Tatsat R. Patel

Bio: Tatsat R. Patel is an academic researcher from University at Buffalo. The author has contributed to research in topics: RNA extraction & Mitral valve. The author has an hindex of 3, co-authored 10 publications receiving 20 citations.

Multi-resolution CNN for brain vessel segmentation from cerebrovascular images of intracranial aneurysm: a comparison of U-Net and DeepMedic

Abstract: Background: Vascular segmentation of cerebral vascular imaging is tedious and manual, hindering translation of imagebased computational tools for neurovascular disease (such as intracranial aneurysm) management. Current cerebrovascular segmentation techniques use classic model-based algorithms, but such algorithms are incapable of distinguishing vasculature from artifacts. Deep Learning, specifically the widely accepted U-Net architecture, could be an effective alternative to conventional approaches for cerebrovascular segmentation, but has been shown to perform poorly in segmentation of smaller yet critical vessels. Methods: In this study, we present a methodology using a specialized convolutional neural network (CNN) architecture— DeepMedic—which uses multi-resolution inputs to enhance the field of view of the architecture, thereby enhancing the accuracy of segmentation of smaller vessels. To show the capability of this architecture, we collected and segmented a total of 100 digital subtraction angiography (DSA) images of cerebral vessels for training, internal validation, and testing (n=80, n=10, and n=10, respectively). Results: The DeepMedic architecture yielded high performance with a Connectivity-Area-Length (CAL) of 0.84±0.07 and a dice similarity coefficient (DSC) of 0.94±0.02 in the independent testing cohort. This was better than U-Net optimized for the patch-size and %-overlap in predictions, which performed with a CAL of 0.79±0.06 and a DSC of 0.92±0.02. Notably, our work demonstrated that DeepMedic (CAL: 0.45±0.12) outperformed U-Net (CAL: 0.59±0.11) for segmentation of smaller vessels. Conclusions: Our work showed DeepMedic performs better than the current state-of-the-art method for cerebrovascular segmentation. We hope this study begins to bring a high fidelity deep-learning based approach closer to clinical translation.

Characterization of Long Non-coding RNA Signatures of Intracranial Aneurysm in Circulating Whole Blood

Abstract: Long non-coding RNAs (lncRNAs) may serve as biomarkers for complex disease states, such as intracranial aneurysms. In this study, we investigated lncRNA expression differences in the whole blood of patients with unruptured aneurysms. Whole blood RNA from 67 subjects (34 with aneurysm, 33 without) was used for next-generation RNA sequencing. Differential expression analysis was used to define a signature of intracranial aneurysm-associated lncRNAs. To estimate the signature’s ability to classify aneurysms and to identify the most predictive lncRNAs, we implemented a nested cross-validation pipeline to train classifiers using linear discriminant analysis. Ingenuity pathway analysis was used to study potential biological roles of differentially expressed lncRNAs, and lncRNA ontology was used to investigate ontologies enriched in signature lncRNAs. Co-expression correlation analysis was performed to investigate associated differential protein-coding messenger RNA expression. Of 4639 detected lncRNAs, 263 were significantly different (p < 0.05) between the two groups, and 84 of those had an absolute fold-change ≥ 1.5. An eight-lncRNA signature (q < 0.35, fold-change ≥ 1.5) was able to separate patients with and without aneurysms on principal component analysis, and had an estimated accuracy of 70.9% in nested cross-validation. Bioinformatics analyses showed that networks of differentially expressed lncRNAs (p < 0.05) were enriched for cell death and survival, connective tissue disorders, carbohydrate metabolism, and cardiovascular disease. Signature lncRNAs shared ontologies that reflected regulation of gene expression, signaling, ubiquitin processing, and p53 signaling. Co-expression analysis showed correlations with messenger RNAs related to inflammatory responses. Differential expression in whole blood lncRNAs is detectable in patients harboring aneurysms, and reflects expression/signaling regulation, and ubiquitin and p53 pathways. Following validation in larger cohorts, these lncRNAs may be potential diagnostic targets for aneurysm detection by blood testing.

Isolation of RNA from Acute Ischemic Stroke Clots Retrieved by Mechanical Thrombectomy.

Abstract: Mechanical thrombectomy (MT) for large vessel acute ischemic stroke (AIS) has enabled biologic analyses of resected clots. While clot histology has been well-studied, little is known about gene expression within the tissue, which could shed light on stroke pathophysiology. In this methodological study, we develop a pipeline for obtaining useful RNA from AIS clots. A total of 73 clot samples retrieved by MT were collected and stored in RNALater and in 10% phosphate-buffered formalin. RNA was extracted from all samples using a modified Chemagen magnetic bead extraction protocol on the PerkinElmer Chemagic 360. RNA was interrogated by UV–Vis absorption and electrophoretic quality control analysis. All samples with sufficient volume underwent traditional qPCR analysis and samples with sufficient RNA quality were subjected to next-generation RNA sequencing on the Illumina NovaSeq platform. Whole blood RNA samples from three patients were used as controls, and H&E-stained histological sections of the clots were used to assess clot cellular makeup. Isolated mRNA was eluted into a volume of 140 µL and had a concentration ranging from 0.01 ng/µL to 46 ng/µL. Most mRNA samples were partially degraded, with RNA integrity numbers ranging from 0 to 9.5. The majority of samples (71/73) underwent qPCR analysis, which showed linear relationships between the expression of three housekeeping genes (GAPDH, GPI, and HPRT1) across all samples. Of these, 48 samples were used for RNA sequencing, which had moderate quality based on MultiQC evaluation (on average, ~35 M reads were sequenced). Analysis of clot histology showed that more acellular samples yielded RNA of lower quantity and quality. We obtained useful mRNA from AIS clot samples stored in RNALater. qPCR analysis could be performed in almost all cases, while sequencing data could only be performed in approximately two-thirds of the samples. Acellular clots tended to have lower RNA quantity and quality.

Clot organization on histology is associated with radiomics features that predict treatment outcomes from mechanical thrombectomy

Abstract: Radiomics is an emerging computer vision technique that extracts high level textural information from medical images. Several studies have reported associations between radiomics features(RFs) and first pass effect(FPE) after mechanical thrombectomy(MT) treatment of acute ischemic stroke(AIS). However, the pathobiology behind the manifestation of such RFs remains unknown. To that end, we collected 15 clots samples retrieved from AIS patients (FPE: 5/15) treated with MT therapy along with their pre-treatment CT imaging (non-contrast CT–NCCT, and CT Angiography–CTA). We then segmented the clot regions on co-registered CT images and extracted 293 RFs, including. 1). shape-size metrics, 2). first-order statistics, and 3). higher order texture features. Univariate analysis was performed to test for significant differences in these RFs between FPE and non-FPE cases. Hematoxylin and eosin-stained clot sections from these cases were analyzed by Orbit Image Analysis software to determine if clot composition (i.e. % red blood cell-RBC, white blood cell-WBC, fibrin/platelets-FP) and structure (i.e. heterogeneity, organization) was significantly related to these RFs. Our results indicated that 5RFs, all from higher-order textural feature analysis, were significantly associated with FPE. These RFs were also associated with patient outcomes (delta NIHSS), albiet less significantly. There was no difference in RFs among clots of different composition (i.e. low vs high RBC clots), however, there were significant associations between the 5 RFs and clot organization parameters indicating that clots with ordered structures were easier to remove. These results need to be validated in larger datasets to establish the ability of RFs to predict FPE.

Vortices formed on the mitral valve tips aid normal left ventricular filling

Abstract: For the left ventricle (LV) to function as an effective pump it must be able to fill from a low left atrial pressure. However, this ability is lost in patients with heart failure. We investigated LV filling by measuring the cardiac blood flow using 2D phase contrast magnetic resonance imaging and quantified the intraventricular pressure gradients and the strength and location of vortices. In normal subjects, blood flows towards the apex prior to the mitral valve opening, and the mitral annulus moves rapidly away after the valve opens, with both effects enhancing the vortex ring at the mitral valve tips. Instead of being a passive by-product of the process as was previously believed, this ring facilitates filling by reducing convective losses and enhancing the function of the LV as a suction pump. The virtual channel thus created by the vortices may help insure efficient mass transfer for the left atrium to the LV apex. Impairment of this mechanism contributes to diastolic dysfunction, with LV filling becoming dependent on left atrial pressure, which can lead to eventual heart failure. Better understanding of the mechanics of this progression may lead to more accurate diagnosis and treatment of this disease.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease

Abstract: Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

A novel spectral relaxation approach for nanofluid flow past a stretching surface in presence of magnetic field and nonlinear radiation

Abstract: The goal of current research is to peruse the influences of magnetic field and nonlinear radiation on stagnation-point flow of nanofluid past a stretching surface. The Joule heating and viscous dissipation properties are considered for analysis in present work. The spectral relaxation numerical approach is implemented to solve the principal equations of the problem. Also, the influences of nanoparticles thermophoretic diffusion and Brownian motion, as well as Prandtl, Eckert, Lewis, and Biot numbers are analyzed and discussed in details. As a main result, it can be concluded that by increasing Prandtl number the temperature profile reduces for different values of radiation parameter. Furthermore, the results show that the nanofluid temperature profile rises with increase of Lewis number. In addition, the findings reveal that increasing the strength of the magnetic field affects the temperature and concentration of nanofluid.

Automatic segmentation of the left ventricle in echocardiographic images using convolutional neural networks

Abstract: Background Two-dimensional echocardiography (2D echo) is the most widely used non-invasive imaging modality due to its fast acquisition time, low cost, and high temporal resolution. Boundary identification of left ventricle (LV) in 2D echo, i.e., image segmentation, is the first step to calculate relevant clinical parameters. Currently, LV segmentation in 2D echo is primarily conducted semi-manually. A fully-automatic segmentation of the LV wall needs further development. Methods We evaluated the performance of the state-of-the-art convolutional neural networks (CNNs) for the segmentation of 2D echo images from 6 standard projections of the LV. We used two segmentation algorithms: U-net and segAN. The models were trained using an in-house dataset, which consists of 1,649 porcine images from 6 to 8 different pigs. In addition, a transfer learning approach was used for the segmentation of long-axis projections by training models with our database based on the previously trained weights obtained from Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset. The models were tested on a separate set of images from two other pigs by computing several metrics. The segmentation process was combined with a 3D reconstruction framework to quantify the physiological indices such as LV volumes and ejection fraction (EF). Results The average dice metric for the LV cavity was 0.90 and 0.91 for the U-net and segAN, respectively, which was higher than 0.82 for the level-set (P value: 3.31×10-25). The average Hausdorff distance for the LV cavity was 2.71 mm and 2.82 mm for the U-net and segAN, respectively, which was lower than 3.64 mm for the level-set (P value: 4.86×10-16). The LV shapes and volumes obtained using the CNN segmentation models were in good agreement with the results segmented by the experts. In addition, the differences of the calculated physiological parameters between two 3D reconstruction models segmented by the experts and CNNs were less than 15%. Conclusions The results showed that both CNN models achieve higher performance on LV segmentation than the level-set method. The error of the reconstruction from automatic segmentation compared to the expert segmentation is less than 15%, which is within the 20% error of echo compared to the gold standard.