A Proposal to Differentiate Homogenous and Speckled Shapes in Indirect Immunofluorescence Images Using Neutrosophic Sets
17 Oct 2019-
TL;DR: An attempt to differentiate Homogeneous and Speckled shapes in IIF images using Neutrosophic Sets (NS) segmentation and a neural network-based classification is performed, showing that the indeterminacy of NS is able to segment cell edges.
Abstract: Automated analysis of Indirect Immunofluorescence images is significant in the computerized detection of Autoimmune Diseases (AIDs). The recognition of particular shapes in Indirect Immunofluorescence (IIF) images is clinically associated with specific AIDs. In this work, an attempt to differentiate Homogeneous and Speckled shapes in IIF images using Neutrosophic Sets (NS) segmentation and a neural network-based classification is performed. The characteristics of NS to handle the edge boundary information of the cells is utilized. The IIF specimen images belonging to the two shapes are obtained from the public dataset. The images are subjected to illumination correction using Top-Hat transform, denoising by Split Bregman Anisotropic Total Variation and contrast enhancement with image normalization. Segmentation of cell boundaries is performed using indeterminate subset of NS. Geometric features are extracted from cell edges to assess its morphology. Multilayer Perceptron (MLP) network is employed to classify the two patterns. Results show that the indeterminacy of NS is able to segment cell edges. The geometric features are obtained to be statistically highly significant (p
References
More filters
TL;DR: This paper proposes a “split Bregman” method, which can solve a very broad class of L1-regularized problems, and applies this technique to the Rudin-Osher-Fatemi functional for image denoising and to a compressed sensing problem that arises in magnetic resonance imaging.
Abstract: The class of L1-regularized optimization problems has received much attention recently because of the introduction of “compressed sensing,” which allows images and signals to be reconstructed from small amounts of data. Despite this recent attention, many L1-regularized problems still remain difficult to solve, or require techniques that are very problem-specific. In this paper, we show that Bregman iteration can be used to solve a wide variety of constrained optimization problems. Using this technique, we propose a “split Bregman” method, which can solve a very broad class of L1-regularized problems. We apply this technique to the Rudin-Osher-Fatemi functional for image denoising and to a compressed sensing problem that arises in magnetic resonance imaging.
4,255 citations
"A Proposal to Differentiate Homogen..." refers methods in this paper
...version of Anisotropic TV (SB-ATV) has been employed to speed up the computation and avoid numerical instabilities [18]....
[...]
...SB technique is used to solve this regularization problem as it is computationally faster and extremely efficient [17] [18]....
[...]
TL;DR: The standard deviation is a valid measure of variability regardless of the distribution, and is used as an estimate of the variability of the population from which the sample was drawn.
Abstract: The terms “standard error” and “standard deviation” are often confused.1 The contrast between these two terms reflects the important distinction between data description and inference, one that all researchers should appreciate.
The standard deviation (often SD) is a measure of variability. When we calculate the standard deviation of a sample, we are using it as an estimate of the variability of the population from which the sample was drawn. For data with a normal distribution,2 about 95% of individuals will have values within 2 standard deviations of the mean, the other 5% being equally scattered above and below these limits. Contrary to popular misconception, the standard deviation is a valid measure of variability regardless of the distribution. About 95% of observations of any distribution usually fall within the 2 standard …
555 citations
"A Proposal to Differentiate Homogen..." refers background in this paper
...95% values that lie within the range of two standard deviations (SD) of the mean for each feature set is calculated [33]....
[...]
01 Jan 2010
TL;DR: The authors generalizes the intuitionistic fuzzy set (IFSFS), paraconsistent set, and intuitionistic set to the neutrosophic set (NS), and distinguishes between NS and IFS.
Abstract: In this paper one generalizes the intuitionistic fuzzy set (IFS), paraconsistent set, and intuitionistic set to the neutrosophic set (NS). Many examples are presented. Distinctions between NS and IFS are underlined.
551 citations
TL;DR: The first edition of the HEp-2 Cells Classification contest aimed to bring together researchers interested in the performance evaluation of algorithms for IIF image analysis and evaluated 28 different recognition systems able to automatically recognize the staining pattern of cells within IIF images.
Abstract: In this paper, we report on the first edition of the HEp-2 Cells Classification contest, held at the 2012 edition of the International Conference on Pattern Recognition, and focused on indirect immunofluorescence (IIF) image analysis. The IIF methodology is used to detect autoimmune diseases by searching for antibodies in the patient serum but, unfortunately, it is still a subjective method that depends too heavily on the experience and expertise of the physician. This has been the motivation behind the recent initial developments of computer aided diagnosis systems in this field. The contest aimed to bring together researchers interested in the performance evaluation of algorithms for IIF image analysis: 28 different recognition systems able to automatically recognize the staining pattern of cells within IIF images were tested on the same undisclosed dataset. In particular, the dataset takes into account the six staining patterns that occur most frequently in the daily diagnostic practice: centromere, nucleolar, homogeneous, fine speckled, coarse speckled, and cytoplasmic. In the paper, we briefly describe all the submitted methods, analyze the obtained results, and discuss the design choices conditioning the performance of each method.
229 citations
"A Proposal to Differentiate Homogen..." refers background or methods in this paper
...Numerous classifiers such as neural nets, Naïve Bayes, Support Vector Machine (SVM) and decision trees have been employed for IIF pattern recognition [3] [4] [8] [30] [31]....
[...]
...Several studies report the disagreement between the two patterns since they possess shape similarities and their nuclei boundaries are reported to be erroneously identified [3] [8] [9]....
[...]
TL;DR: The ICAP consensus is presented on the clinical relevance of the 29 distinct HEp-2 IIFA patterns: this clinical relevance is primarily defined within the context of the suspected disease and includes recommendations for follow-up testing.
Abstract: The indirect immunofluorescence assay (IIFA) on HEp-2 cells is widely used for detection of antinuclear antibodies (ANA). The dichotomous outcome, negative or positive, is integrated in diagnostic and classification criteria for several systemic autoimmune diseases. However, the HEp-2 IIFA test has much more to offer: besides the titre or fluorescence intensity, it also provides fluorescence pattern(s). The latter include the nucleus and the cytoplasm of interphase cells as well as patterns associated with mitotic cells. The International Consensus on ANA Patterns (ICAP) initiative has previously reached consensus on the nomenclature and definitions of HEp-2 IIFA patterns. In the current paper, the ICAP consensus is presented on the clinical relevance of the 29 distinct HEp-2 IIFA patterns. This clinical relevance is primarily defined within the context of the suspected disease and includes recommendations for follow-up testing. The discussion includes how this information may benefit the clinicians in daily practice and how the knowledge can be used to further improve diagnostic and classification criteria.
199 citations
"A Proposal to Differentiate Homogen..." refers background in this paper
...Homogeneous patterns are indicative of systemic lupus erythematosus, autoimmune hepatitis and rheumatoid arthritis, while speckled patterns clinically reveal polymyositis, neonatal lupus syndrome and scleroderma [7]....
[...]