METHODS: A total of 224 patients were recruited. An optimised CT protocol was applied using 100 kV and 1 mL/kg of contrast media dosing. The image quality and radiation dose exposure of this CT protocol were compared to those of a standard 120 kV, 80 mL fixed volume protocol. The radiation dose information and CT Hounsfield units were recorded. The signal-to-noise ratio, contrast-to-noise ratio (CNR) and figure of merit (FOM) were used as comparison metrics. The images were assessed for contrast opacification and visual quality by two radiologists. The renal function, contrast media volume and cost were also evaluated.
RESULTS: The median effective dose was lowered by 16% in the optimised protocol, while the arterial phase images achieved significantly higher CNR and FOM. The radiologists' evaluation showed more than 97% absolute agreement with no significant differences in image quality. No significant differences were found in the pre- and post-CT estimated glomerular filtration rate. However, contrast media usage was significantly reduced by 1,680 mL, with an overall cost savings of USD 421 in the optimised protocol.
CONCLUSION: The optimised weight-based protocol is cost-efficient and lowers radiation dose while maintaining overall contrast enhancement and image quality.
APPROACH: In this paper, we propose a novel model called radiomics-reporting network (Radioport), which incorporates text attention. This model aims to improve the interpretability of deep learning radiomics in mammographic calcification diagnosis. Firstly, it employs convolutional neural networks (CNN) to extract visual features as radiomics for multi-category classification based on Breast Imaging Reporting and Data System (BI-RADS). Then, it builds a mapping between these visual features and textual features to generate diagnostic reports, incorporating an attention module for improved clarity.
MAIN RESULTS: To demonstrate the effectiveness of our proposed model, we conducted experiments on a breast calcification dataset comprising mammograms and diagnostic reports. The results demonstrate that our model can: (i) semantically enhance the interpretability of deep learning radiomics; and, (ii) improve the readability of generated medical reports.
SIGNIFICANCE: Our interpretable textual model can explicitly simulate the mammographic calcification diagnosis process.
METHODS: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method.
RESULTS: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods.
CONCLUSION: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.
METHODS: A cross-sectional study was conducted on all primary care doctors working in government health clinics in Kuala Lumpur, Malaysia, from October 2016 to November 2016. A self-reported questionnaire was used, which included questions on demographic information, knowledge of in-flight medicine, and the attitude and confidence of primary care doctors in managing in-flight medical emergencies.
RESULTS: 182 doctors completed the questionnaire (92.9% response rate). The mean knowledge score was 8.9 out of a maximum score of 20. Only 11.5% of doctors felt confident managing in-flight medical emergencies. The majority (69.2%) would assist in an in-flight medical emergency, but the readiness to assist was reduced if someone else was already helping or if they were not familiar with the emergency. Total knowledge score was positively associated with confidence in managing in-flight medical emergencies (p = 0.03).
CONCLUSION: Only one in ten primary care doctors in this study felt confident managing in-flight medical emergencies. A higher total knowledge score of in-flight medical emergencies was positively associated with greater confidence in managing them. Educational programmes to address this gap in knowledge may be useful to improve doctors' confidence in managing in-flight medical emergencies.