scholarly journals Comparison and Supervised Learning of Segmentation Methods Dedicated to Specular Microscope Images of Corneal Endothelium

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Yann Gavet ◽  
Jean-Charles Pinoli
Keyword(s):  
Image Segmentation ◽  
Cell Layer ◽  
Spatial Density ◽  
Specular Microscopy ◽  
Main Criterion ◽  
Segmentation Methods ◽  
Best Parameter ◽  
Good Transparency ◽  
Parameter Values

The cornea is the front of the eye. Its inner cell layer, called the endothelium, is important because it is closely related to the light transparency of the cornea. An in vivo observation of this layer is performed by using specular microscopy to evaluate the health of the cells: a high spatial density will result in a good transparency. Thus, the main criterion required by ophthalmologists is the cell density of the cornea endothelium, mainly obtained by an image segmentation process. Different methods can perform the image segmentation of these cells, and the three most performing methods are studied here. The question for the ophthalmologists is how to choose the best algorithm and to obtain the best possible results with it. This paper presents a methodology to compare these algorithms together. Moreover, by the way of geometric dissimilarity criteria, the algorithms are tuned up, and the best parameter values are thus proposed to the expert ophthalmologists.

scholarly journals Image segmentation methods for quick characterization of ore chip using RGB images

2021 ◽  
Vol 942 (1) ◽  
pp. 012033
Author(s):  
O Khomiak ◽  
J Benndorf
Keyword(s):  
Image Segmentation ◽  
Spectral Band ◽  
Texture Feature ◽  
Mine Planning ◽  
Process Models ◽  
Spatial Density ◽  
Universal Method ◽  
Segmentation Methods ◽  
Grade Control ◽  
Rgb Images

Abstract The ability to forecast geometallurgical properties during resource extraction is essential to optimize the mine to mill process. Models for mine planning thus often incorporate attributes related to processability. The analysis of these attributes in a laboratory can be time- and cost intensive. Only a limited number of data may be available. During production, grade control drilling may provide access to many more samples. Conducting laboratory analysis to each of these samples would be not realistic. If there was an opportunity to quickly obtain related proxy data, as physical characteristics that can stand in for direct measurements, then these indices could be estimated, certainly less precise but with a significantly increased spatial density. A moderately simple approach to acquire data from grade control drilling is to take digital Red, Green and Blue spectral bands images (RGB images) in from core trays. Although these capture only three spectral band regions, images can contain valuable texture and colour related information. A first necessary step is to automatically extract from an image and analyse objects, that represent ore particles or mineral content. This study aims to investigate the performance of different available segmentation methods under field conditions. First an overview of methods for image segmentation as a basis to create objects is presented. Objects can be related to single grains and minerals within the grains. The aim is to provide a basis for texture feature extraction related to granular rock, such as found in chip trains. Modern image analysis provides a large number of methods for segmentation and classification of objects. This work focuses on evaluating performance on images of 3 levels of complexity of pixel- based segmentation for complex or less noisy images and object-based segmentation (Watershed, Simple Linear Iterative Clustering and Quickshift) as a more advanced and universal method.

Inactivation of Factor XIa in Vivo: Studies in Chimpanzees and in Humans

1996 ◽  
Vol 76 (04) ◽  
pp. 549-555 ◽  
Author(s):  
Walter A Wuillemin ◽  
C Erik Hack ◽  
Wim K Bleeker ◽  
Bart J Biemond ◽  
Marcel Levi ◽  
...  
Keyword(s):  
Antithrombin Iii ◽  
Life Time ◽  
In Vivo Studies ◽  
Clinical Samples ◽  
Plasma Samples ◽  
C1 Inhibitor ◽  
Elimination Kinetics ◽  
Factor Xia ◽  
Best Parameter

SummaryC1-inhibitor (C1Inh), antithrombin III (ATIII), α1-antitrypsin (a1AT), and α2-antiplasmin (a2AP) are known inhibitors of factor XIa (FXIa). However, their precise contribution to FXIa inactivation in vivo is not known. We investigated FXIa inactivation in chimpanzees and assessed the contribution of these inhibitors to FXIa inactivation in patients with presumed FXI activation.Chimpanzees were infused with FXIa and the various FXIa-FXIa inhibitor complexes formed were measured. Most of FXIa was complexed to C1Inh (68%), followed by a2AP (13%), a1AT (10%), and ATIII (9%). Analysis of the plasma elimination kinetics revealed a half-life time of clearance (t1/2) for the FXIa-FXIa inhibitor complexes of 95 to 104 min, except for FXIa-a1AT, which had a t1/2 of 349 min. Due to this long t1/2, FXIa-a1AT complexes were predicted to show the highest levels in plasma samples from patients with activation of FXI. This was indeed shown in patients with disseminated intravascular coagulation, recent myocardial infarction or unstable angina pectoris. We conclude from this study that in vivo C1Inh is the predominant inhibitor of FXIa, but that FXIa-a1 AT complexes due to their relatively long t1/2 may be the best parameter to assess FXI activation in clinical samples.

scholarly journals Chemically-Boosted Corneal Cross-Linking for the Treatment of Keratoconus through a Riboflavin 0.25% Optimized Solution with High Superoxide Anion Release

2021 ◽  
Vol 10 (6) ◽  
pp. 1324
Author(s):  
Cosimo Mazzotta ◽  
Marco Ferrise ◽  
Guido Gabriele ◽  
Paolo Gennaro ◽  
Alessandro Meduri
Keyword(s):  
Superoxide Anion ◽  
Hydroxypropyl Methylcellulose ◽  
Anterior Segment ◽  
Preclinical Study ◽  
Cross Linking ◽  
Specular Microscopy ◽  
The Novel ◽  
Power Setting ◽  
Contralateral Eye

The purpose of this study was to evaluate the effectiveness and safety of a novel buffered riboflavin solution approved for corneal cross-linking (CXL) in progressive keratoconus and secondary corneal ectasia. Following the in vivo preclinical study performed on New Zealand rabbits comparing the novel 0.25% riboflavin solution (Safecross®) containing 1% hydroxypropyl methylcellulose (HPMC) with a 0.25% riboflavin solution containing 0.10% EDTA, accelerated epithelium-off CXL was performed on 10 patients (10 eyes treated, with the contralateral eye used as control) through UV-A at a power setting of 9 mW/cm2 with a total dose of 5.4 J/cm2. Re-epithelialization was evaluated in the postoperative 7 days by fluorescein dye test at biomicroscopy; endothelial cell count and morphology (ECD) were analyzed by specular microscopy at the 1st and 6th month of follow-up and demarcation line depth (DLD) measured by anterior segment optical coherence tomography (AS-OCT) one month after the treatment. We observed complete re-epithelization in all eyes between 72 and 96 h after surgery (88 h on average). ECD and morphology remained unchanged in all eyes. DLD was detected at a mean depth of 362 ± 50 µm, 20% over solutions with equivalent dosage. SafeCross® riboflavin solution chemically-boosted corneal cross-linking seems to optimize CXL oxidative reaction by higher superoxide anion release, improving DLD by a factor of 20%, without adverse events for corneal endothelium.

scholarly journals PyConvU-Net: a lightweight and multiscale network for biomedical image segmentation

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Changyong Li ◽  
Yongxian Fan ◽  
Xiaodong Cai
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
State Of The Art ◽  
Experimental Results ◽  
Actual Situation ◽  
Controlled Experiments ◽  
Biomedical Image ◽  
Segmentation Methods ◽  
Art Performance

Abstract Background With the development of deep learning (DL), more and more methods based on deep learning are proposed and achieve state-of-the-art performance in biomedical image segmentation. However, these methods are usually complex and require the support of powerful computing resources. According to the actual situation, it is impractical that we use huge computing resources in clinical situations. Thus, it is significant to develop accurate DL based biomedical image segmentation methods which depend on resources-constraint computing. Results A lightweight and multiscale network called PyConvU-Net is proposed to potentially work with low-resources computing. Through strictly controlled experiments, PyConvU-Net predictions have a good performance on three biomedical image segmentation tasks with the fewest parameters. Conclusions Our experimental results preliminarily demonstrate the potential of proposed PyConvU-Net in biomedical image segmentation with resources-constraint computing.

scholarly journals A NOVEL IMAGE SEGMENTATION APPROACH BASED ON NEUTROSOPHIC SET AND IMPROVED FUZZY C-MEANS ALGORITHM

2011 ◽  
Vol 07 (01) ◽  
pp. 155-171 ◽  
Author(s):  
H. D. CHENG ◽  
YANHUI GUO ◽  
YINGTAO ZHANG
Keyword(s):  
Image Segmentation ◽  
Point Of View ◽  
Neutrosophic Set ◽  
Convergence Criterion ◽  
Complex Objects ◽  
Fuzzy C Means ◽  
Segmentation Methods ◽  
Segmentation Algorithms ◽  
Segmentation Approach ◽  
Fuzzy C Means Algorithm

Image segmentation is an important component in image processing, pattern recognition and computer vision. Many segmentation algorithms have been proposed. However, segmentation methods for both noisy and noise-free images have not been studied in much detail. Neutrosophic set (NS), a part of neutrosophy theory, studies the origin, nature, and scope of neutralities, as well as their interaction with different ideational spectra. However, neutrosophic set needs to be specified and clarified from a technical point of view for a given application or field to demonstrate its usefulness. In this paper, we apply neutrosophic set and define some operations. Neutrosphic set is integrated with an improved fuzzy c-means method and employed for image segmentation. A new operation, α-mean operation, is proposed to reduce the set indeterminacy. An improved fuzzy c-means (IFCM) is proposed based on neutrosophic set. The computation of membership and the convergence criterion of clustering are redefined accordingly. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can segment images accurately and effectively. Especially, it can segment the clean images and the images having different gray levels and complex objects, which is the most difficult task for image segmentation.

