Data Mining Practical Machine Learning Tools and Techniques

This paper addresses the automatic detection of microaneurysms in color fundus images, which plays a key role in computer assisted diagnosis of diabetic retinopathy, a serious and frequent eye disease. The algorithm can be divided into four steps. The first step consists in image enhancement, shade correction and image normalization of the green channel. The second step aims at detecting candidates, i.e. all patterns possibly corresponding to MA, which is achieved by diameter closing and an automatic threshold scheme. Then, features are extracted, which are used in the last step to automatically classify candidates into real MA and other objects; the classification relies on kernel density estimation with variable bandwidth. A database of 21 annotated images has been used to train the algorithm. The algorithm was compared to manually obtained gradings of 94 images; sensitivity was 88.5% at an average number of 2.13 false positives per image.

Automatic detection of microaneurysms in color fundus images for screening of diabetic retinopathy.

The electroencephalogram (EEG) signals are commonly used in diagnosing and treating sleep disorders. Many existing methods for sleep stages classification mainly depend on the analysis of EEG signals in time or frequency domain to obtain a high classification accuracy. In this paper, the statistical features in time domain, the structural graph similarity and the K-means (SGSKM) are combined to identify six sleep stages using single channel EEG signals. Firstly, each EEG segment is partitioned into sub-segments. The size of a sub-segment is determined empirically. Secondly, statistical features are extracted, sorted into different sets of features and forwarded to the SGSKM to classify EEG sleep stages. We have also investigated the relationships between sleep stages and the time domain features of the EEG data used in this paper. The experimental results show that the proposed method yields better classification results than other four existing methods and the support vector machine (SVM) classifier. A 95.93% average classification accuracy is achieved by using the proposed method.

EEG Sleep Stages Classification Based on Time Domain Features and Structural Graph Similarity

Use of features from RR-time series and EEG signals for automated classification of sleep stages in deep neural network framework

Until now, the human expert segments retinal blood vessels manually in fundus images to inspect human retinal-related diseases, such as diabetic retinopathy and vascular occlusion. Recently, many studies were conducted for automatic retinal vessel segmentation from fundus images through supervised and unsupervised methods to minimize user intervention. However, most of them lack in segmentation robustness and cannot optimize loss functions so that results of the segmentation have made lots of fake or thin branches. This article proposes a new conditional generative adversarial network called M-GAN to conduct accurate and precise retinal vessel segmentation by balancing losses through stacked deep fully convolutional networks. It consists of a newly designed M-generator with deep residual blocks for more robust segmentation and an M-discriminator with a deeper network for more efficient training of the adversarial model. In particular, a multi-kernel pooling block is added between the stacked layers to support the scale-invariance of vessel segmentations of different sizes. The M-generator has down-sampling layers to extract features and up-sampling layers to make segmented retinal blood vessel images from the extracted features. The M-discriminator also has a deeper network similar to the down-sampling of the M-generator, but the final layer is constructed as a fully connected layer for decision making. We conduct pre-processing of the input image using automatic color equalization (ACE) to make the retinal vessels of the input fundus image more clear and perform post-processing that makes the vessel branches smooth and reduces false-negatives using a Lanczos resampling method. To verify the proposed method, we used DRIVE, STARE, HRF, and CHASE-DB1datasets and compared the proposed M-GAN with other studies. We measured accuracy, the intersection of union (IoU), F1 score, and Matthews correlation coefficient (MCC) for comparative analysis. Results of comparison proved that the proposed M-GAN derived superior performance than other studies.

/pdf/m-gan-retinal-blood-vessel-segmentation-by-balancing-losses-mor01re7fv.pdf

M-GAN: Retinal Blood Vessel Segmentation by Balancing Losses Through Stacked Deep Fully Convolutional Networks

Currently, sleep disorders are considered as one of the major human life issues. There are several stable physiological stages that the human brain goes through during sleep. Nowadays, many biomedical signals such as EEG, ECG, EMG, and EOG offer useful details for clinical setups that are used in identifying sleep disorders. In this work, we propose an efficient technique that could be implemented in hardware to differentiate sleep stages which will assist physicians in the diagnosis and treatment of related sleep disorders. This study depends on different EEG datasets from PhysioNet using the Sleep-EDF [Expanded] Database that were acquired and described by scientists for the analysis and diagnosis of sleep stages. Generally, the EEG signal is decomposed into five bands: delta, theta, alpha, beta, and gamma to define the change in brain state. In this work, Butterworth band-pass filters are designed to filter and decompose EEG into the above frequency sub-bands. In addition, various discriminating features including energy, standard deviation and entropy are computed and extracted from each δ, □, α, β and γ sub-band. Furthermore, the extracted features are then fed to a supervised learning classifier; support vector machine (SVM) to be able to recognize the sleep stages state and identify if the acquired signal is corresponding to wake or stage 1 of sleep, according to the purpose of this research. The key novelty of this work is to identify the sleep stages from a publicly available EEG signal dataset by using a feasible set of features, easily implementable filters in any microcontroller device, and an efficient classification method. Therefore, physicians can track these sleep stages to identify certain patterns such as detecting fatigue, drowsiness, and/or various sleep disorders such as sleep apnea. The experimental results on a variety of subjects verify 92.5% of classification accuracy of the proposed work.

