Automated techniques for visualization and mapping of articular cartilage in MR images of the osteoarthritic knee: a base technique for the assessment of microdamage and submicro damage

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

In the medical sector, three-dimensional (3D) images are commonly used like computed tomography (CT) and magnetic resonance imaging (MRI). The 3D MRI is a non-invasive method of studying the soft-tissue structures in a knee joint for osteoarthritis studies. It can greatly improve the accuracy of segmenting structures such as cartilage, bone marrow lesion, and meniscus by identifying the bone structure first. U-net is a convolutional neural network that was originally designed to segment the biological images with limited training data. The input of the original U-net is a single 2D image and the output is a binary 2D image. In this study, we modified the U-net model to identify the knee bone structures using 3D MRI, which is a sequence of 2D slices. A fully automatic model has been proposed to detect and segment knee bones. The proposed model was trained, tested, and validated using 99 knee MRI cases where each case consists of 160 2D slices for a single knee scan. To evaluate the model's performance, the similarity, dice coefficient (DICE), and area error metrics were calculated. Separate models were trained using different knee bone components including tibia, femur, patella, as well as a combined model for segmenting all the knee bones. Using the whole MRI sequence (160 slices), the method was able to detect the beginning and ending bone slices first, and then segment the bone structures for all the slices in between. On the testing set, the detection model accomplished 98.79% accuracy and the segmentation model achieved DICE 96.94% and similarity 93.98%. The proposed method outperforms several state-of-the-art methods, i.e., it outperforms U-net by 3.68%, SegNet by 14.45%, and FCN-8 by 2.34%, in terms of DICE score using the same dataset.

Reproducibility of an Automated Quantitative MRI Assessment of Low-Grade Knee Articular Cartilage Lesions

OBJECTIVE

The goal of this study was to assess the reproducibility of an automated knee cartilage segmentation of 21 cartilage regions with a model-based algorithm and to compare the results with manual segmentation.

DESIGN

Thirteen patients with low-grade femoral cartilage defects were included in the study and were scanned twice on a 7-T magnetic resonance imaging (MRI) scanner 8 days apart. A 3-dimensional double-echo steady-state (3D-DESS) sequence was used to acquire MR images for automated cartilage segmentation, and T2-mapping was performed using a 3D triple-echo steady-state (3D-TESS) sequence. Cartilage volume, thickness, and T2 and texture features were automatically extracted from each knee for each of the 21 subregions. DESS was used for manual cartilage segmentation and compared with automated segmentation using the Dice coefficient. The reproducibility of each variable was expressed using standard error of measurement (SEM) and smallest detectable change (SDC).

RESULTS

The Dice coefficient for the similarity between manual and automated segmentation ranged from 0.83 to 0.88 in different cartilage regions. Test-retest analysis of automated cartilage segmentation and automated quantitative parameter extraction revealed excellent reproducibility for volume measurement (mean SDC for all subregions of 85.6 mm³), for thickness detection (SDC = 0.16 mm) and also for T2 values (SDC = 2.38 ms) and most gray-level co-occurrence matrix features (SDC = 0.1 a.u.).

CONCLUSIONS

The proposed technique of automated knee cartilage evaluation based on the segmentation of 3D MR images and correlation with T2 mapping provides highly reproducible results and significantly reduces the segmentation effort required for the analysis of knee articular cartilage in longitudinal studies.

A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis

In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren-Lawrence (KL) system. The Kellgren-Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

A Coarse-to-Fine Framework for Automated Knee Bone and Cartilage Segmentation Data from the Osteoarthritis Initiative

Knee osteoarthritis (OA) is a degenerative joint disease that is prevalent in advancing age. The pathology of OA disease is still unclear, and there are no effective interventions that can completely alter the OA disease process. Magnetic resonance (MR) image evaluation is sensitive for depicting early changes of knee OA, and therefore important for early clinical intervention for relieving the symptom. Automated cartilage segmentation based on MR images is a vital step in experimental longitudinal studies to follow-up the patients and prospectively define a new quantitative marker from OA progression. In this paper, we develop a deep learning-based coarse-to-fine approach for automated knee bone, cartilage, and meniscus segmentation with high computational efficiency. The proposed method is evaluated using two-fold cross-validation on 507 MR volumes (81,120 slices) with OA from the Osteoarthritis Initiative (OAI)1 dataset. The mean dice similarity coefficients (DSCs) of femoral bone (FB), tibial bone (TB), femoral cartilage (FC), and tibial cartilage (TC) separately are 99.1%, 98.2%, 90.9%, and 85.8%. The time of segmenting each patient is 12 s, which is fast enough to be used in clinical practice. Our proposed approach may provide an automated toolkit to help computer-aided quantitative analyses of OA images.

