Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation.

Deep learning based medical image segmentation is an important step within diagnosis, which relies strongly on capturing sufficient spatial context without requiring too complex models that are hard to train with limited labelled data. Training data is in particular scarce for segmenting infection regions of CT images of COVID-19 patients. Attention models help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent criss-cross-attention module aims to approximate global self-attention while remaining memory and time efficient by separating horizontal and vertical self-similarity computations. However, capturing attention from all non-local locations can adversely impact the accuracy of semantic segmentation networks. We propose a new Dynamic Deformable Attention Network (DDANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on a deformable criss-cross attention block that learns both attention coefficients and attention offsets in a continuous way. A deep U-Net (Schlemper et al., 2019) segmentation network that employs this attention mechanism is able to capture attention from pertinent non-local locations and also improves the performance on semantic segmentation tasks compared to criss-cross attention within a U-Net on a challenging COVID-19 lesion segmentation task. Our validation experiments show that the performance gain of the recursively applied dynamic deformable attention blocks comes from their ability to capture dynamic and precise attention context. Our DDANet achieves Dice scores of 73.4% and 61.3% for Ground-glass opacity and consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.9% points compared to a baseline U-Net and 24.4% points compared to current state of art methods (Fan et al., 2020).

The Cerebro-Renal System- Anatomical and Physiological Considerations.

The brain and kidney both uniquely are highly susceptible to vascular injury from shared vascular risk factors. However these are not sufficient to explain the complete extent of cerebrovascular disease especially small vessel disease in its myriad presentations that patients with chronic kidney disease manifest. They both require a large amount of blood supply to function optimally. Shared anatomical and physiological factors such as the presence of strain vessels, the local vascular autoregulation that control blood supply possible, results in the vulnerability of these organs to the vascular risk factors. Because it is a bidirectional system where each affects the other, it is best considered as a cerebro-renal unit.

Young Ischemic Stroke in Association with Ovarian Hyperstimulation Syndrome.

BACKGROUND: Ovarian hyperstimulation syndrome (OHSS) is a serious and potentially fatal complication of medical ovarian stimulation. Uncommonly, it is associated with thromboembolic complications with venous thrombosis being more common than arterial thromboembolic events. We present a case of cerebral infarction in the setting of severe OHSS secondary to in vitro fertilization treatment with no residual neurological deficits. MATERIALS AND METHODS: We also performed a review of previously published ischemic cerebral infarction and cerebral venous sinus thrombosis (CVST) cases associated with OHSS to evaluate common patterns in presentations, commonly affected central nervous system sites, trends for therapeutic options in these cases, and outcomes. CONCLUSION: We have included 27 cases of ischemic cerebral infarction and 7 cases of CVST previously published in English literature. We have included cases of central retinal artery occlusion in the ischemic cerebral infarction group, and central retinal vein occlusion in the CVST group. Mean ages of presentation were 31 ± 4.84 and 34 ± 4.90 years for ischemic cerebral infarction and CVST, respectively. Ischemic strokes commonly affect large cortical areas with unilateral weakness, aphasia, unilateral sensory changes, and visual field deficits being the common presentations. Middle cerebral artery (n = 7) is the common site of vascular occlusion where vascular imaging has been reported, followed by internal carotid artery occlusion (n = 5). OHSS cannot be considered a direct risk for pathogenesis, but OHSS is frequently associated with hyperviscosity, which may add to the risk factors.

Acute Onset Dystonia after Infarction of Premotor and Supplementary Motor Cortex.

OBJECTIVE: Poststroke dystonia is the second most common movement disorder after chorea and often has a delayed manifestation. Lesions of the contralateral lenticular nucleus, particularly the putamen, have been implicated in the pathogenesis of dystonia. We present an unusual case of rapid onset of focal dystonia of the left upper extremity, which developed after infarction of the right premotor cortex (PMC) and the supplementary motor area (SMA). METHOD: A retrospective chart review of the patient was performed. RESULTS AND CONCLUSION: We propose that disruption of the afferents from PMC and SMA in the setting of chronic striatal abnormality can result in acute dystonia due to disinhibition of the thalamocortical circuit.

New Directions in Infection-Associated Ischemic Stroke.

The relationship between infections and stroke has not been fully characterized, probably delaying the development of specific treatments. This narrative review addresses mechanisms of stroke linked to infections, including hypercoagulability, endothelial dysfunction, vasculitis, and impaired thrombolysis. SARS-CoV-2, the virus that causes COVID-19, may promote the development of stroke, which may represent its most severe neurological complication. The development of specific therapies for infection-associated stroke remains a profound challenge. Perhaps the most important remaining issue is the distinction between infections that trigger a stroke versus infections that are truly incidental. This distinction likely requires the establishment of appropriate biomarkers, candidates of which are elevated levels of fibrin D-dimer and anticardiolipin/antiphospholipid antibodies. These candidate biomarkers might have potential use in identifying pathogenic infections preceding stroke, which is a precursor to establishing specific therapies for this syndrome.

Outcomes of carotid endarterectomy in the elderly: report from the National Cardiovascular Data Registry.

BACKGROUND AND PURPOSE: Benchmark trials of carotid endarterectomy often did not include elderly patients, and the results may not be easily extrapolated to the general population. Using the Carotid Artery Revascularization and Endarterectomy registry, we sought to determine real-world outcomes of carotid endarterectomy in the elderly. METHODS: This was a retrospective cohort study of patients aged >70 years. We compared outcomes stratified by age among symptomatic and asymptomatic patients. RESULTS: There were 4149 patients who underwent carotid endarterectomy; 1376 (33.1%) were symptomatic. Overall mortality rate was 0.5%. The primary outcome of in-hospital death, stroke, and myocardial infarction showed a significant trend and was highest in the age >85 years group (5.6%). Among symptomatic patients, mortality and the primary outcome were not statistically different between those aged >75 years and those aged 70 to 74 years. Among asymptomatic elderly patients, mortality rate was significantly higher in age group >75 years compared with <75 years (0.7% vs 0.0%); however, the combined outcome of stroke, death, and myocardial infarction was not statistically different. CONCLUSIONS: Elderly patients >85 years of age were at increased risk for death or perioperative complications of stroke, death, and myocardial infarction compared with those who were relatively younger. More elderly patients underwent carotid endarterectomy for asymptomatic carotid stenosis and had higher mortality than the younger counterparts, underlining need for caution in subjecting them to the procedure.

Thrombolysis for acute ischemic stroke in Joint Commission-certified and -noncertified hospitals in Michigan.

BACKGROUND: The Joint Commission (JC) for Accreditation of Healthcare Organizations has devised disease specific certification programs for hospitals, including stroke. JC certification as a primary stroke center (PSC) suggests that the hospital has critical measures in place to ensure improving stroke outcomes over the long term. In this study, we focused on the delivery of care for patients with acute ischemic and compared differences in JC-certified and -noncertified centers in Michigan. METHODS: We performed a systematic chart review of patients with acute ischemic stroke from 10 Michigan hospitals, half of whom were JC-certified PSCs. Sixty charts were randomly chosen from 1 calendar year from each hospital. An experienced nurse performed the data abstraction, and data analysis was performed with the Fisher exact test. RESULTS: A total of 602 charts--of which 302 were from JC-certified PSCs--were chosen for the study. The 2 groups were similar with regard to stroke risk factors except that there were significantly more patients with atrial fibrillation in noncertified centers and there were more African American patients in JC-certified PSCs. Significantly more patients were considered for thrombolytic therapy in JC-certified PSCs compared to noncertified centers (90.4% v 66%; P = .0001). Overall, 3.8% of patients had received thrombolytic therapy without any significant difference between JC-certified PSCs and noncertified centers (4.6% v 3%; adjusted odds ratio 1.64; 95% confidence interval 0.64-4.19; P = .87). However, thrombolysis rates among eligible patients was significantly higher in the JC-certified PSCs (48.2% v 8.8%; P = .0001). The most common reason documented for not giving thrombolytic therapy was late arrival outside the therapeutic window, which was more common in JC-certified PSCs (72.8% v 55.6%; P = .0001) compared to noncertified centers. Seventy-four percent of patients from JC-certified PSCs were discharged home or to inpatient rehabilitation facility compared to 71% (P = .38) from noncertified hospitals. The mean length of stay was marginally shorter in JC-certified PSCs compared to noncertified centers (5.53 v 6.25 days; P = .08). CONCLUSIONS: Rates of thrombolysis administration for acute stroke patients across Michigan were low in both JC-certified and noncertified hospitals, although better processes were in place in JC-certified PSCs. While there was no overall difference in the administration of thrombolytic treatment, a greater number of the eligible patients received thrombolysis in the certified centers. There was a tendency to shorter lengths of stay at JC-certified PSCs, but there was no significant difference in discharge to home, inpatient rehabilitation, or inpatient mortality in this study.

Are racial disparities in stroke care still prevalent in certified stroke centers?

Racial differences in stroke risk and risk factor prevalence are well established. The present study explored racial differences in the delivery of care to patients with acute stroke between Joint Commission (JC)-certified hospitals and noncertified hospitals. A retrospective chart review was conducted in patients sustaining ischemic stroke admitted to 5 JC-certified centers and 5 noncertified hospitals. Demographic data, risk factors, utilization of acute stroke therapies, and compliance with core measures were recorded. Racial disparities were investigated in the entire group as well as for JC-certified and noncertified hospitals separately. A total of 574 patients (25.1% African Americans) were included. African Americans were significantly younger and more likely to have previous stroke, whereas Caucasians were more likely to have coronary disease and atrial fibrillation. There were no racial differences in other risk factors or baseline functions. Median National Institutes of Health Stroke Scale scores were similar in African Americans and Caucasians, as were proportions receiving intravenous tissue plasminogen activator (tPA) therapy (2.1% in African Americans, 3.5% in Caucasians; P = .40) and intervention (4.2% in African Americans, 6.8% in Caucasians; P = .26). Caucasians were more likely to arrive by emergency medical services (65.5% vs 51.5%; P = .004), to be evaluated by a stroke team (19.1% vs 7.7%; P = .001), and to have a documented National Institutes of Health Stroke Scale score (40.2% vs 29.9%; P = .03). African Americans often did not receive intravenous tPA because of a delay in arrival. African Americans performed better on virtually all stroke care variables in JC-certified centers. JC certification reduced disparity in certain variables, including tPA and deep venous thrombosis prophylaxis administration. Important racial disparities exist in the delivery of several acute stroke care variables. Efforts must be focused on eliminating disparities in prehospital delays. Guideline-based care tendered at JC-certified centers might help narrow disparities in acute stroke care delivery.

A novel and simple approach to regularise attention frameworks and its efficacy in segmentation.

Deep neural networks with attention mechanism have shown promising results in many computer vision and medical image processing applications. Attention mechanisms help to capture long range interactions. Recently, more sophisticated attention mechanisms like criss-cross attention have been proposed for efficient computation of attention blocks. In this paper, we introduce a simple and low-overhead approach of adding noise to the attention block which we discover to be very effective when using an attention mechanism. Our proposed methodology of introducing regularisation in the attention block by adding noise makes the network more robust and resilient, especially in scenarios where there is limited training data. We incorporate this regularisation mechanism in the criss-cross attention block. This criss-cross attention block enhanced with regularisation is integrated in the bottleneck layer of a U-Net for the task of medical image segmentation. We evaluate our proposed framework on a challenging subset of the NIH dataset for segmenting lung lobes. Our proposed methodology results in improving dice-scores by 2.5 % in this context of medical image segmentation.

Attention-augmented U-Net (AA-U-Net) for semantic segmentation.

