Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

Artificial Intelligence in Fluorescence Lifetime Imaging Ophthalmoscopy (FLIO) Data Analysis-Toward Retinal Metabolic Diagnostics

The purpose of this study was to investigate the possibility of implementing an artificial intelligence (AI) approach for the analysis of fluorescence lifetime imaging ophthalmoscopy (FLIO) data even with small data. FLIO data, including the fluorescence intensity and mean fluorescence lifetime (τm) of two spectral channels, as well as OCT-A data from 26 non-smokers and 28 smokers without systemic and ocular diseases were used. The analysis was performed with support vector machines (SVMs), a well-known AI method for small datasets, and compared with the results of convolutional neural networks (CNNs) and autoencoder networks. The SVM was the only tested AI method, which was able to distinguish τm between non-smokers and heavy smokers. The accuracy was about 80%. OCT-A data did not show significant differences. The feasibility and usefulness of the AI in analyzing FLIO and OCT-A data without any apparent retinal diseases were demonstrated. Although further studies with larger datasets are necessary to validate the results, the results greatly suggest that AI could be useful in analyzing FLIO-data even from healthy subjects without retinal disease and even with small datasets. AI-assisted FLIO is expected to greatly advance early retinal diagnosis.

A Vector Quantization-Based Spike Compression Approach Dedicated to Multichannel Neural Recording Microsystems

Implantable high-density multichannel neural recording microsystems provide simultaneous recording of brain activities. Wireless transmission of the entire recorded data causes high bandwidth usage, which is not tolerable for implantable applications. As a result, a hardware-friendly compression module is required to reduce the amount of data before it is transmitted. This paper presents a novel compression approach that utilizes a spike extractor and a vector quantization (VQ)-based spike compressor. In this approach, extracted spikes are vector quantized using an unsupervised learning process providing a high spike compression ratio (CR) of 10-80. A combination of extracting and compressing neural spikes results in a significant data reduction as well as preserving the spike waveshapes. The compression performance of the proposed approach was evaluated under variant conditions. We also developed new architectures such that the hardware blocks of our approach can be implemented more efficiently. The compression module was implemented in a 180-nm standard CMOS process achieving a SNDR of 14.49[Formula: see text]dB and a classification accuracy (CA) of 99.62% at a CR of 20, while consuming 4[Formula: see text][Formula: see text]W power and 0.16[Formula: see text]mm² chip area per channel.

ESVM-SWRF: Ensemble SVM-based sample weighted random forests for liver disease classification

Recently, a significant way to diagnose the disease is using the model of medical data mining. The most challenging task in the healthcare field is to face a large amount of data during disease analyzes and prediction. Once the data are transformed into valuable data by means of data mining models then the actual prediction and decision making is easier. The existing studies met few shortcomings because of higher execution time, more computational complexities, less scalability, slow convergence, and lack of providing the solution. In this article, we have proposed an ensemble SVM-based sample weighted random forests (eSVM-swRF) with novel improved colliding body optimization (NICBO) algorithm to predict liver diseases. The extraction, loading, transformation, and analysis (ELTA) are used to pre-process the patient data. The significant feature with a suitable model is generated depending upon the filter-based method. Based on eSVM-swRF, the parameter values such as penalty parameter (P), threshold (T), and mTry are optimized via a novel improved colliding boding optimization (NICBO) algorithm. The UCI dataset provides liver disease data for this study. The implementation platform of RapidMiner Studio version 7.6 with different evaluation measures is used to validate the performance of eSVM-swRF with the NICBO method. Anyway, the proposed method yields outstanding performance than other existing methods such as Particle Swarm Optimization-based Support Vector Machine (PSO-SVM), fuzzy adaptive, and neighbor weighted k-NN (FuzzyANWKNN), Naïve Bayes-based Support Vector Machine (NB-SVM), and Neural network.

A non-invasive, automated diagnosis of Menière's disease using radiomics and machine learning on conventional magnetic resonance imaging: A multicentric, case-controlled feasibility study

Purpose

This study investigated the feasibility of a new image analysis technique (radiomics) on conventional MRI for the computer-aided diagnosis of Menière’s disease.

Materials and methods

A retrospective, multicentric diagnostic case–control study was performed. This study included 120 patients with unilateral or bilateral Menière’s disease and 140 controls from four centers in the Netherlands and Belgium. Multiple radiomic features were extracted from conventional MRI scans and used to train a machine learning-based, multi-layer perceptron classification model to distinguish patients with Menière’s disease from controls. The primary outcomes were accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the classification model.

Results

The classification accuracy of the machine learning model on the test set was 82%, with a sensitivity of 83%, and a specificity of 82%. The positive and negative predictive values were 71%, and 90%, respectively.

Conclusion

The multi-layer perceptron classification model yielded a precise, high-diagnostic performance in identifying patients with Menière’s disease based on radiomic features extracted from conventional T2-weighted MRI scans. In the future, radiomics might serve as a fast and noninvasive decision support system, next to clinical evaluation in the diagnosis of Menière’s disease.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11547-021-01425-w.

Hubness weighted svm ensemble for prediction of breast cancer subtypes

BACKGROUND

Breast cancer is a major disease causing panic among women worldwide. Since gene mutations are the root cause for cancer development, analyzing gene expressions can give more insights into various phenotype of cancer treatments. Breast Cancer subtype prediction from gene expression data can provide more information for cancer treatment decisions.

OBJECTIVE

Gene expressions are complex for analysis due to its high dimensional nature. Machine learning algorithms such as k-Nearest Neighbors, Support Vector Machine (SVM) and Random Forest are used with selection of features for prediction of breast cancer subtypes. Prediction accuracy of the existing methods are affected due to high dimensional nature of gene expressions. The objective of the work is to propose an efficient algorithm for the prediction of breast cancer subtypes from gene expression.

METHODS

For subtype prediction, a novel Hubness Weighted Support Vector machine algorithm (HWSVM) using bad hubness score as a weight measure to handle the outliers in the data has been proposed. Based on the various subtypes, features are projected into seven different feature sets and Ensemble based Hubness Aware Weighted Support Vector Machine (HWSVMEns) is implemented for breast cancer subtype prediction.

RESULTS

The proposed algorithms have been compared with the classical SVM and other traditional algorithms such as Random Forest, k-Nearest Neighbor algorithms and also with various gene selection methods.

CONCLUSIONS

Experimental results show that the proposed HWSVM outperforms other algorithms in terms of accuracy, precision, recall and F1 score due to the hubness weightage scheme and the ensemble approach. The experiments have shown an average accuracy of 92% across various gene expression datasets.

LatLRR-FCNs: Latent Low-Rank Representation With Fully Convolutional Networks for Medical Image Fusion

Medical image fusion, which aims to derive complementary information from multi-modality medical images, plays an important role in many clinical applications, such as medical diagnostics and treatment. We propose the LatLRR-FCNs, which is a hybrid medical image fusion framework consisting of the latent low-rank representation (LatLRR) and the fully convolutional networks (FCNs). Specifically, the LatLRR module is used to decompose the multi-modality medical images into low-rank and saliency components, which can provide fine-grained details and preserve energies, respectively. The FCN module aims to preserve both global and local information by generating the weighting maps for each modality image. The final weighting map is obtained using the weighted local energy and the weighted sum of the eight-neighborhood-based modified Laplacian method. The fused low-rank component is generated by combining the low-rank components of each modality image according to the guidance provided by the final weighting map within pyramid-based fusion. A simple sum strategy is used for the saliency components. The usefulness and efficiency of the proposed framework are thoroughly evaluated on four medical image fusion tasks, including computed tomography (CT) and magnetic resonance (MR), T1- and T2-weighted MR, positron emission tomography and MR, and single-photon emission CT and MR. The results demonstrate that by leveraging the LatLRR for image detail extraction and the FCNs for global and local information description, we can achieve performance superior to the state-of-the-art methods in terms of both objective assessment and visual quality in some cases. Furthermore, our method has a competitive performance in terms of computational costs compared to other baselines.

"Textual Prosody" Can Change Impressions of Reading in People With Normal Hearing and Hearing Loss

Recently, dynamic text presentation, such as scrolling text, has been widely used. Texts are often presented at constant timing and speed in conventional dynamic text presentation. However, dynamic text presentation enables visually presented texts to indicate timing information, such as prosody, and the texts might influence the impression of reading. In this paper, we examined this possibility by focusing on the temporal features of digital text in which texts are represented sequentially and with varying speed, duration, and timing. We call this "textual prosody." We used three types of textual prosody: "Recorded," "Shuffled," and "Constant." Recorded prosody is the reproduction of a reader's reading with pauses and varying speed that simulates talking. Shuffled prosody randomly shuffles the time course of speed and pauses in the recorded type. Constant prosody has a constant presentation speed and provides no timing information. Experiment 1 examined the effect of textual prosody on people with normal hearing. Participants read dynamic text with textual prosody silently and rated their impressions of texts. The results showed that readers with normal hearing preferred recorded textual prosody and constant prosody at the optimum speed (6 letters/second). Recorded prosody was also preferred at a low presentation speed. Experiment 2 examined the characteristics of textual prosody using an articulatory suppression paradigm. The results showed that some textual prosody was stored in the articulatory loop despite it being presented visually. In Experiment 3, we examined the effect of textual prosody with readers with hearing loss. The results demonstrated that readers with hearing loss had positive impressions at relatively low presentation speeds when the recorded prosody was presented. The results of this study indicate that the temporal structure is processed regardless of whether the input is visual or auditory. Moreover, these results suggest that textual prosody can enrich reading not only in people with normal hearing but also in those with hearing loss, regardless of acoustic experiences.

Research Insights on Neural Effects of Auditory Deprivation and Restoration in Unilateral Hearing Loss: A Systematic Review

Neuroplasticity following bilateral deafness and auditory restoration has been repeatedly investigated. In clinical practice, however, a significant number of patients present a severe-to-profound unilateral hearing loss (UHL). To date, less is known about the neuroplasticity following monaural hearing deprivation and auditory input restoration. This article provides an overview of the current research insights on the impact of UHL on the brain and the effect of auditory input restoration with a cochlear implant (CI). An exhaustive systematic review of the literature was performed selecting 38 studies that apply different neural analyses techniques. The main results show that the hearing ear becomes functionally dominant after monaural deprivation, reshaping the lateralization of the neural network for auditory processing, a process that can be considered to influence auditory restoration. Furthermore, animal models predict that the onset time of UHL impacts auditory restoration. Hence, the results seem to advocate for early restoration of UHL, although further research is required to disambiguate the effects of duration and onset of UHL on auditory restoration and on structural neuroplasticity following UHL deprivation and restoration. Ongoing developments on CI devices compatible with Magnetic Resonance Imaging (MRI) examinations will provide a unique opportunity to investigate structural and functional neuroplasticity following CI restoration more directly.

Multivariate Approach for Alzheimer's Disease Detection Using Stationary Wavelet Entropy and Predator-Prey Particle Swarm Optimization

BACKGROUND

The number of patients with Alzheimer's disease is increasing rapidly every year. Scholars often use computer vision and machine learning methods to develop an automatic diagnosis system.

OBJECTIVE

In this study, we developed a novel machine learning system that can make diagnoses automatically from brain magnetic resonance images.

METHODS

First, the brain imaging was processed, including skull stripping and spatial normalization. Second, one axial slice was selected from the volumetric image, and stationary wavelet entropy (SWE) was done to extract the texture features. Third, a single-hidden-layer neural network was used as the classifier. Finally, a predator-prey particle swarm optimization was proposed to train the weights and biases of the classifier.