Current status of functional MRI of osteoarthritis for diagnosis and prognosis

PURPOSE OF REVIEW

Osteoarthritis is a major source of disability, pain and socioeconomic cost worldwide. The epidemiology of the disorder is multifactorial including genetic, biological and biomechanical components, some of them detectable by MRI. This review provides the most recent update on MRI biomarkers which can provide functional information of the joint structures for diagnosis, prognosis and treatment response monitoring in osteoarthritis trials.

RECENT FINDINGS

Compositional or functional MRI can provide clinicians with valuable information on glycosaminoglycan content (chemical exchange saturation transfer, sodium MRI, T1ρ) and collagen organization (T2, T2, apparent diffusion coefficient, magnetization transfer) in joint structures. Other parameters may also provide useful information, such as volumetric measurements of joint structures or advanced image data postprocessing and analysis. Automated tools seem to have a great potential to be included in these efforts providing standardization and acceleration of the image data analysis process.

SUMMARY

Functional or compositional MRI has great potential to provide noninvasive imaging biomarkers for osteoarthritis. Osteoarthritis as a whole joint condition needs to be diagnosed in early stages to facilitate selection of patients into clinical trials and/or to measure treatment effectiveness. Advanced evaluation including machine learning, neural networks and multidimensional data analysis allow for wall-to-wall understanding of parameter interactions and their role in clinical evaluation of osteoarthritis.

Visualization of Cartilage from Knee Joint Magnetic Resonance Images and Quantitative Assessment to Study the Effect of Age, Gender and Body Mass Index (BMI) in Progressive Osteoarthritis (OA)

Background:

Osteoarthritis (OA) is a degenerative disease of joint cartilage affecting the elderly people around the world. Visualization and quantification of cartilage is very much essential for the assessment of OA and rehabilitation of the affected people. Magnetic Resonance Imaging (MRI) is the most widely used imaging modality in the treatment of knee joint diseases. But there are many challenges in proper visualization and quantification of articular cartilage using MRI. Volume rendering and 3D visualization can provide an overview of anatomy and disease condition of knee joint. In this work, cartilage is segmented from knee joint MRI, visualized in 3D using Volume of Interest (VOI) approach.

Methods:

Visualization of cartilage helps in the assessment of cartilage degradation in diseased knee joints. Cartilage thickness and volume were quantified using image processing techniques in OA affected knee joints. Statistical analysis is carried out on processed data set consisting of 110 of knee joints which include male (56) and female (54) of normal (22) and different stages of OA (88). The differences in thickness and volume of cartilage were observed in cartilage in groups based on age, gender and BMI in normal and progressive OA knee joints.

Results:

The results show that size and volume of cartilage are found to be significantly low in OA as compared to normal knee joints. The cartilage thickness and volume is significantly low for people with age 50 years and above and Body Mass Index (BMI) equal and greater than 25. Cartilage volume correlates with the progression of the disease and can be used for the evaluation of the response to therapies.

Conclusion:

The developed methods can be used as helping tool in the assessment of cartilage degradation in OA affected knee joint patients and treatment planning.

A Novel Method to Predict Knee Osteoarthritis Progression on MRI Using Machine Learning Methods

This paper explored the hidden biomedical information from knee magnetic resonance (MR) images for osteoarthritis (OA) prediction. We have computed the cartilage damage index (CDI) information from 36 informative locations on tibiofemoral cartilage compartment from 3-D MR imaging and used principal component analysis (PCA) analysis to process the feature set. Four machine learning methods (artificial neural network (ANN), support vector machine, random forest, and naïve Bayes) were employed to predict the progression of OA, which was measured by the change of Kellgren and Lawrence (KL) grade, Joint Space Narrowing on Medial compartment (JSM) grade, and Joint Space Narrowing on Lateral compartment (JSL) grade. To examine the different effects of medial and lateral informative locations, we have divided the 36-D feature set into a 18-D medial feature set and a 18-D lateral feature set and run the experiment on four classifiers separately. Experiment results showed that the medial feature set generated better prediction performance than the lateral feature set, while using the total 36-D feature set generated the best. PCA analysis is helpful in feature space reduction and performance improvement. For KL grade prediction, the best performance was achieved by ANN with AUC = 0.761 and F-measure = 0.714. For JSM grade prediction, the best performance was achieved by random forest with AUC = 0.785 and F-measure = 0.743, while for JSL grade prediction, the best performance was achieved by ANN with AUC = 0.695 and F-measure = 0.796. As experiment results showing that the informative locations on medial compartment provide more distinguishing features than informative locations on the lateral compartment, it could be considered to select more points from the medial compartment while reducing the number of points from the lateral compartment to improve clinical CDI design.

