Deep Learning for Understanding Faces: Machines May Be Just as Good, or Better, than Humans

2018 ◽  
Vol 35 (1) ◽  
pp. 66-83 ◽  
Author(s):  
Rajeev Ranjan ◽  
Swami Sankaranarayanan ◽  
Ankan Bansal ◽  
Navaneeth Bodla ◽  
Jun-Cheng Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Better Than ◽  
Learning For Understanding

scholarly journals Deep learning for intelligent diagnosis in thyroid scintigraphy

2021 ◽  
Vol 49 (1) ◽  
pp. 030006052098284
Author(s):  
Tingting Qiao ◽  
Simin Liu ◽  
Zhijun Cui ◽  
Xiaqing Yu ◽  
Haidong Cai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Disease Diagnosis ◽  
Kappa Coefficient ◽  
Diagnostic Assessment ◽  
First Year ◽  
Thyroid Scintigraphy ◽  
Diagnostic Ability ◽  
The Third ◽  
Classification Time ◽  
Better Than

Objective To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy. Methods We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model’s performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents. Results The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided “diagnostic assistance” to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents. Conclusion DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves’ disease and subacute thyroiditis.

scholarly journals Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Crouzet ◽  
Gwangjin Jeong ◽  
Rachel H. Chae ◽  
Krystal T. LoPresti ◽  
Cody E. Dunn ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prussian Blue ◽  
Processing Speed ◽  
Digital Pathology ◽  
Ground Truth ◽  
Individual Variability ◽  
Rgb Images ◽  
Cerebral Microhemorrhages ◽  
Phasor Analysis ◽  
Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

scholarly journals Deep Learning Methods for Classification of Certain Abnormalities in Echocardiography

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 495
Author(s):  
Imayanmosha Wahlang ◽  
Arnab Kumar Maji ◽  
Goutam Saha ◽  
Prasun Chakrabarti ◽  
Michal Jasinski ◽  
...  
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Support Vector ◽  
Variational Autoencoder ◽  
Different Types ◽  
Static Images ◽  
Long Short Term Memory ◽  
2D And 3D ◽  
Better Than

This article experiments with deep learning methodologies in echocardiogram (echo), a promising and vigorously researched technique in the preponderance field. This paper involves two different kinds of classification in the echo. Firstly, classification into normal (absence of abnormalities) or abnormal (presence of abnormalities) has been done, using 2D echo images, 3D Doppler images, and videographic images. Secondly, based on different types of regurgitation, namely, Mitral Regurgitation (MR), Aortic Regurgitation (AR), Tricuspid Regurgitation (TR), and a combination of the three types of regurgitation are classified using videographic echo images. Two deep-learning methodologies are used for these purposes, a Recurrent Neural Network (RNN) based methodology (Long Short Term Memory (LSTM)) and an Autoencoder based methodology (Variational AutoEncoder (VAE)). The use of videographic images distinguished this work from the existing work using SVM (Support Vector Machine) and also application of deep-learning methodologies is the first of many in this particular field. It was found that deep-learning methodologies perform better than SVM methodology in normal or abnormal classification. Overall, VAE performs better in 2D and 3D Doppler images (static images) while LSTM performs better in the case of videographic images.

scholarly journals Channel state information–based multi-level fingerprinting for indoor localization with deep learning

2018 ◽  
Vol 14 (10) ◽  
pp. 155014771880671 ◽  
Author(s):  
Tao Li ◽  
Hai Wang ◽  
Yuan Shao ◽  
Qiang Niu
Keyword(s):  
Deep Learning ◽  
Channel State Information ◽  
Deep Neural Networks ◽  
Training Phase ◽  
Channel State ◽  
Positioning Accuracy ◽  
State Information ◽  
Filtering Method ◽  
Multi Level ◽  
Better Than

With the rapid growth of indoor positioning requirements without equipment and the convenience of channel state information acquisition, the research on indoor fingerprint positioning based on channel state information is increasingly valued. In this article, a multi-level fingerprinting approach is proposed, which is composed of two-level methods: the first layer is achieved by deep learning and the second layer is implemented by the optimal subcarriers filtering method. This method using channel state information is termed multi-level fingerprinting with deep learning. Deep neural networks are applied in the deep learning of the first layer of multi-level fingerprinting with deep learning, which includes two phases: an offline training phase and an online localization phase. In the offline training phase, deep neural networks are used to train the optimal weights. In the online localization phase, the top five closest positions to the location position are obtained through forward propagation. The second layer optimizes the results of the first layer through the optimal subcarriers filtering method. Under the accuracy of 0.6 m, the positioning accuracy of two common environments has reached, respectively, 96% and 93.9%. The evaluation results show that the positioning accuracy of this method is better than the method based on received signal strength, and it is better than the support vector machine method, which is also slightly improved compared with the deep learning method.

scholarly journals AnnotatorJ: an ImageJ plugin to ease hand-annotation of cellular compartments

2020 ◽  
Author(s):  
Réka Hollandi ◽  
Ákos Diósdi ◽  
Gábor Hollandi ◽  
Nikita Moshkov ◽  
Péter Horváth
Keyword(s):  
Deep Learning ◽  
Training Data ◽  
Automatic Annotation ◽  
Cellular Analysis ◽  
Manual Labour ◽  
Cellular Compartments ◽  
Analysis Quality ◽  
Microscopy Images ◽  
Imagej Plugin ◽  
Better Than

AbstractAnnotatorJ combines single-cell identification with deep learning and manual annotation. Cellular analysis quality depends on accurate and reliable detection and segmentation of cells so that the subsequent steps of analyses e.g. expression measurements may be carried out precisely and without bias. Deep learning has recently become a popular way of segmenting cells, performing unimaginably better than conventional methods. However, such deep learning applications may be trained on a large amount of annotated data to be able to match the highest expectations. High-quality annotations are unfortunately expensive as they require field experts to create them, and often cannot be shared outside the lab due to medical regulations.We propose AnnotatorJ, an ImageJ plugin for the semi-automatic annotation of cells (or generally, objects of interest) on (not only) microscopy images in 2D that helps find the true contour of individual objects by applying U-Net-based pre-segmentation. The manual labour of hand-annotating cells can be significantly accelerated by using our tool. Thus, it enables users to create such datasets that could potentially increase the accuracy of state-of-the-art solutions, deep learning or otherwise, when used as training data.

scholarly journals Design of a Microwave Lowpass – Bandpass Filter using Deep Learning and Artificial Intelligence

2021 ◽  
Vol 3 (1) ◽  
pp. 1-16
Author(s):  
Saeed Roshani ◽  
◽  
Hossein Heshmati ◽  
Sobhan Roshani ◽  
◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Insertion Loss ◽  
Dual Band ◽  
Transmission Zeros ◽  
Compact Size ◽  
Electrical Devices ◽  
Low Pass ◽  
Artificial Neural Network Ann ◽  
Better Than

In this paper, a lowpass – bandpass dual band microwave filter is designed by using deep learning and artificial intelligence. The designed filter has compact size and desirable pass bands. In the proposed filter, the resonators with Z-shaped and T-shaped lines are used to design the low pass channel, while coupling lines, stepped impedance resonators and open ended stubs are utilized to design the bandpass channel. Artificial neural network (ANN) and deep learning (DL) technique has been utilized to extract the proposed filter transfer function, so the values of the transmission zeros can be located in the desired frequency. This technique can also be used for the other electrical devices. The lowpass channel cut off frequency is 1 GHz, with better than 0.2 dB insertion loss. Also, the bandpass channel main frequency is designed at 2.4 GHz with 0.5 dB insertion loss in the passband.

scholarly journals DEEP LEARNING BASED FEATURE MATCHING AND ITS APPLICATION IN IMAGE ORIENTATION

2020 ◽  
Vol V-2-2020 ◽  
pp. 25-33 ◽  
Author(s):  
L. Chen ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Deep Learning ◽  
Feature Matching ◽  
Shape Estimation ◽  
Feature Description ◽  
Performance Benchmark ◽  
Matching Performance ◽  
Affine Shape ◽  
Image Orientation ◽  
Learned Features ◽  
Better Than

Abstract. Matching images containing large viewpoint and viewing direction changes, resulting in large perspective differences, still is a very challenging problem. Affine shape estimation, orientation assignment and feature description algorithms based on detected hand crafted features have shown to be error prone. In this paper, affine shape estimation, orientation assignment and description of local features is achieved through deep learning. Those three modules are trained based on loss functions optimizing the matching performance of input patch pairs. The trained descriptors are first evaluated on the Brown dataset (Brown et al., 2011), a standard descriptor performance benchmark. The whole pipeline is then tested on images of small blocks acquired with an aerial penta camera, to compute image orientation. The results show that learned features perform significantly better than alternatives based on hand crafted features.

scholarly journals Plant Disease Detection and Localization using GRADCAM

2020 ◽  
Vol 8 (6) ◽  
pp. 3069-3075
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
Plant Diseases ◽  
Financial Resources ◽  
Disease Detection ◽  
The World ◽  
Detection And Localization ◽  
Better Than ◽  
Made In

Plant diseases are diseases that change or disrupt its important functions. The reduction in the age at which a plant dies is the main danger of plant diseases. And farmers around the world have to face the challenge of identifying and classifying these diseases and changing their treatments for each disease. This task becomes more difficult when they have to rely on naked eyes to identify diseases due to the lack of proper financial resources. But with the widespread use of smartphones by farmers and advances made in the field of deep learning, researchers around the world are trying to find a solution to this problem. Similarly, the purpose of this paper is to classify these diseases using deep learning and localize them on their respective leaves. We have considered two main models for classification called resnet and efficientnet and for localizing these diseases we have used GRADCAM and CAM. GRADCAM was able to localize diseases better than CAM

scholarly journals Local Regularizer Improves Generalization

2020 ◽  
Vol 34 (04) ◽  
pp. 6861-6868 ◽  
Author(s):  
Yikai Zhang ◽  
Hui Qu ◽  
Dimitris Metaxas ◽  
Chao Chen
Keyword(s):  
Deep Learning ◽  
Theoretical Analysis ◽  
Experimental Evidence ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Training Algorithms ◽  
Training Methods ◽  
Theoretical Understanding ◽  
Better Than

Regularization plays an important role in generalization of deep learning. In this paper, we study the generalization power of an unbiased regularizor for training algorithms in deep learning. We focus on training methods called Locally Regularized Stochastic Gradient Descent (LRSGD). An LRSGD leverages a proximal type penalty in gradient descent steps to regularize SGD in training. We show that by carefully choosing relevant parameters, LRSGD generalizes better than SGD. Our thorough theoretical analysis is supported by experimental evidence. It advances our theoretical understanding of deep learning and provides new perspectives on designing training algorithms. The code is available at https://github.com/huiqu18/LRSGD.

Sign in / Sign up

Export Citation Format

Share Document