Search results

The purpose of this paper is to describe an AI (Artificial Intelligence) that can “think like an African traditional doctor”. The system proposes to model and to use attitudes taken and concepts used by African traditional doctors when facing cases. It is designed to go deep into the concepts of African traditional medicine (ATM) by dealing with all the possible interpretations of those concepts, and to produce more much satisfying and accurate support for medical diagnosis and prescription than existing systems.

To take into account the sometimes strange concepts used and attitudes taken by African traditional healers, including mystical considerations, the system relies on a deep ontology describing all those concepts and attitudes in a more computer readable manner allowing a multi-agent system to have full access to ATM knowledge. Ethnological inquiries, literary analysis and interviews of traditional doctors (the holders of African medicine knowledge) were performed to gather sufficient data to achieve the work.

The paper addresses this question of how to build a practical large-scope computer-aided diagnosis and prescription system which can exploit deep descriptions of ATM concepts, including mystical considerations. The system also provides scientific interpretations to some concepts sometimes considered as mystical facts. It is a java web-based platform combined to a Java Agent Development framework multi-agent system accessing an ontology to provide its results.

Because of the origins of healers involved in this research (from Gabon and Cameroon, countries of Central Africa), the ontology and the collected data may lack generalizability in the African scope and then it is a prototype. Therefore, ATM experts all over the continent are encouraged to participate to improve and standardize the ATM ontology and to populate the knowledge base. On the other side, the system cannot give scientific explanations to all the mystical considerations in ATM, there still some facts which cannot be rationally explained for now.

The paper demonstrates the practical usability of the implemented system on the diagnosis and the treatment of a patient case.

The research describes a system which once validated by traditional experts, will serve as a tool to assist them in their day-to-day diagnosis and prescription tasks and will also serve as a reference on ATM practices for all interested users.

The paper provides an in-depth description of a computer-aided diagnosis system (CADS) that promotes indigenous technology from an African perspective. Comparing to the former systems identified in the literature, the proposed system is the first which deals with believes and mystical considerations in ATM, and also the first which provides a function to rank its results.

One of the main reasons for increase in mortality rate in woman is breast cancer. Accurate early detection of breast cancer seems to be the only solution for diagnosis. In the field of breast cancer research, many new computer-aided diagnosis systems have been developed to reduce the diagnostic test false positives because of the subtle appearance of breast cancer tissues. The purpose of this study is to develop the diagnosis technique for breast cancer using LCFS and TreeHiCARe classifier model.

The proposed diagnosis methodology initiates with the pre-processing procedure. Subsequently, feature extraction is performed. In feature extraction, the image features which preserve the characteristics of the breast tissues are extracted. Consequently, feature selection is performed by the proposed least-mean-square (LMS)-Cuckoo search feature selection (LCFS) algorithm. The feature selection from the vast range of the features extracted from the images is performed with the help of the optimal cut point provided by the LCS algorithm. Then, the image transaction database table is developed using the keywords of the training images and feature vectors. The transaction resembles the itemset and the association rules are generated from the transaction representation based on a priori algorithm with high conviction ratio and lift. After association rule generation, the proposed TreeHiCARe classifier model emanates in the diagnosis methodology. In TreeHICARe classifier, a new feature index is developed for the selection of a central feature for the decision tree centered on which the classification of images into normal or abnormal is performed.

The performance of the proposed method is validated over existing works using accuracy, sensitivity and specificity measures. The experimentation of proposed method on Mammographic Image Analysis Society database resulted in classification of normal and abnormal cancerous mammogram images with an accuracy of 0.8289, sensitivity of 0.9333 and specificity of 0.7273.

This paper proposes a new approach for the breast cancer diagnosis system by using mammogram images. The proposed method uses two new algorithms: LCFS and TreeHiCARe. LCFS is used to select optimal feature split points, and TreeHiCARe is the decision tree classifier model based on association rule agreements.

The purpose of this paper is to show an efficient method for the detection of signs of early lung cancer. Various image processing algorithms are presented for different types of lesions, and a scheme is proposed for the combination of results.

A computer aided detection (CAD) scheme was developed for detection of lung cancer. It enables different lesion enhancer algorithms, sensitive to specific lesion subtypes, to be used simultaneously. Three image processing algorithms are presented for the detection of small nodules, large ones, and infiltrated areas. The outputs are merged, the false detection rate is reduced with four separated support vector machine (SVM) classifiers. The classifier input comes from a feature selection algorithm selecting from various textural and geometric features. A total of 761 images were used for testing, including the database of the Japanese Society of Radiological Technology (JSRT).

