Artificial Intelligence and Computer Vision in Low Back Pain: A Systematic Review

Chronic Low Back Pain (LBP) is a symptom that may be caused by several diseases, and it is currently the leading cause of disability worldwide. The increased amount of digital images in orthopaedics has led to the development of methods related to artificial intelligence, and to computer vision in particular, which aim to improve diagnosis and treatment of LBP. In this manuscript, we have systematically reviewed the available literature on the use of computer vision in the diagnosis and treatment of LBP. A systematic research of PubMed electronic database was performed. The search strategy was set as the combinations of the following keywords: “Artificial Intelligence”, “Feature Extraction”, “Segmentation”, “Computer Vision”, “Machine Learning”, “Deep Learning”, “Neural Network”, “Low Back Pain”, “Lumbar”. Results: The search returned a total of 558 articles. After careful evaluation of the abstracts, 358 were excluded, whereas 124 papers were excluded after full-text examination, taking the number of eligible articles to 76. The main applications of computer vision in LBP include feature extraction and segmentation, which are usually followed by further tasks. Most recent methods use deep learning models rather than digital image processing techniques. The best performing methods for segmentation of vertebrae, intervertebral discs, spinal canal and lumbar muscles achieve Sørensen–Dice scores greater than 90%, whereas studies focusing on localization and identification of structures collectively showed an accuracy greater than 80%. Future advances in artificial intelligence are expected to increase systems’ autonomy and reliability, thus providing even more effective tools for the diagnosis and treatment of LBP.

Download Full-text

Guideline Provides Consensus and Evidence-Based Approach For Diagnosis and Treatment of Low Back Pain

Topics in Pain Management ◽

10.1097/01.tpm.0000310952.41309.81 ◽

2008 ◽

Vol 23 (6) ◽

pp. 6-8

Keyword(s):

Low Back Pain ◽

Back Pain ◽

Diagnosis And Treatment ◽

Evidence Based ◽

Low Back

Download Full-text

Low Back Pain: The Potential Contribution of Supraspinal Motor Control and Proprioception

The Neuroscientist ◽

10.1177/1073858418809074 ◽

2018 ◽

Vol 25 (6) ◽

pp. 583-596 ◽

Cited By ~ 6

Author(s):

Michael Lukas Meier ◽

Andrea Vrana ◽

Petra Schweinhardt

Keyword(s):

Low Back Pain ◽

Motor Control ◽

Back Pain ◽

Control Strategies ◽

Intervertebral Discs ◽

Cortical Reorganization ◽

Potential Contribution ◽

Low Back ◽

Output Side

Motor control, which relies on constant communication between motor and sensory systems, is crucial for spine posture, stability and movement. Adaptions of motor control occur in low back pain (LBP) while different motor adaption strategies exist across individuals, probably to reduce LBP and risk of injury. However, in some individuals with LBP, adapted motor control strategies might have long-term consequences, such as increased spinal loading that has been linked with degeneration of intervertebral discs and other tissues, potentially maintaining recurrent or chronic LBP. Factors contributing to motor control adaptations in LBP have been extensively studied on the motor output side, but less attention has been paid to changes in sensory input, specifically proprioception. Furthermore, motor cortex reorganization has been linked with chronic and recurrent LBP, but underlying factors are poorly understood. Here, we review current research on behavioral and neural effects of motor control adaptions in LBP. We conclude that back pain-induced disrupted or reduced proprioceptive signaling likely plays a pivotal role in driving long-term changes in the top-down control of the motor system via motor and sensory cortical reorganization. In the outlook of this review, we explore whether motor control adaptations are also important for other (musculoskeletal) pain conditions.

Download Full-text

Automated detection of sacroiliitis on plain radiograph using EfficientDet algorithm in young patients with back pain: a pilot study

10.21203/rs.3.rs-272234/v1 ◽

2021 ◽

Author(s):

Sung Hyun Noh ◽

Chansik An ◽

Dain Kim ◽

Seung Hyun Lee ◽

Min-Yung Chang ◽

...

Keyword(s):

Low Back Pain ◽

Deep Learning ◽

Back Pain ◽

Object Detection ◽

Sacroiliac Joint ◽

Plain Radiograph ◽

Young Patients ◽

Training Dataset ◽

Detection Accuracy ◽

Low Back

Abstract Background A computer algorithm that automatically detects sacroiliac joint abnormalities on plain radiograph would help radiologists avoid missing sacroiliitis. This study aimed to develop and validate a deep learning model to detect and diagnose sacroiliitis on plain radiograph in young patients with low back pain. Methods This Institutional Review Board-approved retrospective study included 478 and 468 plain radiographs from 241 and 433 young (< 40 years) patients who complained of low back pain with and without ankylosing spondylitis, respectively. They were randomly split into training and test datasets with a ratio of 8:2. Radiologists reviewed the images and labeled the coordinates of a bounding box and determined the presence or absence of sacroiliitis for each sacroiliac joint. We fine-tined and optimized the EfficientDet-D4 object detection model pre-trained on the COCO 2107 dataset on the training dataset and validated the final model on the test dataset. Results The mean average precision, an evaluation metric for object detection accuracy, was 0.918 at 0.5 intersection over union. In the diagnosis of sacroiliitis, the area under the curve, sensitivity, specificity, accuracy, and F1-score were 0.932 (95% confidence interval, 0.903–0.961), 96.9% (92.9–99.0), 86.8% (81.5–90.9), 91.1% (87.7–93.7), and 90.2% (85.0–93.9), respectively. Conclusions The EfficientDet, a deep learning-based object detection algorithm, could be used to automatically diagnose sacroiliitis on plain radiograph.

Download Full-text