Automatic identification of schizophrenia employing EEG records analyzed with deep learning algorithms

Electroencephalography is a method of detecting and analyzing electrical activity in the brain. This electrical activity can be recorded and processed to aid in the clinical diagnosis of mental disorders. In this study, a novel system for classifying schizophrenia patients from EEG recordings is presented. The developed algorithm decomposes the EEG signals into a system of radial basis functions using the method of fuzzy means. This decomposition helps to obtain the information from the various electrodes of the EEG and allows separating between healthy controls and patients with schizophrenia. The proposed method has been compared with classical machine learning algorithms, such as, K-Nearest Neighbor, Adaboost, Support Vector Machine, and Bayesian Linear Discriminant Analysis. The results show that the proposed method obtains the highest values in terms of balanced accuracy, recall, precision and F1 score, close to 93 % in all cases. The model developed in this study can be implemented in brain activity analysis systems that help in the prediction of patients with schizophrenia.

Image Analysis in Digital Pathology Utilizing Machine Learning and Deep Neural Networks

Detection of regions of interest (ROIs) in whole slide images (WSIs) in a clinical setting is a highly subjective and a labor-intensive task. In this work, recent developments in machine learning and computer vision algorithms are presented to assess their possible usage and performance to enhance and accelerate clinical pathology procedures, such as ROI detection in WSIs. In this context, a state-of-the-art deep learning framework (Detectron2) was trained on two cases linked to the TUPAC16 dataset for object detection and on the JPATHOL dataset for instance segmentation. The predictions were evaluated against competing models and further possible improvements are discussed.

High-Precise Bipolar Disorder Detection by Using Radial Basis Functions Based Neural Network

Presently, several million people suffer from major depressive and bipolar disorders. Thus, the modelling, characterization, classification, diagnosis, and analysis of such mental disorders bears great significance in medical research. Electroencephalogram records provide important information to improve clinical diagnosis and are very useful in the scientific community. In this work, electroencephalogram records and patient data from the Hospital Virgen de la Luz in Cuenca (Spain) were processed for a correct classification of bipolar disorders. This work implemented an innovative radial basis function-based neural network employing a fuzzy means algorithm. The results show that the proposed method is an effective approach for discrimination of two kinds of classes, i.e., bipolar disorder patients and healthy persons. The proposed algorithm achieved the best performance compared with other machine learning techniques such as Bayesian linear discriminant analysis, Gaussian naive Bayes, decision trees, K-nearest neighbour, or support vector machine, showing a very high accuracy close to 97%. Therefore, the neural network technique presented could be used as a new tool for the diagnosis of bipolar disorder, considering the possibility of integrating this method into medical software.

Deep neural network based histological scoring of lung fibrosis and inflammation in the mouse model system

Preclinical studies of novel compounds rely on quantitative readouts from animal models. Frequently employed readouts from histopathological tissue scoring are time consuming, require highly specialized staff and are subject to inherent variability. Recent advances in deep convolutional neural networks (CNN) now allow automating such scoring tasks. Here, we demonstrate this for the case of the Ashcroft fibrosis score and a newly developed inflammation score to characterize fibrotic and inflammatory lung diseases. Sections of lung tissue from mice exhibiting a wide range of fibrotic and inflammatory states were stained with Masson trichrome. Whole slide scans using a 20x objective were acquired and cut into smaller tiles of 512x512 pixels. The tiles were subsequently classified by specialized CNNs, either an "Ashcroft fibrosis CNN" or an "inflammation CNN". For the Ashcroft fibrosis score the CNN was fine-tuned by using 14000 labelled tiles. For the inflammation score the CNN was trained with 3500 labelled tiles. After training, the Ashcroft fibrosis CNN achieved an accuracy of 79.5% and the inflammation CNN an accuracy of 80.0%. An error analysis revealed that misclassifications are almost exclusively with neighboring scores, which reflects the inherent ambiguity of parts of the data. The variability between two experts was found to be larger than the variability between the CNN classifications and the ground truth. The CNN generated Ashcroft score was in very good agreement with the score of a pathologist (r2 = 0.92). Our results demonstrate that costly and time consuming scoring tasks can be automated and standardized with deep learning. New scores such as the inflammation score can be easily developed with the approach presented here.

An advanced image analysis tool for the quantification and characterization of breast cancer in microscopy images

The paper presents an advanced image analysis tool for the accurate and fast characterization and quantification of cancer and apoptotic cells in microscopy images. The proposed tool utilizes adaptive thresholding and a Support Vector Machines classifier. The segmentation results are enhanced through a Majority Voting and a Watershed technique, while an object labeling algorithm has been developed for the fast and accurate validation of the recognized cells. Expert pathologists evaluated the tool and the reported results are satisfying and reproducible.