/pdf/efficient-sleep-stage-classification-based-on-eeg-signals-4shqrm6vtf.pdf

Efficient sleep stage classification based on EEG signals

Diabetic retinopathy (DR) occurs in patients who have had diabetes for at least five years. Diseased small blood vessels in the back of the eye cause a leakage of protein and blood in the retina. Diagnosis of diabetic retinopathy at early stage can be done through detection of blood vessels of retina. Blood vessel segmentation is a helpful tool in the treatment of diabetic retinopathy. Many studies have been carried out in the last decade in order to get an accurate blood vessel detection and segmentation in retinal images since vascular anomalies are one of the strongest manifestations of DR. Here, we propose a ruled-based algorithm called Star Networked Pixel Tracking to decide whether a processed pixel is a part of a vessel or not. The complement of the gray scale of the green channel from the original image is used. The blood vessels are enhanced by applying a strong adaptive histogram equalization algorithm locally and globally. Morphological operations are implemented in designing a background image to generate a normalized retinal image. In order to enhance the vessels' contrast, mathematical and morphological operations are applied. Noise artifacts that look like small vessels is filtered by the proposed eight-direction network pixel tracking algorithm. The proposed method is evaluated on 20 images of well known public domain DRIVE database. We achieved an accuracy of 95.83%. This is the highest accuracy among the ruled-based methods reported for the DRIVE database.

A novel vessel segmentation algorithm in color images of the retina

Epilepsy is a crucial neurological disorder in which patients experience epileptic seizure caused by abnormal electrical discharges from the brain. It is highly common in children and adults at the age of 65-70. Around 1 % of the world's population is affected by this disease. The mechanism of epilepsy is still incomprehensible to researchers; however, 80% of the seizure activity can be treated effectively if proper diagnosis is performed. This disease mostly leads to uncontrollable movements, convulsions and loss of conscious and contends the patient to increased possibility of accidental injury and even death. As a result, monitoring the person with epilepsy from being exposed to the danger is among the basic death to life transformation solutions. In this paper, we propose the most important methodologies that could be implemented in hardware for monitoring an epileptic patient. Many studies show that, Electroencephalogram (EEG) is the most important signal used by physicians in assessing the brain activities and diagnosing different brain disorders. This study is based on different EEG datasets that were obtained and described by researchers for analysis and diagnosis of epilepsy. Butterworth bandpass filters are implemented and used to preprocess and decompose the EEG signal into five different EEG frequency bands (delta, theta, alpha, beta, and gamma). In addition, different features such as energy, standard deviation and entropy are then computed and extracted from each Δ, Θ, α, β and γ sub-band. Furthermore, the extracted features are then fed to a supervised learning classifier; support vector machine (SVM); in order to detect the epileptic events and identify if the acquired signal is corresponding to seizure or not according to the objective of this research. If seizure is experienced, appropriate monitoring should be taken in action. Experimental results on a number of subjects confirm 95% classification accuracy of the proposed work.

Efficient EEG analysis for seizure monitoring in epileptic patients

Sleep apnea (SA) is the most commonly known sleeping disorder characterized by pauses of airflow to the lungs and often results in day and night time symptoms such as impaired concentration, depression, memory loss, snoring, nocturnal arousals, sweating and restless sleep. Obstructive Sleep Apnea (OSA), the most common SA, is a result of a collapsed upper respiratory airway, which is majorly undiagnosed due to the inconvenient Polysomnography (PSG)  testing procedure at sleep labs. This paper introduces an automated approach towards identifying sleep apnea. The idea is based on efficient feature extraction of the electrocardiogram (ECG) signal by employing a hybrid of signal processing techniques and classification using a linear-kernel Support Vector Machine (SVM). The optimum set of RR-interval features of the ECG signal yields a high classification accuracy of  97.1% when tested on the Physionet Apnea-ECG recordings. The results provide motivating insights towards future developments of convenient and effective OSA screening setups.

/pdf/svm-based-sleep-apnea-identification-using-optimal-rr-mtypa6g1uq.pdf

Helen Ocbagabir

Papers

Efficient sleep stage classification based on EEG signals

A novel vessel segmentation algorithm in color images of the retina

Efficient EEG analysis for seizure monitoring in epileptic patients

SVM-Based Sleep Apnea Identification Using Optimal RR-Interval Features of the ECG Signal