scholarly journals Pixel-Label-Based Segmentation of Cross-Sectional Brain MRI Using Simplified SegNet Architecture-Based CNN

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Bijen Khagi ◽  
Goo-Rak Kwon
Keyword(s):  
Brain Mri ◽  
Similarity Index ◽  
Ground Truth ◽  
Specific Class ◽  
Cross Sectional ◽  
Reference Images ◽  
Ground Truth Image ◽  
Optimal Accuracy ◽  
Dice Similarity Index ◽  
Mri Image

Using deep neural networks for segmenting an MRI image of heterogeneously distributed pixels into a specific class assigning a label to each pixel is the concept of the proposed approach. This approach facilitates the application of the segmentation process on a preprocessed MRI image, with a trained network to be utilized for other test images. As labels are considered expensive assets in supervised training, fewer training images and training labels are used to obtain optimal accuracy. To validate the performance of the proposed approach, an experiment is conducted on other test images (available in the same database) that are not part of the training; the obtained result is of good visual quality in terms of segmentation and quite similar to the ground truth image. The average computed Dice similarity index for the test images is approximately 0.8, whereas the Jaccard similarity measure is approximately 0.6, which is better compared to other methods. This implies that the proposed method can be used to obtain reference images almost similar to the segmented ground truth images.

scholarly journals Simulating a Ground Truth for Transit Time Analysis of Indicator Dilution Curves

2020 ◽  
Vol 6 (3) ◽  
pp. 268-271
Author(s):  
Michael Reiß ◽  
Ady Naber ◽  
Werner Nahm
Keyword(s):  
Transit Time ◽  
Sampling Rate ◽  
Ground Truth ◽  
Indicator Dilution ◽  
Cross Sectional ◽  
In Vivo Measurements ◽  
Multiple Indicator Dilution ◽  
Transit Times ◽  
Dilution Curves

AbstractTransit times of a bolus through an organ can provide valuable information for researchers, technicians and clinicians. Therefore, an indicator is injected and the temporal propagation is monitored at two distinct locations. The transit time extracted from two indicator dilution curves can be used to calculate for example blood flow and thus provide the surgeon with important diagnostic information. However, the performance of methods to determine the transit time Δt cannot be assessed quantitatively due to the lack of a sufficient and trustworthy ground truth derived from in vivo measurements. Therefore, we propose a method to obtain an in silico generated dataset of differently subsampled indicator dilution curves with a ground truth of the transit time. This method allows variations on shape, sampling rate and noise while being accurate and easily configurable. COMSOL Multiphysics is used to simulate a laminar flow through a pipe containing blood analogue. The indicator is modelled as a rectangular function of concentration in a segment of the pipe. Afterwards, a flow is applied and the rectangular function will be diluted. Shape varying dilution curves are obtained by discrete-time measurement of the average dye concentration over different cross-sectional areas of the pipe. One dataset is obtained by duplicating one curve followed by subsampling, delaying and applying noise. Multiple indicator dilution curves were simulated, which are qualitatively matching in vivo measurements. The curves temporal resolution, delay and noise level can be chosen according to the requirements of the field of research. Various datasets, each containing two corresponding dilution curves with an existing ground truth transit time, are now available. With additional knowledge or assumptions regarding the detection-specific transfer function, realistic signal characteristics can be simulated. The accuracy of methods for the assessment of Δt can now be quantitatively compared and their sensitivity to noise evaluated.

scholarly journals Fully Data-Driven Pseudohealthy Synthesis for Planning Valve-Sparing Aortic Root Reconstruction using Conditional Variational Autoencoders

2020 ◽  
Vol 6 (3) ◽  
pp. 284-287
Author(s):  
Jannis Hagenah ◽  
Mohamad Mehdi ◽  
Floris Ernst
Keyword(s):  
Aortic Root ◽  
Similarity Index ◽  
Ground Truth ◽  
Representation Learning ◽  
Patient Specific ◽  
Ultrasound Images ◽  
Specific Geometry ◽  
The Individual ◽  
Native Root ◽  
Original Information

