Automated knee ligament injuries classification method based on exemplar pyramid local binary pattern feature extraction and hybrid iterative feature selection

Face recognition is efficiently used in computer vision, pattern recognition, biometric, law enforcement, surveillance, criminal investigations, and missing person detection. However, face recognition is still a challenging task under variant illuminations, pose, expression, occlusion, and background. In this paper, we proposed a cascading of histogram of oriented gradients (HOG) and local binary pattern (LBP) feature extraction method on ORL face dataset, which can improve recognition rates while also addressing pose, scale, expression, and variant illumination issues. The facial recognition network was trained using various classifiers such as with KNN, SVM, and random forest (RF). The results have been shown that the accuracy rate of the combined LBP and HOG feature extraction method is better than individual LBP or HOG features for ORL database face recognition.

BackgroundThe purpose of this study was to determine the prevalence and characteristics of ligamentous knee injuries and to compare patient demographics, associated injuries and hospital stay to pedestrians who did not sustain a ligamentous knee injury.MethodsA retrospective review of all adult patients presenting as pedestrians struck by a motor vehicle to a level 1 trauma center over a three-year period was performed. Demographics, length of stay, orthopedic and non-orthopedic traumatic injuries were recorded. Magnetic resonance imaging was reviewed for ligamentous, bony and chondral injuries.ResultsFive hundred thirty-nine patients were included. Sixty-seven (12.4%) patients sustained a total of 84 ligamentous knee injuries. OF these knee injuries that had MRI (55/84), the majority (96%) were multi-ligamentous in nature. Patients with ligamentous knee injury were more likely to also be affected by traumatic brain injury, solid organ injury, cervical and lumbar spine injury, pelvic ring injuries, distal femur fractures, patella fractures, knee dislocations, tibial plateau fractures, tibial pilon fractures, and deep vein thrombosis when compared to patients who did not sustain ligamentous knee injury. Patients who sustained ligamentous knee injury were more likely to require hospital and intensive care admission and had a longer overall hospital stay.ConclusionGiven the high prevalence of ligamentous knee injuries in this patient population, these patients should be thoroughly evaluated for a ligamentous knee injury. If ligamentous knee injury is suspected, MRI should be considered as a majority of these injuries involved multiple structures. Patients with ligamentous knee injuries often had multi-system injuries with resulting longer hospital stay when compared to those without ligamentous knee injuries.

Background and Objectives: This research aimed to assess knee injuries, which is essential for determining the appropriate therapeutic intervention and outcomes. In this study, Magnetic Resonance Imaging was employed to examine the frequency and distribution of diverse forms of damage in traumatized knee joints. Material and Methods: Individuals referred from the Department of Orthopedic surgery in the Department of Radiology with suspected ligamentous injuries secondary to trauma after clinical evaluation were included in the study. They underwent Magnetic Resonance Imaging (MRI) of the knee as advised by the referring surgeon. The study spanned from July 2022 to June 2023. This study was conducted to assess the effectiveness of MRI in diagnosing ligamentous knee injuries because of its obvious potential. Results: Out of the total 50 subjects, 35 (70%) were men and 15 (30%) were women. Right knee was involved in 56% of the cases. The most common ligamentous knee injury was observed to be Anterior Cruciate Ligament tear (48%) followed by medial meniscal injury (40%). Only 4 cases (8%) pf posterior cruciate ligament were identified. Magnetic Resonance Imaging (MRI) has demonstrated significant efficacy as a diagnostic tool for identifying injuries of the cruciate ligaments and menisci when compared to arthroscopic methodologies. Conclusion: In terms of identification of the problems of menisci and cruciate ligaments, MRI is having a higher degree of sensitivity, specificity and accuracy and can be used effectively to diagnose derangements of internal soft-tissues of the knee joint including traumatic injuries of intracapsular structures. Keywords: ligamentous knee injuries, Magnetic Resonance Imaging, Arthroscopy.

