FIGURE 7 - uploaded by Priya Ranjan
Content may be subject to copyright.
Source publication
Similar publications
the chapter deals with various aspects of detecting cervical cancer in developing countries
the use of manual liquid based cytology , cell block with ihc is described with examples
Citations
This work describes preliminary steps in the ongoing implementation of horizontal visibility graphs (HVG) and related Hamming-Ipsen-Mikhailov (HIM) network similarity (distance) metric to provide automatic disease tag for normal and COVID-positive chest radiographs. A detailed exploration in transformation of a normal or COVID positive chest radiograph to a horizontal visibility graph and its network/graph-theoretic analysis and visualization in R computational environment is presented. Further, HIM network similarity metric is illustrated and its usage in generating automatic disease tag based on test radiograph’s HIM-distance from healthy and COVID positive representative radiographs is presented. Finally, statistically success rate of 60% is observed despite of low quality and mismatched (Normal and COVID positive radiographs are not from same patients) using HVG–HIM and 30% using EMD, which augurs well for the development of this system as a quick disease tag device. Difference in drastic performance is owing to serious computational investment in HVG–HIM. A webservice based portal for automated diseases tagging of chest radiograph is proposed, built and illustrated to take basic clinical services to the poorest of the poor in the LMICs and in African countries. It can be used by primary health care centers (PHCs) for a first aid scan and then patient can be referred to specialists. On a macro scale where patients overwhelm medical facilities due to astronomical numbers involved, this kind of system can relieve the suffering of humanity to some extent. We also reflect on our programmatic and static computational approach as compared to nonlinear dynamical and often unstable, energy-hogging deep learning.
Mammography is an inexpensive and noninvasive imaging tool that is commonly used in detection of breast lesions. However, manual analysis of a mammogramic image can be both time intensive and prone to unwanted error. In recent times, there has been a lot of interest in using computer-aided techniques to classify medical images. The current study explores the efficacy of an Earth Mover’s Distance (EMD)-based mammographic image classification technique to identify the benign and the malignant lumps in the images. We further present a novel leader recognition (LR) technique which aids in the classification process to identify the most benign and malignant images from their respective cohort in the training set. The effect of image diversity in training sets on classification efficacy is also studied by considering training sets of different sizes. The proposed classification technique is found to identify malignant images with up to \(80\%\) sensitivity and also provides a maximum F1 score of \(72.73\%\).KeywordsBreast tumorEMDMammogramsImage classification
With reports of 9.9 million people being infected with tuberculosis by WHO, there is a dire need to curtail the spread of tuberculosis. In spite of having faced many impediments like lack of certified radiologist and chest radiography hardware which are expensive, diagnosis of tuberculosis still remains undetected at early stage. Chest radiography is one of the earliest method of detection used and is an asset for diagnosis of TB especially in early stages of infection, in a resource limited setting as well as for differential diagnosis. In the times of artificial intelligence (AI), we can see many modern platforms for the development of Computer-aided detection (CAD) through machine learning (ML) and deep learning (DL) and there are data coming forth indicating their utilization to the maximum. These approaches involve in hospital settings for examining the diseases through clinical aetiology as well as X-ray images of the patient. Presently, efforts and strategies are being framed and articulated to bring more accuracy adopting the use of the AI and machine learning approaches for the diagnosis of TB. This survey provides an insight to the application and use of CAD for the diagnosis of TB.
Nowadays, with increasing cases of diabetes, one should control the blood sugar as well as perform regular examination of eyes to prevent oneself from blindness. Any person having diabetes is likely to develop diabetic retinopathy (DR). DR is triggered by high blood sugar due to diabetes. After some time, having excessive amount of sugar in blood, can damage retina. When sugar jams the tiny blood vessels the eyes are damaged and this will affect the blood vessels and result in leakage of fluid. Millions of working aged adults suffers from loss of sight due to diabetic retinopathy. DR cannot be treated completely, but early detection of DR prevents the person from vision loss. We proposed a deep learning model for detection of diabetic retinopathy. Detection of DR is a slow process. Physical detection of DR involves a trained clinician to study and estimate the color fundus photographs of the retina. Normal process of identification takes a minimum of two days. In our paper, convolutional neural network architecture has been used to classify images into two classes which is no-diabetic retinopathy and with diabetic retinopathy. APTOS-2019 blindness detection dataset has been used from Kaggle which contains high-resolution retinal images. Those images are used to train the model. Web-based interface has been created for easy interaction with the model.KeywordsContrast limited adaptive histogram equalization (CLAHE)Convolution neural network (CNN)Deep learningDiabetic retinopathy (DR)Gaussian-blur filter
Brain diseases impact more than 1 billion people worldwide and include a wide spectrum of diseases and disorders such as stroke, Alzheimer’s, Parkinson’s, Epilepsy and other Seizure disorders. Most of these brain illnesses are subjected to misclassification, and early diagnosis increases the possibilities of preventing or delaying the development of these disorders. Magnetic Resonance Imaging (MRI) plays an important role in the diagnosis of patients with brain disorders and offers the potential of non-invasive longitudinal monitoring and bio-markers of disease progression. Our work focuses on using machine learning and deep learning techniques for the preemptive diagnosis of Schizophrenia using Kaggle data set and Alzheimer’s using TADPOLE data set comprising of MRI features. Since the number of works using TADPOLE data set is minimum, we have chosen this for our study. Machine learning algorithms such as support vector machine (SVM), Decision Tree, Random Forest, Gaussian Naive Bayes, and 1D-CNN deep learning algorithm have been used for the classification of the disorders. It has been observed that Gaussian NB performed the best on Schizophrenia data, while Random Forest outperformed on Alzheimer’s data compared to the other classifiers.KeywordsMagnetic Resonance Imaging (MRI)Alzheimer’sParkinson’sBrain disorders1D-CNNGaussian Naive Bayes
Due to increasing industry 4.0 practices, massive industrial process data is now available for researchers for modelling and optimization. Artificial Intelligence methods can be applied to the ever-increasing process data to achieve robust control against foreseen and unforeseen system fluctuations. Smart computing techniques, machine learning, deep learning, computer vision, for example, will be inseparable from the highly automated factories of tomorrow. Effective cybersecurity will be a must for all Internet of Things (IoT) enabled work and office spaces.
This book addresses metaheuristics in all aspects of Industry 4.0. It covers metaheuristic applications in IoT, cyber physical systems, control systems, smart computing, artificial intelligence, sensor networks, robotics, cybersecurity, smart factory, predictive analytics and more.
Key features:
Includes industrial case studies.
Includes chapters on cyber physical systems, machine learning, deep learning, cybersecurity, robotics, smart manufacturing and predictive analytics.
surveys current trends and challenges in metaheuristics and industry 4.0.
Metaheuristic Algorithms in Industry 4.0 provides a guiding light to engineers, researchers, students, faculty and other professionals engaged in exploring and implementing industry 4.0 solutions in various systems and processes.