The fusion of algorithms reduced false positives on average by 0.6 per image, while the sensitivity remained 80 per cent. On the JSRT database the system managed to find 60.2 per cent of lesions at an average of 2.0 false positives per image. The effect of using different result evaluation criteria was tested and a difference as high as 4 percentage points in sensitivity was measured. The system was compared to other published methods.

The study described in the paper proves the usefulness of lesion enhancement decomposition, while proposing a scheme for the fusion of algorithms. Furthermore, a new algorithm is introduced for the detection of infiltrated areas, possible signs of lung cancer, neglected by previous solutions.

Diabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers.

In this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.

By conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively.

In this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

Fueled by the rapid growth of internet, steganography has emerged as one of the promising techniques in the communication system to obscure the data. Steganography is defined as the process of concealing the data or message within media files without affecting the perception of the image. Media files, like audio, video, image, etc., are utilized to embed the message. Nowadays, steganography is also used to transmit the medical information or diagnostic reports. The paper aims to discuss these issues.

In this paper, the novel wavelet transform-based steganographic method is proposed for secure data communication using OFDM system. The embedding and extraction process in the proposed steganography method exploits the wavelet transform. Initially, the cost matrix is estimated by the following three aspects: pixel intensity, edge transformation and wavelet transform. The cost estimation matrix provides the location of the cover image where the message is to be entrenched. Then, the wavelet transform is utilized to embed the message into the cover image according to the cost value. Subsequently, in the extraction process, the wavelet transform is applied to the embedded image to retrieve the message efficiently. Finally, in order to transfer the secret information over the channel, the newly developed wavelet-based steganographic method is employed for the OFDM system.

The experimental results are evaluated and performance is analyzed using PSNR and MSE parameters and then compared with existing systems. Thus, the outcome of our wavelet transform steganographic method achieves the PSNR of 71.5 dB which ensures the high imperceptibility of the image. Then, the outcome of the OFDM-based proposed steganographic method attains the higher PSNR of 71.07 dB that proves the confidentiality of the message.

In the authors’ previous work, the embedding and extraction process was done based on the cost estimation matrix. To enhance the security throughout the communication system, the novel wavelet-based embedding and extraction process is applied to the OFDM system in this paper. The idea behind this method is to attain a higher imperceptibility and robustness of the image.

Novel coronavirus is fast spreading pathogen worldwide and is threatening billions of lives. SARS n-CoV2 is known to affect the lungs of the COVID-19 positive patients. Chest x-rays are the most widely used imaging technique for clinical diagnosis due to fast imaging time and low cost. The purpose of this study is to use deep learning technique for automatic detection of COVID-19 using chest x-rays.

The authors used a data set containing confirmed COVID-19 positive, common bacterial pneumonia and healthy cases (no infection). A collection of 1,428 x-ray images is used in this study. The authors used a pre-trained VGG-16 model for the classification task. Transfer learning with fine-tuning was used in this study to effectively train the network on a relatively small chest x-ray data set. Initial experiments show that the model achieves promising results and can be greatly used to expedite COVID-19 detection.

The authors achieved an accuracy of 96% and 92.5% in two and three output class cases, respectively. Based on these findings, the medical community can access using x-ray images as possible diagnostic tool for faster COVID-19 detection to complement the already testing and diagnosis methods.

The proposed method can be used as initial screening which can help health-care professionals to better treat the COVID patients by timely detecting and screening the presence of disease.

Breast cancer is one of the most common malignant tumors in women, which badly have an effect on women's physical and psychological health and even danger to life. Nowadays, mammography is considered as a fundamental criterion for medical practitioners to recognize breast cancer. Though, due to the intricate formation of mammogram images, it is reasonably hard for practitioners to spot breast cancer features.

Breast cancer is one of the most common malignant tumors in women, which badly have an effect on women's physical and psychological health and even danger to life. Nowadays, mammography is considered as a fundamental criterion for medical practitioners to recognize breast cancer. Though, due to the intricate formation of mammogram images, it is reasonably hard for practitioners to spot breast cancer features.