ExHiF: Alzheimer's disease detection using exemplar histogram-based features with CT and MR images

This work has the objective of developing a methodology for the classification of regions of interest (ROI) extracted from mammograms into masses and non-masses. To this end, we conducted a comparative study by combining several techniques in the various stages of the problem. We compared several texture-based techniques for the classification of ROIs. This study combines image processing, phylogenetic trees (PT), local binary patterns (LBP), support vector machines (SVM) and the micro-genetic algorithm (GA). The analysis of texture is performed, either through the combination PT/LBP or with grey levels, to compute the taxonomic diversity () and taxonomic distinction (*) indexes extracted from sub-regions (circular, circular crown, internal mask, external mask and the combination of internal and external mask) of an ROI. A GA is used to estimate the best phylogenetic weights. Then, its results are compared with the results achieved with the use of PT only. We also analyse the behaviour of the methodology when using the ROIs with and without enhancement. This enhancement consists of the application of a mean filter and the contrast-limited adaptive histogram equalisation (CLAHE). PTs and SVM were used to perform the selection of features. To evaluate the performance of the methodologies under analysis, we used the following metrics: sensitivity, specificity, accuracy and area under the receiver operating characteristic (ROC) curve (). Sensitivity and specificity measure the efficiency of the classifier at the correct detection of positive (masses) and negative (non-masses) cases, respectively. Accuracy measures the performance of the classification in both cases. The ROC curve is the graphical representation of the pairs (1-specificity, sensitivity). is the area formed by the ROC curve, which equals to 1 in an ideal test. The comparison of the possible combinations for each stage of the study revealed the following results. In the analyses without feature selection, the best results were (1) 100% accuracy and of 0.99 for the combination of PT, LBP and internal masks and (2) 99.5% accuracy and of 0.99 for the combination of GA, LBP and internal masks for the extraction of features. In the analyses with feature selection, the best results were (1) 100% accuracy and of 1.0 for the combination of GA and LBP (feature extraction) with the union of internal and external masks and (2) 98.5% accuracy and of 0.99 for the combination of PT, LBP and the union of internal and external masks.

<p>The purpose of the present study was to examine the effects of exercise on the rehabilitation of knee ligament injuries in athletes and to identify what the injured athletes consider as the most effective treatment concerning their rehabilitation, through the administration of a reported condition inquiry. Two hundred ninety six healthy subjects, 22,59+6,31 years old, participated in the research. All the subjects were active or former athletes, competed or had competed in athletic clubs throughout Greece, in various team sports or individual sports and competing categories and had suffered a knee ligament injury in their career as athletes. The effects of exercise on the rehabilitation of knee ligament injuries were measured through a scale of measurements. For data analysis was used the <em>descriptive analysis</em> of the <em>SPSS version 20 for Windows</em>. Data processing showed that the highest percentage of the knee injuries (43,80%) concerns anterior cruciate ligament (ACL) rupture, 34,40% partial or total meniscus rupture, 15,60% ligament injuries and 6,20% medial collateral ligament (MCL) or lateral collateral ligament (LCL) rupture. More than half of the knee injuries (53,10%), namely ruptures of ACL (76,50%), the partial-total rupture of meniscus (17,60%), and the patella dislocations and partial ruptures of MCL and LCL (5,90%), were treated surgically, combined with abstaining from training and matches, medication, bandage usage, immobilization with plaster-brace, medical examinations, physiotherapies, and special therapeutic exercise. The rest of the cases of the knee injuries (46,90%), namely all the cases of ligament over-voltages, ¾ of the meniscus ruptures, half of the patella dislocations and partial ruptures of MCL and LCL, as well as 1,25% of ACL rupture, were treated conservatively, with different combinations of  physiotherapies, special therapeutic exercises, abstention from training and games, medication, bandage usage, immobilization with plaster-brace, further medical examinations. In addition, almost all the injured athletes (except a 6,20%) did a combination of exercise modes for the rehabilitation of their knee ligament injury. More specifically, 18,80% did exercises with straps, resistance bands, weightbearing and isokinetic machine. In addition, 15,60% did exercises with straps, resistance bands, weightbearing, exercises in the water and isokinetic machine and the same percentage (15,60%) did exercises with straps, resistance bands, weightbearing and exercises in the water. 12,50% did exercises with resistance bands and weightbearing, 9,40% did exercises with resistance bands and in smaller percentages the athletes did exercises in the water and gaiting (6,20%), exercises with straps, resistance bands and weightbearing (6,20%), exercises with straps and resistance bands (3,10%), exercises with isokinetic machine and exercises in the water (3,10%), as well as exercises with resistance bands, exercises in the water and in the isokinetic machine (3,10%). In addition, 93,80% of the athletes stated that their knee ligament injury is completely or partially restored. Concerning the athletes’ opinions,  43,80% consider that the most effective treatment for the rehabilitation of their knee ligament injury was strengthening with weightbearing and resistance bands. Likewise, 35,30% of the athletes who underwent surgery consider strengthening mainly by weightbearing and resistance bands as the most effective treatment for the rehabilitation of their injury. In conclusion, according to the opinions of the athletes, who treated their knee ligament injury both non-operatively and operatively, the most effective treatment for the rehabilitation of the knee ligament injury was exercise in the mode of weightbearing and resistance bands. Thus, it could be said that exercise brings about significant positive effects on the rehabilitation of the knee ligament injury. Consequently, exercise should be an integral part of the knee ligament injury rehabilitation and prevention. </p>

Stress Radiographs for Ligamentous Knee Injuries

Objective: To determine the pattern of musculoskeletal injuries incurred by physical training in patients and training personnel as assessed by Magnetic Resonance Imaging. Study Design: Cross-sectional study. Place and Duration of Study: Combined Military Hospital, Abbottabad Pakistan, from Sep 2021 to Jun 2022. Methodology: Patients from local institutes with rigorous training schedules for their students referred to the Radiology Department of Combined Military Hospital, Abbottabad for musculoskeletal Magnetic Resonance Imaging were included in the study. Data regarding duration of symptoms, and Magnetic Resonance Imaging I findings, site, nature and grading of injury, laterality, and associated features, were recorded for each patient. The nature of injuries, their grading, frequency, and relationship among different types of injuries were assessed. Results: Stress fracture of the lower limbs was the most common injury associated with physical training, with 28.6% (n=38/105) presenting mostly in the second half of training. Maximum patients presented with the highest grade of stress fractures; it was more common in females, seen in 90% at the time of presentation (n=9/10). Anterior cruciate ligament injury of the knee was the second most common injury (20%-n=21/105). Most patients with meniscal injuries had anterior cruciate ligament injury. Conclusion: Stress fractures and knee ligamentous injuries are the most common physical training-related injuries. The majority of female patients had stress fractures at their first presentation. Although less common, meniscal injuries were significantly associated with anterior cruciate ligament injury of the knee.

Objective measures to quantitate the amount of lateral compartment opening for patients with lateral and posterolateral knee injuries have not been well documented. The purpose of the present study was to measure lateral compartment opening secondary to applied varus stresses following posterolateral corner structure sectioning and to develop radiographic guidelines to quantify the amount of lateral compartment gapping seen with these injuries.Ten nonpaired fresh-frozen cadaver lower extremities were used. Two varus loads, a 12-Nm moment and a clinician-applied varus stress, were applied to the intact knees and after sequential sectioning of the fibular collateral ligament, popliteus tendon, popliteofibular ligament, and anterior and posterior cruciate ligaments to simulate degrees of posterolateral knee and associated combined cruciate ligament injuries. The shortest distance between the most distal subchondral bone surface of the lateral femoral condyle and the corresponding lateral tibial plateau was measured to quantify lateral compartment opening and was analyzed on digital radiographs. Three observers were used to determine interobserver reproducibility and intraobserver repeatability.In the intact knee, the mean lateral compartment gapping due to a 12-Nm moment and a clinician-applied varus stress was 8.9 and 9.7 mm, respectively. Lateral gapping significantly increased by 2.1 and 2.7 mm in association with sectioning of the fibular collateral ligament and by 3.4 and 4.0 mm in knees with a simulated posterolateral corner injury for each respective load-application technique (p < 0.0001 for all comparisons). Intraobserver repeatability was high, with all observers independently obtaining an intraclass correlation coefficient of 0.99, whereas the analysis of interobserver reproducibility demonstrated an intraclass correlation coefficient of 0.97.Measurements with use of current clinical digital imaging systems can be used to quantify the amount of lateral compartment knee opening. Clinicians should suspect an isolated fibular collateral ligament injury if opening on clinician-applied varus stress radiographs increases by approximately 2.7 mm and a grade-III posterolateral corner injury if values increase by approximately 4.0 mm.Varus stress radiographs appear to provide an objective and reproducible measure of lateral compartment gapping that should prove useful for the diagnosis, management, and postoperative follow-up of patients with fibular collateral ligament and posterolateral knee injuries.

Retrieval of similar images from large dataset of brain images across patients would help the experts in the decision diagnosis process of diseases. Generally used feature extraction methods are color, texture and shape. In medical images texture and shape features are most efficient. Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) are good descriptor for brain MR image retrieval. But there are many challenges facing in medical application. An empirical study of the impact of increasing bins number in the HOG descriptor concluded that larger the number is more accurate the descriptor is. In fact this is due to the reduction of orientations range that each bin covers. Despite the efficiency of augmenting the bins number, this technique has limited spatial support as the augmentation of the number of bins used leads to increase the histogram dimension. So here proposed a method called Histogram of Fuzzy Oriented Gradients (HFOG), in which a pixel can belong several bins with different degrees. The Local Binary Patterns feature extraction method is widely used for texture analysis; however, the original LBP is based on hard thresholding the neighborhood of each pixel. Therefore, texture representation with LBP is very sensitive to noise and cannot distinguish between a strong and a weak pattern. In this study, Fuzzy Local Binary Patterns was introduced to improve the original LBP.

