scholarly journals Automatic Segmentation and Measurement of Vascular Biomarkers in OCT-A Images

Proceedings ◽  
2018 ◽  
Vol 2 (18) ◽  
pp. 1169
Author(s):  
Macarena Díaz ◽  
Jorge Novo ◽  
Manuel G. Penedo ◽  
Marcos Ortega
Keyword(s):  
Correlation Coefficient ◽  
Automatic Segmentation ◽  
Clinical Analysis ◽  
Jaccard Index ◽  
Monitoring Process ◽  
Vascular Biomarkers

We propose an automatic methodology that identifies the vascularity zones in OCT-A images and their measurement for its use in clinical analysis and diagnostic processes. The segmentation and measurement contributes objectivity and repeatability in the results, desirable characteristics in any diagnosis and monitoring process. In the validation of the method, the correlation coefficient of Pearson and Jaccard index were used, obtaining satisfactory results.

scholarly journals Automated skull stripping in mouse fMRI analysis using 3D U-Net

2021 ◽  
Author(s):  
Guohui Ruan ◽  
Jiaming Liu ◽  
Ziqi An ◽  
Kaiibin Wu ◽  
Chuanjun Tong ◽  
...  
Keyword(s):  
Hausdorff Distance ◽  
Automatic Segmentation ◽  
Resting State Fmri ◽  
Jaccard Index ◽  
Brain Extraction ◽  
Functional Images ◽  
Skull Stripping ◽  
Anatomical Images ◽  
Fmri Analysis ◽  
T2 Weighted Images

Skull stripping is an initial and critical step in the pipeline of mouse fMRI analysis. Manual labeling of the brain usually suffers from intra- and inter-rater variability and is highly time-consuming. Hence, an automatic and efficient skull-stripping method is in high demand for mouse fMRI studies. In this study, we investigated a 3D U-Net based method for automatic brain extraction in mouse fMRI studies. Two U-Net models were separately trained on T2-weighted anatomical images and T2*-weighted functional images. The trained models were tested on both interior and exterior datasets. The 3D U-Net models yielded a higher accuracy in brain extraction from both T2-weighted images (Dice > 0.984, Jaccard index > 0.968 and Hausdorff distance < 7.7) and T2*-weighted images (Dice > 0.964, Jaccard index > 0.931 and Hausdorff distance < 3.3), compared with the two widely used mouse skull-stripping methods (RATS and SHERM). The resting-state fMRI results using automatic segmentation with the 3D U-Net models are identical to those obtained by manual segmentation for both the seed-based and group independent component analysis. These results demonstrate that the 3D U-Net based method can replace manual brain extraction in mouse fMRI analysis.

scholarly journals Automatic quantification of superficial foveal avascular zone in optical coherence tomography angiography implemented with deep learning

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Menglin Guo ◽  
Mei Zhao ◽  
Allen M. Y. Cheong ◽  
Houjiao Dai ◽  
Andrew K. C. Lam ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Optical Coherence Tomography Angiography ◽  
Automatic Segmentation ◽  
Clinical Analysis ◽  
Foveal Avascular Zone ◽  
Dice Similarity Coefficient ◽  
Optical Coherence ◽  
Hole Filling ◽  
Avascular Zone

AbstractAn accurate segmentation and quantification of the superficial foveal avascular zone (sFAZ) is important to facilitate the diagnosis and treatment of many retinal diseases, such as diabetic retinopathy and retinal vein occlusion. We proposed a method based on deep learning for the automatic segmentation and quantification of the sFAZ in optical coherence tomography angiography (OCTA) images with robustness to brightness and contrast (B/C) variations. A dataset of 405 OCTA images from 45 participants was acquired with Zeiss Cirrus HD-OCT 5000 and the ground truth (GT) was manually segmented subsequently. A deep learning network with an encoder–decoder architecture was created to classify each pixel into an sFAZ or non-sFAZ class. Subsequently, we applied largest-connected-region extraction and hole-filling to fine-tune the automatic segmentation results. A maximum mean dice similarity coefficient (DSC) of 0.976 ± 0.011 was obtained when the automatic segmentation results were compared against the GT. The correlation coefficient between the area calculated from the automatic segmentation results and that calculated from the GT was 0.997. In all nine parameter groups with various brightness/contrast, all the DSCs of the proposed method were higher than 0.96. The proposed method achieved better performance in the sFAZ segmentation and quantification compared to two previously reported methods. In conclusion, we proposed and successfully verified an automatic sFAZ segmentation and quantification method based on deep learning with robustness to B/C variations. For clinical applications, this is an important progress in creating an automated segmentation and quantification applicable to clinical analysis.

scholarly journals Automatic Segmentation and Visualisation of the Epirretinal Membrane in OCT Scans Using Densely Connected Convolutional Networks

2021 ◽  
Vol 7 (1) ◽  
pp. 2
Author(s):  
Mateo Gende ◽  
Joaquim de Moura ◽  
Jorge Novo ◽  
Pablo Charlón ◽  
Marcos Ortega
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Epiretinal Membrane ◽  
State Of The Art ◽  
Automatic Segmentation ◽  
Jaccard Index ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Inner Limiting Membrane ◽  
Cellular Layer

The Epiretinal Membrane (ERM) is an ocular disease that appears as a fibro-cellular layer of tissue over the retina, specifically, over the Inner Limiting Membrane (ILM). It causes vision blurring and distortion, and its presence can be indicative of other ocular pathologies, such as diabetic macular edema. The ERM diagnosis is usually performed by visually inspecting Optical Coherence Tomography (OCT) images, a manual process which is tiresome and prone to subjectivity. In this work, we present a methodology for the automatic segmentation and visualisation of the ERM in OCT volumes using deep learning. By employing a Densely Connected Convolutional Network, every pixel in the ILM can be classified into either healthy or pathological. Thus, a segmentation of the region susceptible to ERM appearance can be produced. This methodology also produces an intuitive colour map representation of the ERM presence over a visualisation of the eye fundus created from the OCT volume. In a series of representative experiments conducted to evaluate this methodology, it achieved a Dice score of 0.826±0.112 and a Jaccard index of 0.714±0.155. The results that were obtained demonstrate the competitive performance of the proposed methodology when compared to other works in the state of the art.

scholarly journals Correlating Information Contents of Gene Ontology Terms to Infer Semantic Similarity of Gene Products

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Mingxin Gan
Keyword(s):  
Gene Ontology ◽  
Gene Product ◽  
Correlation Coefficient ◽  
Semantic Similarity ◽  
Biological Process ◽  
Jaccard Index ◽  
Biological Knowledge ◽  
Gene Products ◽  
Functional Relationships ◽  
Information Contents

Successful applications of the gene ontology to the inference of functional relationships between gene products in recent years have raised the need for computational methods to automatically calculate semantic similarity between gene products based on semantic similarity of gene ontology terms. Nevertheless, existing methods, though having been widely used in a variety of applications, may significantly overestimate semantic similarity between genes that are actually not functionally related, thereby yielding misleading results in applications. To overcome this limitation, we propose to represent a gene product as a vector that is composed of information contents of gene ontology terms annotated for the gene product, and we suggest calculating similarity between two gene products as the relatedness of their corresponding vectors using three measures: Pearson’s correlation coefficient, cosine similarity, and the Jaccard index. We focus on the biological process domain of the gene ontology and annotations of yeast proteins to study the effectiveness of the proposed measures. Results show that semantic similarity scores calculated using the proposed measures are more consistent with known biological knowledge than those derived using a list of existing methods, suggesting the effectiveness of our method in characterizing functional relationships between gene products.

Verification of Access GI Monitor (CA 19-9) Assay on Beckman Coulter Unicel DXI 800

2019 ◽  
Vol 152 (Supplement_1) ◽  
pp. S19-S19
Author(s):  
Eric Ollila ◽  
Liyun Cao ◽  
Qing Wei ◽  
Mariam Youssef
Keyword(s):  
Correlation Coefficient ◽  
Reference Range ◽  
Clinical History ◽  
Gastrointestinal Diseases ◽  
Clinical Analysis ◽  
Measurement Range ◽  
Response To Therapy ◽  
Negative Results ◽  
Deming Regression ◽  
High Level

