Knee osteoarthritis (OA) is the most common musculoskeletal disorder. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from subjectivity. In this study, we present a new transparent computer-aided diagnosis method based on the Deep Siamese Convolutional Neural Network to automatically score knee OA severity according to the Kellgren-Lawrence grading scale. We trained our method using the data solely from the Multicenter Osteoarthritis Study and validated it on randomly selected 3,000 subjects (5,960 knees) from Osteoarthritis Initiative dataset. Our method yielded a quadratic Kappa coefficient of 0.83 and average multiclass accuracy of 66.71% compared to the annotations given by a committee of clinical experts. Here, we also report a radiological OA diagnosis area under the ROC curve of 0.93. Besides this, we present attention maps highlighting the radiological features affecting the network decision. Such information makes the decision process transparent for the practitioner, which builds better trust toward automatic methods. We believe that our model is useful for clinical decision making and for OA research; therefore, we openly release our training codes and the data set created in this study.

Knee osteoarthritis (OA) is the most common musculoskeletal disease without a cure, and current treatment options are limited to symptomatic relief. Prediction of OA progression is a very challenging and timely issue, and it could, if resolved, accelerate the disease modifying drug development and ultimately help to prevent millions of total joint replacement surgeries performed annually. Here, we present a multi-modal machine learning-based OA progression prediction model that utilises raw radiographic data, clinical examination results and previous medical history of the patient. We validated this approach on an independent test set of 3,918 knee images from 2,129 subjects. Our method yielded area under the ROC curve (AUC) of 0.79 (0.78–0.81) and Average Precision (AP) of 0.68 (0.66–0.70). In contrast, a reference approach, based on logistic regression, yielded AUC of 0.75 (0.74–0.77) and AP of 0.62 (0.60–0.64). The proposed method could significantly improve the subject selection process for OA drug-development trials and help the development of personalised therapeutic plans.

Despite increasing evidence that subchondral bone contributes to osteoarthritis (OA) pathogenesis, little is known about local changes in bone structure compared to cartilage degeneration. This study linked structural adaptation of subchondral bone with histological OA grade. Twenty‐five osteochondral samples of macroscopically different degeneration were prepared from tibiae of 14 patients. Samples were scanned with micro‐computed tomography (μCT) and both conventional structural parameters and novel 3D parameters based on local patterns were analyzed from the subchondral plate and trabecular bone. Subsequently, samples were processed for histology and evaluated for OARSI grade. Each bone parameter and OARSI grade was compared to assess structural adaptation of bone with OA severity. In addition, thicknesses of cartilage, calcified cartilage, and subchondral plate were analyzed from histological sections and compared with subchondral bone plate thickness from μCT. With increasing OARSI grade, the subchondral plate became thicker along with decreased specific bone surface, while there was no change in tissue mineral density. Histological analysis showed that subchondral plate thickness from μCT also includes calcified cartilage. Entropy of local patterns increased with OA severity, reflecting higher tissue heterogeneity. In the trabecular compartment, bone volume fraction and both trabecular thickness and number increased with OARSI grade while trabecular separation and structure model index decreased. Also, elevation of local patterns became longitudinal in the subchondral plate and axial transverse in trabecular bone with increasing OARSI grade. This study demonstrates the possibility of radiological assessment of OA severity by structural analysis of bone. © 2016 The Authors. Journal of Orthopaedic Research Published by Wiley Periodicals, Inc. J Orthop Res 35:785–792, 2017.

No abstract

Automatic medical diagnosis is an emerging center of interest in computer vision as it provides unobtrusive objective information on a patient's condition. The face, as a mirror of health status, can reveal symptomatic indications of specific diseases. Thus, the detection of facial abnormalities or atypical features is at upmost importance when it comes to medical diagnostics. This survey aims to give an overview of the recent developments in medical diagnostics from facial images based on computer vision methods. Various approaches have been considered to assess facial symptoms and to eventually provide further help to the practitioners. However, the developed tools are still seldom used in clinical practice, since their reliability is still a concern due to the lack of clinical validation of the methodologies and their inadequate applicability. Nonetheless, efforts are being made to provide robust solutions suitable for healthcare environments, by dealing with practical issues such as real-time assessment or patients positioning. This survey provides an updated collection of the most relevant and innovative solutions in facial images analysis. The findings show that with the help of computer vision methods, over 30 medical conditions can be preliminarily diagnosed from the automatic detection of some of their symptoms. Furthermore, future perspectives, such as the need for interdisciplinary collaboration and collecting publicly available databases, are highlighted.