Fusion of multinuclear magnetic resonance images of knee for the assessment of articular cartilage

The onset of osteoarthritis (OA), a most common knee joint disease, can be characterized by the degeneration of articular cartilage (AC). Degenerative changes in AC have been assessed by the morphological and physiological measurements using non-invasive modality such as Magnetic Resonance Imaging (MRI) to obtain MRI images of the knee. However, visualization and quantification of AC from MR images is difficult due to the low visibility contrast of AC compared to surrounding tissues, low and varying signal intensities in cartilage region and variable intensities in different slices of single dataset. In this work, we present a method to fuse multinuclear ((23)Na and (1)H) MR images acquired in the same plane without changing the position of the human knee as well as the Radio Frequency (RF) coil. This work is performed towards our hypothesis that fusion of sodium and proton images will provide an enhanced image that can be used for an accurate assessment of cartilage morphology. Our result shows that merging of sodium knee MR image with proton knee MR image resulting in enhanced contrast information in the cartilage region and resolves low visibility and varying intensities issue with 2D/3D proton MR. We conclude that the proposed method can further be utilized for the accurate assessment of cartilage morphology.

Sensitivity of standing radiographs to detect knee arthritis: a systematic review of Level I studies

PURPOSE

The purpose of this study was to perform a systematic review of the available literature to define the level of quality evidence for determining the sensitivity and specificity of different radiographic views in detecting knee osteoarthritis and to determine the impact of different grading systems on the ability to detect knee osteoarthritis.

METHODS

A systematic review of the literature was conducted to identify studies that evaluated the standing anteroposterior (AP) and 45° posteroanterior (PA) views for tibiofemoral and patellofemoral arthritis and those comparing the use of the Kellgren-Lawrence versus the joint space narrowing (JSN) radiographic grading systems using arthroscopy as the gold standard. A comprehensive search of PubMed, Scopus, CINAHL, the Cochrane Database, Clinicaltrial.gov, and EMBASE was performed using the keywords "osteoarthritis," "knee," "x-ray," "sensitivity," and "arthroscopy."

RESULTS

Six studies were included in the evaluation. The 45° flexion PA view showed a higher sensitivity than the standing AP view for detecting severe arthritis involving either the medial or lateral tibiofemoral compartment. There was no difference in the specificities for the 2 views. The direct comparison of the Kellgren-Lawrence and the JSN radiographic grading systems found no clinical difference between the 2 systems regarding the sensitivities, although the specificity was greater for the JSN system.

CONCLUSIONS

The ability to detect knee osteoarthritis continues to be difficult without using advanced imaging. However, as an inexpensive screening tool, the 45° flexion PA view is more sensitive than the standing AP view to detect severe tibiofemoral osteoarthritis. When evaluating the radiograph for severe osteoarthritis using either the Kellgren-Lawrence or JSN grading system, there is no clinical difference in the sensitivity between the 2 methods; however, the JSN may be more specific for ruling in severe osteoarthritis in the medial compartment.

LEVEL OF EVIDENCE

Level I, systematic review of Level I studies.

Development of a rapid knee cartilage damage quantification method using magnetic resonance images

BACKGROUND

Cartilage morphometry based on magnetic resonance images (MRIs) is an emerging outcome measure for clinical trials among patients with knee osteoarthritis (KOA). However, current methods for cartilage morphometry take many hours per knee and require extensive training on the use of the associated software. In this study we tested the feasibility, reliability, and construct validity of a novel osteoarthritis cartilage damage quantification method (Cartilage Damage Index [CDI]) that utilizes informative locations on knee MRIs.

METHODS

We selected 102 knee MRIs from the Osteoarthritis Initiative that represented a range of KOA structural severity (Kellgren Lawrence [KL] Grade 0 - 4). We tested the intra- and inter-tester reliability of the CDI and compared the CDI scores against different measures of severity (radiographic joint space narrowing [JSN] grade, KL score, joint space width [JSW]) and static knee alignment, both cross-sectionally and longitudinally.