AbstractAortic root aneurysm is treated by replacing the dilated root by a grafted prosthesis which mimics the native root morphology of the individual patient. The challenge in predicting the optimal prosthesis size rises from the highly patient-specific geometry as well as the absence of the original information on the healthy root. Therefore, the estimation is only possible based on the available pathological data. In this paper, we show that representation learning with Conditional Variational Autoencoders is capable of turning the distorted geometry of the aortic root into smoother shapes while the information on the individual anatomy is preserved. We evaluated this method using ultrasound images of the porcine aortic root alongside their labels. The observed results show highly realistic resemblance in shape and size to the ground truth images. Furthermore, the similarity index has noticeably improved compared to the pathological images. This provides a promising technique in planning individual aortic root replacement.

Changes in brain MRI under different lunar cycles: a cross-sectional study

2021 ◽  
pp. 1-7
Author(s):  
Ayyoub Malek ◽  
Mohammad Hossein Daghighi ◽  
Masoud Pourisa ◽  
Tohid Pourmohammadi ◽  
Saeed Dastgiri ◽  
...  
Keyword(s):  
Brain Mri ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
Lunar Cycles

Fish Intake and MRI Burden of Cerebrovascular Disease in Older Adults

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012916
Author(s):  
Aline Thomas ◽  
Fabrice Crivello ◽  
Bernard Mazoyer ◽  
Stephanie Debette ◽  
Christophe Tzourio ◽  
...  
Keyword(s):  
Factor Analysis ◽  
Cerebrovascular Disease ◽  
Brain Mri ◽  
Large Population ◽  
Population Based ◽  
Fish Intake ◽  
Mixed Data ◽  
Perivascular Spaces ◽  
Intracranial Volume ◽  
Cross Sectional

Background and Objective:Fish intake may prevent cerebrovascular disease (CVD), yet the mechanisms are unclear, especially regarding its impact on subclinical damage. Assuming that fish may have pleiotropic effect on cerebrovascular health, we investigated the association of fish intake with global CVD burden based on brain MRI markers.Methods:This cross-sectional analysis included participants from the Three-City Dijon population-based cohort (aged ≥65 years) without dementia, stroke, or history of hospitalized cardiovascular disease, who underwent brain MRI with automated assessment of white matter hyperintensities, visual detection of covert infarcts, and grading of dilated perivascular spaces. Fish intake was assessed through a frequency questionnaire and the primary outcome measure was defined as the first component of a factor analysis of mixed data applied to MRI markers. The association of fish intake with the CVD burden indicator was studied using linear regressions.Results:In total, 1,623 participants (mean age, 72.3 years; 63% women) were included. The first component of factor analysis (32.4% of explained variance) was associated with higher levels of all three MRI markers. Higher fish intake was associated with lower CVD burden. In a model adjusted for total intracranial volume, compared to participants consuming fish <1 per week, those consuming fish 2-3 and ≥4 times per week had a β = -0.19 (95% CI, -0.37; -0.01) and β = -0.30 (-0.57; -0.03) lower indicator of CVD burden, respectively (P trend <0.001). We found evidence of effect modification by age, so that the association of fish to CVD was stronger in younger participants (65-69 years) and not significant in participants aged ≥75 years. For comparison, in the younger age group, consuming fish 2-3 times a week was roughly equivalent (in opposite direction) to the effect of hypertension.Discussion:In this large population-based study, higher frequency of fish intake was associated with lower CVD burden, especially among participants younger than 75 years, suggesting a beneficial effect on brain vascular health before manifestation of overt brain disease.Classification of Evidence:This study provides Class II evidence that in individuals without stroke or dementia, higher fish intake is associated with lower subclinical CVD at MRI.

scholarly journals Semantic segmentation of gonio-photographs via adaptive ROI localisation and uncertainty estimation

2021 ◽  
Vol 6 (1) ◽  
pp. e000898
Author(s):  
Andrea Peroni ◽  
Anna Paviotti ◽  
Mauro Campigotto ◽  
Luis Abegão Pinto ◽  
Carlo Alberto Cutolo ◽  
...  
Keyword(s):  
Region Of Interest ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Uncertainty Estimation ◽  
Depth Of Field ◽  
Clinical Settings ◽  
Proposed Model ◽  
Validation Experiment ◽  
Segmentation Accuracy ◽  
Ground Truth Image