A Survey on Solar Image Segmentation Techniques

2014 ◽  
Vol 945-949 ◽  
pp. 1899-1902
Author(s):  
Yuan Yuan Fan ◽  
Wei Jiang Li ◽  
Feng Wang
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Image Analysis ◽  
Image Segmentation ◽  
Image Retrieval ◽  
Fundamental Issue ◽  
Solar Image ◽  
Segmentation Methods

Image segmentation is one of the basic problems of image processing, also is the first essential and fundamental issue in the solar image analysis and pattern recognition. This paper summarizes systematically on the image segmentation techniques in the solar image retrieval and the recent applications of image segmentation. Then the merits and demerits of each method are discussed in this paper, in this way we can combine some methods for image segmentation to reach the better effects in astronomy. Finally, according to the characteristics of the solar image itself, the more appropriate image segmentation methods are summed up, and some remarks on the prospects and development of image segmentation are presented.

Image Segmentation Using Rough Set Theory

2014 ◽  
Vol 1 (2) ◽  
pp. 62-74 ◽  
Author(s):  
Payel Roy ◽  
Srijan Goswami ◽  
Sayan Chakraborty ◽  
Ahmad Taher Azar ◽  
Nilanjan Dey
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Gray Level ◽  
Rule Generation ◽  
Local Minima ◽  
Fuzzy Correlation ◽  
Segmentation Methods

In the domain of image processing, image segmentation has become one of the key application that is involved in most of the image based operations. Image segmentation refers to the process of breaking or partitioning any image. Although, like several image processing operations, image segmentation also faces some problems and issues when segmenting process becomes much more complicated. Previously lot of work has proved that Rough-set theory can be a useful method to overcome such complications during image segmentation. The Rough-set theory helps in very fast convergence and in avoiding local minima problem, thereby enhancing the performance of the EM, better result can be achieved. During rough-set-theoretic rule generation, each band is individualized by using the fuzzy-correlation-based gray-level thresholding. Therefore, use of Rough-set in image segmentation can be very useful. In this paper, a summary of all previous Rough-set based image segmentation methods are described in detail and also categorized accordingly. Rough-set based image segmentation provides a stable and better framework for image segmentation.

scholarly journals Infarcted Left Ventricles Have Stiffer Material Properties and Lower Stiffness Variation: Three-Dimensional Echo-Based Modeling to Quantify In Vivo Ventricle Material Properties

2015 ◽  
Vol 137 (8) ◽  
Author(s):  
Longling Fan ◽  
Jing Yao ◽  
Chun Yang ◽  
Dalin Tang ◽  
Di Xu
Keyword(s):  
Wall Thickness ◽  
Material Properties ◽  
Strain Curve ◽  
Stress And Strain ◽  
Stress Strain ◽  
Material Stiffness ◽  
The Mean ◽  
Lv Volume ◽  
Parameter Values

Methods to quantify ventricle material properties noninvasively using in vivo data are of great important in clinical applications. An ultrasound echo-based computational modeling approach was proposed to quantify left ventricle (LV) material properties, curvature, and stress/strain conditions and find differences between normal LV and LV with infarct. Echo image data were acquired from five patients with myocardial infarction (I-Group) and five healthy volunteers as control (H-Group). Finite element models were constructed to obtain ventricle stress and strain conditions. Material stiffening and softening were used to model ventricle active contraction and relaxation. Systolic and diastolic material parameter values were obtained by adjusting the models to match echo volume data. Young's modulus (YM) value was obtained for each material stress–strain curve for easy comparison. LV wall thickness, circumferential and longitudinal curvatures (C- and L-curvature), material parameter values, and stress/strain values were recorded for analysis. Using the mean value of H-Group as the base value, at end-diastole, I-Group mean YM value for the fiber direction stress–strain curve was 54% stiffer than that of H-Group (136.24 kPa versus 88.68 kPa). At end-systole, the mean YM values from the two groups were similar (175.84 kPa versus 200.2 kPa). More interestingly, H-Group end-systole mean YM was 126% higher that its end-diastole value, while I-Group end-systole mean YM was only 29% higher that its end-diastole value. This indicated that H-Group had much greater systole–diastole material stiffness variations. At beginning-of-ejection (BE), LV ejection fraction (LVEF) showed positive correlation with C-curvature, stress, and strain, and negative correlation with LV volume, respectively. At beginning-of-filling (BF), LVEF showed positive correlation with C-curvature and strain, but negative correlation with stress and LV volume, respectively. Using averaged values of two groups at BE, I-Group stress, strain, and wall thickness were 32%, 29%, and 18% lower (thinner), respectively, compared to those of H-Group. L-curvature from I-Group was 61% higher than that from H-Group. Difference in C-curvature between the two groups was not statistically significant. Our results indicated that our modeling approach has the potential to determine in vivo ventricle material properties, which in turn could lead to methods to infer presence of infarct from LV contractibility and material stiffness variations. Quantitative differences in LV volume, curvatures, stress, strain, and wall thickness between the two groups were provided.

Sign in / Sign up

Export Citation Format

Share Document