Abstract CA 19-9 antigen has been identified in patients with colorectal, pancreatic, bile duct, hepatocellular, stomach, and esophageal cancers. Noncancerous conditions that may elevate CA 19-9 levels include cirrhosis, cholangitis, hepatitis, pancreatitis, and nonmalignant gastrointestinal diseases. CA 19-9 antigen levels may be used as an aid in monitoring response to therapy or disease progression in cancer patients. The objective of this study was to assess the analytical performance of the Access GI Monitor assay on Beckman Coulter UniCel DXI 800. CA 19-9 was quantitatively determined on the Beckman Coulter UniCel DXI 800 following CLSI guidelines. The performance was evaluated for linearity, sensitivity, reference range, and precision. The within-run and between-run precisions were assessed by analyzing QC material at low and high levels of concentrations. Accuracy was assessed by comparison with the previously established Siemens ADVIA Centaur XP. Antigen level values were classified as positive or negative based on the upper limit of the reference range to assess concordance between the two analyzers. The accuracy of each analyzer was also assessed by correlating the discordant antigen values with the patients’ clinical history. For the Beckman Coulter DXI assay, the analytic measurement range was determined to be linear between 0.8 and 2,000 U/mL with a slope of 1.018 and intercept of 4.13. The limit of blank was determined as 0.09 U/mL. The reference range was verified as 0 to 35 U/mL. The within-run CVs for CA 19-9 were 3.7% at both the low level of 23.54 U/mL and high level of 262.56 U/mL. The between-run CVs at low and high levels were 4.34% and 6.36%, respectively. A total of 327 patient samples were analyzed in the comparison of CA 19-9 levels on Beckman Coulter DXI and Siemens ADVIA Centaur XP. On Deming regression, the slope was 0.665 with an intercept of 136.4 and correlation coefficient of 0.8964; there was wide scatter between the two methods. The mean bias between the two analyzers was –291.1 (–22.8%). The correlation coefficient was 0.8931, and the bias was –770.7 (–26.1%) when both were positive. The correlation coefficient was 0.7949, and the bias was –0.8 (–6.1%) when both were negative. The agreement of the two methods was 91% (n = 298) and disagreement was 9% (n = 29). After clinical analysis of 18 discordant values, six data points correlated better with the Siemens Centaur XP and the remaining 12 correlated better with the Beckman Coulter DXI. Our data demonstrate that CA 19-9 on Beckman Coulter DXI has good linearity and precision. There is poor to fair correlation between the two methods. Agreement based on clinical classification of positive and negative results is good. The Beckman Coulter DXI correlates with the patient clinical history better than the Siemens Centaur XP when comparing discordant values between the analyzers.

1630: Clinical Analysis of Factors Affecting Poor Graft Functions Following Kidney Transplants from Non-Heart Beating Cadaveric Donors

2005 ◽  
Vol 173 (4S) ◽  
pp. 441-441
Author(s):  
Ryoichi Shiroki ◽  
Hitomi Sasaki ◽  
Yuusuke Kubota ◽  
Tohru Higuchi ◽  
Mamoru Kusaka ◽  
...  
Keyword(s):  
Clinical Analysis ◽  
Kidney Transplants ◽  
Factors Affecting ◽  
Heart Beating ◽  
Cadaveric Donors

Paraoxonase-1 and myeloperoxidase correlate with vascular biomarkers in overweight patients with newly diagnosed untreated hyperlipidaemia

VASA ◽  
2017 ◽  
Vol 46 (5) ◽  
pp. 370-376 ◽  
Author(s):  
Anita Szentpéteri ◽  
Noémi Zsíros ◽  
Viktória E. Varga ◽  
Hajnalka Lőrincz ◽  
Mónika Katkó ◽  
...  
Keyword(s):  
Adhesion Molecule ◽  
Oxidized Ldl ◽  
Vascular Complications ◽  
Cd40 Ligand ◽  
Paraoxonase 1 ◽  
Intercellular Adhesion Molecule ◽  
Pon1 Activity ◽  
Intercellular Adhesion Molecule 1 ◽  
Inflammatory Parameters ◽  
Vascular Biomarkers

Abstract. Background: In hyperlipidaemic state, increased levels of myeloperoxidase (MPO) and decreased paraoxonase-1 (PON1) activity have been reported; however, their relationships with other atherosclerotic biomarkers have not been completely clarified. Patients and methods: Serum concentrations of lipid and inflammatory parameters, MPO levels, and PON1 activities were investigated in 167 untreated hyperlipidaemic patients with and without vascular complications and in 32 healthy controls. Additionally, levels of CD40 ligand (sCD40L) and asymmetric dimethyl arginine (ADMA), soluble intercellular adhesion molecule-1 (sICAM-1), soluble vascular cell adhesion molecule-1, and oxidized LDL were determined. Results: We found elevated C-reactive protein (CRP), ADMA, sCD40L, sICAM-1 concentrations, and higher MPO levels in patients with vascular complications compared to those without. The PON1 arylesterase activity correlated negatively with sCD40L, ADMA, and sICAM-1 levels, respectively. In contrast, MPO concentrations showed positive correlations with sCD40L, ADMA, and sICAM-1 levels, respectively. Conclusions: It can therefore be stated that PON1 activity and MPO level correlate strongly with the vascular biomarkers, highlighting the importance of the HDL-associated pro- and antioxidant enzymes in the development of endothelial dysfunction and atherogenesis.

Sign in / Sign up

Export Citation Format

Share Document