Deep learning-based image segmentation models rely strongly on capturing sufficient spatial context without requiring complex models that are hard to train with limited labeled data. For COVID-19 infection segmentation on CT images, training data are currently scarce. Attention models, in particular the most recent self-attention methods, have shown to help gather contextual information within deep networks and benefit semantic segmentation tasks. The recent attention-augmented convolution model aims to capture long range interactions by concatenating self-attention and convolution feature maps. This work proposes a novel attention-augmented convolution U-Net (AA-U-Net) that enables a more accurate spatial aggregation of contextual information by integrating attention-augmented convolution in the bottleneck of an encoder-decoder segmentation architecture. A deep segmentation network (U-Net) with this attention mechanism significantly improves the performance of semantic segmentation tasks on challenging COVID-19 lesion segmentation. The validation experiments show that the performance gain of the attention-augmented U-Net comes from their ability to capture dynamic and precise (wider) attention context. The AA-U-Net achieves Dice scores of 72.3% and 61.4% for ground-glass opacity and consolidation lesions for COVID-19 segmentation and improves the accuracy by 4.2% points against a baseline U-Net and 3.09% points compared to a baseline U-Net with matched parameters. Supplementary Information: The online version contains supplementary material available at 10.1007/s11760-022-02302-3.

Deformable attention (DANet) for semantic image segmentation.

Deep learning based medical image segmentation is currently a widely researched topic. Attention mechanism used with deep networks significantly benefit semantic segmen-tation tasks. The recent criss-cross-attention module captures global self-attention while remaining memory and time efficient. However, capturing attention from only the pertinent non-local locations can cardinally boost the accuracy of semantic segmentation networks. We propose a new Deformable Attention Network (DANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on learning the deformation of the query, key and value attention feature maps in a continuous way. A deep segmentation network with this attention mechanism is able to capture attention from germane non-local locations. This boosts the segmentation performance of COVID-19 lesion segmentation compared to criss-cross attention within aU-Net. Our validation experiments show that the performance gain of the recursively applied deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. DANet achieves Dice scores of 60.17% for COVID-19 lesions segmentation and improves the accuracy by 4.4% points compared to a baseline U-Net.

Novel Insights on Induced Sparsity in Multi-Time Attention Networks.

Current deep learning approaches for dealing with sparse irregularly sampled time-series data do not exploit the extent of sparsity of the input data. Our work is inspired by the sparse and irregularly sampled nature of physiological time series data in electronic health records. We explore the effect of inducing varying degrees of sparsity on the predictive performance of Multi-Time Attention Networks (mTAN) [1]. Our methodology is to induce sparsity by first sub-sampling the time-series before feeding it to the mTAN network. We conduct empirical experiments with sub-sampling ranging from 10 to 90 %. We investigate the performance of our methodology on the Human Activity dataset and Physionet 2012 mortality prediction task. Our results demonstrate that our proposed time-point sub-sampling coupled with mTAN improves the performance by 2 % on the Human Activity dataset with 80 % lesser time-points for training. On the Physionet dataset, our approach achieves comparable performance as baseline with 30 % lesser time-points. Our experiments reveal that time-series data could be further coarsely acquired when used in tandem with state-of-the-art networks capable of handling sparse data (mTAN). This could be of immense help for various applications where data acquisition and labeling is a significant challenge.

Descriptive analysis of Acute Ischemic stroke in COVID-19 patients through the course of the COVID-19 pandemic.

Coronavirus disease 2019 (COVID-19) has been associated with Acute Ischemic Stroke (AIS). Here, we characterize our institutional experience with management of COVID-19 and AIS. Baseline demographics, clinical, imaging, and outcomes data were determined in patients with COVID-19 and AIS presenting within March 2020 to October 2020, and November 2020 to August 2021, based on institutional COVID-19 hospitalization volume. Of 2512 COVID-19 patients, 35 (1.39%, mean age 63.3 years, 54% women) had AIS. AIS recognition was frequently delayed after COVID-19 symptoms (median 19.5 days). Four patients (11%) were on therapeutic anticoagulation at AIS recognition. AIS mechanism was undetermined or due to multiple etiologies in most cases (n = 20, 57%). Three patients underwent IV TPA, and three underwent mechanical thrombectomy, of which two suffered re-occlusion. Three patients had incomplete mRNA vaccination course. Fourteen (40%) died, with 26 (74%) having poor outcomes. Critical COVID-19 severity was associated with worsened mortality (p = 0.02). More patients (12/16; 75%) had either worsened or similar 3-month functional outcomes, than those with improvement, indicating the devastating impact of co-existing AIS and COVID-19. Comparative analysis showed that patients in the later cohort had earlier AIS presentation, fewer stroke risk factors, more comprehensive workup, more defined stroke mechanisms, less instance of critical COVID-19 severity, more utilization of IV TPA, and a trend towards worse outcomes for the sub-group of mild-to-moderate COVID-19 severity. AIS incidence, NIHSS, and overall outcomes were similar. Further studies should investigate outcomes beyond 3 months and their predictive factors, impact of completed vaccination course, and access to neurologic care.

