Deep Convolution Neural Network Based System for Early Diagnosis of Alzheimer's Disease

ObjectivesAlzheimer's Disease (AD) is the most general type of dementia. In all leading countries, it is one of the primary reasons of death in senior citizens. Currently, it is diagnosed by calculating the MSME score and by the manual study of MRI Scan. Also, different machine learning methods are utilized for automatic diagnosis but existing has some limitations in terms of accuracy. So, main objective of this paper to include a preprocessing method before CNN model to increase the accuracy of classification.Materials and methodIn this paper, we present a deep learning-based approach for detection of Alzheimer's Disease from ADNI database of Alzheimer's disease patients, the dataset contains fMRI and PET images of Alzheimer's patients along with normal person's image. We have applied 3D to 2D conversion and resizing of images before applying VGG-16 architecture of Convolution neural network for feature extraction. Finally, for classification SVM, Linear Discriminate, K means clustering, and Decision tree classifiers are used.ResultsThe experimental result shows that the average accuracy of 99.95% is achieved for the classification of the fMRI dataset, while the average accuracy of 73.46% is achieved with the PET dataset. On comparing results on the basis of accuracy, specificity, sensitivity and on some other parameters we found that these results are better than existing methods.Conclusionsthis paper, suggested a unique way to increase the performance of CNN models by applying some preprocessing on image dataset before sending to CNN architecture for feature extraction. We applied this method on ADNI database and on comparing the accuracies with other similar approaches it shows better results.     

An Approach Based on Mutually Informed Neural Networks to Optimize the Generalization Capabilities of Decision Support Systems Developed for Heart Failure Prediction

Available clinical methods for heart failure (HF) diagnosis are expensive and require a high-level of experts intervention. Recently, various machine learning models have been developed for the prediction of HF where most of them have an issue of over-fitting. Over-fitting occurs when machine learning based predictive models show better performance on the training data yet demonstrate a poor performance on the testing data and the other way around. Developing a machine learning model which is able to produce generalization capabilities (such that the model exhibits better performance on both the training and the testing data sets) could overall minimize the prediction errors. Hence, such prediction models could potentially be helpful to cardiologists for the effective diagnose of HF. This paper proposes a two-stage decision support system to overcome the over-fitting issue and to optimize the generalization factor. The first stage uses a mutual information based statistical model while the second stage uses a neural network. We applied our approach to the HF subset of publicly available Cleveland heart disease database. Our experimental results show that the proposed decision support system has optimized the generalization capabilities and has reduced the mean percent error (MPE) to 8.8% which is significantly less than the recently published studies. In addition, our model exhibits a 93.33% accuracy rate which is higher than twenty eight recently developed HF risk prediction models that achieved accuracy in the range of 57.85% to 92.31%. We can hope that our decision support system will be helpful to cardiologists if deployed in clinical setup.     

Modeling vegetation greenness and its climate sensitivity with deep‐learning technology

Climate sensitivity of vegetation has long been explored using statistical or process‐based models. However, great uncertainties still remain due to the methodologies’ deficiency in capturing the complex interactions between climate and vegetation. Here, we developed global gridded climate–vegetation models based on long short‐term memory (LSTM) network, which is a powerful deep‐learning algorithm for long‐time series modeling, to achieve accurate vegetation monitoring and investigate the complex relationship between climate and vegetation. We selected the normalized difference vegetation index (NDVI) that represents vegetation greenness as model outputs. The climate data (monthly temperature and precipitation) were used as inputs. We trained the networks with data from 1982 to 2003, and the data from 2004 to 2015 were used to validate the models. Error analysis and sensitivity analysis were performed to assess the model errors and investigate the sensitivity of global vegetation to climate change. Results show that models based on deep learning are very effective in simulating and predicting the vegetation greenness dynamics. For models training, the root mean square error (RMSE) is <0.01. Model validation also assure the accuracy of our models. Furthermore, sensitivity analysis of models revealed a spatial pattern of global vegetation to climate, which provides us a new way to investigate the climate sensitivity of vegetation. Our study suggests that it is a good way to integrate deep‐learning method to monitor the vegetation change under global change. In the future, we can explore more complex climatic and ecological systems with deep learning and coupling with certain physical process to better understand the nature.     

Physiological mechanisms in the control of bioluminescent countershading in a midwater shrimp

In the oceanic midwater environment, most animals have evolved an extraordinary anti‐predation behavior using bioluminescent countershading (counterillumination) to help them remain cryptic to visual predators. For the midwater penaeid shrimp, Sergestes similis, the interaction of both hormonal and neural systems may be involved in the control of counterillumination. S. similis responds to downward‐directed illumination, detected by the eyes, with light emission from five hepatic light organs. Dark‐adapted specimens undergo a slow induction process prior to production of the conventional counterillumination response. The induction of bio‐luminescence may involve a hormonal pathway mediated by the light‐adapting retinal distal pigment dispersing hormone. Once induced, the rapid control of counterillumination may involve a neural pathway. Because counterilluminating animals directly respond to their optical environment, an understanding of the control of bioluminescence provides an insight into the poorly understood visual processing capabilities of deep‐sea animals.     

A gait index may underestimate changes of gait: a comparison of the Movement Deviation Profile and the Gait Deviation Index

The ability of the Movement Deviation Profile (MDP) and Gait Deviation Index (GDI) to detect gait changes was compared in a child with cerebral palsy who underwent game training. Conventional gait analysis showed that sagittal plane angles became mirrored about normality after training. Despite considerable gait changes, the GDI showed minimal change, while the MDP detected a difference equal to a shift between 10-9 on the Functional Assessment Questionnaire scale. Responses of the GDI and MDP were examined during a synthetic transition of the patient's curves from before intervention to a state mirrored about normality. The GDI showed a symmetric response on the two opposite sides of normality but the neural network based MDP gave an asymmetric response reflecting faithfully the unequal biomechanical consequences of joint angle changes. In conclusion, the MDP can detect altered gait even if the changes are missed by the GDI.     

Accounting for robustness in modeling signal transduction responses

Abstract

A classical question in systems biology is to find a Boolean model which is able to predict the observed responses of a signaling network. It has been previously shown that such models can be tailored based on experimental data. While fitting a minimum-size network to the experimentally observed data is a natural assumption, it can potentially result in a network which is not so robust against the noises in the training dataset. Indeed, it is widely accepted now that biological systems are generally evolved to be very robust. Therefore, in the present work, we extended the classical formulation of Boolean network construction in order to put weight on the robustness of the created network. We show that our method results generally in more relevant networks. Consequently, considering robustness as a design principle of biological networks can result in more realistic models.