ObjectiveTo develop and test a deep learning (DL) model for semantic segmentation of anatomical layers of the anterior chamber angle (ACA) in digital gonio-photographs.Methods and analysisWe used a pilot dataset of 274 ACA sector images, annotated by expert ophthalmologists to delineate five anatomical layers: iris root, ciliary body band, scleral spur, trabecular meshwork and cornea. Narrow depth-of-field and peripheral vignetting prevented clinicians from annotating part of each image with sufficient confidence, introducing a degree of subjectivity and features correlation in the ground truth. To overcome these limitations, we present a DL model, designed and trained to perform two tasks simultaneously: (1) maximise the segmentation accuracy within the annotated region of each frame and (2) identify a region of interest (ROI) based on local image informativeness. Moreover, our calibrated model provides results interpretability returning pixel-wise classification uncertainty through Monte Carlo dropout.ResultsThe model was trained and validated in a 5-fold cross-validation experiment on ~90% of available data, achieving ~91% average segmentation accuracy within the annotated part of each ground truth image of the hold-out test set. An appropriate ROI was successfully identified in all test frames. The uncertainty estimation module located correctly inaccuracies and errors of segmentation outputs.ConclusionThe proposed model improves the only previously published work on gonio-photographs segmentation and may be a valid support for the automatic processing of these images to evaluate local tissue morphology. Uncertainty estimation is expected to facilitate acceptance of this system in clinical settings.

scholarly journals Atrial Fibrillation and Brain Magnetic Resonance Imaging Abnormalities

Stroke ◽  
2019 ◽  
Vol 50 (4) ◽  
pp. 783-788 ◽  
Author(s):  
Jeremy P. Berman ◽  
Faye L. Norby ◽  
Thomas Mosley ◽  
Elsayed Z. Soliman ◽  
Rebecca F. Gottesman ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Brain Volume ◽  
Brain Mri ◽  
Brain Magnetic Resonance Imaging ◽  
White Matter Hyperintensity ◽  
Resonance Imaging ◽  
Total Brain Volume ◽  
Cross Sectional ◽  
Total Brain ◽  
Sectional Analysis

Background and Purpose— Atrial fibrillation (AF) is associated with dementia independent of clinical stroke. The mechanisms underlying this association remain unclear. In a community-based cohort, the ARIC study (Atherosclerosis Risk in Communities), we evaluated (1) the longitudinal association of incident AF and (2) the cross-sectional association of prevalent AF with brain magnetic resonance imaging (MRI) abnormalities. Methods— The longitudinal analysis included 963 participants (mean age, 73±4.4 years; 62% women; 51% black) without prevalent stroke or AF who underwent a brain MRI in 1993 to 1995 and a second MRI in 2004 to 2006 (mean, 10.6±0.8 years). Outcomes included subclinical cerebral infarctions, sulcal size, ventricular size, and, for the cross-sectional analysis, white matter hyperintensity volume and total brain volume. Results— In the longitudinal analysis, 29 (3.0%) participants developed AF after the first brain MRI. Those who developed AF had higher odds of increase in subclinical cerebral infarctions (odds ratio [OR], 3.08; 95% CI, 1.39–6.83), worsening sulcal grade (OR, 3.56; 95% CI, 1.04–12.2), and worsening ventricular grade (OR, 9.34; 95% CI, 1.24–70.2). In cross-sectional analysis, of 969 participants, 35 (3.6%) had prevalent AF at the time of the 2004 to 2006 MRI scan. Those with AF had greater odds of higher sulcal (OR, 3.9; 95% CI, 1.7–9.1) and ventricular grade (OR, 2.4; 95% CI, 1.0–5.7) after multivariable adjustment and no difference in white matter hyperintensity or total brain volume. Conclusions— AF is independently associated with increase in subclinical cerebral infarction and worsening sulcal and ventricular grade—morphological changes associated with aging and dementia. More research is needed to define the mechanisms underlying AF-related neurodegeneration.

Sign in / Sign up

Export Citation Format

Share Document