Brain diseases can cause invisible disorders, cognitive and behavioral changes. Their symptoms vary widely. In some cases, treatment can improve the symptoms while in other cases injuries become permanent. Many disorders are progressive. Therefore, early and accurate diagnosis of disorder is essential for improving disorder condition and patient’s quality of life. This paper presents the brain disease diagnosis system in which two feature extraction methods are compared. One of the feature extraction methods uses local binary pattern and steerable pyramid (SP) to decompose magnetic resonance (MR) brain images into subbands which are termed as LBPSP subbands. Another feature extraction method uses SP solely to decompose MR images into SP subbands. Energies over LBPSP and SP subbands are calculated. The features are subjected to backpropagation neural network classifier. To prove the effectiveness of the proposed system, multi-class disease classification is carried out on four MR image datasets. Also, ‘one-vs-all’ binary classification is performed on one of the datasets. Energy features of LBPSP subbands achieve multi-class classification accuracies of 97.67%, 97.27%, 94.67% and 85.01% on datasets DS-200, DS-310, DS-255 and DS-612, respectively. The performance measures of ‘one-vs-all’ binary class classification prove the competency and efficiency of LBPSP subband features over the existing methods.The comparative results of two feature extraction methods indicate that the energy features of LBPSP subbands have more discriminating potential than energy features of SP subbands. Experimental results reveal that energy features of LBPSP subbands lead to the existing classification methods.

Knee ligament injury is among the most common sports injuries and is associated with long recovery periods and low return-to-sport rates. Unfortunately, the mechanics of ligament injury are difficult to study in vivo, and computational studies provide limited insight. The objective of this study was to implement and validate a robotic system capable of reproducing natural six degree-of-freedom clamped-kinematic trajectories on human cadaver knees (meaning that positions and orientations are rigidly controlled and resultant loads are measured). To accomplish this, we leveraged the field's recent access to high-fidelity bone kinematics from dynamic biplanar radiography (DBR), and implemented these kinematics in a coordinate frame built around the knee's natural flexion-extension axis. We assessed our system's capabilities in the context of ACL injury, by moving seven cadaveric knee specimens through kinematics derived from walking, running, drop jump, and ACL injury. We then used robotically simulated clinical stability tests to evaluate the hypothesis that knee stability would be only reduced by the motions intended to injure the knee. Our results show that the structural integrity of the knee was not compromised by non-injurious motions, while the injury motion produced a clinically relevant ACL injury with characteristic anterior and valgus instability. We also demonstrated that our robotic system can provide direct measurements of reaction loads during a variety of motions, and facilitate gross evaluation of ligament failure mechanisms. Clamped-kinematic robotic evaluation of cadaver knees has the potential to deepen understanding of the mechanics of knee ligament injury.

Initial endoscopy for dyspepsia may be cost-effective if unit costs can be reduced

Fracture dislocations of the knee joint are complex injuries usually sustained following high velocity trauma. It is important to identify ligamentous injuries in patients with fractures around the knee joint, as persistent instability can lead to a poor outcome. Certain fracture patterns are more commonly associated with knee ligamentous injuries and can serve as signposts to them. Management of these injuries requires a combination of the principles of fracture management along with ligament repair and reconstruction. This chapter will cover the common fractures associated with knee ligament injuries and discuss management strategies.

In the member of mud crab, species of Scylla are the most traded seafood commodity in Asia and the culturing practice is already done in most of Asia country a few years ago. The demand for mud crabs has increased rapidly over the last decade, providing great potential for the development of the mud crab aquaculture industry. But, there is still unsolved problem where limitation of knowledge in identification is limited due to similar colours and feature characteristic. Thus, this study proposed an automatic technique that can evaluate and produce the subset of mud crab genus Scylla features by using Local Binary Pattern (LBP) as a feature extraction tool. The main objective of the study is to find the optimal subset of mud crab genus Scylla features from a carapace images dataset. Based on 153 extracted features chosen by LBP features selection methods, the accuracy rates of three classification algorithms were obtained for analysis. The results from the MatLab experiment demonstrated that, the LBP method produced an accuracy under 60% for entire classifier.