scholarly journals Automatic detection and monitoring of abnormal skull shape in children with deformational plagiocephaly using deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Seyed Amir Hossein Tabatabaei ◽  
Patrick Fischer ◽  
Sonja Wattendorf ◽  
Fatemeh Sabouripour ◽  
Hans-Peter Howaldt ◽  
...  
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Treatment Phase ◽  
Vital Role ◽  
Classification Model ◽  
Deformational Plagiocephaly ◽  
Deep Learning Network ◽  
Medical Examinations ◽  
The Impact ◽  
The Given

AbstractCraniofacial anomaly including deformational plagiocephaly as a result of deformities in head and facial bones evolution is a serious health problem in newbies. The impact of such condition on the affected infants is profound from both medical and social viewpoint. Indeed, timely diagnosing through different medical examinations like anthropometric measurements of the skull or even Computer Tomography (CT) image modality followed by a periodical screening and monitoring plays a vital role in treatment phase. In this paper, a classification model for detecting and monitoring deformational plagiocephaly in affected infants is presented. The presented model is based on a deep learning network architecture. The given model achieves high accuracy of 99.01% with other classification parameters. The input to the model are the images captured by commonly used smartphone cameras which waives the requirement to sophisticated medical imaging modalities. The method is deployed into a mobile application which enables the parents/caregivers and non-clinical experts to monitor and report the treatment progress at home.

scholarly journals VISUAL TRACKING UTILIZING OBJECT CONCEPT FROM DEEP LEARNING NETWORK

2017 ◽  
Vol IV-1/W1 ◽  
pp. 125-132 ◽  
Author(s):  
C. Xiao ◽  
A. Yilmaz ◽  
S. Lia
Keyword(s):  
Deep Learning ◽  
Visual Tracking ◽  
Large Scale ◽  
Target Position ◽  
Appearance Model ◽  
Learning Network ◽  
Concept Model ◽  
Deep Learning Network ◽  
High Level ◽  
The Given

Despite having achieved good performance, visual tracking is still an open area of research, especially when target undergoes serious appearance changes which are not included in the model. So, in this paper, we replace the appearance model by a concept model which is learned from large-scale datasets using a deep learning network. The concept model is a combination of high-level semantic information that is learned from myriads of objects with various appearances. In our tracking method, we generate the target’s concept by combining the learned object concepts from classification task. We also demonstrate that the last convolutional feature map can be used to generate a heat map to highlight the possible location of the given target in new frames. Finally, in the proposed tracking framework, we utilize the target image, the search image cropped from the new frame and their heat maps as input into a localization network to find the final target position. Compared to the other state-of-the-art trackers, the proposed method shows the comparable and at times better performance in real-time.

scholarly journals Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1689
Author(s):  
Chuang Lin ◽  
Shanxin Guo ◽  
Jinsong Chen ◽  
Luyi Sun ◽  
Xiaorou Zheng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Network Performance ◽  
Aerial Image ◽  
Label Noise ◽  
Remote Sensing Classification ◽  
Learning Network ◽  
Training Samples ◽  
Deep Learning Network ◽  
The Impact

The deep-learning-network performance depends on the accuracy of the training samples. The training samples are commonly labeled by human visual investigation or inherited from historical land-cover or land-use maps, which usually contain label noise, depending on subjective knowledge and the time of the historical map. Helping the network to distinguish noisy labels during the training process is a prerequisite for applying the model for training across time and locations. This study proposes an antinoise framework, the Weight Loss Network (WLN), to achieve this goal. The WLN contains three main parts: (1) the segmentation subnetwork, which any state-of-the-art segmentation network can replace; (2) the attention subnetwork (λ); and (3) the class-balance coefficient (α). Four types of label noise (an insufficient label, redundant label, missing label and incorrect label) were simulated by dilate and erode processing to test the network’s antinoise ability. The segmentation task was set to extract buildings from the Inria Aerial Image Labeling Dataset, which includes Austin, Chicago, Kitsap County, Western Tyrol and Vienna. The network’s performance was evaluated by comparing it with the original U-Net model by adding noisy training samples with different noise rates and noise levels. The result shows that the proposed antinoise framework (WLN) can maintain high accuracy, while the accuracy of the U-Net model dropped. Specifically, after adding 50% of dilated-label samples at noise level 3, the U-Net model’s accuracy dropped by 12.7% for OA, 20.7% for the Mean Intersection over Union (MIOU) and 13.8% for Kappa scores. By contrast, the accuracy of the WLN dropped by 0.2% for OA, 0.3% for the MIOU and 0.8% for Kappa scores. For eroded-label samples at the same level, the accuracy of the U-Net model dropped by 8.4% for OA, 24.2% for the MIOU and 43.3% for Kappa scores, while the accuracy of the WLN dropped by 4.5% for OA, 4.7% for the MIOU and 0.5% for Kappa scores. This result shows that the antinoise framework proposed in this paper can help current segmentation models to avoid the impact of noisy training labels and has the potential to be trained by a larger remote sensing image set regardless of the inner label error.