RESULTS

Our method used 4-level decomposition and yielded 13 SWE features. The classification yielded an overall accuracy of 92.73±1.03%, a sensitivity of 92.69±1.29%, and a specificity of 92.78±1.51%. The area under the curve is 0.95±0.02. Additionally, this method only cost 0.88 s to identify a subject in online stage, after its volumetric image is preprocessed.

CONCLUSION

In terms of classification performance, our method performs better than 10 state-of-the-art approaches and the performance of human observers. Therefore, this proposed method is effective in the detection of Alzheimer's disease.

In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer

In contrast to conventional optical imaging modalities, hyperspectral imaging (HSI) is able to capture much more information from a certain scene, both within and beyond the visual spectral range (from 400 to 700 nm). This imaging modality is based on the principle that each material provides different responses to light reflection, absorption, and scattering across the electromagnetic spectrum. Due to these properties, it is possible to differentiate and identify the different materials/substances presented in a certain scene by their spectral signature. Over the last two decades, HSI has demonstrated potential to become a powerful tool to study and identify several diseases in the medical field, being a non-contact, non-ionizing, and a label-free imaging modality. In this review, the use of HSI as an imaging tool for the analysis and detection of cancer is presented. The basic concepts related to this technology are detailed. The most relevant, state-of-the-art studies that can be found in the literature using HSI for cancer analysis are presented and summarized, both in-vivo and ex-vivo. Lastly, we discuss the current limitations of this technology in the field of cancer detection, together with some insights into possible future steps in the improvement of this technology.

Inefficient Involvement of Insula in Sensorineural Hearing Loss

The insular cortex plays an important role in multimodal sensory processing, audio-visual integration and emotion; however, little is known about how the insula is affected by auditory deprivation due to sensorineural hearing loss (SNHL). To address this issue, we used structural and functional magnetic resonance imaging to determine if the neural activity within the insula and its interregional functional connectivity (FC) was disrupted by SNHL and if these alterations were correlated clinical measures of emotion and cognition. Thirty-five SNHL subjects and 54 Controls enrolled in our study underwent auditory evaluation, neuropsychological assessments, functional and structure MRI, respectively. Twenty five patients and 20 Controls underwent arterial spin labeling scanning. FC of six insula subdivisions were assessed and the FC results were compared to the neuropsychological tests. Interregional connections were also compared among insula-associated networks, including salience network (SN), default mode network (DMN), and central executive network (CEN). Compared to Controls, SNHL subjects demonstrated hyperperfusion in the insula and significantly decreased FC between some insula subdivisions and other brain regions, including thalamus, putamen, precentral gyrus, postcentral gyrus, mid-cingulate cortex, dorsolateral prefrontal cortex, rolandic operculum. Anxiety, depression and cognitive impairments were correlated with FC values. Abnormal interactions among SN, DMN, and CEN were observed in SNHL group. Our result provides support for the "inefficient high-order control" theory of the insula in which the auditory deprivation caused by SNHL contributes to impaired sensory integration and central deficits in emotional and cognitive processing.

Multi-View Maximum Entropy Clustering by Jointly Leveraging Inter-View Collaborations and Intra-View-Weighted Attributes

As a dedicated countermeasure for heterogeneous multi-view data, multi-view clustering is currently a hot topic in machine learning. However, many existing methods either neglect the effective collaborations among views during clustering or do not distinguish the respective importance of attributes in views, instead treating them equivalently. Motivated by such challenges, based on maximum entropy clustering (MEC), two specialized criteria-inter-view collaborative learning (IEVCL) and intra-view-weighted attributes (IAVWA)-are first devised as the bases. Then, by organically incorporating IEVCL and IAVWA into the formulation of classic MEC, a novel, collaborative multi-view clustering model and the matching algorithm referred to as the view-collaborative, attribute-weighted MEC (VC-AW-MEC) are proposed. The significance of our efforts is three-fold: 1) both IEVCL and IAVWA are dedicatedly devised based on MEC so that the proposed VC-AW-MEC is qualified to effectively handle as many multi-view data scenes as possible; 2) IEVCL is competent in seeking the consensus across all involved views throughout clustering, whereas IAVWA is capable of adaptively discriminating the individual impact regarding the attributes within each view; and 3) benefiting from jointly leveraging IEVCL and IAVWA, compared with some existing state-of-the-art approaches, the proposed VC-AW-MEC algorithm generally exhibits preferable clustering effectiveness and stability on heterogeneous multi-view data. Our efforts have been verified in many synthetic or real-world multi-view data scenes.

Automatic Change Detection for Real-Time Monitoring of EEG Signals

In recent years, automatic change detection for real-time monitoring of electroencephalogram (EEG) signals has attracted widespread interest with a large number of clinical applications. However, it is still a challenging problem. This paper presents a novel framework for this task where joint time-domain features are firstly computed to extract temporal fluctuations of a given EEG data stream; and then, an auto-regressive (AR) linear model is adopted to model the data and temporal anomalies are subsequently calculated from that model to reflect the possibilities that a change occurs; a non-parametric statistical test based on Randomized Power Martingale (RPM) is last performed for making change decision from the resulting anomaly scores. We conducted experiments on the publicly-available Bern-Barcelona EEG database where promising results for terms of detection precision (96.97%), detection recall (97.66%) as well as computational efficiency have been achieved. Meanwhile, we also evaluated the proposed method for real detection of seizures occurrence for a monitoring epilepsy patient. The results of experiments by using both the testing database and real application demonstrated the effectiveness and feasibility of the method for the purpose of change detection in EEG signals. The proposed framework has two additional properties: (1) it uses a pre-defined AR model for modeling of the past observed data so that it can be operated in an unsupervised manner, and (2) it uses an adjustable threshold to achieve a scalable decision making so that a coarse-to-fine detection strategy can be developed for quick detection or further analysis purposes.

Classification of Alzheimer's Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling

Alzheimer's disease (AD) is a progressive brain disease. The goal of this study is to provide a new computer-vision based technique to detect it in an efficient way. The brain-imaging data of 98 AD patients and 98 healthy controls was collected using data augmentation method. Then, convolutional neural network (CNN) was used, CNN is the most successful tool in deep learning. An 8-layer CNN was created with optimal structure obtained by experiences. Three activation functions (AFs): sigmoid, rectified linear unit (ReLU), and leaky ReLU. The three pooling-functions were also tested: average pooling, max pooling, and stochastic pooling. The numerical experiments demonstrated that leaky ReLU and max pooling gave the greatest result in terms of performance. It achieved a sensitivity of 97.96%, a specificity of 97.35%, and an accuracy of 97.65%, respectively. In addition, the proposed approach was compared with eight state-of-the-art approaches. The method increased the classification accuracy by approximately 5% compared to state-of-the-art methods.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations

Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.

Paroxysmal atrial fibrillation recognition based on multi-scale wavelet α-entropy

BACKGROUND

This study proposed an effective method based on the wavelet multi-scale α-entropy features of heart rate variability (HRV) for the recognition of paroxysmal atrial fibrillation (PAF). This new algorithm combines wavelet decomposition and non-linear analysis methods. The PAF signal, the signal distant from PAF, and the normal sinus signals can be identified and distinguished by extracting the characteristic parameters from HRV signals and analyzing their quantification indexes. The original ECG signals for QRS detection and HRV signal extraction are first processed. The features from the HRV signals are extracted as feature vectors using the wavelet multi-scale entropy. A support vector machine-based classifier is used for PAF prediction.

RESULTS

The performance of the proposed method in predicting PAF episodes is evaluated with 100 signals from the MIT-BIT PAF prediction database. With regard to the dynamics and uncertainty of PAF signals, our proposed method obtains the values of 92.18, 94.88, and 89.48% for the evaluation criteria of correct rate, sensitivity, and specificity, respectively.

CONCLUSIONS

Our proposed method presents better results than the existing studies based on time domain, frequency domain, and non-linear methods. Thus, our method shows considerable potential for clinical monitoring and treatment.