ObjectiveOsteoarthritis (OA) has often regarded as a disease of articular cartilage only. New evidence has shifted the paradigm towards a system biology approach, where also the surrounding tissue, especially bone is studied more vigorously. However, the histological features of subchondral bone are only poorly characterized in current histological grading scales of OA. The aim of this study is to specifically characterize histological changes occurring in subchondral bone at different stages of OA and propose a simple grading system for them.Design20 patients undergoing total knee replacement surgery were randomly selected for the study and series of osteochondral samples were harvested from the tibial plateaus for histological analysis. Cartilage degeneration was assessed using the standardized OARSI grading system, while a novel four-stage grading system was developed to illustrate the changes in subchondral bone. Subchondral bone histology was further quantitatively analyzed by measuring the thickness of uncalcified and calcified cartilage as well as subchondral bone plate. Furthermore, internal structure of calcified cartilage-bone interface was characterized utilizing local binary patterns (LBP) based method.ResultsThe histological appearance of subchondral bone changed drastically in correlation with the OARSI grading of cartilage degeneration. As the cartilage layer thickness decreases the subchondral plate thickness and disorientation, as measured with LBP, increases. Calcified cartilage thickness was highest in samples with moderate OA.ConclusionThe proposed grading system for subchondral bone has significant relationship with the corresponding OARSI grading for cartilage. Our results suggest that subchondral bone remodeling is a fundamental factor already in early stages of cartilage degeneration.

Osteoarthritis causes changes in the subchondral bone structure and composition. Plain radiography is a cheap, fast, and widely available imaging method. Bone tissue can be well seen from plain radiograph, which however is only a 2D projection of the actual 3D structure. Therefore, the aim was to investigate the relationship between bone density- and structure-related parameters from 2D plain radiograph and 3D bone parameters assessed from micro computed tomography (μCT) ex vivo. Right tibiae from eleven cadavers without any diagnosed joint disease were imaged using radiography and with μCT. Bone density- and structure-related parameters were calculated from four different locations from the radiographs of proximal tibia and compared with the volumetric bone microarchitecture from the corresponding regions. Bone density from the plain radiograph was significantly related with the bone volume fraction (r = 0.86; n = 44; p < 0.01). Mean homogeneity index for orientation of local binary patterns (HIangle,mean) and fractal dimension of vertical structures (FDVer) were related (p < 0.01) with connectivity density (HIangle,mean: r = −0.73, FDVer: r = 0.69) and trabecular separation (HIangle,mean: r = 0.73, FDVer: r = −0.70) when all ROIs were pooled together (n = 44). Bone density and structure in tibia from standard clinically available 2D radiographs are significantly correlated with true 3D microstructure of bone.

ObjectivesTo investigate whether subchondral bone structure from plain radiographs is different between subjects with and without articular cartilage damage or bone marrow lesions (BMLs).MethodsRadiography-based bone structure was assessed from 80 subjects with different stages of knee osteoarthritis using entropy of Laplacian-based image (ELap) and local binary patterns (ELBP), homogeneity index of local angles (HIAngles,mean), and horizontal (FDHor) and vertical fractal dimensions (FDVer). Medial tibial articular cartilage damage and BMLs were scored using the magnetic resonance imaging osteoarthritis knee score. Level of statistical significance was set to p < 0.05.ResultsSubjects with medial tibial cartilage damage had significantly higher FDVer and ELBP as well as lower ELap and HIAngles,mean in the medial tibial subchondral bone region than subjects without damage. FDHor, FDVer, and ELBP were significantly higher, whereas ELap and HIAngles,mean were lower in the medial trabecular bone region. Subjects with medial tibial BMLs had significantly higher FDVer and ELBP as well as lower ELap and HIAngles,mean in medial tibial subchondral bone. FDHor, FDVer, and ELBP were higher, whereas ELap and HIAngles,mean were lower in medial trabecular bone.ConclusionsOur results support the use of bone structural analysis from radiographs when examining subjects with osteoarthritis or at risk of having it.Key points• Knee osteoarthritis causes changes in articular cartilage and subchondral bone • Magnetic resonance imaging is a comprehensive imaging modality for knee osteoarthritis • Radiography-based bone structure analysis can provide additional information of osteoarthritic subjects