Search

Advanced microscopic techniques such as high-throughput, high-content, multispectral, and 3D imaging could include many images per experiment requiring hundreds of gigabytes (GBs) of memory. Efficient lossy image-compression methods such as joint photographic experts group (JPEG) and JPEG 2000 are crucial to managing these large amounts of data. However, these methods can get visual quality with high compression ratios but do not necessarily maintain the medical data and information integrity. This paper proposes a novel and improved medical image compression method based on color wavelet difference reduction. Specifically, the proposed method is an extension of the standard wavelet difference reduction (WDR) method using mean co-located pixel difference to select the optimum quantity of color images that present the highest similarity in the spatial and temporal domain. The images with large spatiotemporal coherence are encoded as one volume and evaluated regarding the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). The proposed method is evaluated in the challenging histopathological microscopy image analysis field using 31 slides of colorectal cancer. It is found that the perceptual quality of the medical image is remarkably high. The results indicate that the PSNR improvement over existing schemes may reach up to 22.65 dB compared to JPEG 2000. Also, it can reach up to 10.33dB compared to a method utilizing discrete wavelet transform (DWT), leading us to implement a mobile and web platform that can be used for compressing and transmitting microscopic medical images in real time.

Hemiplegia is a condition caused by brain injury and affects a significant percentage of the population. The effect of patients suffering from this condition is a varying degree of weakness, spasticity, and motor impairment to the left or right side of the body. This paper proposes an automatic feature selection and construction method based on grammatical evolution (GE) for radial basis function (RBF) networks that can classify the hemiplegia type between patients and healthy individuals. The proposed algorithm is tested in a dataset containing entries from the accelerometer sensors of the RehaGait mobile gait analysis system, which are placed in various patients’ body parts. The collected data were split into 2-second windows and underwent a manual pre-processing and feature extraction stage. Then, the extracted data are presented as input to the proposed GE-based method to create new, more efficient features, which are then introduced as input to an RBF network. The paper’s experimental part involved testing the proposed method with four classification methods: RBF network, multi-layer perceptron (MLP) trained with the Broyden–Fletcher–Goldfarb–Shanno (BFGS) training algorithm, support vector machine (SVM), and a GE-based parallel tool for data classification (GenClass). The test results revealed that the proposed solution had the highest classification accuracy (90.07%) compared to the other four methods.

Non-alcoholic fatty liver disease (NAFLD) covers a range of chronic medical conditions varying from hepatocellular inflammation which characterizes nonalcoholic steatohepatitis (NASH) to steatosis, as the key element of a nonalcoholic fatty liver (NAFL). It is globally linked to the increasing prevalence of obesity and other components of metabolic syndrome and is expected to be the main indication for the existence of the liver disease in the coming years. Its eradication has become a major challenge due to the difficulties in clinical diagnosis, complex pathogenesis and the lack of approved therapies. In this study, an automated image analysis method is presented providing quantitative assessments of fat deposition in steatotic liver biopsy specimens. The methodology applies image processing, machine learning and evolutionary algorithm optimization techniques, producing a 1.93% mean classification error compared to the semiquantitative interpretations of specialized hepatologists.

Electroencephalography is one of the most commonly used methods for extracting information about the brain’s condition and can be used for diagnosing epilepsy. The EEG signal’s wave shape contains vital information about the brain’s state, which can be challenging to analyse and interpret by a human observer. Moreover, the characteristic waveforms of epilepsy (sharp waves, spikes) can occur randomly through time. Considering all the above reasons, automatic EEG signal extraction and analysis using computers can significantly impact the successful diagnosis of epilepsy. This research explores the impact of different window sizes on EEG signals’ classification accuracy using four machine learning classifiers. The machine learning methods included a neural network with ten hidden nodes trained using three different training algorithms and the k-nearest neighbours classifier. The neural network training methods included the Broyden–Fletcher–Goldfarb–Shanno algorithm, the multistart method for global optimization problems, and a genetic algorithm. The current research utilized the University of Bonn dataset containing EEG data, divided into epochs having 50% overlap and window lengths ranging from 1 to 24 s. Then, statistical and spectral features were extracted and used to train the above four classifiers. The outcome from the above experiments showed that large window sizes with a length of about 21 s could positively impact the classification accuracy between the compared methods.