Novel no-reference multi-dimensional perceptual similarity metric.

Enormous progress has been made in the domain of determining image quality. However, even the recently proposed deep learning based perceptual quality metrics and the classical structural similarity metric (SSIM) are not designed to operate in the absence of a good quality reference image. Many of the image acquisition processes, especially in medical imaging, would immensely benefit from a metric that can indicate if the quality of an image is improving or worsening based on adaptation of the acquisition parameters. In this work, we propose a novel multi-dimensional no-reference perceptual similarity metric that can compute the quality of a given image without a reference pristine quality image by combining no-reference image quality metric (PIQUE) and perceptual similarity. The dimensions of quality currently explored are in the axis of noise, blur, and contrast. Our experiments demonstrate that our proposed novel no-reference perceptual similarity metric correlates very well with the quality of an image in a multi-dimensional sense.

Evaluation Tool to Diagnose Faults and Discrepancy in Semi-Automated or Manual Annotations in Ultrasound Cine Loops (Videos).

Good quality (annotated) data is one of the most important aspects of supervised deep learning. Tasks such as semantic segmentation have a huge data requirement in exchange for only satisfactory performance. Large-scale annotations spread across multiple annotators tends to create inconsistencies, as there are various manual and semi-automated techniques involved. This mandates an external evaluator or expert to check and narrow down the problematic annotations. Studies have shown that even marking a few instances wrong in classification can lead to a significant performance drop in the model (mislabeling only 10% of one class can degrade the total performance of all classes by up to 10%). It has been noticed that fault localization by a medical expert is one of the most expensive and time-consuming processes. In this paper, we propose a novel framework for detecting the inconsistencies in the annotation of every object/anatomy in a specific image. We leverage the power of semi-supervised deep learning models (STCN) to help produce high-quality data for AI segmentation algorithms. Evaluation using this algorithm has been shown to reduce annotation review time by at least 5 hours for just 1000 images, and the quality of ground truth data improved thereby increasing the performance of the model by almost 3%.

Factors associated with misdiagnosis of acute stroke in young adults.

Misdiagnosis or delayed diagnosis of acute ischemic stroke can result in neurologic worsening or a missed opportunity for thrombolysis. Because stroke in young adults is less common than stroke in the elderly, we sought to determine clinical characteristics associated with misdiagnosis of stroke in young adults. Patients from the prospectively maintained Young Stroke Registry in our comprehensive stroke center were reviewed. Demographic information, past medical history, presentation within the 3-hour time window, and outcomes were assessed. We compared patients misdiagnosed and those correctly diagnosed to identify factors associated with misdiagnosis of acute stroke. A total of 57 patients aged 16-50 were enrolled in the registry during 2001-2006. Eight patients (14%; 4 men and 4 women; mean age, 38 years) were misdiagnosed. Seven of these 8 patients were discharged from the emergency department initially. Patients age <35 years (P = .05) and patients with posterior circulation stroke (P = .006) were more likely to be misdiagnosed. All 8 misdiagnosed patients were initially evaluated at hospitals that were not certified primary stroke centers. Patients presenting with vertebrobasilar territory ischemia have a greater rate of misdiagnosis. Our study demonstrates the increasing need for "young stroke awareness" among emergency department personnel. Initial misdiagnosis can potentially lead to a lost opportunity for thrombolysis in otherwise good candidates.