scholarly journals CLASSIFICATION OF MEDICAL IMAGES USING MACHINE LEARNING

10.6036/10117 ◽  
2022 ◽  
Vol 97 (1) ◽  
pp. 35-38
Author(s):  
EDUARDO PEREZ CARETA ◽  
RAFAEL GUZMÁN SEPÚLVEDA ◽  
JOSE MERCED LOZANO GARCIA ◽  
MIGUEL TORRES CISNEROS ◽  
RAFAEL GUZMAN CABRERA
Keyword(s):  
Neural Network ◽  
Medical Diagnosis ◽  
Cross Validation ◽  
Support Vector ◽  
Computational Tools ◽  
Standard Methods ◽  
Vector Machines ◽  
Test Sets ◽  
Classification Of Images

The popularity of the use of computational tools such as artificial intelligence has been increasing in recent years, and its importance in medicine is a fact. This field has benefited greatly thanks to the incorporation of more effective and faster methodologies in the medical diagnosis and registration processes. In the present work, the classification of images related to three diseases: Tuberculosis, Glaucoma and Parkinson's is carried out. We used deep learning and the RESNET50 convolutional neural network to extract classification characteristics, and then perform the classification based on standard methods, such as support vector machines, Naïve Bayes, and Centroid-based classifier, which are incorporated into two scenarios (cross validation; training and test sets). The classifier's performance is evaluated quantitatively using three evaluation metrics. The results obtained support the feasibility of the proposed methodology and its potential to improve medical diagnosis.

scholarly journals SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING NEURAL NETWORK ALGORITHM AND HIERARCHICAL SEGMENTATION

2019 ◽  
Vol XLII-2/W12 ◽  
pp. 1-5
Author(s):  
D. Akbari ◽  
M. Moradizadeh ◽  
M. Akbari
Keyword(s):  
Neural Network ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Support Vector ◽  
Washington Dc ◽  
Hierarchical Segmentation ◽  
Vector Machines ◽  
Neural Network Algorithm ◽  
New Framework

<p><strong>Abstract.</strong> This paper describes a new framework for classification of hyperspectral images, based on both spectral and spatial information. The spatial information is obtained by an enhanced Marker-based Hierarchical Segmentation (MHS) algorithm. The hyperspectral data is first fed into the Multi-Layer Perceptron (MLP) neural network classification algorithm. Then, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, the markers are extracted from the classification maps obtained by MLP and Support Vector Machines (SVM) classifiers. Experimental results on Washington DC Mall hyperspectral dataset, demonstrate the superiority of proposed approach compared to the MLP and the original MHS algorithms.</p>

scholarly journals Deep Learning and Handcrafted Features for Virus Image Classification

2020 ◽  
Vol 6 (12) ◽  
pp. 143
Author(s):  
Loris Nanni ◽  
Eugenio De Luca ◽  
Marco Ludovico Facin ◽  
Gianluca Maguolo
Keyword(s):  
Neural Network ◽  
Electron Microscopy ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Support Vector ◽  
Transmission Electron ◽  
Vector Machines ◽  
Multiple Support ◽  
Multiple Support Vector Machines

In this work, we present an ensemble of descriptors for the classification of virus images acquired using transmission electron microscopy. We trained multiple support vector machines on different sets of features extracted from the data. We used both handcrafted algorithms and a pretrained deep neural network as feature extractors. The proposed fusion strongly boosts the performance obtained by each stand-alone approach, obtaining state of the art performance.

scholarly journals BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

2016 ◽  
Vol XLI-B7 ◽  
pp. 335-340 ◽  
Author(s):  
F. Pirotti ◽  
F. Sunar ◽  
M. Piragnolo
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Cross Validation ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Learning Methods ◽  
Control Dataset ◽  
Vector Machines ◽  
Sentinel 2

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. <br><br> In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km<sup>2</sup>, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. <br><br> Validation is carried out using three different approaches: (i) using pixels from the training dataset (<i>train</i>), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (<i>kfold</i>) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (<i>full</i>) and with k-fold cross-validation (<i>kfold</i>) with ten folds. Results from validation of predictions of the whole dataset (<i>full</i>) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

scholarly journals BENCHMARK OF MACHINE LEARNING METHODS FOR CLASSIFICATION OF A SENTINEL-2 IMAGE

