of disease severity. Methods: A fast region-based convolutional neural network was trained to crop the knee joints in sagittal dual-echo steady state MRI sequences obtained from the Osteoarthritis Initiative (OAI). Publicly available annotations of the cartilage and menisci were used as references to annotate the tibia and the femur in 61 knees. Another deep neural network (U-Net) was developed to learn these annotations. Model predictions were compared with radiologist-driven annotations on an independent test set (27 knees). The U-Net was applied to automatically extract the knee joint structures on the larger OAI dataset (9,434 knees). We defined subchondral bone length (SBL), a novel shape measure characterizing the extent of overlying cartilage and bone flattening, and examined its relationship with radiographic joint space narrowing (JSN), concurrent WOMAC pain and disability as well as subsequent partial or total knee replacement (KR). Odds ratios for each outcome were estimated using relative changes in SBL on the OAI dataset into quartiles. Result: Mean SBL values for knees with JSN were consistently different from knees without JSN. Greater changes of SBL from baseline were associated with greater pain and disability. For knees with medial or lateral JSN, the odds ratios between lowest and highest quartiles corresponding to SBL changes for future KR were 5.68 (95% CI:[3.90,8.27]) and 7.19 (95% CI:[3.71,13.95]), respectively. Conclusion: SBL quantified OA status based on JSN severity. It has promise as an imaging marker in predicting clinical and structural OA outcomes.


2021 ◽  
Author(s):  
James Chung Wai Cheung ◽  
Yiu Chow TAM ◽  
Lok Chun CHAN ◽  
Ping Keung CHAN ◽  
Chunyi WEN

Abstract Objectives To develop a deep convolutional neural network (CNN) for the segmentation of femur and tibia on plain x-ray radiographs, hence enabling an automated measurement of joint space width (JSW) to predict the severity and progression of knee osteoarthritis (KOA). Methods A CNN with ResU-Net architecture was developed for knee X-ray imaging segmentation. The efficiency was evaluated by the Intersection over Union (IoU) score by comparing the outputs with the annotated contour of the distal femur and proximal tibia. By leveraging imaging segmentation, the minimal and multiple JSWs in the tibiofemoral joint were estimated and then validated by radiologists’ measurements in the Osteoarthritis Initiative (OAI) dataset using Pearson correlation and Bland–Altman plot. The estimated JSWs were deployed to predict the radiographic severity and progression of KOA defined by Kellgren-Lawrence (KL) grades using the XGBoost model. The classification performance was assessed using F1 and area under receiver operating curve (AUC). Results The network has attained a segmentation efficiency of 98.9% IoU. Meanwhile, the agreement between the CNN-based estimation and radiologist’s measurement of minimal JSW reached 0.7801 (p < 0.0001). Moreover, the 32-point multiple JSW obtained the highest AUC score of 0.656 to classify KL-grade of KOA. Whereas the 64-point multiple JSWs achieved the best performance in predicting KOA progression defined by KL grade change within 48 months, with AUC of 0.621. The multiple JSWs outperform the commonly used minimum JSW with 0.587 AUC in KL-grade classification and 0.554 AUC in disease progression prediction. Conclusion Fine-grained characterization of joint space width of KOA yields comparable performance to the radiologist in assessing disease severity and progression. We provide a fully automated and efficient radiographic assessment tool for KOA.


PLoS ONE ◽  
2019 ◽  
Vol 14 (7) ◽  
pp. e0219902 ◽  
Author(s):  
Soili Törmälehto ◽  
Emma Aarnio ◽  
Mika E. Mononen ◽  
Jari P. A. Arokoski ◽  
Rami K. Korhonen ◽  
...  

Author(s):  
M. Yu. Gerasimenko ◽  
E. P. Glushkova ◽  
D. Yu. Gorbunova ◽  
Yu. Yu. Byalovsky ◽  
S. V. Bulatetskiy ◽  
...  

Background. Osteoarthrosis is characterized by wide prevalence, especially among patients of older age groups, a high risk of restrictions on the musculoskeletal system function, which results in the patients impaired ability to work and reduced quality of life. Aim: investigate the possibilities of thermographic assessment of efficiency of magnetotherapy of the articular syndrome in osteoarthrosis of the knee joints. Methods. The study included 57 patients (46 women and 11 men) with osteoarthrosis of the knee joints (mean age 61.27.4 years). The patients were divided into two groups. In the group 1 (n=29), magnetotherapy with the ALMAG-01 apparatus was used, while in the group 2 (n=28), the placebo apparatus was applied. Results. The inclusion of magnetotherapy in the complex therapy of osteoarthrosis of the knee joints, according to thermographic data, increases significantly the efficiency of treatment and differs significantly from the placebo magnetotherapy procedures. In patients with osteoarthrosis of the knee joints of the X-ray stages I and II, a combination of course treatment using a traveling pulsed magnetic field and standard drug therapy revealed a positive dynamics in normalization of the temperature balance of the joints. In patients with osteoarthrosis of the X-ray stage I, the minimum efficiency of magnetotherapy was revealed according to thermography, which indicates low severity of the inflammatory joint syndrome. Conclusion. The method of infrared thermography can be used as a diagnostic technique, as it reflects the degree of activity of the inflammatory process in the joints with osteoarthrosis.


2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Christopher M. Dunn ◽  
Michael C. Nevitt ◽  
John A. Lynch ◽  
Matlock A. Jeffries

AbstractKnee osteoarthritis (OA) is a leading cause of chronic disability worldwide, but no diagnostic or prognostic biomarkers are available. Increasing evidence supports epigenetic dysregulation as a contributor to OA pathogenesis. In this pilot study, we investigated epigenetic patterns in peripheral blood mononuclear cells (PBMCs) as models to predict future radiographic progression in OA patients enrolled in the longitudinal Osteoarthritis Initiative (OAI) study. PBMC DNA was analyzed from baseline OAI visits in 58 future radiographic progressors (joint space narrowing at 24 months, sustained at 48 months) compared to 58 non-progressors. DNA methylation was quantified via Illumina microarrays and beta- and M-values were used to generate linear classification models. Data were randomly split into a 60% development and 40% validation subsets, models developed and tested, and cross-validated in a total of 40 cycles. M-value based models outperformed beta-value based models (ROC-AUC 0.81 ± 0.01 vs. 0.73 ± 0.02, mean ± SEM, comparison p = 0.002), with a mean classification accuracy of 73 ± 1% (mean ± SEM) for M- and 69 ± 1% for beta-based models. Adjusting for covariates did not significantly alter model performance. Our findings suggest that PBMC DNA methylation-based models may be useful as biomarkers of OA progression and warrant additional evaluation in larger patient cohorts.


Author(s):  
Ю.А. Лушпаева

Целью исследования было выявление возможных проблем диагностики, междисциплинарного взаимодействия и причины дефектов терапии пациентов с остеоартритом на амбулаторном приеме, а также оценка эффективности и безопасности применения в рутинной клинической практике у пациентов с остеоартритом коленных суставов препарата, основой которого является биоактивный концентрат мелких морских рыб. Проанализированы результаты амбулаторного приема ревматолога и истории болезни 2312 пациентов с направительным диагнозом «остеоартрит» различной локализации. Оказалось, что из всех обратившихся к ревматологу пациентов с направительным диагнозом «остеоартрит» 47% направлений можно расценить как безосновательные. Было обнаружено, что 45% пациентов даже при установленном достоверном диагнозе «остеоартрит» на амбулаторном приеме терапия назначалась не в полном объеме и не соответствовала рекомендациям по ведению данной категории больных. После двух курсов (в течение года) лечения препаратом на основе биоактивного концентрата мелких морских рыб эффектом от терапии были удовлетворены 67% пациентов с остеоартритом коленных суставов, отметившие снижение интенсивности боли, улучшение функции суставов и качества жизни. В группе наблюдения не было зарегистрировано нежелательных явлений. Несмотря на то, что в настоящее время проблема остеоартрита хорошо освещена, в реальной клинической практике на этапе первичного звена врачи нередко сталкиваются со сложностями решения как диагностических, так и терапевтических задач. В связи с этим возникает острая необходимость в пересмотре и адаптации к рутинной амбулаторной практике междисциплинарных алгоритмов ведения больных остеоартритом, с определением порога вмешательства врача первичного звена и специалиста. Существует также необходимость в разработке и внедрении в рутинную клиническую практику оптимизированных шкал/опросников для динамической оценки качества жизни пациентов с остеоартритом коленных суставов. Проведенное исследование демонстрирует достаточно высокую эффективность, безопасность и доступность препарата на основе биоактивного концентрата мелких морских рыб, а лечение данным препаратом может широко применяться в комплексной терапии остеоартрита коленных суставов. The purpose of the study was to identify the problems of diagnosis, interdisciplinary interaction and the causes of defects in the treatment of patients with osteoarthritis on an outpatient basis, as well as to assess the efficacy and safety of using the medicine from bioactive concentrate of small marine fish, in routine clinical practice in patients with knee osteoarthritis. The results of an out-patient reception hours with a rheumatologist and case histories of 2312 patients with a referral diagnosis of osteoarthritis of various localization were analyzed. It turned out that 47% of all referrals to a rheumatologist with a referral diagnosis of osteoarthritis can be regarded as unfounded. It was found that 45% of patients, even with an established reliable diagnosis of osteoarthritis, on an outpatient basis, therapy was not prescribed in full and did not comply with the recommendations for the management of this category of patients. After 2 courses (within a year) of treatment with a drug based on a bioactive concentrate of small marine fish, 67% of patients with osteoarthritis of the knee joints were satisfied with the effect of therapy, noting a decrease in pain intensity, an improvement in knee joint function and quality of life. No adverse events were reported in the observation group. Despite the fact that at present the problem of osteoarthritis is well covered, in real clinical practice at the stage of primary care physicians often face difficulties in solving both diagnostic and therapeutic problems. In this regard, there is an urgent need to revise and adapt to the routine outpatient practice of interdisciplinary algorithms for managing patients with osteoarthritis, with the determination of the intervention threshold of a primary care physician and a specialist physician. However, there is a need to develop and introduce into routine clinical practice optimized scales/questionnaires for dynamic assessment of the quality of life of patients with knee osteoarthritis. The study demonstrates a fairly high efficacy, safety and availability of a drug based on a bioactive concentrate of small marine fish, and treatment with this drug can be widely used in the complex therapy of osteoarthritis of the knee joints.


2020 ◽  
Vol 111 (3) ◽  
pp. 667-676 ◽  
Author(s):  
Chang Xu ◽  
Nathalie E Marchand ◽  
Jeffrey B Driban ◽  
Timothy McAlindon ◽  
Charles B Eaton ◽  
...  

ABSTRACT Background While some individual foods and nutrients have been associated with knee osteoarthritis (KOA) progression, the association between dietary patterns and KOA progression has received little research attention. Objective The objective of this study was to determine whether dietary patterns, derived by principal components analysis (PCA), are associated with KOA progression. Methods In the Osteoarthritis Initiative (OAI), a prospective cohort with clinical centers in Maryland, Ohio, Pennsylvania, and Rhode Island, 2757 participants with existing KOA (mean age 62 y) and diet assessed at baseline were followed for ≤72 mo. Using PCA, Western and prudent dietary patterns were derived. Radiographic KOA progression was assessed using 2 separate measures, 1 full Kellgren–Lawrence (KL) grade increase and loss in joint space width (JSW). Symptomatic KOA progression was defined as an increase in or remaining in 1 of the 2 highest classification categories of the Western Ontario and McMaster Universities Arthritis Index (WOMAC). Results Adherence to Western and prudent dietary patterns was significantly associated with radiographic and symptomatic progression of KOA. With increasing Western pattern score, there was increased KL-worsening risk (compared with quartile 1, HR for quartile 4: 1.30; 95% CI: 1.05, 1.61; P-trend &lt; 0.01) and increased odds of progression to higher WOMAC score (compared with quartile 1, OR for quartile 4: 1.39; 95% CI: 1.18, 1.63; P-trend &lt; 0.01) but no significant change in JSW loss. With increasing prudent pattern score there was decreased KL-worsening risk (compared with quartile 1, HR for quartile 4: 0.79; 95% CI: 0.64, 0.98; P-trend = 0.02), decreased JSW loss (quartile 1: 0.46 mm; quartile 4: 0.38 mm; P-trend &lt; 0.01), and decreased odds of higher WOMAC progression (compared with quartile 1, OR for quartile 4 0.73; 95% CI: 0.62, 0.86; P-trend &lt; 0.01) in multivariable adjusted models. Conclusions Adherence to a Western dietary pattern was associated with increased radiographic and symptomatic KOA progression, while following a prudent pattern was associated with reduced progression. In general, for people already diagnosed with KOA, eating a diet rich in fruits, vegetables, fish, whole grains, and legumes may be related to decreased radiographic and symptomatic disease progression.


Sign in / Sign up

Export Citation Format

Share Document