Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists.

BACKGROUND: As the number of conventional radiographic examinations in pediatric emergency departments increases, so, too, does the number of reading errors by radiologists. OBJECTIVE: The aim of this study is to investigate the ability of artificial intelligence (AI) to improve the detection of fractures by radiologists in children and young adults. MATERIALS AND METHODS: A cohort of 300 anonymized radiographs performed for the detection of appendicular fractures in patients ages 2 to 21 years was collected retrospectively. The ground truth for each examination was established after an independent review by two radiologists with expertise in musculoskeletal imaging. Discrepancies were resolved by consensus with a third radiologist. Half of the 300 examinations showed at least 1 fracture. Radiographs were read by three senior pediatric radiologists and five radiology residents in the usual manner and then read again immediately after with the help of AI. RESULTS: The mean sensitivity for all groups was 73.3% (110/150) without AI; it increased significantly by almost 10% (P<0.001) to 82.8% (125/150) with AI. For junior radiologists, it increased by 10.3% (P<0.001) and for senior radiologists by 8.2% (P=0.08). On average, there was no significant change in specificity (from 89.6% to 90.3% [+0.7%, P=0.28]); for junior radiologists, specificity increased from 86.2% to 87.6% (+1.4%, P=0.42) and for senior radiologists, it decreased from 95.1% to 94.9% (-0.2%, P=0.23). The stand-alone sensitivity and specificity of the AI were, respectively, 91% and 90%. CONCLUSION: With the help of AI, sensitivity increased by an average of 10% without significantly decreasing specificity in fracture detection in a predominantly pediatric population.

Long-term outcomes of prostate artery embolization for acute urinary retention: An analysis of 88 patients.

PURPOSE: The purpose of this study was to assess long-term outcome of prostate artery embolization (PAE) in patients presenting with acute urinary retention related to benign prostatic hyperplasia. MATERIALS AND METHODS: All consecutive patients who underwent PAE for acute urinary retention due to benign prostatic hyperplasia from August 2011 to December 2021 in a single institution were retrospectively included. There were 88 men with a mean age of 72 ± 12 (standard deviation [SD]) years (range: 42-99 years). Patients underwent a first attempt of catheter removal two weeks after PAE. Clinical success was defined as the absence of acute urinary retention recurrence. Correlations between long-term clinical success and patient variables or bilateral PAE were searched for using Spearman correlation test. Catheter-free survival was assessed using Kaplan-Meier analysis. RESULTS: Successful catheter removal in the month following PAE was performed in 72 (72/88; 82%) patients and 16 (16/88; 18%) patients had immediate recurrence. Clinical success persisted for 58 (58/88; 66%) patients at long-term follow-up (mean follow-up: 19.5 months ± 16.5 [SD]; range: 2-74 months). Recurrence occurred at a mean of 16.2 months ± 12.2 (SD) (range: 1.5-43 months) post-PAE. Overall, 21 (21/88; 24%) patients of the cohort underwent prostatic surgery, at a mean of 10.4 months ± 12.2 (SD) (range: 1.2-42.4 months) from initial PAE. No correlations between patients variables or bilateral PAE and long-term clinical success were identified. Kaplan-Meier analysis showed a three-year catheter free probability of 60%. CONCLUSION: PAE is a valuable technique for acute urinary retention related to benign prostatic hyperplasia, with a long-term success rate of 66%. However acute urinary retention relapse affects 15% of patients.

Non-Hemorrhagic Adrenal Infarction during Pregnancy: The Diagnostic Imaging Keys.

Background: non-hemorrhagic adrenal infarction (NHAI) is a rare cause of acute abdominal/flank pain during pregnancy; in order to ensure prompt and appropriate treatment, this diagnosis should not be overlooked. This case series highlights pertinent imaging findings, including ultrasounds (USs), computed tomography (CT), and magnetic resonance imaging (MRI) of recent NHAI cases. Methods: we compiled all consecutive NHAI cases from two university hospitals over a two-year period and checked the relevant clinical, laboratory, and imaging findings. Relevant articles on NHAI published from January 2010 to March 2021 were analyzed. Results: six cases were found in our database. CT-scans typically showed enlarged, hypodense, and non-enhanced adrenal glands. Unenhanced MRIs allowed for diagnoses and showed enlarged adrenal glands in the signal hyperintensity on T2 and diffusion-weighted imaging, without any signal hyperintensity on T1. In two of our six cases, USs showed swollen adrenal glands with fluid collection. Conclusion: NHAI and its differential diagnosis-in cases of acute pain during pregnancy-highlight the crucial roles of integrated radiological examination and cooperation between obstetricians and radiologists, both of whom should consider the location of the pain, the accessibility and tolerance of MRI, and the radiation exposure of CT. Despite its supposed poor sensitivity, an US performed because the patient reports pain should also be used to examine the adrenal gland regions. Non-enhanced MRI is clearly of value and access to it in emergencies is important to avoid radiation exposure.