State-of-the-art anterior cruciate ligament tears: A primer for primary care physicians

Bioinspired adaptable multiplanar mechano-vibrotactile haptic system

Several gaps persist in haptic device development due to the multifaceted nature of the sense of touch. Existing gaps include challenges enhancing touch feedback fidelity, providing diverse haptic sensations, and ensuring wearability for delivering tactile stimuli to the fingertips. Here, we introduce the Bioinspired Adaptable Multiplanar Haptic system, offering mechanotactile/steady and vibrotactile pulse stimuli with adjustable intensity (up to 298.1 mN) and frequencies (up to 130 Hz). This system can deliver simultaneous stimuli across multiple fingertip areas. The paper includes a full characterisation of our system. As the device can play an important role in further understanding human touch, we performed human stimuli sensitivity and differentiation experiments to evaluate the capability of delivering mechano-vibrotactile, variable intensity, simultaneous, multiplanar and operator agnostic stimuli. Our system promises to accelerate the development of touch perception devices, providing painless, operator-independent data crucial for researching and diagnosing touch-related disorders.

[Imaging of the anterior cruciate ligament and anterolateral rotational instability of the knee joint]

The anterior cruciate ligament (ACL) is essential for the stability of the knee joint and ACL tears are one of the most common sports injuries with a high incidence, especially in sports that require rotational movements and abrupt changes in direction. Injuries of the ACL are rarely isolated and are often accompanied by meniscal and other internal knee injuries, which increase the risk of osteoarthritis. The spectrum of ACL injuries includes strains, partial tears and complete tears. Magnetic resonance imaging (MRI) plays a pivotal role in the diagnostics as it can accurately depict not only the ACL but also accompanying injuries. Proton density and T2-weighted sequences are particularly suitable for evaluating the ACL, which is usually well visible and assessable in all planes. In addition to depicting fiber disruption as a direct sign and central diagnostic indicator of an ACL tear, there are numerous other direct and indirect signs of an ACL injury in MRI. These include abnormal fiber orientations, signal increases and an anterior subluxation of the tibia relative to the femur. The bone marrow edema patterns often associated with ACL tears are indicative of the underlying injury mechanism. The treatment of ACL tears can be conservative or surgical depending on various factors, such as the patient's activity level and the presence of accompanying injuries. The precise and comprehensive description of ACL injuries by radiology is crucial for optimal treatment planning. Anterolateral rotational instability (ALRI) of the knee joint characterizes a condition of excessive lateral and rotational mobility of the tibia in relation to the femur in the anterolateral knee region. This instability is primarily caused by a rupture of the ACL, with the anterolateral ligament (ALL) that was rediscovered about 10 years ago, also being attributed a role in stabilizing the knee. Although ALRI is primarily diagnosed through clinical examinations, MRI is indispensable for detecting injuries to the ACL, ALL, and other internal knee structures, which is essential for developing an optimal treatment strategy.

The Relationship between Lower Extremity Functional Performance and Balance after Anterior Cruciate Ligament Reconstruction: Results of Patients Treated with the Modified All-Inside Technique

BACKGROUND AND OBJECTIVES

Anterior cruciate ligament (ACL) ruptures are common injuries, and ACL reconstruction (ACLR) is among the most common surgical procedures in sports surgery. Our research aims to compare the 6-month post-operative results of the modified all-inside (MAI) ACLR technique, single leg hop tests (SLHT), and Y balance tests applied in different directions on the operated and non-operated sides.

MATERIALS AND METHODS

A retrospective cohort of 22 male recreational athletes who underwent MAI ACLR techniques performed by the same surgeon were evaluated. The functional knee strengths of the participants on the operated and non-operated sides were evaluated with five different tests of SLHTs: single hop for distance (SH), triple hop for distance (TH), crossover triple hop for distance (CH), medial side triple hop for distance (MSTH), and medial rotation (90°) with hop for distance (MRH). Their dynamic balance was evaluated with the Y balance Test.

RESULTS

Compared to pre-operative levels, there was a significant improvement in the mean Lysholm, Tegner, and IKDC scores during the post-operative period (p < 0.05). There was a difference between SH, THD, CHD, MSTH, and MRH on the operated and non-operative sides (p < 0.05). There was no difference between Y balance scores on the operated and non-operative sides, and there were no differences between LSI scores resulting from SLHTs (p > 0.05). There were no significant relationships between YBT (composite scores) and SH, TH, CH, MSTH, and MRH distances in the healthy leg (p > 0.05), but a significant correlation with only CH in the ACL leg (p < 0.05).

CONCLUSIONS

Our research shows that sixth-month post-operative SLHT findings were lower on the ACL side compared to the healthy side in patients tested with the MAI ACLR technique. However, when these scores are evaluated in terms of balance, it can be seen that both sides reveal similar findings. The similarity of LSIs in SLHTs applied in different directions, and balance scores of ACL and healthy sides revealed that the MAI technique is also an ACLR technique that can be used in athletes from a functional point of view.

Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model

OBJECTIVES

Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention.

METHODS

In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set.

RESULTS

In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004).

CONCLUSIONS

The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs.

KEY POINTS

• YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes.

Artificial Intelligence-Assisted Diagnosis of Anterior Cruciate Ligament Tears From Magnetic Resonance Images: Algorithm Development and Validation Study

BACKGROUND

Anterior cruciate ligament (ACL) injuries are common in sports and are critical knee injuries that require prompt diagnosis. Magnetic resonance imaging (MRI) is a strong, noninvasive tool for detecting ACL tears, which requires training to read accurately. Clinicians with different experiences in reading MR images require different information for the diagnosis of ACL tears. Artificial intelligence (AI) image processing could be a promising approach in the diagnosis of ACL tears.

