Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI.

Background Assessment of lumbar spinal stenosis at MRI is repetitive and time consuming. Deep learning (DL) could improve -productivity and the consistency of reporting. Purpose To develop a DL model for automated detection and classification of lumbar central canal, lateral recess, and neural -foraminal stenosis. Materials and Methods In this retrospective study, lumbar spine MRI scans obtained from September 2015 to September 2018 were included. Studies of patients with spinal instrumentation or studies with suboptimal image quality, as well as postgadolinium studies and studies of patients with scoliosis, were excluded. Axial T2-weighted and sagittal T1-weighted images were used. Studies were split into an internal training set (80%), validation set (9%), and test set (11%). Training data were labeled by four radiologists using predefined gradings (normal, mild, moderate, and severe). A two-component DL model was developed. First, a convolutional neural network (CNN) was trained to detect the region of interest (ROI), with a second CNN for classification. An internal test set was labeled by a musculoskeletal radiologist with 31 years of experience (reference standard) and two subspecialist radiologists (radiologist 1: A.M., 5 years of experience; radiologist 2: J.T.P.D.H., 9 years of experience). DL model performance on an external test set was evaluated. Detection recall (in percentage), interrater agreement (Gwet κ), sensitivity, and specificity were calculated. Results Overall, 446 MRI lumbar spine studies were analyzed (446 patients; mean age ± standard deviation, 52 years ± 19; 240 women), with 396 patients in the training (80%) and validation (9%) sets and 50 (11%) in the internal test set. For internal testing, DL model and radiologist central canal recall were greater than 99%, with reduced neural foramina recall for the DL model (84.5%) and radiologist 1 (83.9%) compared with radiologist 2 (97.1%) (P < .001). For internal testing, dichotomous classification (normal or mild vs moderate or severe) showed almost-perfect agreement for both radiologists and the DL model, with respective κ values of 0.98, 0.98, and 0.96 for the central canal; 0.92, 0.95, and 0.92 for lateral recesses; and 0.94, 0.95, and 0.89 for neural foramina (P < .001). External testing with 100 MRI scans of lumbar spines showed almost perfect agreement for the DL model for dichotomous classification of all ROIs (κ, 0.95-0.96; P < .001). Conclusion A deep learning model showed comparable agreement with subspecialist radiologists for detection and classification of central canal and lateral recess stenosis, with slightly lower agreement for neural foraminal stenosis at lumbar spine MRI. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Radiation Dose and Image Quality in Pediatric Cardiac Computed Tomography: A Comparison Between Sequential and Third-Generation Dual-Source High-Pitch Spiral Techniques.

The aim of this study was to investigate whether there is a reduction in radiation dose and improvement in image quality of pediatric cardiac computed tomography scans performed using the high-pitch spiral technique on a new third-generation dual-source 2 × 192-slice scanner (group B) compared with scans performed using the sequential technique on a single-source 256-slice scanner (group A). We performed a retrospective observational study on 40 patients aged ≤18 years who underwent prospectively electrocardiogram-triggered cardiac computed tomography. Image quality was assessed by pre-defined objective indices and a four-point subjective score. Apart from a higher mean heart rate in group A (P = 0.016), there were otherwise no significant inter-group differences in patient characteristics. The median effective dose was 4.41 mSv (interquartile range 2.58-5.90 mSv) in group A and 0.52 mSv (interquartile range 0.39-0.59 mSv) in group B (P < 0.001), representing a 88 % reduction. Subjective image quality score was significantly better in group B (4 = excellent with no artifact, mode 57.1 %) than in group A (3 = good with mild artifact, mode 57.9 %) (P < 0.001). Noise index, signal-to-noise ratio and contrast-to-noise ratio between both groups were not statistically significant. New third-generation dual-source high-pitch spiral scan technique can deliver excellent image quality with low radiation dose. Our results suggest that it should be considered as a first-choice technique for performing cardiac computed tomography in the pediatric population.

Multiple Myeloma: Case of a "Moving" Sternal Wire.

Multiple myeloma generally occurs in older adults, with the clonal proliferation of plasma cells and accumulation of monoclonal protein resulting in a broad range of clinical manifestations and complications, including hypercalcemia, renal dysfunction, anaemia, and bone destruction (termed CRAB features). A 64-year-old man with no history of malignancy presented with an enlarging precordial lump occurring three years post-sternotomy for uneventful coronary artery bypass grafting surgery. Initial investigations showed anaemia and impaired renal function. Multimodal imaging performed for further evaluation showcases the radio-pathological features which can be encountered in haematological malignancy. Subsequent percutaneous biopsy confirmed an underlying plasma cell neoplasm, and a diagnosis of multiple myeloma was achieved. The prompt resolution of the lesions upon the initiation of treatment highlights the importance of early diagnosis and treatment.

A case study of pyelolymphatic backflow demonstrated on CT.

Pyelolymphatic backflow is a rare type of pyelolymphatic fistula that occurs in cases of urinary obstruction. This phenomenon may help to decompress an acutely obstructed kidney, and therefore, alleviate renal function from deteriorating. Pyelolymphatic backflow has specific imaging characteristics best shown on CT urography. Our case study aims to improve the understanding and diagnosis of pyelolymphatic backflow by presenting a case of pyelolymphatic backflow seen on CT urography, including discussions on the pathophysiology, clinical relevance and management of this phenomenon. Our case study demonstrates the opacification of landmark lymphatic structures including the retroperitoneal para-aortic lymphatic chain, cisterna chyli and thoracic duct, which have not been demonstrated previously.