Dataset Information

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages.

ABSTRACT: Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5-40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

SUBMITTER: Crouzet C

PROVIDER: S-EPMC8140127 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages.

Crouzet Christian C Jeong Gwangjin G Chae Rachel H RH LoPresti Krystal T KT Dunn Cody E CE Xie Danny F DF Agu Chiagoziem C Fang Chuo C Nunes Ane C F ACF Lau Wei Ling WL Kim Sehwan S Cribbs David H DH Fisher Mark M Choi Bernard B

Scientific reports 20210521 1

Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5-40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three di ...[more]

PMID: 34021170

Similar Datasets

Project description:Study objectiveTriage quickly identifies critically ill patients, facilitating timely interventions. Many emergency departments (EDs) use emergency severity index (ESI) or abnormal vital sign triggers to guide triage. However, both use fixed thresholds, and false activations are costly. Prior approaches using machinelearning have relied on information that is often unavailable during the triage process. We examined whether deep-learning approaches could identify critically ill patients only using data immediately available at triage.MethodsWe conducted a retrospective, cross-sectional study at an urban tertiary care center, from January 1, 2012-January 1, 2020. De-identified triage information included structured (age, sex, initial vital signs) and textual (chief complaint) data, with critical illness (mortality or ICU admission within 24 hours) as the outcome. Four progressively complex deep-learning models were trained and applied to triage information from all patients. We compared the accuracy of the models against ESI as the standard diagnostic test, using area under the receiver-operator curve (AUC).ResultsA total of 445,925 patients were included, with 60,901 (13.7%) critically ill. Vital sign thresholds identified critically ill patients with AUC 0.521 (95% confidence interval [CI] = 0.519-0.522), and ESI <3 demonstrated AUC 0.672 (95% CI = 0.671-0.674), logistic regression classified patients with AUC 0.803 (95% CI = 0.802-0.804), 2-layer neural network with structured data with AUC 0.811 (95% CI = 0.807-0.815), gradient tree boosting with AUC 0.820 (95% CI = 0.818-0.821), and the neural network model with textual data with AUC 0.851 (95% CI = 0.849-0.852). All successive increases in AUC were statistically significant.ConclusionDeep-learning techniques represent a promising method of augmenting triage, even with limited information. Further research is needed to determine if improved predictions yield clinical and operational benefits.

Project description:Cerebral microhemorrhages (CMH) are the pathological substrate for MRI-demonstrable cerebral microbleeds, which are associated with cognitive impairment and stroke. Aging and hypertension are the main risk factors for CMH. In this study, we investigated the development of CMH in a mouse model of aging and hypertension. Hypertension was induced in aged (17-month-old) female and male C57BL/6J mice via angiotensin II (Ang II), a potent vasoconstrictor. We investigated the vascular origin of CMH using three-dimensional images of 1-mm thick brain sections. We examined Ang II-induced CMH formation with and without telmisartan, an Ang II type 1 receptor (AT1R) blocker. To evaluate the effect of microglia and perivascular macrophages on CMH formation, mice were treated with PLX3397, a selective colony-stimulating factor 1 receptor (CSF1R) inhibitor, to achieve microglial and macrophage depletion. Iba-1 and CD206 labeling were used to study the relative contributions of microglia and macrophages, respectively, on CMH formation. CMH quantification was performed with analysis of histological sections labeled with Prussian blue. Vessels surrounding CMH were primarily of capillary size range (< 10 μm in diameter). Ang II-infused mice exhibited elevated blood pressure (p < 0.0001) and CMH burden (p < 0.001). CMH burden was significantly correlated with mean arterial pressure in mice with and without Ang II (r = 0.52, p < 0.05). Ang II infusion significantly increased Iba-1 immunoreactivity (p < 0.0001), and CMH burden was significantly correlated with Iba-1 in mice with and without Ang II (r = 0.32, p < 0.05). Telmisartan prevented elevation of blood pressure due to Ang II infusion and blocked Ang II-induced CMH formation without affecting Iba-1 immunoreactivity. PLX3397 treatment reduced Iba-1 immunoreactivity in Ang II-infused mice (p < 0.001) and blocked Ang II-induced CMH (p < 0.0001). No significant association between CMH burden and CD206 reactivity was observed. Our findings demonstrate Ang II infusion increases CMH burden. CMH in this model appear to be capillary-derived and Ang II-induced CMH are largely mediated by blood pressure. In addition, microglial activation may represent an alternate pathway for CMH formation. These observations emphasize the continuing importance of blood pressure control and the role of microglia in hemorrhagic cerebral microvascular disease.

Project description:Previous literature shows that deep learning is an effective tool to decode the motor intent from neural signals obtained from different parts of the nervous system. However, deep neural networks are often computationally complex and not feasible to work in real-time. Here we investigate different approaches' advantages and disadvantages to enhance the deep learning-based motor decoding paradigm's efficiency and inform its future implementation in real-time. Our data are recorded from the amputee's residual peripheral nerves. While the primary analysis is offline, the nerve data is cut using a sliding window to create a "pseudo-online" dataset that resembles the conditions in a real-time paradigm. First, a comprehensive collection of feature extraction techniques is applied to reduce the input data dimensionality, which later helps substantially lower the motor decoder's complexity, making it feasible for translation to a real-time paradigm. Next, we investigate two different strategies for deploying deep learning models: a one-step (1S) approach when big input data are available and a two-step (2S) when input data are limited. This research predicts five individual finger movements and four combinations of the fingers. The 1S approach using a recurrent neural network (RNN) to concurrently predict all fingers' trajectories generally gives better prediction results than all the machine learning algorithms that do the same task. This result reaffirms that deep learning is more advantageous than classic machine learning methods for handling a large dataset. However, when training on a smaller input data set in the 2S approach, which includes a classification stage to identify active fingers before predicting their trajectories, machine learning techniques offer a simpler implementation while ensuring comparably good decoding outcomes to the deep learning ones. In the classification step, either machine learning or deep learning models achieve the accuracy and F1 score of 0.99. Thanks to the classification step, in the regression step, both types of models result in a comparable mean squared error (MSE) and variance accounted for (VAF) scores as those of the 1S approach. Our study outlines the trade-offs to inform the future implementation of real-time, low-latency, and high accuracy deep learning-based motor decoder for clinical applications.

Dataset Information

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages.

Publications

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets