scholarly journals Image Features Based on Characteristic Curves and Local Binary Patterns for Automated HER2 Scoring

2017 ◽  
Author(s):  
Ramakrishnan Mukundan
Keyword(s):  
Characteristic Curve ◽  
Intraclass Correlation ◽  
Smooth Curve ◽  
Local Binary Patterns ◽  
Image Features ◽  
Classification Algorithms ◽  
Automated Scoring ◽  
Feature Descriptors ◽  
Whole Slide Images

This paper presents novel feature descriptors and classification algorithms for automated scoring of HER2 in Whole Slide Images (WSI) of breast cancer histology slides. Since a large amount of processing is involved in analyzing WSI images, the primary design goal has been to keep the computational complexity to the minimum possible level and to use simple, yet robust feature descriptors that can provide accurate classification of the slides. We propose two types of feature descriptors that encode important information about staining patterns and the percentage of staining present in ImmunoHistoChemistry (IHC) stained slides. The first descriptor is called a characteristic curve which is a smooth non-increasing curve that represents the variation of percentage of staining with saturation levels. The second new descriptor introduced in this paper is an LBP feature curve which is also a non-increasing smooth curve that represents the local texture of the staining patterns. Both descriptors show excellent interclass variance and intraclass correlation, and are suitable for the design of automatic HER2 classification algorithms. This paper gives the detailed theoretical aspects of the feature descriptors and also provides experimental results and comparative analysis.

scholarly journals Pleasant/Unpleasant Filtering for Affective Image Retrieval Based on Cross-Correlation of EEG Features

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Keranmu Xielifuguli ◽  
Akira Fujisawa ◽  
Yusuke Kusumoto ◽  
Kazuyuki Matsumoto ◽  
Kenji Kita
Keyword(s):  
Cross Correlation ◽  
Local Binary Patterns ◽  
Image Features ◽  
Entropy Method ◽  
Biological Information ◽  
Linear Regression Method ◽  
Similarity Retrieval ◽  
Classification Of Images ◽  
Biological Information Processing

People often make decisions based on sensitivity rather than rationality. In the field of biological information processing, methods are available for analyzing biological information directly based on electroencephalogram: EEG to determine the pleasant/unpleasant reactions of users. In this study, we propose a sensitivity filtering technique for discriminating preferences (pleasant/unpleasant) for images using a sensitivity image filtering system based on EEG. Using a set of images retrieved by similarity retrieval, we perform the sensitivity-based pleasant/unpleasant classification of images based on the affective features extracted from images with the maximum entropy method: MEM. In the present study, the affective features comprised cross-correlation features obtained from EEGs produced when an individual observed an image. However, it is difficult to measure the EEG when a subject visualizes an unknown image. Thus, we propose a solution where a linear regression method based on canonical correlation is used to estimate the cross-correlation features from image features. Experiments were conducted to evaluate the validity of sensitivity filtering compared with image similarity retrieval methods based on image features. We found that sensitivity filtering using color correlograms was suitable for the classification of preferred images, while sensitivity filtering using local binary patterns was suitable for the classification of unpleasant images. Moreover, sensitivity filtering using local binary patterns for unpleasant images had a 90% success rate. Thus, we conclude that the proposed method is efficient for filtering unpleasant images.

scholarly journals Detection of Early Signs of Diabetic Retinopathy Based on Textural and Morphological Information in Fundus Images

Sensors ◽  
2020 ◽  
Vol 20 (4) ◽  
pp. 1005 ◽  
Author(s):  
Adrián Colomer ◽  
Jorge Igual ◽  
Valery Naranjo
Keyword(s):  
Diabetic Retinopathy ◽  
Large Degree ◽  
Local Binary Patterns ◽  
Classification Algorithms ◽  
Lesion Segmentation ◽  
Retinal Tissue ◽  
Image Descriptors ◽  
Map Generation ◽  
Novel Algorithms

Estimated blind people in the world will exceed 40 million by 2025. To develop novel algorithms based on fundus image descriptors that allow the automatic classification of retinal tissue into healthy and pathological in early stages is necessary. In this paper, we focus on one of the most common pathologies in the current society: diabetic retinopathy. The proposed method avoids the necessity of lesion segmentation or candidate map generation before the classification stage. Local binary patterns and granulometric profiles are locally computed to extract texture and morphological information from retinal images. Different combinations of this information feed classification algorithms to optimally discriminate bright and dark lesions from healthy tissues. Through several experiments, the ability of the proposed system to identify diabetic retinopathy signs is validated using different public databases with a large degree of variability and without image exclusion.

scholarly journals Computational Segmentation and Classification of Diabetic Glomerulosclerosis

2019 ◽  
Vol 30 (10) ◽  
pp. 1953-1967 ◽  
Author(s):  
Brandon Ginley ◽  
Brendon Lutnick ◽  
Kuang-Yu Jen ◽  
Agnes B. Fogo ◽  
Sanjay Jain ◽  
...  
Keyword(s):  
Network Architecture ◽  
Periodic Acid ◽  
Image Features ◽  
Clinical Diagnostics ◽  
Diabetic Glomerulosclerosis ◽  
Periodic Acid Schiff ◽  
Visual Classification ◽  
Structural Progression ◽  
Whole Slide Images

BackgroundPathologists use visual classification of glomerular lesions to assess samples from patients with diabetic nephropathy (DN). The results may vary among pathologists. Digital algorithms may reduce this variability and provide more consistent image structure interpretation.MethodsWe developed a digital pipeline to classify renal biopsies from patients with DN. We combined traditional image analysis with modern machine learning to efficiently capture important structures, minimize manual effort and supervision, and enforce biologic prior information onto our model. To computationally quantify glomerular structure despite its complexity, we simplified it to three components consisting of nuclei, capillary lumina and Bowman spaces; and Periodic Acid-Schiff positive structures. We detected glomerular boundaries and nuclei from whole slide images using convolutional neural networks, and the remaining glomerular structures using an unsupervised technique developed expressly for this purpose. We defined a set of digital features which quantify the structural progression of DN, and a recurrent network architecture which processes these features into a classification.ResultsOur digital classification agreed with a senior pathologist whose classifications were used as ground truth with moderate Cohen’s kappa κ = 0.55 and 95% confidence interval [0.50, 0.60]. Two other renal pathologists agreed with the digital classification with κ1 = 0.68, 95% interval [0.50, 0.86] and κ2 = 0.48, 95% interval [0.32, 0.64]. Our results suggest computational approaches are comparable to human visual classification methods, and can offer improved precision in clinical decision workflows. We detected glomerular boundaries from whole slide images with 0.93±0.04 balanced accuracy, glomerular nuclei with 0.94 sensitivity and 0.93 specificity, and glomerular structural components with 0.95 sensitivity and 0.99 specificity.ConclusionsComputationally derived, histologic image features hold significant diagnostic information that may augment clinical diagnostics.

A Study on Multi Class Classification from Breast Cancer Images using Ensemble Network and Transfer Learning

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Classification ◽  
Disease Diagnosis ◽  
Feature Descriptors ◽  
Histopathological Images ◽  
Viable Approach ◽  
Multi Class Classification

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.

Classification of papillary thyroid carcinoma histological images based on deep learning

2021 ◽  
pp. 1-11
Author(s):  
Yaning Liu ◽  
Lin Han ◽  
Hexiang Wang ◽  
Bo Yin
Keyword(s):  
Neural Network ◽  
Differential Diagnosis ◽  
Deep Learning ◽  
Papillary Thyroid Carcinoma ◽  
Thyroid Carcinoma ◽  
Image Features ◽  
Papillary Thyroid ◽  
Histological Image ◽  
Histological Images

Papillary thyroid carcinoma (PTC) is a common carcinoma in thyroid. As many benign thyroid nodules have the papillary structure which could easily be confused with PTC in morphology. Thus, pathologists have to take a lot of time on differential diagnosis of PTC besides personal diagnostic experience and there is no doubt that it is subjective and difficult to obtain consistency among observers. To address this issue, we applied deep learning to the differential diagnosis of PTC and proposed a histological image classification method for PTC based on the Inception Residual convolutional neural network (IRCNN) and support vector machine (SVM). First, in order to expand the dataset and solve the problem of histological image color inconsistency, a pre-processing module was constructed that included color transfer and mirror transform. Then, to alleviate overfitting of the deep learning model, we optimized the convolution neural network by combining Inception Network and Residual Network to extract image features. Finally, the SVM was trained via image features extracted by IRCNN to perform the classification task. Experimental results show effectiveness of the proposed method in the classification of PTC histological images.

Volumetric analysis of subarachnoid hemorrhage: assessment of the reliability of two computerized methods and their comparison with other radiographic scales

2013 ◽  
Vol 118 (1) ◽  
pp. 84-93 ◽  
Author(s):  
Luis Jiménez-Roldán ◽  
Jose F. Alén ◽  
Pedro A. Gómez ◽  
Ramiro D. Lobato ◽  
Ana Ramos ◽  
...  
Keyword(s):  
Subarachnoid Hemorrhage ◽  
Quantitative Methods ◽  
Interobserver Reliability ◽  
Characteristic Curve ◽  
Intraclass Correlation ◽  
Delayed Cerebral Ischemia ◽  
Interobserver Reproducibility ◽  
Poor Outcome ◽  
Bleeding Volume ◽  
Volumetric Measurements

Object There were two main purposes to this study: first, to assess the feasibility and reliability of 2 quantitative methods to assess bleeding volume in patients who suffered spontaneous subarachnoid hemorrhage (SAH), and second, to compare these methods to other qualitative and semiquantitative scales in terms of reliability and accuracy in predicting delayed cerebral ischemia (DCI) and outcome. Methods A prospective series of 150 patients consecutively admitted to the Hospital 12 de Octubre over a 4-year period were included in the study. All of these patients had a diagnosis of SAH, and diagnostic CT was able to be performed in the first 24 hours after the onset of the symptoms. All CT scans were evaluated by 2 independent observers in a blinded fashion, using 2 different quantitative methods to estimate the aneurysmal bleeding volume: region of interest (ROI) volume and the Cavalieri method. The images were also graded using the Fisher scale, modified Fisher scale, Claasen scale, and the semiquantitative Hijdra scale. Weighted κ coefficients were calculated for assessing the interobserver reliability of qualitative scales and the Hijdra scores. For assessing the intermethod and interrater reliability of volumetric measurements, intraclass correlation coefficients (ICCs) were used as well as the methodology proposed by Bland and Altman. Finally, weighted κ coefficients were calculated for the different quartiles of the volumetric measurements to make comparison with qualitative scales easier. Patients surviving more than 48 hours were included in the analysis of DCI predisposing factors and analyzed using the chi-square or the Mann-Whitney U-tests. Logistic regression analysis was used for predicting DCI and outcome in the different quartiles of bleeding volume to obtain adjusted ORs. The diagnostic accuracy of each scale was obtained by calculating the area under the receiver operating characteristic curve (AUC). Results Qualitative scores showed a moderate interobserver reproducibility (weighted κ indexes were always < 0.65), whereas the semiquantitative and quantitative scores had a very strong interobserver reproducibility. Reliability was very high for all quantitative measures as expressed by the ICCs for intermethod and interobserver agreement. Poor outcome and DCI occurred in 49% and 31% of patients, respectively. Larger bleeding volumes were related to a poorer outcome and a higher risk of developing DCI, and the proportion of patients suffering DCI or a poor outcome increased with each quartile, maintaining this relationship after adjusting for the main clinical factors related to outcome. Quantitative analysis of total bleeding volume achieved the highest AUC, and had a greater discriminative ability than the qualitative scales for predicting the development of DCI and outcome. Conclusions The use of quantitative measures may reduce interobserver variability in comparison with categorical scales. These measures are feasible using dedicated software and show a better prognostic capability in relation to outcome and DCI than conventional categorical scales.

