scholarly journals NSCR-Based DenseNet for Lung Tumor Recognition Using Chest CT Image

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Zhou Tao ◽  
Huo Bingqiang ◽  
Lu Huiling ◽  
Yang Zaoli ◽  
Shi Hongbin
Keyword(s):  
Lung Tumor ◽  
Coefficient Matrix ◽  
Chest Ct ◽  
Collaborative Representation ◽  
Ct Image ◽  
Evaluation Indexes ◽  
Specificity And Sensitivity ◽  
Tumor Recognition ◽  
Medical Analysis

Nonnegative sparse representation has become a popular methodology in medical analysis and diagnosis in recent years. In order to resolve network degradation, higher dimensionality in feature extraction, data redundancy, and other issues faced when medical images parameters are trained using convolutional neural networks. Lung tumors in chest CT image based on nonnegative, sparse, and collaborative representation classification of DenseNet (DenseNet-NSCR) are proposed by this paper: firstly, initialization parameters of pretrained DenseNet model using transfer learning; secondly, training DenseNet using CT images to extract feature vectors for the full connectivity layer; thirdly, a nonnegative, sparse, and collaborative representation (NSCR) is used to represent the feature vector and solve the coding coefficient matrix; fourthly, the residual similarity is used for classification. The experimental results show that the DenseNet-NSCR classification is better than the other models, and the various evaluation indexes such as specificity and sensitivity are also high, and the method has better robustness and generalization ability through comparison experiment using AlexNet, GoogleNet, and DenseNet-201 models.

scholarly journals Classification of COVID-19 by Compressed Chest CT Image through Deep Learning on a Large Patients Cohort

2021 ◽  
Vol 13 (1) ◽  
pp. 73-82
Author(s):  
Ziwei Zhu ◽  
Zhang Xingming ◽  
Guihua Tao ◽  
Tingting Dan ◽  
Jiao Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Chest Ct ◽  
Ct Image

scholarly journals Segmentation of infected region in CT images of COVID-19 patients based on QC-HC U-net

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Qin Zhang ◽  
Xiaoqiang Ren ◽  
Benzheng Wei
Keyword(s):  
Network Structure ◽  
Lung Tumor ◽  
Experimental Results ◽  
Training Effect ◽  
Insufficient Data ◽  
Ct Image ◽  
Specificity And Sensitivity ◽  
Medical Institutions ◽  
Rapid Spread ◽  
Infected Area

AbstractSince the outbreak of COVID-19 in 2019, the rapid spread of the epidemic has brought huge challenges to medical institutions. If the pathological region in the COVID-19 CT image can be automatically segmented, it will help doctors quickly determine the patient’s infection, thereby speeding up the diagnosis process. To be able to automatically segment the infected area, we proposed a new network structure and named QC-HC U-Net. First, we combine residual connection and dense connection to form a new connection method and apply it to the encoder and the decoder. Second, we choose to add Hypercolumns in the decoder section. Compared with the benchmark 3D U-Net, the improved network can effectively avoid vanishing gradient while extracting more features. To improve the situation of insufficient data, resampling and data enhancement methods are selected in this paper to expand the datasets. We used 63 cases of MSD lung tumor data for training and testing, continuously verified to ensure the training effect of this model, and then selected 20 cases of public COVID-19 data for training and testing. Experimental results showed that in the segmentation of COVID-19, the specificity and sensitivity were 85.3% and 83.6%, respectively, and in the segmentation of MSD lung tumors, the specificity and sensitivity were 81.45% and 80.93%, respectively, without any fitting.

scholarly journals Classification of Malignant Melanoma and Benign Lung Cancer by using Deep Learning Based Neural Network

2020 ◽  
Vol 9 (3) ◽  
pp. 2958-2963
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Malignant Melanoma ◽  
Lung Tumor ◽  
Classification Methods ◽  
Border Detection ◽  
The Neural Network ◽  
Tumor Recognition ◽  
Cancer Lesion

Humanoid Tumor is one of the utmost hazardous syndromes which is mostly affected by heritable uncertainty of manifold molecular modifications. Midst numerous methods of humanoid tumor, Lung cancer is the utmost communal one. To classify Lung cancer at an initial phase and examine them over several procedures entitled as segmentation and feature extraction. Here, in this scheme is suggested to emphasis extraordinary attentiveness of Melanoma Heir which bases the Lung Cancer. This development is based on samples replica skill is used for malignant melanoma Lung tumor recognition. In this scheme dissimilar stage for melanoma Lung cancer lesion classification i.e., first the Image Gaining Method, preprocessing, separation, define piece for Lung cancer Feature Collection regulates lesion description, classification methods. In the Feature abstraction by numerical image treating method includes, regularity detection, Border Detection, color, and width discovery and also we used GLCM for excerpt the surface based features. Here we planned the Neural Network to categorize the benign or malignant stage.

