scholarly journals Convolutional Neural Networks for Differential Diagnosis of Raynaud’s Phenomenon Based on Hands Thermal Patterns

2021 ◽  
Vol 11 (8) ◽  
pp. 3614
Author(s):  
Chiara Filippini ◽  
Daniela Cardone ◽  
David Perpetuini ◽  
Antonio Maria Chiarelli ◽  
Giulio Gualdi ◽  
...  
Keyword(s):  
Neural Network ◽  
Systemic Sclerosis ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Raynaud’S Phenomenon ◽  
Connective Tissue Diseases ◽  
Raynaud's Phenomenon ◽  
Neural Network Models ◽  
Thermal Images ◽  
Cold Challenge

Raynaud’s phenomenon (RP) is a microvessels’ disorder resulting in transient ischemia. It can be either primary or secondary to connective tissue diseases, such as systemic sclerosis. The differentiation between primary and secondary to systemic sclerosis is of paramount importance to set the proper therapeutic strategy. Thus far, thermal infrared imaging has been employed to accomplish this task by monitoring the finger temperature response to a controlled cold challenge. A completely automated methodology based on deep convolutional neural network is here introduced with the purpose of being able to differentiate systemic sclerosis from primary RP patients by relying uniquely on thermal images of the hands acquired at rest. The classification performance of such a method was compared to that of a three-dimensional convolutional neural network model implemented to classify thermal images of the hands recorded during rewarming from a cold challenge. No significant differences were found between the two procedures, thus ensuring the possibility to avoid the cold challenge. Moreover, the convolutional neural network models were compared with standard feature-based approaches and showed higher performances, thus overcoming the limitations related to the feature extraction (e.g., biases introduced by the operator). Such automated procedures can constitute promising tools for large scale screening of primary RP and secondary to systemic sclerosis in clinical practice.

scholarly journals Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition

2018 ◽  
Vol 7 (3.15) ◽  
pp. 95 ◽  
Author(s):  
M Zabir ◽  
N Fazira ◽  
Zaidah Ibrahim ◽  
Nurbaity Sabri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Visual Recognition ◽  
Error Function ◽  
Network Models ◽  
Neural Network Models ◽  
California Institute Of Technology ◽  
Institute Of Technology ◽  
Similar Accuracy

This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models. 

scholarly journals Methods for assessment of microcirculation

2021 ◽  
Vol 29 (1) ◽  
pp. 73-84
Author(s):  
Vladimira Boyadzhieva ◽  
Nikolay Stoilov
Keyword(s):  
Blood Flow ◽  
Systemic Sclerosis ◽  
Vascular Function ◽  
Raynaud’S Phenomenon ◽  
Connective Tissue Diseases ◽  
Raynaud's Phenomenon ◽  
Systemic Autoimmune Disease ◽  
Discriminative Ability ◽  
Limited Application ◽  
Secondary Raynaud’S Phenomenon

To date, many methods have entered rheumatological practice in order to evaluate more accurately the microcirculation. Most of them are non-invasive or minimally invasive, easily accessible, providing different information depending on the specifics of the study. Over the years, some of them (such as chromametry and volumetry) have lost their routine application and have acquired rather historical significance, while others have become an integral part of the rheumatological armentarium. An example of this is video capillaroscopy, which, through its dynamic development over the last 20 years, has evolved in the knowledge of changes in microcirculation in systemic sclerosis, as well as in other systemic connective tissue diseases. The expansion of knowledge in this area has led to the updating of the classification criteria for systemic sclerosis, allowing the addition of capillaroscopic changes as recognized by the European League against Rheumatism (EULAR). Another important indication for performing video capillaroscopy is the differentiation of primary from secondary Raynaud's phenomenon. Laser Doppler perfusion imaging is also used to detect secondary Raynaud's phenomenon in order to distinguish whether reduced blood flow is due to systemic autoimmune disease. Thermography also has a helpful role in diagnosing Raynaud's phenomenon, but unlike the other two methods, it has a much more limited application due to the lack of discriminative ability to distinguish nutritional from thermoregulatory blood flow, which leads to erroneous conclusions in pathological conditions. Venous occlusive plethysmography is one of the "gold standards" in the assessment of vascular function in health and disease and is an accurate, reproducible and convenient method to assess the effect of new vasoactive drugs. However, its application in everyday rheumatological practice is quite limited.

scholarly journals Towards Physics-Based Generalizable Convolutional Neural Network Models for Indoor Propagation

2021 ◽  
Author(s):  
Aristeidis Seretis
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Network Models ◽  
Radiowave Propagation ◽  
Indoor Propagation ◽  
Neural Network Models ◽  
Small Set ◽  
The Impact

A fundamental challenge for machine learning models for electromagnetics is their ability to predict output quantities of interest (such as fields and scattering parameters) in geometries that the model has not been trained for. Addressing this challenge is a key to fulfilling one of the most appealing promises of machine learning for computational electromagnetics: the rapid solution of problems of interest just by processing the geometry and the sources involved. The impact of such models that can "generalize" to new geometries is more profound for large-scale computations, such as those encountered in wireless propagation scenarios. We present generalizable models for indoor propagation that can predict received signal strengths within new geometries, beyond those of the training set of the model, for transmitters and receivers of multiple positions, and for new frequencies. We show that a convolutional neural network can "learn" the physics of indoor radiowave propagation from ray-tracing solutions of a small set of training geometries, so that it can eventually deal with substantially different geometries. We emphasize the role of exploiting physical insights in the training of the network, by defining input parameters and cost functions that assist the network to efficiently learn basic and complex propagation mechanisms.

scholarly journals Towards Physics-Based Generalizable Convolutional Neural Network Models for Indoor Propagation

2021 ◽  
Author(s):  
Aristeidis Seretis
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Network Models ◽  
Radiowave Propagation ◽  
Indoor Propagation ◽  
Neural Network Models ◽  
Small Set ◽  
The Impact

A fundamental challenge for machine learning models for electromagnetics is their ability to predict output quantities of interest (such as fields and scattering parameters) in geometries that the model has not been trained for. Addressing this challenge is a key to fulfilling one of the most appealing promises of machine learning for computational electromagnetics: the rapid solution of problems of interest just by processing the geometry and the sources involved. The impact of such models that can "generalize" to new geometries is more profound for large-scale computations, such as those encountered in wireless propagation scenarios. We present generalizable models for indoor propagation that can predict received signal strengths within new geometries, beyond those of the training set of the model, for transmitters and receivers of multiple positions, and for new frequencies. We show that a convolutional neural network can "learn" the physics of indoor radiowave propagation from ray-tracing solutions of a small set of training geometries, so that it can eventually deal with substantially different geometries. We emphasize the role of exploiting physical insights in the training of the network, by defining input parameters and cost functions that assist the network to efficiently learn basic and complex propagation mechanisms.

Ascorbic Acid does not Improve Endothelium-Dependent Flow-mediated Dilatation of the Brachial Artery in Patients with Raynaud’s Phenomenon Secondary to Systemic Sclerosis

2003 ◽  
Vol 73 (1) ◽  
pp. 3-7 ◽  
Author(s):  
M. E. Mavrikakis ◽  
J. P. Lekakis ◽  
M. Papamichael ◽  
K. S. Stamatelopoulos ◽  
Ch. C. Kostopoulos ◽  
...  
Keyword(s):  
Ascorbic Acid ◽  
Smooth Muscle ◽  
Systemic Sclerosis ◽  
Endothelial Dysfunction ◽  
Brachial Artery ◽  
Raynaud’S Phenomenon ◽  
Raynaud's Phenomenon ◽  
Water Soluble ◽  
Placebo Administration ◽  
Flow Mediated Dilatation

Previous studies have shown that patients with Raynaud’s phenomenon secondary to systemic sclerosis present abnormal endothelial function; the mechanisms responsible for the endothelial dysfunction are unknown but increased vascular oxidative stress could be a possible cause. The hypothesis that a potent water-soluble antioxidant can reverse endothelial dysfunction in these patients was tested in the present study. We examined 11 female patients with Raynaud’s phenomenon secondary to systemic sclerosis and ten healthy control women by ultrasound imaging of the brachial artery to assess flow-mediated (endothelium-dependent) and nitrate-induced (endothelium-independent) vasodilatation. Flow-mediated dilatation and nitrate-induced dilatation were significantly reduced in patients with Raynaud’s phenomenon, indicating abnormal endothelial and smooth muscle cell function. Patients with Raynaud’s phenomenon entered a double-blind, randomized, crossover placebo-controlled trial and received orally 2 g of ascorbic acid or placebo; vascular studies were repeated two hours after ascorbic acid or placebo administration. Flow-mediated dilatation did not improve after ascorbic acid (1.6 ± 2.2% to 2.2 ± 2.5%, ns) or placebo administration (1.2 ± 1,9% to 1.7 ± 1.4%, ns); also nitrate-induced dilatation was similar after ascorbic acid or placebo (16 ± 7.4% vs 17 ± 8%, ns), suggesting no effect of ascorbic acid on endothelial and vascular smooth muscle function. In conclusion, ascorbic acid does not reverse endothelial vasomotor dysfunction in the brachial circulation of patients with Raynaud’s phenomenon secondary to systemic sclerosis. The use of different antioxidants or different dosing of ascorbic acid may be required to show a beneficial effect on endothelial vasodilator function.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document