Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Sequelae of bilateral luxatio erecta in the acute post-reduction period demonstrated by MRI: a case report and literature review.

Luxatio erecta humeri (LEH), also known as inferior shoulder dislocation, is uncommon, comprising about 0.5% of all cases of shoulder dislocation. Synchronous bilateral LEH is exceedingly rare and, to our knowledge, there are no descriptions of axillary nerve injury on magnetic resonance imaging (MRI) following LEH. We present a case of traumatic bilateral LEH in a 59-year-old woman who fell from a fast-moving mobility scooter and sustained direct axial loading forces on the fully abducted shoulders. Both shoulders were successfully reduced using the traction-countertraction technique in the emergency department. In this article, we describe the characteristic features of LEH on plain radiography and the pattern of acute soft-tissue injuries on MRI. We emphasize the importance of reviewing the axillary neurovascular bundle, which by virtue of its location beneath the shoulder joint, is prone to injury in inferior shoulder dislocation and thus has a substantial impact on functional recovery. This important complication is unfortunately not routinely examined by radiologists, partly because of the paucity of literature highlighting its clinical significance.

Review of Junior Resident Plain Film Reporting and Audit in Singapore.

BACKGROUND: Graduate medical education in Singapore recently underwent significant restructuring, leading to the accreditation of residency programs by the Accreditation Council for Graduate Medical Education-International (ACGME-I). In radiology, this involved a change in teaching and quality assurance of plain film (PF) reporting. PF reported by junior residents (postgraduate year 1-3) are subject to a 50% random audit. To date, national data on junior resident performance in PF reporting have not been published. OBJECTIVE: We reviewed performance in PF reporting under the current teaching and audit framework. METHODS: Retrospective review of junior resident reported PF audit data from all 3 radiology residency programs in Singapore. The number of residents audited, number of PF reported and audited, and major discrepancy rates were analyzed. RESULTS: On average, 86 440 PF were audited annually nationwide from an estimated 184 288 junior resident-reported PF. Each program trained between 4 to 24 junior residents annually (mean 15), averaging about 44 each year nationwide. A mean of 28 813 PF were audited annually in each program (range 4355-50 880). An estimated mean of 4148 PF (range 1452-9752) were reported per junior resident per year, about 346 PF per month. The major discrepancy rate ranged from 0.04% to 1.13% (mean 0.34%). One resident required remediation in the study period. CONCLUSIONS: Structured residency training in Singapore has produced a high level of junior resident competency in PF interpretation.

Evolution of gout: "malignant" change over time?

Gout is a common entity; yet it is such a great mimicker in its imaging features that it can confuse clinicians and radiologists alike, sometimes leading to unnecessary investigations and treatment. We present a case of a 52 year old male renal transplant patient who presented with a slow growing mass in his left shin. The initial radiograph demonstrated a non-aggressive looking calcified lesion. A fine needle aspiration demonstrated this lesion to be gout deposition. The lesion was unchanged in the following eight years until the patient reported a sudden growth in size. Imaging showed features of an aggressive lesion with disruption of the previous calcification as well as enhancement on magnetic resonance imaging. Surgical excision biopsy was performed in view of the worrisome features on imaging and the histology showed tophaceous gout. Following description of our case, we reviewed the clinical and imaging features of gout and discussed its differential diagnoses.

Peritoneal lymphomatosis mimicking peritoneal carcinomatosis: important imaging clues for correct diagnosis.

Peritoneal lymphomatosis, a rare presentation of lymphoma, can mimic peritoneal carcinomatosis. Computed tomography findings in both conditions include omental caking, as well as peritoneal enhancement, thickening and nodularity. We report three cases of peritoneal lymphomatosis and give an analysis of the salient imaging features that aided in the accurate diagnosis of the condition in each case. Two of the three cases demonstrated elevated serum cancer antigen 125 levels, a marker commonly associated with ovarian carcinoma. It is thus critical to distinguish peritoneal lymphomatosis from carcinomatosis, as the prognosis and management are dramatically different.