Ability of weakly supervised learning to detect acute ischemic stroke and hemorrhagic infarction lesions with diffusion-weighted imaging

Neuroimaging Modalities Used for Ischemic Stroke Diagnosis and Monitoring

Strokes are one of the global leading causes of physical or mental impairment and fatality, classified into hemorrhagic and ischemic strokes. Ischemic strokes happen when a thrombus blocks or plugs an artery and interrupts or reduces blood supply to the brain tissue. Deciding on the imaging modality which will be used for stroke detection depends on the expertise and availability of staff and the infrastructure of hospitals. Magnetic resonance imaging provides valuable information, and its sensitivity for smaller infarcts is greater, while computed tomography is more extensively used, since it can promptly exclude acute cerebral hemorrhages and is more favorable speed-wise. The aim of this article was to give information about the neuroimaging modalities used for the diagnosis and monitoring of ischemic strokes. We reviewed the available literature and presented the use of computed tomography, CT angiography, CT perfusion, magnetic resonance imaging, MR angiography and MR perfusion for the detection of ischemic strokes and their monitoring in different phases of stroke development.

Radiomics and artificial neural networks modelling for identification of high-risk carotid plaques

Objective

In this study, we aimed to investigate the classification of symptomatic plaques by evaluating the models generated via two different approaches, a radiomics-based machine learning (ML) approach, and an end-to-end learning approach which utilized deep learning (DL) techniques with several representative model frameworks.

Methods

We collected high-resolution magnetic resonance imaging (HRMRI) data from 104 patients with carotid artery stenosis, who were diagnosed with either symptomatic plaques (SPs) or asymptomatic plaques (ASPs), in two medical centers. 74 patients were diagnosed with SPs and 30 patients were ASPs. Sampling Perfection with Application-optimized Contrasts (SPACE) by using different flip angle Evolutions was used for MRI imaging. Repeated stratified five-fold cross-validation was used to evaluate the accuracy and receiver operating characteristic (ROC) of the trained classifier. The two proposed approaches were investigated to train the models separately. The difference in the model performance of the two proposed methods was quantitatively evaluated to find a better model to differentiate between SPs and ASPs.

Results

3D-SE-Densenet-121 model showed the best performance among all prediction models (AUC, accuracy, precision, sensitivity, and F1-score of 0.9300, 0.9308, 0.9008, 0.8588, and 0.8614, respectively), which were 0.0689, 0.1119, 0.1043, 0.0805, and 0.1089 higher than the best radiomics-based ML model (MLP). Decision curve analysis showed that the 3D-SE-Densenet-121 model delivered more net benefit than the best radiomics-based ML model (MLP) with a wider threshold probability.

Conclusion

The DL models were able to accurately differentiate between symptomatic and asymptomatic carotid plaques with limited data, which outperformed radiomics-based ML models in identifying symptomatic plaques.

Artificial intelligence in emergency radiology: A review of applications and possibilities

Artificial intelligence (AI) applications in radiology have been rising exponentially in the last decade. Although AI has found usage in various areas of healthcare, its utilization in the emergency department (ED) as a tool for emergency radiologists shows great promise towards easing some of the challenges faced daily. There have been numerous reported studies examining the application of AI-based algorithms in identifying common ED conditions to ensure more rapid reporting and in turn quicker patient care. In addition to interpretive applications, AI assists with many of the non-interpretive tasks that are encountered every day by emergency radiologists. These include, but are not limited to, protocolling, image quality control and workflow prioritization. AI continues to face challenges such as physician uptake or costs, but is a long-term investment that shows great potential to relieve many difficulties faced by emergency radiologists and ultimately improve patient outcomes. This review sums up the current advances of AI in emergency radiology, including current diagnostic applications (interpretive) and applications that stretch beyond imaging (non-interpretive), analyzes current drawbacks of AI in emergency radiology and discusses future challenges.