RESULTS

Determination of the CDI took on average14.4 minutes (s.d. 2.1) per knee pair (baseline and follow-up of one knee). Repeatability was good (intra- and inter-tester reliability: intraclass correlation coefficient >0.86). The mean CDI scores related to all four measures of osteoarthritis severity (JSN grade, KL score, JSW, and knee alignment; all p values < 0.05). Baseline JSN grade and knee alignment also predicted subsequent 24-month longitudinal change in the CDI (p trends <0.05). During 24 months, knees with worsening in JSN or KL grade (i.e. progressors) had greater change in CDI score.

CONCLUSIONS

The CDI is a novel knee cartilage quantification method that is rapid, reliable, and has construct validity for assessment of medial tibiofemoral osteoarthritis structural severity and its progression. It has the potential to addresses the barriers inherent to studies requiring assessment of cartilage damage on large numbers of knees, and as a biomarker for knee osteoarthritis progression.

Systematic review of the concurrent and predictive validity of MRI biomarkers in OA

OBJECTIVE

To summarize literature on the concurrent and predictive validity of MRI-based measures of osteoarthritis (OA) structural change.

METHODS

An online literature search was conducted of the OVID, EMBASE, CINAHL, PsychInfo and Cochrane databases of articles published up to the time of the search, April 2009. 1338 abstracts obtained with this search were preliminarily screened for relevance by two reviewers. Of these, 243 were selected for data extraction for this analysis on validity as well as separate reviews on discriminate validity and diagnostic performance. Of these 142 manuscripts included data pertinent to concurrent validity and 61 manuscripts for the predictive validity review. For this analysis we extracted data on criterion (concurrent and predictive) validity from both longitudinal and cross-sectional studies for all synovial joint tissues as it relates to MRI measurement in OA.

RESULTS

Concurrent validity of MRI in OA has been examined compared to symptoms, radiography, histology/pathology, arthroscopy, CT, and alignment. The relation of bone marrow lesions, synovitis and effusion to pain was moderate to strong. There was a weak or no relation of cartilage morphology or meniscal tears to pain. The relation of cartilage morphology to radiographic OA and radiographic joint space was inconsistent. There was a higher frequency of meniscal tears, synovitis and other features in persons with radiographic OA. The relation of cartilage to other constructs including histology and arthroscopy was stronger. Predictive validity of MRI in OA has been examined for ability to predict total knee replacement (TKR), change in symptoms, radiographic progression as well as MRI progression. Quantitative cartilage volume change and presence of cartilage defects or bone marrow lesions are potential predictors of TKR.

CONCLUSION

MRI has inherent strengths and unique advantages in its ability to visualize multiple individual tissue pathologies relating to pain and also predict clinical outcome. The complex disease of OA which involves an array of tissue abnormalities is best imaged using this imaging tool.

Quantitative cartilage imaging in knee osteoarthritis

Quantitative measures of cartilage morphology (i.e., thickness) represent potentially powerful surrogate endpoints in osteoarthritis (OA). These can be used to identify risk factors of structural disease progression and can facilitate the clinical efficacy testing of structure modifying drugs in OA. This paper focuses on quantitative imaging of articular cartilage morphology in the knee, and will specifically deal with different cartilage morphology outcome variables and regions of interest, the relative performance and relationship between cartilage morphology measures, reference values for MRI-based knee cartilage morphometry, imaging protocols for measurement of cartilage morphology (including those used in the Osteoarthritis Initiative), sensitivity to change observed in knee OA, spatial patterns of cartilage loss as derived by subregional analysis, comparison of MRI changes with radiographic changes, risk factors of MRI-based cartilage loss in knee OA, the correlation of MRI-based cartilage loss with clinical outcomes, treatment response in knee OA, and future directions of the field.

Magnetic resonance imaging-based semiquantitative and quantitative assessment in osteoarthritis

