Dataset Information

Pathophysiology, classification, and MRI parallels in microvascular disease of the heart and brain.

ABSTRACT: Diagnostic imaging technology in vascular disease has long focused on large vessels and the pathologic processes that impact them. With improved diagnostic techniques, investigators are now able to uncover many underlying mechanisms and prognostic factors for microvascular disease. In the heart and brain, these pathologic entities include coronary microvascular disease and cerebral small vessel disease, both of which have significant impact on patients, causing angina, myocardial infarction, heart failure, stroke, and dementia. In the current paper, we will discuss parallels in pathophysiology, classification, and diagnostic modalities, with a focus on the role of magnetic resonance imaging in microvascular disease of the heart and brain. Novel approaches for streamlined imaging of the cardiac and central nervous systems including the use of intravascular contrast agents such as ferumoxytol are presented, and unmet research gaps in diagnostics are summarized.

SUBMITTER: Thomas MA

PROVIDER: S-EPMC7680357 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pathophysiology, classification, and MRI parallels in microvascular disease of the heart and brain.

Thomas Michael A MA Hazany Saman S Ellingson Benjamin M BM Hu Peng P Nguyen Kim-Lien KL

Microcirculation (New York, N.Y. : 1994) 20200726 8

Diagnostic imaging technology in vascular disease has long focused on large vessels and the pathologic processes that impact them. With improved diagnostic techniques, investigators are now able to uncover many underlying mechanisms and prognostic factors for microvascular disease. In the heart and brain, these pathologic entities include coronary microvascular disease and cerebral small vessel disease, both of which have significant impact on patients, causing angina, myocardial infarction, hea ...[more]

PMID: 32640064

Similar Datasets

Project description:Movement disorders are a prominent and common feature in many autoantibody-associated neurological diseases, a group of potentially treatable conditions that can mimic infectious, metabolic or neurodegenerative disease. Certain movement disorders are likely to associate with certain autoantibodies; for example, the characteristic dyskinesias, chorea and dystonia associated with NMDAR antibodies, stiff person spectrum disorders with GAD, glycine receptor, amphiphysin or DPPX antibodies, specific paroxysmal dystonias with LGI1 antibodies, and cerebellar ataxia with various anti-neuronal antibodies. There are also less-recognized movement disorder presentations of antibody-related disease, and a considerable overlap between the clinical phenotypes and the associated antibody spectra. In this review, we first describe the antibodies associated with each syndrome, highlight distinctive clinical or radiological 'red flags', and suggest a syndromic approach based on the predominant movement disorder presentation, age, and associated features. We then examine the underlying immunopathophysiology, which may guide treatment decisions in these neuroimmunological disorders, and highlight the exceptional interface between neuronal antibodies and neurodegeneration, such as the tauopathy associated with IgLON5 antibodies. Moreover, we elaborate the emerging pathophysiological parallels between genetic movement disorders and immunological conditions, with proteins being either affected by mutations or targeted by autoantibodies. Hereditary hyperekplexia, for example, is caused by mutations of the alpha subunit of the glycine receptor leading to an infantile-onset disorder with exaggerated startle and stiffness, whereas antibodies targeting glycine receptors can induce acquired hyperekplexia. The spectrum of such immunological and genetic analogies also includes cerebellar ataxias and some encephalopathies. Lastly, we discuss how these pathophysiological considerations could reflect on possible future directions regarding antigen-specific immunotherapies or targeting the pathophysiological cascades downstream of the antibody effects.

Project description:ObjectivesTo employ different automated convolutional neural network (CNN)-based transfer learning (TL) methods for both binary and multiclass classification of Alzheimer's disease (AD) using brain MRI.MethodsHerein, we applied three popular pre-trained CNN models (ResNet101, Xception, and InceptionV3) using a fine-tuned approach of TL on 3D T1-weighted brain MRI from a subset of ADNI dataset (n = 305 subjects). To evaluate power of TL, the aforementioned networks were also trained from scratch for performance comparison. Initially, Unet network segmentedthe MRI scans into characteristic components of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). The proposed networks were trained and tested over the pre-processed and augmented segmented and whole images for both binary (NC/AD + progressive mild cognitive impairment (pMCI)+stable MCI (sMCI)) and 4-class (AD/pMCI/sMCI/NC) classification. Also, two independent test sets from the OASIS (n = 30) and AIBL (n = 60) datasets were used to externally assess the performance of the proposed algorithms.ResultsThe proposed TL-based CNN models achieved better performance compared to the training CNN models from scratch. On the ADNI test set, InceptionV3-TL achieved the highest accuracy of 93.75% and AUC of 92.0% for binary classification, as well as the highest accuracy of 93.75% and AUC of 96.0% for multiclass classification of AD on the whole images. On the OASIS test set, InceptionV3-TL outperformed two other models by achieving 93.33% accuracy with 93.0% AUC in binary classification of AD on the whole images. On the AIBL test set, InceptionV3-TL also outperformed two other models in both binary and multiclass classification tasks on the whole MR images and achieved accuracy/AUC of 93.33%/95.0% and 90.0%/93.0%, respectively. The GM segment as input provided the highest performance in both binary and multiclass classification of AD, as compared to the WM and CSF segments.ConclusionThis study demonstrates the potential of applying deep TL approach for automated detection and classification of AD using brain MRI with high accuracy and robustness across internal and external test data, suggesting that these models can possibly be used as a supportive tool to assist clinicians in creating objective opinion and correct diagnosis.Advances in knowledgeWe used CNN-based TL approaches and the augmentation techniques to overcome the insufficient data problem. Our study provides evidence that deep TL algorithms can be used for both binary and multiclass classification of AD with high accuracy.

Dataset Information

Pathophysiology, classification, and MRI parallels in microvascular disease of the heart and brain.

Publications

Pathophysiology, classification, and MRI parallels in microvascular disease of the heart and brain.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets