Search

PURPOSE: To explore the impact of different user interfaces (UIs) for artificial intelligence (AI) outputs on radiologist performance and user preference in detecting lung nodules and masses on chest radiographs. MATERIALS AND METHODS: A retrospective paired-reader study with a 4-week washout period was used to evaluate three different AI UIs compared with no AI output. Ten radiologists (eight radiology attending physicians and two trainees) evaluated 140 chest radiographs (81 with histologically confirmed nodules and 59 confirmed as normal with CT), with either no AI or one of three UI outputs: (a) text-only, (b) combined AI confidence score and text, or (c) combined text, AI confidence score, and image overlay. Areas under the receiver operating characteristic curve were calculated to compare radiologist diagnostic performance with each UI with their diagnostic performance without AI. Radiologists reported their UI preference. RESULTS: The area under the receiver operating characteristic curve improved when radiologists used the text-only output compared with no AI (0.87 vs 0.82; P < .001). There was no difference in performance for the combined text and AI confidence score output compared with no AI (0.77 vs 0.82; P = .46) and for the combined text, AI confidence score, and image overlay output compared with no AI (0.80 vs 0.82; P = .66). Eight of the 10 radiologists (80%) preferred the combined text, AI confidence score, and image overlay output over the other two interfaces. CONCLUSION: Text-only UI output significantly improved radiologist performance compared with no AI in the detection of lung nodules and masses on chest radiographs, but user preference did not correspond with user performance. Keywords: Artificial Intelligence, Chest Radiograph, Conventional Radiography, Lung Nodule, Mass Detection © RSNA, 2023

Lung ultrasound is rapidly gaining popularity based on point of care ease of use, diagnostic fidelity and lack of ionizing radiation. This was particularly notable at the beginning of the COVID-19 pandemic, where concerns of contamination of the x-ray department led to a reluctance to order frequent chest x-rays. Early COVID-19 lung involvement is of a bronchopneumonia, and patches of consolidation adjacent to the chest wall were easily detectable by ultrasound. A large number of proposed scanning protocols were advocated and are often complex and largely based on traditional stethoscope examination or access points on the chest wall rather than the underlying lung anatomy. A surgical understanding of lung anatomy and related surface anatomy has led us to develop a simplified three zone scanning protocol in 2013. The anterior zone corresponds to the upper lobe, and the posterior zone is divided between upper lobe and lower lobe. The relationship between lung lobes and the surface of the chest wall provides the anatomical basis for a simple three scanning zone lung ultrasound protocol.

Diffuse leptomeningeal glioneuronal tumours (DLGNT) are rare primary CNS tumours, traditionally characterised by leptomeningeal growth and usually affecting children. A recent large study defined DLGNT on a molecular basis, of which all demonstrated 1p deletions. The vast majority also demonstrated MAPK/ERK pathway activations, however BRAF V600E mutation has not been previously documented in adult cases. In this case report, we describe an unusual cerebral DLGNT, with limited leptomeningeal spread, intact 1p status and a BRAF V600E mutation.

Correct catheter position is crucial to ensuring appropriate function of the catheter and avoid complications. This paper describes a dataset consisting of 50,612 image level and 17,999 manually labelled annotations from 30,083 chest radiographs from the publicly available NIH ChestXRay14 dataset with manually annotated and segmented endotracheal tubes (ETT), nasoenteric tubes (NET) and central venous catheters (CVCs)., Measurement(s)Catheter DeviceTechnology Type(s)AnnotationSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.15113043