Turning brain MRI into diagnostic PET: 15O-water PET CBF synthesis from multi-contrast MRI via attention-based encoder-decoder networks.

Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of a wide range of neurological diseases. Positron emission tomography (PET) with radiolabeled water (15O-water) is the gold-standard for the measurement of CBF in humans, however, it is not widely available due to its prohibitive costs and the use of short-lived radiopharmaceutical tracers that require onsite cyclotron production. Magnetic resonance imaging (MRI), in contrast, is more accessible and does not involve ionizing radiation. This study presents a convolutional encoder-decoder network with attention mechanisms to predict the gold-standard 15O-water PET CBF from multi-contrast MRI scans, thus eliminating the need for radioactive tracers. The model was trained and validated using 5-fold cross-validation in a group of 126 subjects consisting of healthy controls and cerebrovascular disease patients, all of whom underwent simultaneous 15O-water PET/MRI. The results demonstrate that the model can successfully synthesize high-quality PET CBF measurements (with an average SSIM of 0.924 and PSNR of 38.8 dB) and is more accurate compared to concurrent and previous PET synthesis methods. We also demonstrate the clinical significance of the proposed algorithm by evaluating the agreement for identifying the vascular territories with impaired CBF. Such methods may enable more widespread and accurate CBF evaluation in larger cohorts who cannot undergo PET imaging due to radiation concerns, lack of access, or logistic challenges.

Automated detection of arterial landmarks and vascular occlusions in patients with acute stroke receiving digital subtraction angiography using deep learning.

BACKGROUND: Digital subtraction angiography (DSA) is the gold-standard method of assessing arterial blood flow and blockages prior to endovascular thrombectomy. OBJECTIVE: To detect anatomical features and arterial occlusions with DSA using artificial intelligence techniques. METHODS: We included 82 patients with acute ischemic stroke who underwent DSA imaging and whose carotid terminus was visible in at least one run. Two neurointerventionalists labeled the carotid location (when visible) and vascular occlusions on 382 total individual DSA runs. For detecting the carotid terminus, positive and negative image patches (either containing or not containing the internal carotid artery terminus) were extracted in a 1:1 ratio. Two convolutional neural network architectures (ResNet-50 pretrained on ImageNet and ResNet-50 trained from scratch) were evaluated. Area under the curve (AUC) of the receiver operating characteristic and pixel distance from the ground truth were calculated. The same training and analysis methods were used for detecting arterial occlusions. RESULTS: The ResNet-50 trained from scratch most accurately detected the carotid terminus (AUC 0.998 (95% CI 0.997 to 0.999), p<0.00001) and arterial occlusions (AUC 0.973 (95% CI 0.971 to 0.975), p<0.0001). Average pixel distances from ground truth for carotid terminus and occlusion localization were 63±45 and 98±84, corresponding to approximately 1.26±0.90 cm and 1.96±1.68 cm for a standard angiographic field-of-view. CONCLUSION: These results may serve as an unbiased standard for clinical stroke trials, as optimal standardization would be useful for core laboratories in endovascular thrombectomy studies, and also expedite decision-making during DSA-based procedures.

Multi-Channel Vision Transformer for Epileptic Seizure Prediction.

Epilepsy is a neurological disorder that causes recurrent seizures and sometimes loss of awareness. Around 30% of epileptic patients continue to have seizures despite taking anti-seizure medication. The ability to predict the future occurrence of seizures would enable the patients to take precautions against probable injuries and administer timely treatment to abort or control impending seizures. In this study, we introduce a Transformer-based approach called Multi-channel Vision Transformer (MViT) for automated and simultaneous learning of the spatio-temporal-spectral features in multi-channel EEG data. Continuous wavelet transform, a simple yet efficient pre-processing approach, is first used for turning the time-series EEG signals into image-like time-frequency representations named Scalograms. Each scalogram is split into a sequence of fixed-size non-overlapping patches, which are then fed as inputs to the MViT for EEG classification. Extensive experiments on three benchmark EEG datasets demonstrate the superiority of the proposed MViT algorithm over the state-of-the-art seizure prediction methods, achieving an average prediction sensitivity of 99.80% for surface EEG and 90.28-91.15% for invasive EEG data.

A convolutional-recurrent neural network approach to resting-state EEG classification in Parkinson's disease.

BACKGROUND: Parkinson's disease (PD) is expected to become more common, particularly with an aging population. Diagnosis and monitoring of the disease typically rely on the laborious examination of physical symptoms by medical experts, which is necessarily limited and may not detect the prodromal stages of the disease. NEW METHOD: We propose a lightweight (~20 K parameters) deep learning model to classify resting-state EEG recorded from people with PD and healthy controls (HC). The proposed CRNN model consists of convolutional neural networks (CNN) and a recurrent neural network (RNN) with gated recurrent units (GRUs). The 1D CNN layers are designed to extract spatiotemporal features across EEG channels, which are subsequently supplied to the GRUs to discover temporal features pertinent to the classification. RESULTS: The CRNN model achieved 99.2% accuracy, 98.9% precision, and 99.4% recall in classifying PD from HC. Interrogating the model, we further demonstrate that the model is sensitive to dopaminergic medication effects and predominantly uses phase information in the EEG signals. COMPARISON WITH EXISTING METHODS: The CRNN model achieves superior performance compared to baseline machine learning methods and other recently proposed deep learning model. CONCLUSION: The approach proposed in this study adequately extracts spatial and temporal features in multi-channel EEG signals that enable accurate differentiation between PD and HC. The CRNN model has excellent potential for use as an oscillatory biomarker for assisting in the diagnosis and monitoring of people with PD. Future studies to further improve and validate the model's performance in clinical practice are warranted.

Semi-dilated convolutional neural networks for epileptic seizure prediction.

Epilepsy is a neurological brain disorder that affects ∼75 million people worldwide. Predicting epileptic seizures holds great potential for improving the quality of life of people with epilepsy, but seizure prediction solely from the Electroencephalogram (EEG) is challenging. Classical machine learning algorithms and a variety of feature engineering methods have become a mainstay in seizure prediction, yet performance has been variable. In this work, we first propose an efficient data pre-processing method that maps the time-series EEG signals into an image-like format (a "scalogram") using continuous wavelet transform. We then develop a novel convolution module named "semi-dilated convolution" that better exploits the geometry of wavelet scalograms and nonsquare-shape images. Finally, we propose a neural network architecture named "semi-dilated convolutional network (SDCN)" that uses semi-dilated convolutions to solely expand the receptive field along the long dimension (image width) while maintaining high resolution along the short dimension (image height). Results demonstrate that the proposed SDCN architecture outperforms previous seizure prediction methods, achieving an average seizure prediction sensitivity of 98.90% for scalp EEG and 88.45-89.52% for invasive EEG.

Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals.

OBJECTIVE: Automatic detection of epileptic seizures based on deep learning methods received much attention last year. However, the potential of deep neural networks in seizure detection has not been fully exploited in terms of the optimal design of the model architecture and the detection power of the time-series brain data. In this work, a deep neural network architecture is introduced to learn the temporal dependencies in Electroencephalogram (EEG) data for robust detection of epileptic seizures. METHODS: A deep Long Short-Term Memory (LSTM) network is first used to learn the high-level representations of different EEG patterns. Then, a Fully Connected (FC) layer is adopted to extract the most robust EEG features relevant to epileptic seizures. Finally, these features are supplied to a softmax layer to output predicted labels. RESULTS: The results on a benchmark clinical dataset reveal the prevalence of the proposed approach over the baseline techniques; achieving 100% classification accuracy, 100% sensitivity, and 100% specificity. Our approach is additionally shown to be robust in noisy and real-life conditions. It maintains high detection performance in the existence of common EEG artifacts (muscle activities and eye movement) as well as background noise. CONCLUSIONS: We demonstrate the clinical feasibility of our seizure detection approach achieving superior performance over the cutting-edge techniques in terms of seizure detection performance and robustness. SIGNIFICANCE: Our seizure detection approach can contribute to accurate and robust detection of epileptic seizures in ideal and real-life situations.