Whole organ magnetic resonance imaging (MRI)-based semiquantitative (SQ) assessment of knee osteoarthritis (OA), based on reliable scoring methods and expert reading, has become a powerful research tool in OA. SQ morphologic scoring has been applied to large observational cross-sectional and longitudinal epidemiologic studies as well as interventional clinical trials. SQ whole organ scoring analyzes all joint structures that are potentially relevant as surrogate outcome measures of OA and potential disease modification, including cartilage, subchondral bone, osteophytes, intra- and periarticular ligaments, menisci, synovial lining, cysts, and bursae. Resources needed for SQ scoring rely on the MRI protocol, image quality, experience of the expert readers, method of documentation, and the individual scoring system that will be applied. The first part of this article discusses the different available OA whole organ scoring systems, focusing on MRI of the knee, and also reviews alternative approaches. Rheumatologists are made aware of artifacts and differential diagnoses when applying any of the SQ scoring systems. The second part focuses on quantitative approaches in OA, particularly measurement of (subregional) cartilage loss. This approach allows one to determine minute changes that occur relatively homogeneously across cartilage structures and that are not apparent to the naked eye. To this end, the cartilage surfaces need to be segmented by trained users using specialized software. Measurements of knee cartilage loss based on water-excitation spoiled gradient recalled echo acquisition in the steady state, fast low-angle shot, or double-echo steady-state imaging sequences reported a 1% to 2% decrease in cartilage thickness annually, and a high degree of spatial heterogeneity of cartilage thickness changes in femorotibial subregions between subjects. Risk factors identified by quantitative measurement technology included a high body mass index, meniscal extrusion and meniscal tears, knee malalignment, advanced radiographic OA grade, bone marrow alterations, and focal cartilage lesions.

Ultrasound biomicroscopy imaging for monitoring progressive trypsin digestion and inhibition in articular cartilage

This study reports an ultrasound biomicroscopy (UBM) imaging approach to monitor the progressive trypsin-induced depletion of proteoglycan (PG) and its inhibition in articular cartilage. Three fresh, normal bovine patellae were obtained and four full-thickness cartilage-bone specimens were prepared from the lower medial side of each patella. One sample was used as a control and the other three were divided into three groups: Groups A, B and C (n=3 for each group). After a 40min 0.25% trypsin digestion, samples from group A were continuously digested in trypsin solution, while those in groups B and C were immersed in physiologic saline and fetal bovine serum (FBS), respectively, for another 280min. The trypsin penetration front was observed by UBM and M-mode images were acquired using 50MHz focused ultrasound and custom-developed software. The results show that the 40min trypsin digestion degraded nearly the whole surface layer of the cartilage tissue. Further digestion in trypsin or residual digestion in saline for 280min depleted most of the PG content, as observed in groups A and B. The replacement of trypsin with a physiologic saline solution only slightly slowed the digestion process (group B), while trypsin inhibitors in FBS stopped the digestion in approximately 1.5h (group C). The normalized digestion fractions of the digested tissues were calculated from ultrasound data and histology sections, and then compared between the groups. Without the use of FBS, 80% to 100% of the full thickness was digested, while this number was only approximately 50% when using FBS. Our findings indicate that the UBM imaging system could provide two-dimensional (2-D) visual information for monitoring progressive trypsin-induced PG depletion in articular cartilage. The system also potentially offers a useful tool for preparing cartilage degeneration models with precisely controlled PG depletion.

Web-based multilayer viewing interface for knee cartilage

Many adults suffer from osteoarthritis (OA) with the majority of people over 65 showing radiographic evidence of the disease. To carry out effective diagnosis and treatment, it is necessary to understand the progression of cartilage loss and study the effectiveness of therapeutic interventions. Hence, it is important to have accurate, fast diagnosis of the disease. In this paper, we describe a Web-based user interface that enables the direct viewing of 2-D and 3-D image data from the visceral and tissue levels of the biological continuum (i.e., the continuum comprising systems, viscera, tissue, cells, proteins, and genes)--while preserving geometric integrity. This is achieved despite the fact that the data are from different modalities (i.e., magnetic resonance (MR) and light microscopy). The user interface was tested using image data acquired from a study of articular cartilage thickness in the porcine knee. The interface allows the clinician to view both MR and light microscopy images in an integrated manner-with the information linked geometrically.

Cartilage thickness visualization using 2D WearMaps and TrackBack

Osteoarthritis (OA) has a significant impact in terms of morbidity, quality of life, economic and social cost. It is the most prevalent form of arthritis - affecting a large proportion of the population, internationally. The use of Magnetic Resonance (MR) Imaging (MRI) has gained significant support. MRI allows detailed, multi-planar analysis of the joint anatomy, as well as cartilage and underlying bone status; with the ability to view articular surfaces at any angle. In this paper we describe a user interface to visualize the articular cartilage thickness using 2D WearMap derived using MR knee images. The user interface comprises an interactive function (TrackBack) which allows to the Clinician to easily and rapidly refer to the radiological information (e.g. MR images), while maintaining the geometric integrity between the WearMap and the MR image.