scholarly journals Classification of Traffic Vehicle Density Using Deep Learning

2020 ◽  
Vol 14 (1) ◽  
pp. 69
Author(s):  
Abdul Kholik ◽  
Agus Harjoko ◽  
Wahyono Wahyono
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Cross Validation ◽  
Classification Model ◽  
Density Level ◽  
Vehicle Density ◽  
The Impact ◽  
Fold Cross Validation

The volume density of vehicles is a problem that often occurs in every city, as for the impact of vehicle density is congestion. Classification of vehicle density levels on certain roads is required because there are at least 7 vehicle density level conditions. Monitoring conducted by the police, the Department of Transportation and the organizers of the road currently using video-based surveillance such as CCTV that is still monitored by people manually. Deep Learning is an approach of synthetic neural network-based learning machines that are actively developed and researched lately because it has succeeded in delivering good results in solving various soft-computing problems, This research uses the convolutional neural network architecture. This research tries to change the supporting parameters on the convolutional neural network to further calibrate the maximum accuracy. After the experiment changed the parameters, the classification model was tested using K-fold cross-validation, confusion matrix and model exam with data testing. On the K-fold cross-validation test with an average yield of 92.83% with a value of K (fold) = 5, model testing is done by entering data testing amounting to 100 data, the model can predict or classify correctly i.e. 81 data.

Comparing optimization methods for deep learning in image processing applications

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Alexander Geng ◽  
Ali Moghiseh ◽  
Claudia Redenbach ◽  
Katja Schladitz
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Optimization Methods ◽  
Optimization Method ◽  
Stochastic Gradient Descent ◽  
Style Transfer ◽  
Artistic Style ◽  
Deep Learning Network ◽  
The Individual ◽  
The Impact

Abstract Training a deep learning network requires choosing its weights such that the output minimizes a given loss function. In practice, stochastic gradient descent is frequently used for solving the optimization problem. Several variants of this approach have been suggested in the literature. We study the impact of the choice of the optimization method on the outcome of the learning process at the example of two image processing applications from quite different fields. The first one is artistic style transfer, where the content of one image is combined with the style of another one. The second application is a real world classification task from industry, namely detecting defects in images of air filters. In both cases, clear differences between the results of the individual optimization methods are observed.

Deep Learning based Fruit Freshness Classification and Detection with CMOS Image sensors and Edge processors

2020 ◽  
Vol 2020 (12) ◽  
pp. 172-1-172-7 ◽  
Author(s):  
Tejaswini Ananthanarayana ◽  
Raymond Ptucha ◽  
Sean C. Kelly
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Image Classification ◽  
High Speed ◽  
Image Sensor ◽  
Vital Role ◽  
Image Sensors ◽  
Classification Model ◽  
Detection Model ◽  
Cmos Image Sensors

CMOS Image sensors play a vital role in the exponentially growing field of Artificial Intelligence (AI). Applications like image classification, object detection and tracking are just some of the many problems now solved with the help of AI, and specifically deep learning. In this work, we target image classification to discern between six categories of fruits — fresh/ rotten apples, fresh/ rotten oranges, fresh/ rotten bananas. Using images captured from high speed CMOS sensors along with lightweight CNN architectures, we show the results on various edge platforms. Specifically, we show results using ON Semiconductor’s global-shutter based, 12MP, 90 frame per second image sensor (XGS-12), and ON Semiconductor’s 13 MP AR1335 image sensor feeding into MobileNetV2, implemented on NVIDIA Jetson platforms. In addition to using the data captured with these sensors, we utilize an open-source fruits dataset to increase the number of training images. For image classification, we train our model on approximately 30,000 RGB images from the six categories of fruits. The model achieves an accuracy of 97% on edge platforms using ON Semiconductor’s 13 MP camera with AR1335 sensor. In addition to the image classification model, work is currently in progress to improve the accuracy of object detection using SSD and SSDLite with MobileNetV2 as the feature extractor. In this paper, we show preliminary results on the object detection model for the same six categories of fruits.

