Faculty Bibliography

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.

PURPOSE:To evaluate if the hepatic arterial perfusion index (HPI) in liver parenchyma of cirrhotic patients can serve as a surrogate parameter for stratifying the degree of esophageal varices and related bleeding risks. METHODS:CT image data of sixty-six patients (59 men; mean age 68 years ± 10 years) with liver cirrhosis (Child-Pugh class A (35/66, 53%), B (25/66, 38%), and C (6/66, 9%) who underwent perfusion CT (PCT) for hepatocellular carcinoma (HCC) screening between April 2010 and January 2019 were retrospectively identified. HPI, a parameter calculated by a commercially available CT liver perfusion analysis software that is based on the double maximum slope model, using time attenuation curve to determine perfusion, was correlated with the degree of esophageal varices diagnosed at endoscopy and the number of bleeding events. RESULTS:Eta correlation coefficient for HPI/presence of esophageal varices was very weak (0.083). Spearman-Rho for HPI/grading of esophageal varices was very weak (0.037 (p = 0.804)). Kendall-Tau-b for HPI/grading of esophageal varices was very weak (0.027 (p = 0.807)). ANOVA and Bonferroni post-hoc-tests showed no significant difference of HPI between different grades of esophageal varices (F (3, 62) = 1.676, p = 0.186). Eta correlation coefficient for HPI/bleeding event was very weak (0.126). CONCLUSION:The stratification of the degree of esophageal varices and the related bleeding risk by correlation with the HPI as a surrogate parameter for portal venous hypertension was not possible for patients with liver cirrhosis in Child-Pugh class A and B.

Medial and lateral elbow pain are often due to degenerative tendinosis and less commonly due to trauma. The involved structures include the flexor-pronator tendon origin in medial-sided pain and the extensor tendon origin in lateral-sided pain. Multimodality imaging is often obtained to verify the clinically suspected diagnosis, evaluate the extent of injury, and guide treatment decisions. Image-guided procedures can provide symptom relief to support physical therapy and also induce tendon healing. Surgical debridement and repair are typically performed in refractory cases, resulting in good to excellent outcomes in most cases. In this article, we review and illustrate pertinent anatomical structures of the distal humerus, emphasizing the structure and contributions of the flexor-pronator and extensor tendon origins in acute and chronic tendon abnormalities. We also discuss approaches to image-guided treatment and surgical management of medial and lateral epicondylitis.

ABSTRACT/UNASSIGNED:Musculoskeletal magnetic resonance imaging (MRI) is a careful negotiation between spatial, temporal, and contrast resolution, which builds the foundation for diagnostic performance and value. Many aspects of musculoskeletal MRI can improve the image quality and increase the acquisition speed; however, 3.0-T field strength has the highest impact within the current diagnostic range. In addition to the favorable attributes of 3.0-T field strength translating into high temporal, spatial, and contrast resolution, many 3.0-T MRI systems yield additional gains through high-performance gradients systems and radiofrequency pulse transmission technology, advanced multichannel receiver technology, and high-end surface coils. Compared with 1.5 T, 3.0-T MRI systems yield approximately 2-fold higher signal-to-noise ratios, enabling 4 times faster data acquisition or double the matrix size. Clinically, 3.0-T field strength translates into markedly higher scan efficiency, better image quality, more accurate visualization of small anatomic structures and abnormalities, and the ability to offer high-end applications, such as quantitative MRI and magnetic resonance neurography. Challenges of 3.0-T MRI include higher magnetic susceptibility, chemical shift, dielectric effects, and higher radiofrequency energy deposition, which can be managed successfully. The higher total cost of ownership of 3.0-T MRI systems can be offset by shorter musculoskeletal MRI examinations, higher-quality examinations, and utilization of advanced MRI techniques, which then can achieve higher gains and value than lower field systems. We provide a practice-focused review of the value of 3.0-T field strength for musculoskeletal MRI, practical solutions to challenges, and illustrations of a wide spectrum of gainful clinical applications.