2016 ◽  
Vol XLI-B7 ◽  
pp. 335-340 ◽  
Author(s):  
F. Pirotti ◽  
F. Sunar ◽  
M. Piragnolo
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Cross Validation ◽  
Training Dataset ◽  
Support Vector ◽  
Machine Learning Methods ◽  
Control Dataset ◽  
Vector Machines ◽  
Sentinel 2

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. &lt;br&gt;&lt;br&gt; In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km&lt;sup&gt;2&lt;/sup&gt;, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. &lt;br&gt;&lt;br&gt; Validation is carried out using three different approaches: (i) using pixels from the training dataset (&lt;i&gt;train&lt;/i&gt;), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (&lt;i&gt;kfold&lt;/i&gt;) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (&lt;i&gt;full&lt;/i&gt;) and with k-fold cross-validation (&lt;i&gt;kfold&lt;/i&gt;) with ten folds. Results from validation of predictions of the whole dataset (&lt;i&gt;full&lt;/i&gt;) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

scholarly journals Classification of Healthy and Rot Leaves of Apple using Gradient Boosting and Support Vector Classifier

2019 ◽  
Vol 8 (12) ◽  
pp. 2868-2872
Keyword(s):  
Neural Network ◽  
Confusion Matrix ◽  
Gradient Boosting ◽  
Support Vector ◽  
Diseased Leaf ◽  
Support Vector Classifier ◽  
Novel Approach ◽  
Good Scale ◽  
Classification Of Images

Conventional Techniques Such As Convolutional Neural Network (Cnn), Deep Neural Network Have Shown Its Own Footprints In The Field Of Image Classification With Promising Results. In The Past Decades, Classification Of Images Has Been Done With Varying Features Like Shape, Texture Etc. In This Paper, A Novel Approach Is Used To Classify The Leaf Images And Determine The Health And The Diseased Leaf. The Image Is Preprocessed By Extracting The Shape Feature And Classified The Leaves Of Apple As Healthy And Diseased (Rot Leaves) Using Two Novel Effective Approaches Gradient Boosting And Support Vector Classifier. We Have Collected 1813 Images Of Apple Leaves As Dataset And Out Of These, 70% Of The Data Is Used To Train And Remaining 30% Is Used To Test The Data. Our Algorithm Has Outperformed Other Traditional Techniques With Good Scale Of Accuracy(Gradient Boosting-87%, Support Vector Classifier91%). Strong Comparison Of Both Gradient Boosting And Support Vector Is Made And There Is Dominant Show Off Of The Confusion Matrix. Classification Of Healthy And Diseased Leaf Well In Advance Gives Nice Warning To The Producer Thereby Decreasing The Rate Of Diseased.

scholarly journals Automatic Classification of the Ripeness Stage of Mango Fruit Using Machine a Learning Approach

2022 ◽  
Vol 4 (1) ◽  
pp. 32-47
Author(s):  
Denchai Worasawate ◽  
Panarit Sakunasinha ◽  
Surasak Chiangga
Keyword(s):  
Neural Network ◽  
Skin Color ◽  
Human Error ◽  
Cross Validation ◽  
The Other ◽  
Support Vector ◽  
Maturity Stage ◽  
Learning Approach ◽  
Mango Fruit

Most mango farms classify the maturity stage manually by trained workers using external indicators such as size, shape, and skin color, which can lead to human error or inconsistencies. We developed four common machine learning (ML) classifiers, the k-mean, naïve Bayes, support vector machine, and feed-forward artificial neural network (FANN), all of which were aimed at classifying the ripeness stage of mangoes at harvest. The ML classifiers were trained on biochemical data and then tested on physical and electrical data.The performance of the ML models was compared using fourfold cross validation. The FANN classifier performed the best, with a mean accuracy of 89.6% for unripe, ripe, and overripe classes, when compared to the other classifiers.

Sign in / Sign up

Export Citation Format

Share Document