scholarly journals Deep Learning to Unveil Correlations between Urban Landscape and Population Health

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 2105 ◽  
Author(s):  
Daniele Pala ◽  
Alessandro Aldo Caldarone ◽  
Marica Franzini ◽  
Alberto Malovini ◽  
Cristiana Larizza ◽  
...  
Keyword(s):  
New York ◽  
New York City ◽  
Deep Learning ◽  
York City ◽  
Network Architecture ◽  
Urban Landscape ◽  
Healthcare Providers ◽  
Classification Model ◽  
Gradual Change ◽  
Public Health Decision

The global healthcare landscape is continuously changing throughout the world as technology advances, leading to a gradual change in lifestyle. Several diseases such as asthma and cardiovascular conditions are becoming more diffuse, due to a rise in pollution exposure and a more sedentary lifestyle. Healthcare providers deal with increasing new challenges, and thanks to fast-developing big data technologies, they can be faced with systems that provide direct support to citizens. In this context, within the EU-funded Participatory Urban Living for Sustainable Environments (PULSE) project, we are implementing a data analytic platform designed to provide public health decision makers with advanced approaches, to jointly analyze maps and geospatial information with healthcare and air pollution data. In this paper we describe a component of such platforms, which couples deep learning analysis of urban geospatial images with healthcare indexes collected by the 500 Cities project. By applying a pre-learned deep Neural Network architecture, satellite images of New York City are analyzed and latent feature variables are extracted. These features are used to derive clusters, which are correlated with healthcare indicators by means of a multivariate classification model. Thanks to this pipeline, it is possible to show that, in New York City, health care indexes are significantly correlated to the urban landscape. This pipeline can serve as a basis to ease urban planning, since the same interventions can be organized on similar areas, even if geographically distant.

scholarly journals P137 Deep learning enables accurate automatic sleep stage classification in a clinical paediatric population

2021 ◽  
Vol 2 (Supplement_1) ◽  
pp. A66-A66
Author(s):  
P Somaskandhan ◽  
H Korkalainen ◽  
P Terrill ◽  
S Sigurðardóttir ◽  
E Arnardóttir ◽  
...  
Keyword(s):  
Deep Learning ◽  
Sleep Disorders ◽  
Network Architecture ◽  
Short Term Memory ◽  
Sleep Stage ◽  
Paediatric Population ◽  
Classification Model ◽  
Sleep Stages ◽  
Automatic Method ◽  
Accurate Identification

Abstract Introduction Sleep disorders are widespread in children and associated with a myriad of detrimental health sequelae. Accurate identification of sleep stages is crucial in diagnosing various sleep disorders; however, manual sleep stage scoring can be subjective, laborious, and costly. To tackle these shortcomings, we aimed to develop an accurate deep learning-based approach to automate sleep staging in a paediatric cohort. Methods A clinical dataset (n=115, 35% girls) containing overnight polysomnographic recordings of 10–13-year-old Icelandic children from the EuroPrevall-iFAAM study was utilised to develop a combined convolutional and long short-term memory neural network architecture. A three-channel input comprising electroencephalography (F4-M1), electrooculography (E1-M2), and chin electromyography was used to train and evaluate the model to classify sleep into five stages (wake/N1/N2/N3/REM) using 10-fold cross-validation. Further, inter-rater reliabilities between two manual scorers and the automatic method were investigated in a subset (n=10) of the population. Results The automatic classification model achieved an accuracy of 84.5% (Cohen’s kappa κ=0.78: substantial agreement with manual scorings). Inter-rater reliability attained between two manual scorers was 84.6% (κ=0.78), and the automatic method achieved similar concordances with them, 83.4% (κ=0.76) and 82.7% (κ=0.75). Discussion The developed model achieved high accuracy and compared favourably to previously published state-of-the-art methods (performance range: 74.8%-84.3%). Inter-rater reliabilities were on par with the consensus between manual scorers and even better than among international sleep centres (commonly 0.57–0.63 as per literature). Therefore, incorporating the proposed methodology in clinical practice could be highly beneficial as it enables fast, cost-effective, and accurate sleep classification in children.

Sign in / Sign up

Export Citation Format

Share Document