AI MSK clinical applications: spine imaging

Cervical Spondylosis Diagnosis Based on Convolutional Neural Network with X-ray Images

The increase in Cervical Spondylosis cases and the expansion of the affected demographic to younger patients have escalated the demand for X-ray screening. Challenges include variability in imaging technology, differences in equipment specifications, and the diverse experience levels of clinicians, which collectively hinder diagnostic accuracy. In response, a deep learning approach utilizing a ResNet-34 convolutional neural network has been developed. This model, trained on a comprehensive dataset of 1235 cervical spine X-ray images representing a wide range of projection angles, aims to mitigate these issues by providing a robust tool for diagnosis. Validation of the model was performed on an independent set of 136 X-ray images, also varied in projection angles, to ensure its efficacy across diverse clinical scenarios. The model achieved a classification accuracy of 89.7%, significantly outperforming the traditional manual diagnostic approach, which has an accuracy of 68.3%. This advancement demonstrates the viability of deep learning models to not only complement but enhance the diagnostic capabilities of clinicians in identifying Cervical Spondylosis, offering a promising avenue for improving diagnostic accuracy and efficiency in clinical settings.

Diagnostic Performance of the Darth Vader Sign for the Diagnosis of Lumbar Spondylolysis in Routinely Acquired Abdominal CT

Spondylolysis is underdiagnosed and often missed in non-musculoskeletal abdominal CT imaging. Our aim was to assess the inter-reader agreement and diagnostic performance of a novel "Darth Vader sign" for the detection of spondylolysis in routine axial images. We performed a retrospective search in the institutional report archives through keyword strings for lumbar spondylolysis and spondylolisthesis. Abdominal CTs from 53 spondylolysis cases (41% female) and from controls (n = 6) without spine abnormalities were identified. A total of 139 single axial slices covering the lumbar spine (86 normal images, 40 with spondylolysis, 13 with degenerative spondylolisthesis without spondylolysis) were exported. Two radiology residents rated all images for the presence or absence of the "Darth Vader sign". The diagnostic accuracy for both readers, as well as the inter-reader agreement, was calculated. The "Darth Vader sign" showed an inter-reader agreement of 0.77. Using the "Darth Vader sign", spondylolysis was detected with a sensitivity and specificity of 65.0-88.2% and 96.2-99.0%, respectively. The "Darth Vader sign" shows excellent diagnostic performance at a substantial inter-reader agreement for the detection of spondylolysis. Using the "Darth Vader sign" in the CT reading routine may be an easy yet effective tool to improve the detection rate of spondylolysis in non-musculoskeletal cases and hence improve patient care.

Revolutionizing Spinal Care: Current Applications and Future Directions of Artificial Intelligence and Machine Learning

Artificial intelligence (AI) and machine learning (ML) are rapidly becoming integral components of modern healthcare, offering new avenues for diagnosis, treatment, and outcome prediction. This review explores their current applications and potential future in the field of spinal care. From enhancing imaging techniques to predicting patient outcomes, AI and ML are revolutionizing the way we approach spinal diseases. AI and ML have significantly improved spinal imaging by augmenting detection and classification capabilities, thereby boosting diagnostic accuracy. Predictive models have also been developed to guide treatment plans and foresee patient outcomes, driving a shift towards more personalized care. Looking towards the future, we envision AI and ML further ingraining themselves in spinal care with the development of algorithms capable of deciphering complex spinal pathologies to aid decision making. Despite the promise these technologies hold, their integration into clinical practice is not without challenges. Data quality, integration hurdles, data security, and ethical considerations are some of the key areas that need to be addressed for their successful and responsible implementation. In conclusion, AI and ML represent potent tools for transforming spinal care. Thoughtful and balanced integration of these technologies, guided by ethical considerations, can lead to significant advancements, ushering in an era of more personalized, effective, and efficient healthcare.

Original research: utilization of a convolutional neural network for automated detection of lytic spinal lesions on body CTs

OBJECTIVE

To develop, train, and test a convolutional neural network (CNN) for detection of spinal lytic lesions in chest, abdomen, and pelvis CT scans.

