Search results for "deep learning"

Automatic left ventricle volume calculation with explainability through a deep learning weak-supervision methodology

2021

[EN] Background and objective: Magnetic resonance imaging is the most reliable imaging technique to assess the heart. More specifically there is great importance in the analysis of the left ventricle, as the main pathologies directly affect this region. In order to characterize the left ventricle, it is necessary to extract its volume. In this work we present a neural network architecture that is capable of directly estimating the left ventricle volume in short axis cine Magnetic Resonance Imaging in the end-diastolic frame and provide a segmentation of the region which is the basis of the volume calculation, thus offering explain-ability to the estimated value. Methods: The network was des…

Deep Learning-Based Real-Time Object Detection in Inland Navigation

2019

International audience; Semi-autonomous and fully-autonomous systems must have knowledge about the objects in their environment to ensure a safe navigation. Modern approaches implement deep learning techniques to train a neural network for object detection. This project will study the effectiveness of using several promising algorithms such as Faster R-CNN, SSD, and different versions of YOLO, to detect, classify, and track objects in near real-time fluvial domain. Since no dataset is available for this purpose in literature, we first started by annotating a dataset of 2488 images with almost 35 400 annotations for training the convolutional neural network architectures. We made this data s…

Computational Offloading in Mobile Edge with Comprehensive and Energy Efficient Cost Function: A Deep Learning Approach

2021

In mobile edge computing (MEC), partial computational offloading can be intelligently investigated to reduce the energy consumption and service delay of user equipment (UE) by dividing a single task into different components. Some of the components execute locally on the UE while the remaining are offloaded to a mobile edge server (MES). In this paper, we investigate the partial offloading technique in MEC using a supervised deep learning approach. The proposed technique, comprehensive and energy efficient deep learning-based offloading technique (CEDOT), intelligently selects the partial offloading policy and also the size of each component of a task to reduce the service delay and energy …

A 3D Network Based Shape Prior for Automatic Myocardial Disease Segmentation in Delayed-Enhancement MRI

2021

Abstract Objectives: In this work, a new deep learning model for relevant myocardial infarction segmentation from Late Gadolinium Enhancement (LGE)-MRI is proposed. Moreover, our novel segmentation method aims to detect microvascular-obstructed regions accurately. Material and methods: We first segment the anatomical structures, i.e., the left ventricular cavity and the myocardium, to achieve a preliminary segmentation. Then, a shape prior based framework that fuses the 3D U-Net architecture with 3D Autoencoder segmentation framework to constrain the segmentation process of pathological tissues is applied. Results: The proposed network reached outstanding myocardial segmentation compared wi…

Convolutional Neural Networks for the Identification of Regions of Interest in PET Scans: A Study of Representation Learning for Diagnosing Alzheimer…

2017

When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.

A convolutional neural network framework for blind mesh visual quality assessment

2017

In this paper, we propose a new method for blind mesh visual quality assessment using a deep learning approach. To do this, we first extract visual representative features by computing locally curvature and dihedral angles from each distorted mesh. Then, we determine from these features a set of 2D patches which are learned to a convolutional neural network (CNN). The network consists of two convolutional layers with two max-pooling layers. Then, a multilayer perceptron (MLP) with two fully connected layers is integrated to summarize the learned representation into an output node. With this network structure, feature learning and regression are used to predict the quality score of a given d…

A Deep Learning Approach for Automated Fault Detection on Solar Modules Using Image Composites

2021

Aerial inspection of solar modules is becoming increasingly popular in automatizing operations and maintenance in large-scale photovoltaic power plants. Current practices are typically time-consuming as they make use of manual acquisitions and analysis of thousands of images to scan for faults and anomalies in the modules. In this paper, we explore and evaluate the use of computer vision and deep learning methods for automating the analysis of fault detection and classification in large scale photovoltaic module installations. We use convolutional neural networks to analyze thermal and visible color images acquired by cameras mounted on unmanned aerial vehicles. We generate composite images…

2020

Abstract Background and objective Deep learning approaches are common in image processing, but often rely on supervised learning, which requires a large volume of training images, usually accompanied by hand-crafted labels. As labelled data are often not available, it would be desirable to develop methods that allow such data to be compiled automatically. In this study, we used a Generative Adversarial Network (GAN) to generate realistic B-mode musculoskeletal ultrasound images, and tested the suitability of two automated labelling approaches. Methods We used a model including two GANs each trained to transfer an image from one domain to another. The two inputs were a set of 100 longitudina…

Quality-preserving low-cost probabilistic 3D denoising with applications to Computed Tomography

2021

AbstractWe propose a pipeline for a synthetic generation of personalized Computer Tomography (CT) images, with a radiation exposure evaluation and a lifetime attributable risk (LAR) assessment. We perform a patient-specific performance evaluation for a broad range of denoising algorithms (including the most popular Deep Learning denoising approaches, wavelets-based methods, methods based on Mumford-Shah denoising etc.), focusing both on accessing the capability to reduce the patient-specific CT-induced LAR and on computational cost scalability. We introduce a parallel probabilistic Mumford-Shah denoising model (PMS), showing that it markedly-outperforms the compared common denoising methods…

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

2019

In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of …