Computer-aided detection of breast cancer on mammograms: a swarm intelligence optimized wavelet neural network approach

Breast cancer is the second leading cause of cancer death in women. Accurate early detection can effectively reduce the mortality rate caused by breast cancer. Masses and microcalcification clusters are an important early signs of breast cancer. However, it is often difficult to distinguish abnormalities from normal breast tissues because of their subtle appearance and ambiguous margins. Computer aided diagnosis (CAD) helps the radiologist in detecting the abnormalities in an efficient way. This paper investigates a new classification approach for detection of breast abnormalities in digital mammograms using Particle Swarm Optimized Wavelet Neural Network (PSOWNN). The proposed abnormality detection algorithm is based on extracting Laws Texture Energy Measures from the mammograms and classifying the suspicious regions by applying a pattern classifier. The method is applied to real clinical database of 216 mammograms collected from mammogram screening centers. The detection performance of the CAD system is analyzed using Receiver Operating Characteristic (ROC) curve. This curve indicates the trade-offs between sensitivity and specificity that is available from a diagnostic system, and thus describes the inherent discrimination capacity of the proposed system. The result shows that the area under the ROC curve of the proposed algorithm is 0.96853 with a sensitivity 94.167% of and specificity of 92.105%.

Ratsnake: a versatile image annotation tool with application to computer-aided diagnosis

Image segmentation and annotation are key components of image-based medical computer-aided diagnosis (CAD) systems. In this paper we present Ratsnake, a publicly available generic image annotation tool providing annotation efficiency, semantic awareness, versatility, and extensibility, features that can be exploited to transform it into an effective CAD system. In order to demonstrate this unique capability, we present its novel application for the evaluation and quantification of salient objects and structures of interest in kidney biopsy images. Accurate annotation identifying and quantifying such structures in microscopy images can provide an estimation of pathogenesis in obstructive nephropathy, which is a rather common disease with severe implication in children and infants. However a tool for detecting and quantifying the disease is not yet available. A machine learning-based approach, which utilizes prior domain knowledge and textural image features, is considered for the generation of an image force field customizing the presented tool for automatic evaluation of kidney biopsy images. The experimental evaluation of the proposed application of Ratsnake demonstrates its efficiency and effectiveness and promises its wide applicability across a variety of medical imaging domains.

Advanced characterization of microscopic kidney biopsies utilizing image analysis techniques

Correct annotation and identification of salient regions in Kidney biopsy images can provide an estimation of pathogenesis in obstructive nephropathy. This paper presents a tool for the automatic or manual segmentation of such regions along with methodology for their characterization in terms of the exhibited pathology. The proposed implementation is based on custom code written in Java and the utilization of open source tools (i.e. RapidMiner, ImageJ). The corresponding implementation details along with the initial evaluation of the proposed integrated system are also presented in the paper.

Cancer cells detection and pathology quantification utilizing image analysis techniques

This paper presents an advanced image analysis tool for the accurate and fast characterization and quantification of cancer and apoptotic cells in microscopy images utilizing adaptive thresholding and a Support Vector Machines classifier. The segmentation results are also enhanced through a Majority Voting and a Watershed technique. The proposed tool was evaluated by experts on breast cancer images and the reported results were accurate and reproducible.

A collaborative biomedical image mining framework: application on the image analysis of microscopic kidney biopsies

The analysis and characterization of biomedical image data is a complex procedure involving several processing phases, like data acquisition, preprocessing, segmentation, feature extraction and classification. The proper combination and parameterization of the utilized methods are heavily relying on the given image data set and experiment type. They may thus necessitate advanced image processing and classification knowledge and skills from the side of the biomedical expert. In this work, an application, exploiting web services and applying ontological modeling, is presented, to enable the intelligent creation of image mining workflows. The described tool can be directly integrated to the RapidMiner, Taverna or similar workflow management platforms. A case study dealing with the creation of a sample workflow for the analysis of kidney biopsy microscopy images is presented to demonstrate the functionality of the proposed framework.

AUTOMATIC THYROID NODULE SEGMENTATION AND COMPONENT ANALYSIS IN ULTRASOUND IMAGES

Heterogeneous thyroid nodules have distinct components and vague boundaries in ultrasound (US) images. It is difficult for radiologists and physicians to manually draw the complete shape of a nodule, or distinguish what kind of components a nodule has. Hence, this article presents an automatic process for nodule segmentation and component classification. A decision-tree algorithm is used to segment the possible nodular area. A refinement process is then applied to recover the nodular shape. Finally, a hierarchical method based on support vector machines (SVMs) is used to identify the components in the nodular lesion. Experimental results of the proposed approach were compared with those of other methods.

Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

Background

Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test.

Results

Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed overall classification accuracy above a median value of 0.63, but for most sensitivity was around or even lower than a median value of 0.5.

Conclusions

When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.

LEARNING PATTERNS OF LIVER MASSES USING IMPROVED RBF NETWORKS

This study proposes a diagnosis system for liver masses based on the improved radial basis function (RBF) neural networks. In this article, RBF networks are improved by sigmoid function and the growing and pruning algorithm. The proposed improved RBF networks adopt the sigmoid function as their kernel due to its increased flexibility over the Gaussian kernel. Furthermore, the growing and pruning algorithm is used to adjust the network size dynamically according to the neuron's significance. This investigation formulates discriminating among cysts, hepatoma, cavernous hemangioma, and normal tissue as a supervised learning problem. The current work calculates several texture and gray-level features derived from regions of interest as input in the proposed classifier. Receiver operating characteristic (ROC) curves evaluate the diagnosis performance, and demonstrate the proposed method's good performance.