Search

Alzheimer's disease (AD) poses an enormous challenge to modern healthcare. Since 2017, researchers have been using deep learning (DL) models for the early detection of AD using neuroimaging biomarkers. In this paper, we implement the EfficietNet-b0 convolutional neural network (CNN) with a novel approach—"fusion of end-to-end and transfer learning"—to classify different stages of AD. 245 T1W MRI scans of cognitively normal (CN) subjects, 229 scans of AD subjects, and 229 scans of subjects with stable mild cognitive impairment (sMCI) were employed. Each scan was preprocessed using a standard pipeline. The proposed models were trained and evaluated using preprocessed scans. For the sMCI vs. AD classification task we obtained 95.29% accuracy and 95.35% area under the curve (AUC) for model training and 93.10% accuracy and 93.00% AUC for model testing. For the multiclass AD vs. CN vs. sMCI classification task we obtained 85.66% accuracy and 86% AUC for model training and 87.38% accuracy and 88.00% AUC for model testing. Based on our experimental results, we conclude that CNN-based DL models can be used to analyze complicated MRI scan features in clinical settings. [ABSTRACT FROM AUTHOR]

This paper dispenses an exhaustive review on deep learning techniques used in the prognosis of eight different neuropsychiatric and neurological disorders such as stroke, alzheimer, parkinson's, epilepsy, autism, migraine, cerebral palsy, and multiple sclerosis. These diseases are critical, life-threatening and in most of the cases may lead to other precarious human disorders. Deep learning techniques are emerging soft computing technique which has been lucratively used to unravel different real-life problems such as pattern recognition (Face, Emotion, and Speech), traffic management, drug discovery, disease diagnosis, and network intrusion detection. This study confers the discipline, frameworks, and methodologies used by different deep learning techniques to diagnose different human neurological disorders. Here, one hundred and thirty-six different articles related to neurological and neuropsychiatric disorders diagnosed using different deep learning techniques are studied. The morbidity and mortality rate of major neuropsychiatric and neurological disorders has also been delineated. The performance and publication trend of different deep learning techniques employed in the investigation of these diseases has been examined and analyzed. Different performance metrics like accuracy, specificity, and sensitivity have also been examined. The research implication, challenges and the future directions related to the study have also been highlighted. Eventually, the research breaches are identified and it is witnessed that there is more scope in the diagnosis of migraine, cerebral palsy and stroke using different deep learning models. Likewise, there is a potential opportunity to use and explore the performance of Restricted Boltzmann Machine, Deep Boltzmann Machine and Deep Belief Network for diagnosis of different human neuropsychiatric and neurological disorders. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is an eye disease, which affects the people who are all having the diabetes for more than 10 years. The ophthalmologist identifies when the dilated eye exam causes severe in any one of the following deviations in the retina: changes in blood vessels, leaking blood vessels, newly grown blood vessels, swelling of the macula, changes in the lens, and damages to the nerve tissue. It can eventually lead to vision loss. The early detection of DR prevents the cause of blindness. In this paper, we propose the retinal image segmentation and extraction of blood vessels by morphological processing, thresholding, edge detection, and adaptive histogram equalization. For the automatic diagnosis of DR from the fundus image, we also developed a network with the convolutional neural network architecture for accurately classifying its severity. By using high-end graphical processor unit (GPU), we trained this network on the publicly available dataset such as DRIVE, DIARETDB0, and DIARETDB1_v1, and the images collected from the Aravind Eye Hospital, Coimbatore, India. Our proposed CNN achieves a sensitivity of 98%, a specificity of 93%, and an accuracy of 96.9% containing a database of 854 images. [ABSTRACT FROM AUTHOR]

Accurate and reliable brain tumor segmentation is a critical component in cancer diagnosis. According to deep learning model, a novel brain tumor segmentation method is developed by integrating fully convolutional neural networks (FCNN) and dense micro-block difference feature (DMDF) into a unified framework so as to obtain segmentation results with appearance and spatial consistency. Firstly, we propose a local feature to describe the rotation invariant property of the texture. In order to deal with the change of rotation and scale in texture image, Fisher vector encoding method is used to analyze the texture feature, which can combine with the scale information without increasing the dimension of the local feature. The obtained local features have strong robustness to rotation and gray intensity variation. Then, the non-quantifiable local feature is fused to the FCNN to perform fine boundary segmentation. Since brain tumors occupy a small portion of the image, deconvolutional layers are designed with skip connections to obtain a high quality feature map. Compared with the traditional MRI brain tumor segmentation methods, the experimental results show that the segmentation accuracy and stability has been greatly improved. Average Dice index can be up to 90.98%. And the proposed method has very high real-time performance, where brain tumor image can segment within 1 s. [ABSTRACT FROM AUTHOR]

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Efficient retrieval of relevant medical cases using semantically similar medical images from large scale repositories can assist medical experts in timely decision making and diagnosis. However, the ever-increasing volume of images hinder performance of image retrieval systems. Recently, features from deep convolutional neural networks (CNN) have yielded state-of-the-art performance in image retrieval. Further, locality sensitive hashing based approaches have become popular for their ability to allow efficient retrieval in large scale datasets. In this paper, we present a highly efficient method to compress selective convolutional features into sequence of bits using Fast Fourier Transform (FFT). Firstly, highly reactive convolutional feature maps from a pre-trained CNN are identified for medical images based on their neuronal responses using optimal subset selection algorithm. Then, layer-wise global mean activations of the selected feature maps are transformed into compact binary codes using binarization of its Fourier spectrum. The acquired hash codes are highly discriminative and can be obtained efficiently from the original feature vectors without any training. The proposed framework has been evaluated on two large datasets of radiology and endoscopy images. Experimental evaluations reveal that the proposed method significantly outperforms other features extraction and hashing schemes in both effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

In this work, an attempt has been made to classify emotional states using electrodermal activity (EDA) signals and multiscale convolutional neural networks. For this, EDA signals are considered from a publicly available "A Dataset for Emotion Analysis using Physiological Signals" (DEAP) database. These signals are decomposed into multiple-scales using the coarse-grained method. The multiscale signals are applied to the Multiscale Convolutional Neural Network (MSCNN) to automatically learn robust features directly from the raw signals. Experiments are performed with the MSCNN approach to evaluate the hypothesis (i) improved classification with electrodermal activity signals, and (ii) multiscale learning captures robust complementary features at a different scale. Results show that the proposed approach is able to differentiate various emotional states. The proposed approach yields a classification accuracy of 69.33% and 71.43% for valence and arousal states, respectively. It is observed that the number of layers and the signal length are the determinants for the classifier performance. The performance of the proposed approach outperforms the single-layer convolutional neural network. The MSCNN approach provides end-to-end learning and classification of emotional states without additional signal processing. Thus, it appears that the proposed method could be a useful tool to assess the difference in emotional states for automated decision making. [ABSTRACT FROM AUTHOR]

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU. [ABSTRACT FROM AUTHOR]