Non-alcoholic fatty pancreas disease (NAFPD) is a common and at the same time not extensively examined pathological condition that is significantly associated with obesity, metabolic syndrome, and insulin resistance. These factors can lead to the development of critical pathogens such as type-2 diabetes mellitus (T2DM), atherosclerosis, acute pancreatitis, and pancreatic cancer. Until recently, the diagnosis of NAFPD was based on noninvasive medical imaging methods and visual evaluations of microscopic histological samples. The present study focuses on the quantification of steatosis prevalence in pancreatic biopsy specimens with varying degrees of NAFPD. All quantification results are extracted using a methodology consisting of digital image processing and transfer learning in pretrained convolutional neural networks for the detection of histological fat structures. The proposed method is applied to 20 digitized histological samples, producing an 0.08% mean fat quantification error thanks to an ensemble CNN voting system and 83.3% mean Dice fat segmentation similarity compared to the semi-quantitative estimates of specialist physicians.

Hemiplegia affects a significant portion of the human population. It is a condition that causes motor impairment and severely reduces the patient’s quality of life. This paper presents an automatic system for identifying the hemiplegia type (right or left part of the body is affected). The proposed system utilizes the data taken from patients and healthy subjects using the accelerometer sensor from the RehaGait mobile gait analysis system. The collected data undergo a pre-processing procedure followed by a feature extraction stage. The extracted features are then sent to a neural network trained by the Levenberg-Marquardt backpropagation (LM-BP) algorithm. The experimental part of this research involved creating a custom-created dataset containing entries taken from ten healthy and twenty non-healthy subjects. The data were taken from seven different sensors placed in specific areas of the subjects’ bodies. These sensors can capture a three-dimensional (3D) signal using the accelerometer, magnetometer, and gyroscope device types. The proposed system used the signals taken from the accelerometers, which were split into 2-sec windows. The proposed system achieved a classification accuracy of 95.12% and was compared with fourteen commonly used machine learning approaches.

Discrimination of eye movements and visual states is a flourishing field of research and there is an urgent need for non-manual EEG-based wheelchair control and navigation systems. This paper presents a novel system that utilizes a brain–computer interface (BCI) to capture electroencephalographic (EEG) signals from human subjects while eye movement and subsequently classify them into six categories by applying a random forests (RF) classification algorithm. RF is an ensemble learning method that constructs a series of decision trees where each tree gives a class prediction, and the class with the highest number of class predictions becomes the model’s prediction. The categories of the proposed random forests brain–computer interface (RF-BCI) are defined according to the position of the subject’s eyes: open, closed, left, right, up, and down. The purpose of RF-BCI is to be utilized as an EEG-based control system for driving an electromechanical wheelchair (rehabilitation device). The proposed approach has been tested using a dataset containing 219 records taken from 10 different patients. The BCI implemented the EPOC Flex head cap system, which includes 32 saline felt sensors for capturing the subjects’ EEG signals. Each sensor caught four different brain waves (delta, theta, alpha, and beta) per second. Then, these signals were split in 4-second windows resulting in 512 samples per record and the band energy was extracted for each EEG rhythm. The proposed system was compared with naïve Bayes, Bayes Network, k-nearest neighbors (K-NN), multilayer perceptron (MLP), support vector machine (SVM), J48-C4.5 decision tree, and Bagging classification algorithms. The experimental results showed that the RF algorithm outperformed compared to the other approaches and high levels of accuracy (85.39%) for a 6-class classification are obtained. This method exploits high spatial information acquired from the Emotiv EPOC Flex wearable EEG recording device and examines successfully the potential of this device to be used for BCI wheelchair technology.

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor’s accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method’s outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area—resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM).