Search

Introduction Coronavirus disease 2019 (COVID‐19) has infected over 215 million individuals worldwide. Chest radiographs (CXR) and computed tomography (CT) have assisted with diagnosis and assessment of COVID‐19. Previous reports have described peripheral and lower zone predominant opacities on chest radiographs. Whilst the most common patterns on CT are bilateral, peripheral basal predominant ground glass opacities (Wong et al., Radiology, 296, 2020, E72; Karimian and Azami, Pol J Radiol, 86, 2021, e31). This study describes the imaging findings in an Australian tertiary hospital population. Methods COVID‐PCR‐positive patients who had chest imaging (CXR, CT and ventilation perfusion (V/Q) scans) from January 2020 to August 2020 were included. Distribution, location and pattern of involvement was recorded. Evaluation of the assessors was performed using Fleiss Kappa calculations for review of radiographic findings and qualitative analysis of CT findings. Results A total of 681 studies (616 CXRs, 59 CTs, 6 V/Q) from 181 patients were reviewed. The most common chest radiograph finding was bilateral lower lobe predominant diffuse opacification and most common CT pattern being ground glass opacities. Of the CT imaging, 33 were CT Pulmonary Angiograms of which five demonstrated acute pulmonary emboli. There was good inter‐rater agreement between radiologists in assessment of imaging appearances on CXR (kappa 0.29–0.73) and CT studies. Conclusion A review of imaging in an Australian tertiary hospital demonstrates similar patterns of COVID‐19 infection on chest X‐ray and CT imaging when compared to the international population.

Introduction To evaluate the accuracy of deep convolutional neural networks (DCNNs) for detecting neck of femur (NoF) fractures on radiographs, in comparison with perceptual training in medically-naive individuals. Methods This study extends a previous study that conducted perceptual training in medically-naive individuals for the detection of NoF fractures on a variety of dataset sizes. The same anteroposterior hip radiograph dataset was used to train two DCNNs (AlexNet and GoogLeNet) to detect NoF fractures. For direct comparison with perceptual training results, deep learning was completed across a variety of dataset sizes (200, 320 and 640 images) with images split into training (80%) and validation (20%). An additional 160 images were used as the final test set. Multiple pre-processing and augmentation techniques were utilised. Results AlexNet and GoogLeNet DCNNs NoF fracture detection accuracy increased with larger training dataset sizes and mildly with augmentation. Accuracy increased from 81.9% and 88.1% to 89.4% and 94.4% for AlexNet and GoogLeNet respectively. Similarly, the test accuracy for the perceptual training in top-performing medically-naive individuals increased from 87.6% to 90.5% when trained on 640 images compared with 200 images. Conclusions Single detection tasks in radiology are commonly used in DCNN research with their results often used to make broader claims about machine learning being able to perform as well as subspecialty radiologists. This study suggests that as impressive as recognising fractures is for a DCNN, similar learning can be achieved by top-performing medically-naive humans with less than 1 hour of perceptual training.

OBJECTIVES We sought to compare the effects of conventional wire cerclage with that of the band and plate fixation of the sternum. METHODS A parallel randomized open-label trial with 1:1 allocation ratio compared healing after adult cardiac surgery using ‘figure-of-8’ stainless steel wire cerclage or a band and plate system (plates). The primary end point was maximal sternal edge displacement during active coughing of ≥2 mm in ≥2 of 4 sites measured with ultrasound by 2 assessors blinded to the other at 6 weeks postoperatively. Secondary end points at 12 weeks included ultrasound assessment, computed tomography (CT) scan and multidimensional assessment of quality of recovery using the Postoperative Quality of Recovery Scale. RESULTS Of 50 patients, 26 received plates and 24 wires. Two patients died and 1 withdrew consent leaving 25 plates and 22 wires for primary end point analysis. Operations included 37 coronary, 5 valve and 8 combined coronary and valve procedures. At 6 weeks, less sternal movement was observed in patients with plates than those with wires, 4% (1/25) vs 32% (7/22), P = 0.018. Agreement between observers was high, kappa = 0.850. At 12 weeks, less ultrasound motion was seen in patients with plates, 0% (0/23) than those with wires, 25% (5/20), P = 0.014. Recovery from pain was higher for patients with plates 92% (22/24) than those with wires 67% (14/21), P = 0.004. CT bone edge separation was less for plates 38% (9/24) than wires 71% (15/21), P = 0.036. CT mild bone synthesis or greater was similar between patients with plates 21% (5/24) and wires 14% (3/21), P = 0.71. CONCLUSIONS Patients receiving the band and plate system had significantly less sternal edge motion than those receiving wires, 6 and 12 weeks after cardiac surgery and experienced less pain. Clinical trial registration clinicaltrials.gov NCT03282578.

Many artefacts can mimic pulmonary emboli (PE) on CT pulmonary angiography (CTPA), most commonly in the peripheral pulmonary arteries (PA's). We describe flow-related artefact mimicking PE in the central PA's of two patients, both with pulmonary arterial hypertension (PAH). To our knowledge, this is the first report of this PE mimic in the central PA's.

Neurofibromatosis type 1 (NF1) is a multisystem phakomatosis. The intrathoracic manifestations of NF1 are protean. We describe a rare case of a plexiform neurofibroma infiltrating the mediastinum and lungs with multiple endobronchial neurofibromata. To our knowledge, a mediastinal plexiform neurofibroma extending into the lungs on CT has not been reported.

Diagnosing certain fractures in conventional radiographs can be a difficult task, usually taking years to master. Typically, students are trained ad-hoc, in a primarily-rule based fashion. Our study investigated whether students can more rapidly learn to diagnose proximal neck of femur fractures via perceptual training, without having to learn an explicit set of rules. One hundred and thirty-nine students with no prior medical or radiology training were shown a sequence of plain film X-ray images of the right hip and for each image were asked to indicate whether a fracture was present. Students were told if they were correct and the location of any fracture, if present. No other feedback was given. The more able students achieved the same level of accuracy as board certified radiologists at identifying hip fractures in less than an hour of training. Surprisingly, perceptual learning was reduced when the training set was constructed to over-represent the types of images participants found more difficult to categorise. Conversely, repeating training images did not reduce post-training performance relative to showing an equivalent number of unique images. Perceptual training is an effective way of helping novices learn to identify hip fractures in X-ray images and should supplement the current education programme for students.