The performance analysis was done for both segmentation and classification. From the analysis, the accuracy of the proposed IAP-CSA-based fuzzy was 41.9% improved than the fuzzy classifier, 2.80% improved than PSO, WOA, and CSA, and 2.32% improved than GWO-based fuzzy classifiers. Additionally, the accuracy of the developed IAP-CSA-fuzzy was 9.54% better than NN, 35.8% better than SVM, and 41.9% better than the existing fuzzy classifier. Hence, it is concluded that the implemented breast cancer detection model was efficient in determining the normal, benign and malignant images.

This paper adopts the latest Improved Awareness Probability-based Crow Search Algorithm (IAP-CSA)-based Region growing and fuzzy classifier for enhancing the breast cancer detection of mammogram images, and this is the first work that utilizes this method.

The purpose of this paper is to present the basic ideas of magnetic nanoparticles' usage in the breast cancer treatment, which is called magnetic fluid hyperthermia. The proposed approach offers a relatively simple methodology of energy deposition, allowing an adequate temperature control at the target tissue, in this case a cancerous one. By means of a numerical method the authors aim to investigate two heating effects caused by varying magnetic fields, i.e. to compare the power density heating effects of eddy currents and magnetic nanoparticles.

In order to numerically investigate the combination of the overheating effect of magnetic nanoparticles and eddy currents, the Finite Element Method solver based on FEniCS project has been prepared. To include the magnetic fluid in the model it has been assumed that power losses in the magnetic nanoparticles are completely converted into heat, according to experimentally developed formula. That formula can be interpreted as the hysteresis losses with regard to the volume of magnetic fluid. Finally, the total power density has been calculated as the product of the sum of power density from eddy currents and hysteresis losses. That methodology has been applied to calculate the effectiveness of magnetic fluid hyperthermia with regard to the female breast phantom.

The paper presents the methodology which can be used in magnetic fluid hyperthermia therapy planning and Computer Aid Diagnosis (CAD). Furthermore, it is shown how to overcome one of the most serious engineering challenges connected with hyperthermia, i.e. achieving adequate temperature in deep tumors without overheating the body surface.

The obtained results connected with the assessment of eddy currents effect suggest that during hyperthermia treatment the configuration which consists of an exciting coil and human body, plays a curial role. Moreover, the authors believe that these results will help to predict the skin surface overheating that accompanies deep heating. The presented methodology can be used by engineers in the development of Computer Aid Diagnosis systems.

In a given patient's situation a number of choices must be made to determine the parameters of the hyperthermia treatment. These include the need of multiple‐point temperature measurements for accurate and thorough monitoring. Treatment planning will require accurate characterization of the applicator deposition pattern and the tissue parameters, as well as the numerical techniques to predict the resultant heating pattern. The presented paper shows how to overcome these problems from the numerical point of view at least.

As a result of reorganisation within the Company, AVX Limited have appointed Keith France as General Manager, Sales and Marketing. Previously General Manager, Sales, Europe, Mr France now assumes the added responsibility for the marketing of AVX products throughout Europe.

According to the World Health Organization, arrhythmia is one of the primary causes of deaths across the globe. In order to reduce mortality rate, cardiovascular disease should be properly identified and the proper treatment for the same should be immediately provided to the patients. The objective of this paper was to implement a better heartbeat classification model which will work better than the other implemented heartbeat classification methods.

In this paper, the ensemble of two deep learning models is proposed to classify the MIT-BIH arrhythmia database into four different classes according to ANSI-AAMI standards. First, a convolutional neural network (CNN) model is used to classify heartbeats on a raw data set. Secondly, four features (wavelets, R-R intervals, morphological and higher-order statistics) are extracted from the data set and then applied to a long short-term memory (LSTM) model to classify the heartbeats. Finally, the ensemble of CNN and LSTM model with sum rule, product rule and majority voting has been used to identify the heartbeat classes.

Among these, the highest accuracy obtained is 98.58% using ensemble method with product rule. The results show that the ensemble of CNN and BLSTM has offered satisfactory performance compared to other techniques discussed in this study.

In this study, we have developed a new combination of two deep learning models to enhance the performance of arrhythmia classification using segmentation of input ECG signals. The contributions of this study are as follows: First, a deep CNN model is built to classify ECG heartbeat using a raw data set. Second, four types of features (R-R interval, HOS, morphological and wavelet) were extracted from the raw data set and then applied to the bidirectional LSTM model to classify the ECG heartbeat. Third, combination rules (sum rules, product rules and majority voting rules) were tested to ensure the accumulated probabilities of the CNN and LSTM models.