An MRI derived articular cartilage visualization framework

OBJECTIVE

We present a multi-dimensional framework for the visualization of femoral articular cartilage. The framework comprises methods for visualizing and quantifying changes in cartilage thickness and surface morphology derived from MRI based cartilage segmentation. Adequate visualization of cartilage allows accurate and clinically meaningful assessment of cartilage surface morphology and thickness. In current practice the routine use of conventional 2D MR images provides limited qualitative information and is inconvenient because the imaged volume has to be reviewed slice by slice.

METHOD

A Graphical User Interface (GUI) that encapsulates the framework described above was developed. In the first stage of the analysis MR images of the knee are segmented to delineate cartilage boundaries. Cartilage thicknesses are subsequently measured. The detected points and corresponding thickness data are utilized to produce a visualization framework.

RESULTS

The system was tested using data from six example patients. The spatial distribution of cartilage on the articular surface was visualized using a 3D WearMap. The 2D WearMap allowed the entire cartilage surface to be studied at once. Quantitative interaction with the 2D WearMap was assisted by the ability to ascertain cartilage surface dimensions and TrackBack from a point of interest to the original MR image. As a result, the detection of wear patterns and lesions was efficiently carried out.

CONCLUSION

A means of quantitatively visualizing cartilage defects non-invasively is presented. This stands to reduce clinician reporting times, as well as allowing quantitative follow-up that facilitates osteoarthritis (OA) screening and planning/evaluating interventions.

Addressing the future of clinical information systems--Web-based multilayer visualization

This paper addresses some key issues relating to the development of new technology for clinical information systems (CIS) in relation to imaging and visualizing data. With the increasing importance of molecular and cellular biology, a new type of medicine, molecular based medicine, is now developing. This will significantly alter the way in which medicine is practiced. The view is presented that CIS will need to operate seamlessly across the Biological Continuum, i.e., the hierarchy of the human organism comprising systems, viscera, tissue, cells, proteins, and genes. We propose a multilayered visualization interface, which operates across the Biological Continuum, based on Web-based technology. A visualization interface package for two-dimensional and three-dimensional image data at the visceral and cellular levels is described. Two application examples are presented: 1) MR knee images, at the visceral level and 2) endothelial nuclei images, acquired from confocal laser microscopy, at the cellular level.

Viewing interfaces for segmentation and measurement results

In the paper we describe a web-based interface to view 2-D and 3-D results generated from segmentation and measurement process interactively. Our implementation takes a fully web-based approach to provide universal access and visualization to a wide range of patient data (i.e. at multiple locations). An example case study is presented: thickness measurement of articular cartilage from MR knee images used in the diagnosis of osteoarthritis (OA).

Geometric Framework linking different levels of the Biological Continuum

With the increasing importance of molecular and cellular biology, a new type of medicine, molecular based medicine, is now developing. This will significantly alter the way in which medicine is practiced. Central to these developments is the concept of the Biological Continuum (BC). Medicine today is often practiced at one or two of these levels, i.e. there is generally no vertically integrated approach. In any area of application there will be a wide range of data (both 2-D and 3-D) across the BC. Hence, there is a need to readily access and view the full range of data. In this paper we describe a web-based interface which allows the user to view images and other data, and to navigate seamlessly from one level of the BC to another level (e.g. from Visceral to Tissue). We present a geometric framework to link images from these two levels. The interface was developed using SVG and Javascript. An example case study, which focuses on the knee, is presented MR images of knee at the visceral level and histology images of cartilage at the tissue level. We have shown that with such an interface it is possible to view images from different levels of the BC in a vertically integrated manner.

Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals

Knee joint disorders are common in the elderly population, athletes, and outdoor sports enthusiasts. These disorders are often painful and incapacitating. Vibration signals [vibroarthrographic (VAG)] are emitted at the knee joint during the swinging movement of the knee. These VAG signals contain information that can be used to characterize certain pathological aspects of the knee joint. In this paper, we present a noninvasive method for screening knee joint disorders using the VAG signals. The proposed approach uses wavelet packet decompositions and a modified local discriminant bases algorithm to analyze the VAG signals and to identify the highly discriminatory basis functions. We demonstrate the effectiveness of using a combination of multiple dissimilarity measures to arrive at the optimal set of discriminatory basis functions, thereby maximizing the classification accuracy. A database of 89 VAG signals containing 51 normal and 38 abnormal samples were used in this study. The features extracted from the coefficients of the selected basis functions were analyzed and classified using a linear-discriminant-analysis-based classifier. A classification accuracy as high as 80% was achieved using this true nonstationary signal analysis approach.