Faculty Bibliography

OBJECTIVE:To establish the effectiveness of cooled radiofrequency ablation in managing hip pain from osteoarthritis at 6 months after receiving treatment in patients who failed conservative treatments and are not surgical candidates due to comorbidities or unwillingness to undergo arthroplasty surgery by targeting the femoral and obturator branches and assessing the degree of hip pain relief and change of function. MATERIALS AND METHODS/METHODS:This prospective pilot study includes a total of 11 consecutive patients experiencing persistent chronic hip pain in the setting of advanced osteoarthritis. Patients initially underwent anesthetic blocks of the obturator and femoral nerve branches to determine cooled radiofrequency ablation candidacy. After adequate response to the anesthetic blocks (> 50% immediate pain relief), patients were subjected to the procedures 2-3 weeks later. Treatment response was evaluated utilizing clinically validated questionnaires and visual analog score in order to assess impact on pain severity, stiffness, and functional activities of daily living. Follow-up outcome scores were collected up to 6 months after cooled radiofrequency ablation procedure. RESULTS:A total of 11 hips were treated consecutively between August 2019 and March 2020 (mean patient age 61.4 years; 8 M:3F). The mean total HOOS score improved significantly from baseline at 17.0 ± 6.0 to 52.9 ± 5.4 at a mean of 6.2 months after treatment (p < 0.0001), with significant improvement in mean pain score from 16.1 ± 6.6 to 53.4 ± 7.4 (p < 0.0001) and mean stiffness score from 15.0 ± 8.1 to 53.6 ± 11.0 (p < 0.0001). No major complications were encountered. No patients went on to re-treatment, surgery, or other intervention. CONCLUSION/CONCLUSIONS:Image-guided obturator and femoral nerve cooled radiofrequency ablation is effective and safe in treating chronic hip pain/stiffness in the setting of advanced osteoarthritis.

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.

Artificial intelligence (AI) and deep learning have multiple potential uses in aiding the musculoskeletal radiologist in the radiological evaluation of orthopedic implants. These include identification of implants, characterization of implants according to anatomic type, identification of specific implant models, and evaluation of implants for positioning and complications. In addition, natural language processing (NLP) can aid in the acquisition of clinical information from the medical record that can help with tasks like prepopulating radiology reports. Several proof-of-concept works have been published in the literature describing the application of deep learning toward these various tasks, with performance comparable to that of expert musculoskeletal radiologists. Although much work remains to bring these proof-of-concept algorithms into clinical deployment, AI has tremendous potential toward automating these tasks, thereby augmenting the musculoskeletal radiologist.

OBJECTIVE:To evaluate the behavior of a publicly available deep convolutional neural network (DCNN) bone age algorithm when presented with inappropriate data inputs in both radiological and non-radiological domains. METHODS:We evaluated a publicly available DCNN-based bone age application. The DCNN was trained on 12,612 pediatric hand radiographs and won the 2017 RSNA Pediatric Bone Age Challenge (concordance of 0.991 with radiologist ground-truth). We used the application to analyze 50 left-hand radiographs (appropriate data inputs) and seven classes of inappropriate data inputs in radiological (i.e., chest radiographs) and non-radiological (i.e., image of street numbers) domains. For each image, we noted if (1) the application distinguished between appropriate and inappropriate data inputs and (2) inference time per image. Mean inference times were compared using ANOVA. RESULTS:The 16Bit Bone Age application calculated bone age for all pediatric hand radiographs with mean inference time of 1.1 s. The application did not distinguish between pediatric hand radiographs and inappropriate image types, including radiological and non-radiological domains. The application inappropriately calculated bone age for all inappropriate image types, with mean inference time of 1.1 s for all categories (p = 1). CONCLUSION/CONCLUSIONS:A publicly available DCNN-based bone age application failed to distinguish between appropriate and inappropriate data inputs and calculated bone age for inappropriate images. The awareness of inappropriate outputs based on inappropriate DCNN input is important if tasks such as bone age determination are automated, emphasizing the need for appropriate oversight at the data input and verification stage to avoid unrecognized erroneous results.

Artificial intelligence and deep learning (DL) offer musculoskeletal radiology exciting possibilities in multiple areas, including image reconstruction and transformation, tissue segmentation, workflow support, and disease detection. Novel DL-based image reconstruction algorithms correcting aliasing artifacts, signal loss, and noise amplification with previously unobtainable effectiveness are prime examples of how DL algorithms deliver promised value propositions in musculoskeletal radiology. The speed of DL-based tissue segmentation promises great efficiency gains that may permit the inclusion of tissue compositional-based information routinely into radiology reports. Similarly, DL algorithms give rise to a myriad of opportunities for workflow improvements, including intelligent and adaptive hanging protocols, speech recognition, report generation, scheduling, precertification, and billing. The value propositions of disease-detecting DL algorithms include reduced error rates and increased productivity. However, more studies using authentic clinical workflow settings are necessary to fully understand the value of DL algorithms for disease detection in clinical practice. Successful workflow integration and management of multiple algorithms are critical for translating the value propositions of DL algorithms into clinical practice but represent a major roadblock for which solutions are critically needed. While there is no consensus about the most sustainable business model, radiology departments will need to carefully weigh the benefits and disadvantages of each commercially available DL algorithm. Although more studies are needed to understand the value and impact of DL algorithms on clinical practice, DL technology will likely play an important role in the future of musculoskeletal imaging.

In the last few years, major developments have been observed in the field of magnetic resonance imaging (MRI). Advances in both scanner hardware and software technologies have witnessed great leaps, enhancing the diagnostic quality and, therefore, the value of MRI. In musculoskeletal radiology, three-dimensional (3D) MRI has become an integral component of the diagnostic pathway at our institutions. This technique is particularly relevant in patients with hand and wrist symptoms, due to the intricate nature of the anatomical structures and the wide range of differential diagnoses for most presentations. We review the benefits of 3D MRI of the hand and wrist, commonly used pulse sequences, clinical applications, limitations, and future directions. We offer guidance for enhancing the image quality and tips for image interpretation of 3D MRI of the hand and wrist.

Magnetic resonance imaging (MRI) is a powerful imaging modality for visualizing a wide range of ankle disorders that affect ligaments, tendons, and articular cartilage. Standard two-dimensional (2D) fast spin-echo (FSE) and turbo spin-echo (TSE) pulse sequences offer high signal-to-noise and contrast-to-noise ratios, but slice thickness limitations create partial volume effects. Modern three-dimensional (3D) FSE/TSE pulse sequences with isotropic voxel dimensions can achieve higher spatial resolution and similar contrast resolutions in ≤ 5 minutes of acquisition time. Advanced acceleration schemes have reduced the blurring effects of 3D FSE/TSE pulse sequences by affording shorter echo train lengths. The ability for thin-slice partitions and multiplanar reformation capabilities eliminate relevant partial volume effects and render modern 3D FSE/TSE pulse sequences excellently suited for MRI visualization of several oblique and curved structures around the ankle. Clinical efficiency gains can be achieved by replacing two or three 2D FSE/TSE sequences within an ankle protocol with a single isotropic 3D FSE/TSE pulse sequence. In this article, we review technical pulse sequence properties for 3D MRI of the ankle, discuss practical considerations for clinical implementation and achieving the highest image quality, compare diagnostic performance metrics of 2D and 3D MRI for major ankle structures, and illustrate a broad spectrum of ankle abnormalities.