Meta-heuristic Techniques to train Artificial Neural Networks for Medical Image Classification: A Review

2020 ◽  
Vol 13 ◽  
Author(s):  
Priyanka Jindal ◽  
Dharmender Kumar
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Medical Imaging ◽  
Image Classification ◽  
Medical Image ◽  
The Body ◽  
Clinical Practices ◽  
Heuristic Techniques ◽  
Medical Image Classification ◽  
Artificial Neural

: Medical imaging has been utilized in various forms in clinical applications for better diagnostic and treatment of diseases. These imaging technologies help in recognizing body's ailing region with ease. In addition, it causes no pain to patient as the interior part of the body can be seen without opening too much of the body. Nowadays, various image processing techniques such as segmentation, registration, classification, restoration, contrast enhancement and many more exists to enhance image quality. Among all these techniques, classification plays an important role in computer-aided diagnosis for easy analysis and interpretation of these images. Image classification not only classifies diseases with high accuracy but also finds out which part of the body is infected by the disease. The usage of Neural networks classifier in medical imaging applications opened new doors or opportunities to researchers stirring them to excel in this domain. Moreover, accuracy in clinical practices and development of more sophisticated equipment is necessary in medical field for more accurate and quicker decisions. Therefore, keeping this in mind, researchers started focusing on adding intelligence by using meta-heuristic techniques to classification methods. This paper provides a brief survey on role of artificial neural networks in medical image classification, various types of meta-heuristic algorithms applied for optimization purpose, their hybridization. A comparative analysis showing the effect of applying these algorithms on some classification parameters such as accuracy, sensitivity, specificity is also provided. From the comparison, it can be observed that the usage of these methods significantly optimizes these parameters leading us to diagnosis and treatment of a number of diseases in their early stage.

scholarly journals Artificial Neural Networks for Satellite Image Classification of Shoreline Extraction for Land and Water Classes of the North West Coast of Peninsular Malaysia

2018 ◽  
Vol 24 (2) ◽  
pp. 1382-1387 ◽  
Author(s):  
Syaifulnizam Abd Manaf ◽  
Norwati Mustapha ◽  
Md. Nasir Sulaiman ◽  
Nor Azura Husin ◽  
Mohd Radzi Abdul Hamid
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Image Classification ◽  
West Coast ◽  
Satellite Image ◽  
Peninsular Malaysia ◽  
North West ◽  
The North ◽  
Artificial Neural

scholarly journals Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks with Transfer Learning

2021 ◽  
Author(s):  
Akinori Minagi ◽  
Hokuto Hirano ◽  
Kazuhiro Takemoto
Keyword(s):  
Neural Networks ◽  
Image Classification ◽  
Transfer Learning ◽  
Medical Image ◽  
Deep Neural Networks ◽  
Disease Diagnosis ◽  
Natural Images ◽  
Fine Tuning ◽  
Security And Privacy ◽  
Medical Image Classification

Abstract Transfer learning from natural images is well used in deep neural networks (DNNs) for medical image classification to achieve computer-aided clinical diagnosis. Although the adversarial vulnerability of DNNs hinders practical applications owing to the high stakes of diagnosis, adversarial attacks are expected to be limited because training data — which are often required for adversarial attacks — are generally unavailable in terms of security and privacy preservation. Nevertheless, we hypothesized that adversarial attacks are also possible using natural images because pre-trained models do not change significantly after fine-tuning. We focused on three representative DNN-based medical image classification tasks (i.e., skin cancer, referable diabetic retinopathy, and pneumonia classifications) and investigated whether medical DNN models with transfer learning are vulnerable to universal adversarial perturbations (UAPs), generated using natural images. UAPs from natural images are useful for both non-targeted and targeted attacks. The performance of UAPs from natural images was significantly higher than that of random controls, although slightly lower than that of UAPs from training images. Vulnerability to UAPs from natural images was observed between different natural image datasets and between different model architectures. The use of transfer learning causes a security hole, which decreases the reliability and safety of computer-based disease diagnosis. Model training from random initialization (without transfer learning) reduced the performance of UAPs from natural images; however, it did not completely avoid vulnerability to UAPs. The vulnerability of UAPs from natural images will become a remarkable security threat.

scholarly journals Reconstruction of Depolarization Pattern in Myocardial Infarction Cases Using Two Cascaded Stages of Artificial Neural Networks

2021 ◽  
Vol 2128 (1) ◽  
pp. 012016
Author(s):  
Nihal A. Mabrouk ◽  
Abdelreheem M. Khalifa ◽  
Abdelmenem A. Nasser ◽  
Moustafa H. Aly
Keyword(s):  
Myocardial Infarction ◽  
Neural Networks ◽  
Inverse Problem ◽  
Artificial Neural Networks ◽  
Electrical Activity ◽  
Heart Diseases ◽  
Three Dimensional ◽  
The Body ◽  
Forward Model ◽  
Artificial Neural

Abstract Our paper introduces a new technique for diagnosis of various heart diseases without the need of highly experts to investigate the electrocardiogram (ECG). Using the same electrodes of the ECG machine, it will be able to transmit directly the electrical activity inside the heart to a moving picture. Our technique is based on artificial intelligence algorithm using artificial neural networks (ANN). Finding the trans-membrane potential (TMP) inside the heart from the body surface potential (BSP) is known as the inverse problem of ECG. To have a unique solution for the inverse problem the data used should be obtained from a forward model. A three dimensional (3-D) model of cellular activation whole heart embedded in torso is simulated and solved using COMSOL Multiphysics software. In our previous paper, one ANN succeeded in displaying the wave propagation on the surface of a normal heart. In this paper, we used a configuration of ANNs to display different cases of heart with myocardial infarction (MI). To check the system accuracy, eight MI cases with different sizes and locations in the heart are simulated in the forward model. This configuration proved to be highly accurate in displaying each MI case -size and location- presenting the infarction as an area with no electrical activity.

scholarly journals Image Classification Using Artificial Neural Networks

2020 ◽  
Author(s):  
Dian Ade Kurnia
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Image Classification ◽  
Activation Function ◽  
Process Information ◽  
Artificial Neuron ◽  
Artificial Neural

Artificial neural networks use the same analogy, and process information using artificial neurons.Information is transferred from one artificial neuron to another, which finally leads to an activation function, which acts like a brain and makes a decision

Sign in / Sign up

Export Citation Format

Share Document