Deep Learning Body Region Classification of MRI and CT Examinations.

This study demonstrates the high performance of deep learning in identification of body regions covering the entire human body from magnetic resonance (MR) and computed tomography (CT) axial images across diverse acquisition protocols and modality manufacturers. Pixel-based analysis of anatomy contained in image sets can provide accurate anatomic labeling. For this purpose, a convolutional neural network (CNN)-based classifier was developed to identify body regions in CT and MRI studies. Seventeen CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective datasets were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test datasets originated from a different healthcare network than the train and validation datasets. Sensitivity and specificity of the classifier was evaluated for patient age, patient sex, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2891 anonymized CT cases (training, 1804 studies; validation, 602 studies; test, 485 studies) and 3339 anonymized MRI cases (training, 1911 studies; validation, 636 studies; test, 792 studies). Twenty-seven institutions from primary care hospitals, community hospitals, and imaging centers contributed to the test datasets. The data included cases of all sexes in equal proportions and subjects aged from 18 years old to + 90 years old. Image-level weighted sensitivity of 92.5% (92.1-92.8) for CT and 92.3% (92.0-92.5) for MRI and weighted specificity of 99.4% (99.4-99.5) for CT and 99.2% (99.1-99.2) for MRI were achieved. Deep learning models can classify CT and MR images by body region including lower and upper extremities with high accuracy.

Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology.

Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada.

Get a kick out of this: the spectrum of knee extensor mechanism injuries.

At the end of this article, the reader should be able to (1) recognise normal anatomy and anatomical variants of the extensor mechanism of the knee on various imaging modalities, including plain film, ultrasound and MRI; (2) diagnose a broad spectrum of EM injuries in adult and paediatric patients including patellar and quadriceps tendinopathy, Osgood-Schlatter disease, Sindig-Larsen-Johansson syndrome, chondromalacia patellae and patellar fractures on various imaging modalities; and (3) appreciate the important role of imaging in the diagnosis of musculoskeletal injuries.

Infrapatellar bursitis in children with juvenile idiopathic arthritis: a case series.

Children with juvenile idiopathic arthritis (JIA) may infrequently present with localized anterior knee pain or swelling, in addition to generalize knee pain induced by JIA. We report five cases of deep infrapatellar bursitis in children with JIA. The clinical features, radiological findings, management, and outcome of five children with JIA and deep infrapatellar bursitis are reviewed. Three boys and two girls with a mean age of 9.8 years (range 6-14 years) were reviewed. Four children had persistent oligoarticular JIA, and one child had extended oligoarticular JIA. The presentation of deep infrapatellar bursitis was variable. In only one patient was the bursal swelling painful. Knee magnetic resonance imaging (MRI) was performed in four patients and demonstrated coexistent knee joint synovitis in three. Treatment included targeted corticosteroid injections into the deep infrapatellar bursa in two cases with complete resolution. One case was treated with corticosteroid injection by an outside health care provider with poor clinical response. Two cases are being treated with non-steroidal anti-inflammatory drugs and methotrexate. Deep infrapatellar bursitis can occur as an isolated finding or concurrently with knee joint synovitis in patients with JIA. Awareness of this entity is important because direct injection of the bursa may be needed for treatment, as the bursa does not communicate with the knee joint. Furthermore, when bursitis is suspected in JIA, MRI can be helpful to confirm the diagnosis, detect concurrent knee joint synovitis, and exclude other pathologies.

Serious musculoskeletal infections in children receiving anti-tumor necrosis factor-alpha therapy: a case series.

Anti-tumor necrosis factor-alpha (anti-TNF-alpha) agents are widely used to treat children with juvenile idiopathic arthritis (JIA) whose disease is resistant to conventional therapy. Although generally well tolerated, use of these agents has been associated with an increased risk of infection. In particular, in patients treated with anti-TNF-alpha agents, there is an increased susceptibility to infection by intracellular organisms such as tuberculosis, and common infections may present atypically or be more severe. We report four cases of serious musculoskeletal infections among 31 children with JIA being treated with anti-TNF-alpha agents, two of which were secondary to group A beta-hemolytic Streptococcus.

Schimke immunoosseous dysplasia: defining skeletal features.

Schimke immunoosseous dysplasia (SIOD) is an autosomal recessive multisystem disorder characterized by prominent spondyloepiphyseal dysplasia, T cell deficiency, and focal segmental glomerulosclerosis. Biallelic mutations in swi/snf-related, matrix-associated, actin-dependent regulator of chromatin, subfamily a-like 1 (SMARCAL1) are the only identified cause of SIOD, but approximately half of patients referred for molecular studies do not have detectable mutations in SMARCAL1. We hypothesized that skeletal features distinguish between those with or without SMARCAL1 mutations. Therefore, we analyzed the skeletal radiographs of 22 patients with and 11 without detectable SMARCAL1 mutations. We found that patients with SMARCAL1 mutations have a spondyloepiphyseal dysplasia (SED) essentially limited to the spine, pelvis, capital femoral epiphyses, and possibly the sella turcica, whereas the hands and other long bones are basically normal. Additionally, we found that several of the adolescent and young adult patients developed osteoporosis and coxarthrosis. Of the 11 patients without detectable SMARCAL1 mutations, seven had a SED indistinguishable from patients with SMARCAL1 mutations. We conclude therefore that SED is a feature of patients with SMARCAL1 mutations and that skeletal features do not distinguish who of those with SED have SMARCAL1 mutations.

Cystic bone lesions in a boy with Darier disease: a magnetic resonance imaging assessment.

We describe asymptomatic bone cysts in the right humerus of a 17-year-old boy with Darier disease. The cysts were found when a radiographic skeletal survey was performed to monitor for adverse effects of oral retinoid therapy. Magnetic resonance imaging was used to confirm that the lesions were cystic and to delineate their extent. The literature was reviewed for previous reports of this association.

Sudden death in spondylo-meta-epiphyseal dysplasia, short limb-abnormal calcification type.

The spondylo-meta-epiphyseal dysplasias are an expanding group of skeletal dysplasias with specific features differentiating each subtype. We review the precocious carpal mineralization, unique metacarpal shape, triangular distal phalanges and mushroom cloud-shaped proximal phalanges present at an early age in spondylo-meta-epiphyseal dysplasia, short limb-abnormal calcification type (SMED SL-AC) and report two patients with clinical and radiographic features consistent with SMED SL-AC, who died suddenly because of spinal cord compression. The patients presented are female siblings, providing further evidence for autosomal recessive inheritance. Cervical cord compression is found in half of reported patients and is the major cause of mortality. SMED SL-AC should be added to the list of genetic causes of sudden death. Radiological features in the hand may be used in the first few years of life to support an early diagnosis and thus allow for prevention of premature demise.

Rheumatic manifestations of Bartonella infection in 2 children.

We describe 2 patients with very unusual rheumatological presentations presumably caused by Bartonella infection: one had myositis of proximal thigh muscles bilaterally, and the other had arthritis and skin nodules. Both patients had very high levels of antibody to Bartonella that decreased in association with clinical improvement. Bartonella infection should be considered in the differential diagnosis of unusual myositis or arthritis in children.