OBJECTIVE

This study sought to use AI to (1) diagnose ACL tears from complete MR images, (2) identify torn-ACL images from complete MR images with a diagnosis of ACL tears, and (3) differentiate intact-ACL and torn-ACL MR images from the selected MR images.

METHODS

The sagittal MR images of torn ACL (n=1205) and intact ACL (n=1018) from 800 cases and the complete knee MR images of 200 cases (100 torn ACL and 100 intact ACL) from patients aged 20-40 years were retrospectively collected. An AI approach using a convolutional neural network was applied to build models for the objective. The MR images of 200 independent cases (100 torn ACL and 100 intact ACL) were used as the test set for the models. The MR images of 40 randomly selected cases from the test set were used to compare the reading accuracy of ACL tears between the trained model and clinicians with different levels of experience.

RESULTS

The first model differentiated between torn-ACL, intact-ACL, and other images from complete MR images with an accuracy of 0.9946, and the sensitivity, specificity, precision, and F1-score were 0.9344, 0.9743, 0.8659, and 0.8980, respectively. The final accuracy for ACL-tear diagnosis was 0.96. The model showed a significantly higher reading accuracy than less experienced clinicians. The second model identified torn-ACL images from complete MR images with a diagnosis of ACL tear with an accuracy of 0.9943, and the sensitivity, specificity, precision, and F1-score were 0.9154, 0.9660, 0.8167, and 0.8632, respectively. The third model differentiated torn- and intact-ACL images with an accuracy of 0.9691, and the sensitivity, specificity, precision, and F1-score were 0.9827, 0.9519, 0.9632, and 0.9728, respectively.

CONCLUSIONS

This study demonstrates the feasibility of using an AI approach to provide information to clinicians who need different information from MRI to diagnose ACL tears.

Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches

Deep learning-based MRI diagnosis of internal joint derangement is an emerging field of artificial intelligence, which offers many exciting possibilities for musculoskeletal radiology. A variety of investigational deep learning algorithms have been developed to detect anterior cruciate ligament tears, meniscus tears, and rotator cuff disorders. Additional deep learning-based MRI algorithms have been investigated to detect Achilles tendon tears, recurrence prediction of musculoskeletal neoplasms, and complex segmentation of nerves, bones, and muscles. Proof-of-concept studies suggest that deep learning algorithms may achieve similar diagnostic performances when compared to human readers in meta-analyses; however, musculoskeletal radiologists outperformed most deep learning algorithms in studies including a direct comparison. Earlier investigations and developments of deep learning algorithms focused on the binary classification of the presence or absence of an abnormality, whereas more advanced deep learning algorithms start to include features for characterization and severity grading. While many studies have focused on comparing deep learning algorithms against human readers, there is a paucity of data on the performance differences of radiologists interpreting musculoskeletal MRI studies without and with artificial intelligence support. Similarly, studies demonstrating the generalizability and clinical applicability of deep learning algorithms using realistic clinical settings with workflow-integrated deep learning algorithms are sparse. Contingent upon future studies showing the clinical utility of deep learning algorithms, artificial intelligence may eventually translate into clinical practice to assist detection and characterization of various conditions on musculoskeletal MRI exams.

Deep Convolutional Neural Network-Based Diagnosis of Anterior Cruciate Ligament Tears: Performance Comparison of Homogenous Versus Heterogeneous Knee MRI Cohorts With Different Pulse Sequence Protocols and 1.5-T and 3-T Magnetic Field Strengths

Objectives

The aim of this study was to clinically validate a Deep Convolutional Neural Network (DCNN) for the detection of surgically proven anterior cruciate ligament (ACL) tears in a large patient cohort and to analyze the effect of magnetic resonance examinations from different institutions, varying protocols, and field strengths.

Materials and Methods

After ethics committee approval, this retrospective analysis of prospectively collected data was performed on 512 consecutive subjects, who underwent knee magnetic resonance imaging (MRI) in a total of 59 different institutions followed by arthroscopic knee surgery at our institution. The DCNN and 3 fellowship-trained full-time academic musculoskeletal radiologists evaluated the MRI examinations for full-thickness ACL tears independently. Surgical reports served as the reference standard. Statistics included diagnostic performance metrics, including sensitivity, specificity, area under the receiver operating curve (“AUC ROC”), and kappa statistics. P values less than 0.05 were considered to represent statistical significance.

Results

Anterior cruciate ligament tears were present in 45.7% (234/512) and absent in 54.3% (278/512) of the subjects. The DCNN had a sensitivity of 96.1%, which was not significantly different from the readers (97.5%–97.9%; all P ≥ 0.118), but significantly lower specificity of 93.1% (readers, 99.6%–100%; all P < 0.001) and “AUC ROC” of 0.935 (readers, 0.989–0.991; all P < 0.001) for the entire cohort. Subgroup analysis showed a significantly lower sensitivity, specificity, and “AUC ROC” of the DCNN for outside MRI (92.5%, 87.1%, and 0.898, respectively) than in-house MRI (99.0%, 94.4%, and 0.967, respectively) examinations (P = 0.026, P = 0.043, and P < 0.05, respectively). There were no significant differences in DCNN performance for 1.5-T and 3-T MRI examinations (all P ≥ 0.753, respectively).

Conclusions

Deep Convolutional Neural Network performance of ACL tear diagnosis can approach performance levels similar to fellowship-trained full-time academic musculoskeletal radiologists at 1.5 T and 3 T; however, the performance may decrease with increasing MRI examination heterogeneity.