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

An effective technique for diabetic retinopathy using hybrid machine learning technique

2021 ◽  
pp. 096228022098354
Author(s):  
N Satyanarayana Murthy ◽  
B Arunadevi
Keyword(s):  
Diabetic Retinopathy ◽  
Short Term Memory ◽  
Early Recognition ◽  
Hybrid Techniques ◽  
Specificity And Sensitivity ◽  
Retinal Blood Vessels ◽  
Segmented Images ◽  
Fuzzy C Means Clustering ◽  
Working Region

Diabetic retinopathy (DR) stays as an eye issue that has continuously developed in individuals who experienced diabetes. The complexities in diabetes cause harm to the vein at the back of the retina. In outrageous cases, DR could swift apparition disaster or visual impairment. This genuine impact had the option to charge through convenient treatment and early recognition. As of late, this issue has been spreading quickly, particularly in the working region, which in the end constrained the interest of an analysis of this disease from the most prompt stage. Therefore, that are castoff to protect the progressions of this disorder, revealing of the retinal blood vessels (RBVs) play a foremost role. The growth of an abnormal vessel leads to the development steps of DR, where it can be well known by extracting the RBV. The recognition of the BV for DR by developing an automatic approach is a major aim of our research study. In the proposed method, there are two major steps: one is segmentation and the second one is classification of affected retinal BV. The proposed method uses the Kinetic Gas Molecule Optimization based on centroid initialization used for the Fuzzy C-means Clustering. In the classification step, those segmented images are given as input to hybrid techniques such as a convolution neural network with bidirectional-long short-term memory (CNN with Bi-LSTM). The learning degree of Bi-LSTM is revised by using the self-attention mechanism for refining the classification accuracy. The trial consequences disclosed that the mixture algorithm achieved higher accuracy, specificity, and sensitivity than existing techniques.

scholarly journals An Ensemble Feature Selection Approach to Identify Relevant Features from EEG Signals

2021 ◽  
Vol 11 (15) ◽  
pp. 6983
Author(s):  
Maritza Mera-Gaona ◽  
Diego M. López ◽  
Rubiel Vargas-Canas
Keyword(s):  
Feature Selection ◽  
Sensitivity And Specificity ◽  
Eeg Signals ◽  
Specificity And Sensitivity ◽  
Selection Approach ◽  
Feature Selection Approach ◽  
The Stability ◽  
Selection Algorithms ◽  
Epileptiform Events

Identifying relevant data to support the automatic analysis of electroencephalograms (EEG) has become a challenge. Although there are many proposals to support the diagnosis of neurological pathologies, the current challenge is to improve the reliability of the tools to classify or detect abnormalities. In this study, we used an ensemble feature selection approach to integrate the advantages of several feature selection algorithms to improve the identification of the characteristics with high power of differentiation in the classification of normal and abnormal EEG signals. Discrimination was evaluated using several classifiers, i.e., decision tree, logistic regression, random forest, and Support Vecctor Machine (SVM); furthermore, performance was assessed by accuracy, specificity, and sensitivity metrics. The evaluation results showed that Ensemble Feature Selection (EFS) is a helpful tool to select relevant features from the EEGs. Thus, the stability calculated for the EFS method proposed was almost perfect in most of the cases evaluated. Moreover, the assessed classifiers evidenced that the models improved in performance when trained with the EFS approach’s features. In addition, the classifier of epileptiform events built using the features selected by the EFS method achieved an accuracy, sensitivity, and specificity of 97.64%, 96.78%, and 97.95%, respectively; finally, the stability of the EFS method evidenced a reliable subset of relevant features. Moreover, the accuracy, sensitivity, and specificity of the EEG detector are equal to or greater than the values reported in the literature.

scholarly journals Adaptive Iterative Dose Reduction Using Three Dimensional Processing (AIDR3D) Improves Chest CT Image Quality and Reduces Radiation Exposure

PLoS ONE ◽  
2014 ◽  
Vol 9 (8) ◽  
pp. e105735 ◽  
Author(s):  
Tsuneo Yamashiro ◽  
Tetsuhiro Miyara ◽  
Osamu Honda ◽  
Hisashi Kamiya ◽  
Kiyoshi Murata ◽  
...  
Keyword(s):  
Image Quality ◽  
Radiation Exposure ◽  
Dose Reduction ◽  
Three Dimensional ◽  
Chest Ct ◽  
Ct Image ◽  
Ct Image Quality ◽  
Dimensional Processing

Intelligent Classification of Cocoa Bean using E-nose

Mekatronika ◽  
2020 ◽  
Vol 2 (2) ◽  
pp. 28-35
Author(s):  
Nur Amanda Nazli ◽  
Muhammad Sharfi Najib ◽  
Suhaimi Mohd Daud ◽  
Mujahid Mohammad
Keyword(s):  
Electronic Nose ◽  
Chemical Sensors ◽  
Classification Accuracy ◽  
Electronic Device ◽  
Raw Material ◽  
Cocoa Bean ◽  
Cocoa Beans ◽  
Microsoft Excel ◽  
Specificity And Sensitivity

Cocoa bean (Theobrama cacao) is an essential raw material in the manufacture of chocolate, and their classification is crucial for the synthesis of good chocolate flavour. Cocoa beans appear to be very similar to one another when visualised. Hence, an electronic device named the electronic nose (E-Nose) is used to classify the odor of cocoa beans to give the best cocoa bean quality. E-nose is a set of an array of chemical sensors used to sense the gas vapours produced by the cocoa bean and the raw data collected was kept in Microsoft Excel, and the classification took place in Octave. They then underwent normalisation technique to increase classification accuracy, and their features were extracted using mean calculation. The features were classified using CBR, and the similarity value is obtained. The results show that CBR's classification accuracy, specificity and sensitivity are all 100%.

Sign in / Sign up

Export Citation Format

Share Document