MATERIALS AND METHODS

Cases of malignant spinal lytic lesions in CT scans were identified. Images were manually segmented for the following classes: (i) lesion, (ii) normal bone, (iii) background. If more than one lesion was on a single slice, all lesions were segmented. Images were stored as 128×128 pixel grayscale, with 10% segregated for testing. The training pipeline of the dataset included histogram equalization and data augmentation. A model was trained on Keras/Tensorflow using an 80/20 training/validation split, based on U-Net architecture. Additional testing of the model was performed on 1106 images of healthy controls. Global sensitivity measured detection of any lesion on a single image. Local sensitivity and positive predictive value (PPV) measured detection of all lesions on an image. Global specificity measured false positive rate in non-pathologic bone.

RESULTS

Six hundred images were obtained for model creation. The training set consisted of 540 images, which was augmented to 20,000. The test set consisted of 60 images. Model training was performed in triplicate. Mean Dice scores were 0.61 for lytic lesion, 0.95 for normal bone, and 0.99 for background. Mean global sensitivity was 90.6%, local sensitivity was 74.0%, local PPV was 78.3%, and global specificity was 63.3%. At least one false positive lesion was noted in 28.8-44.9% of control images.

CONCLUSION

A task-trained CNN showed good sensitivity in detecting spinal lytic lesions in axial CT images.

Detection of Imperceptible Intervertebral Disc Fissures in Conventional MRI-An AI Strategy for Improved Diagnostics

Annular fissures in the intervertebral discs are believed to be closely related to back pain. However, no sensitive non-invasive method exists to detect annular fissures. This study aimed to propose and test a method capable of detecting the presence and position of annular fissures in conventional magnetic resonance (MR) images non-invasively. The method utilizes textural features calculated from conventional MR images combined with attention mapping and artificial intelligence (AI)-based classification models. As ground truth, reference standard computed tomography (CT) discography was used. One hundred twenty-three intervertebral discs in 43 patients were examined with MR imaging followed by discography and CT. The fissure classification model determined the presence of fissures with 100% sensitivity and 97% specificity. Moreover, the true position of the fissures was correctly determined in 90 (87%) of the analyzed discs. Additionally, the proposed method was significantly more accurate at identifying fissures than the conventional radiological high-intensity zone marker. In conclusion, the findings suggest that the proposed method is a promising diagnostic tool to detect annular fissures of importance for back pain and might aid in clinical practice and allow for new non-invasive research related to the presence and position of individual fissures.

Assessment of Posterolateral Lumbar Fusion: A Systematic Review of Imaging-Based Fusion Criteria

BACKGROUND

Noninvasive assessment of osseous fusion after spinal fusion surgery is essential for timely diagnosis of patients with symptomatic pseudarthrosis and for evaluation of the performance of spinal fusion procedures. There is, however, no consensus on the definition and assessment of successful posterolateral fusion (PLF) of the lumbar spine. This systematic review aimed to (1) summarize the criteria used for imaging-based fusion assessment after instrumented PLF and (2) evaluate their diagnostic accuracy and reliability.

METHODS

First, a search of the literature was conducted in November 2018 to identify reproducible criteria for imaging-based fusion assessment after primary instrumented PLF between T10 and S1 in adult patients, and to determine their frequency of use. A second search in July 2021 was directed at primary studies on the diagnostic accuracy (with surgical exploration as the reference) and/or reliability (interobserver and intraobserver agreement) of these criteria. Article selection and data extraction were performed by at least 2 reviewers independently. The methodological quality of validation studies was assessed with the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) and QAREL (Quality Appraisal of Reliability Studies).

RESULTS

Of the 187 articles included from the first search, 47% used a classification system and 63% used ≥1 descriptive criterion related to osseous bridging (104 articles), absence of motion (78 articles), and/or absence of static signs of nonunion (39 articles). A great variation in terminology, cutoff values, and assessed anatomical locations was observed. While the use of computed tomography (CT) increased over time, radiographs remained predominant. The second search yielded 11 articles with considerable variation in outcomes and quality concerns. Agreement between imaging-based assessment and surgical exploration with regard to demonstration of fusion ranged between 55% and 80%, while reliability ranged from poor to excellent.

CONCLUSIONS

None of the available criteria for noninvasive assessment of fusion status after instrumented PLF were demonstrated to have both sufficient accuracy and reliability. Further elaboration and validation of a well-defined systematic CT-based assessment method that allows grading of the intertransverse and interfacet fusion mass at each side of each fusion level and includes signs of nonunion is recommended.

LEVEL OF EVIDENCE

Diagnostic Level III. See Instructions for Authors for a complete description of levels of evidence.