Analysing Temporal Effects on Classification of SAR and Optical Images

2021 ◽  
Author(s):  
Ahmet Batuhan Polat ◽  
Ozgun Akcay ◽  
Fusun Balik Sanli
Keyword(s):  
Rural Areas ◽  
Classification Accuracy ◽  
Winter Season ◽  
Support Vector ◽  
Classification Algorithms ◽  
Sar Images ◽  
Optical Images ◽  
Object Based ◽  
Training Samples

&lt;p&gt;Obtaining high accuracy in land cover classification is a non-trivial problem in geosciences for monitoring urban and rural areas. In this study, different classification algorithms were tested with different types of data, and besides the effects of seasonal changes on these classification algorithms and the evaluation of the data used are investigated. In addition, the effect of increasing classification training samples on classification accuracy has been revealed as a result of the study. Sentinel-1 Synthetic Aperture Radar (SAR) images and Sentinel-2 multispectral optical images were used as datasets. Object-based approach was used for the classification of various fused image combinations. The classification algorithms Support Vector Machines (SVM), Random Forest (RF) and K-Nearest Neighborhood (kNN) methods were used for this process. In addition, Normalized Difference Vegetation Index (NDVI) was examined separately to define the exact contribution to the classification accuracy. &amp;#160;As a result, the overall accuracies were compared by classifying the fused data generated by combining optical and SAR images. It has been determined that the increase in the number of training samples improve the classification accuracy. Moreover, it was determined that the object-based classification obtained from single SAR imagery produced the lowest classification accuracy among the used different dataset combinations in this study. In addition, it has been shown that NDVI data does not increase the accuracy of the classification in the winter season as the trees shed their leaves due to climate conditions.&lt;/p&gt;

scholarly journals Machine learning classification of new asteroid families members

2020 ◽  
Author(s):  
Valerio Carruba
Keyword(s):  
Machine Learning ◽  
Family Members ◽  
Classification Algorithms ◽  
New Members ◽  
Machine Learning Classification ◽  
New Family ◽  
Robotic Telescope ◽  
Traditional Approaches ◽  
Asteroid Families

&lt;p&gt;Asteroid families are groups of asteroids that are the product of collisions or of the rotational fission of a parent object. &amp;#160;These groups are mainly identified in proper elements or frequencies domains. &amp;#160; Because of robotic telescope surveys, the number of known asteroids has increased from about 10,000 in the early 90's to more than 750,000 nowadays. Traditional approaches for identifying new members of asteroid families, like the hierarchical clustering method (HCM), may &amp;#160; struggle to keep up with the growing rate of new discoveries. Here we used machine learning classification algorithms to identify new family members based on the orbital distribution in proper (a,e,sin(i)) of previously known family constituents. We compared the outcome of nine classification algorithms from stand alone and ensemble approaches. &amp;#160;The Extremely Randomized Trees (ExtraTree) method had the highest precision, enabling to&amp;#160; retrieve up to 97% of family members identified with standard HCM.&lt;/p&gt;

scholarly journals Machine learning approaches to predict the Plant-associated phenotype of Xanthomonas strains

BMC Genomics ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Dennie te Molder ◽  
Wasin Poncheewin ◽  
Peter J. Schaap ◽  
Jasper J. Koehorst
Keyword(s):  
Machine Learning ◽  
Plant Pathogens ◽  
De Novo ◽  
Classification Algorithms ◽  
Learning Approaches ◽  
Enabling Factors ◽  
Essential Step ◽  
The World ◽  
Genome Content

Abstract Background The genus Xanthomonas has long been considered to consist predominantly of plant pathogens, but over the last decade there has been an increasing number of reports on non-pathogenic and endophytic members. As Xanthomonas species are prevalent pathogens on a wide variety of important crops around the world, there is a need to distinguish between these plant-associated phenotypes. To date a large number of Xanthomonas genomes have been sequenced, which enables the application of machine learning (ML) approaches on the genome content to predict this phenotype. Until now such approaches to the pathogenomics of Xanthomonas strains have been hampered by the fragmentation of information regarding pathogenicity of individual strains over many studies. Unification of this information into a single resource was therefore considered to be an essential step. Results Mining of 39 papers considering both plant-associated phenotypes, allowed for a phenotypic classification of 578 Xanthomonas strains. For 65 plant-pathogenic and 53 non-pathogenic strains the corresponding genomes were available and de novo annotated for the presence of Pfam protein domains used as features to train and compare three ML classification algorithms; CART, Lasso and Random Forest. Conclusion The literature resource in combination with recursive feature extraction used in the ML classification algorithms provided further insights into the virulence enabling factors, but also highlighted domains linked to traits not present in pathogenic strains.

Sign in / Sign up

Export Citation Format

Share Document