scholarly journals Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images

2021 ◽  
Vol 7 ◽  
pp. e719
Author(s):  
Hai Thanh Nguyen ◽  
Toan Bao Tran ◽  
Huong Hoang Luong ◽  
Tuan Khoi Nguyen Huynh
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
World Health Organisation ◽  
High Accuracy ◽  
World Health ◽  
Network Architectures ◽  
Ct Scanner ◽  
Segmentation Methods ◽  
Feature Pyramid ◽  
Significant Effort

Coronavirus Disease 2019 (COVID-19) pandemic has been ferociously destroying global health and economics. According to World Health Organisation (WHO), until May 2021, more than one hundred million infected cases and 3.2 million deaths have been reported in over 200 countries. Unfortunately, the numbers are still on the rise. Therefore, scientists are making a significant effort in researching accurate, efficient diagnoses. Several studies advocating artificial intelligence proposed COVID diagnosis methods on lung images with high accuracy. Furthermore, some affected areas in the lung images can be detected accurately by segmentation methods. This work has considered state-of-the-art Convolutional Neural Network architectures, combined with the Unet family and Feature Pyramid Network (FPN) for COVID segmentation tasks on Computed Tomography (CT) scanner samples the Italian Society of Medical and Interventional Radiology dataset. The experiments show that the decoder-based Unet family has reached the best (a mean Intersection Over Union (mIoU) of 0.9234, 0.9032 in dice score, and a recall of 0.9349) with a combination between SE ResNeXt and Unet++. The decoder with the Unet family obtained better COVID segmentation performance in comparison with Feature Pyramid Network. Furthermore, the proposed method outperforms recent segmentation state-of-the-art approaches such as the SegNet-based network, ADID-UNET, and A-SegNet + FTL. Therefore, it is expected to provide good segmentation visualizations of medical images.

scholarly journals Robust Mouse Tracking in Complex Environments using Neural Networks

2018 ◽  
Author(s):  
Brian Q. Geuther ◽  
Sean P. Deats ◽  
Kai J. Fox ◽  
Steve A. Murray ◽  
Robert E. Braun ◽  
...  
Keyword(s):  
Neural Network ◽  
Environmental Conditions ◽  
State Of The Art ◽  
High Accuracy ◽  
General Purpose ◽  
Training Data ◽  
Network Architectures ◽  
Complex Environments ◽  
Behavioral Experiments ◽  
Modern Machine

AbstractThe ability to track animals accurately is critical for behavioral experiments. For video-based assays, this is often accomplished by manipulating environmental conditions to increase contrast between the animal and the background, in order to achieve proper foreground/background detection (segmentation). However, as behavioral paradigms become more sophisticated with ethologically relevant environments, the approach of modifying environmental conditions offers diminishing returns, particularly for scalable experiments. Currently, there is a need for methods to monitor behaviors over long periods of time, under dynamic environmental conditions, and in animals that are genetically and behaviorally heterogeneous. To address this need, we developed a state-of-the-art neural network-based tracker for mice, using modern machine vision techniques. We test three different neural network architectures to determine their performance on genetically diverse mice under varying environmental conditions. We find that an encoder-decoder segmentation neural network achieves high accuracy and speed with minimal training data. Furthermore, we provide a labeling interface, labeled training data, tuned hyperparameters, and a pre-trained network for the mouse behavior and neuroscience communities. This general-purpose neural network tracker can be easily extended to other experimental paradigms and even to other animals, through transfer learning, thus providing a robust, generalizable solution for biobehavioral research.

scholarly journals An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

2021 ◽  
Author(s):  
Anh Nguyen ◽  
Khoa Pham ◽  
Dat Ngo ◽  
Thanh Ngo ◽  
Lam Pham
Keyword(s):  
Neural Network ◽  
Supervised Classification ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Network Architectures ◽  
Activation Functions ◽  
Scene Classification ◽  
Learning Network ◽  
Deep Learning Network

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions.Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

scholarly journals Automatic Prediction of Meningioma Grade Image Based on Data Amplification and Improved Convolutional Neural Network

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Hong Zhu ◽  
Qianhao Fang ◽  
Hanzhi He ◽  
Junfeng Hu ◽  
Daihong Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Accuracy ◽  
World Health ◽  
Tumor Type ◽  
Grade Prediction ◽  
Health Organization ◽  
Deep Learning Model ◽  
The Brain

Meningioma is the second most commonly encountered tumor type in the brain. There are three grades of meningioma by the standards of the World Health Organization. Preoperative grade prediction of meningioma is extraordinarily important for clinical treatment planning and prognosis evaluation. In this paper, we present a new deep learning model for assisting automatic prediction of meningioma grades to reduce the recurrence of meningioma. Our model is based on an improved LeNet-5 model of convolutional neural network (CNN) and does not require the extraction of the diseased tissue, which can greatly enhance the efficiency. To address the issue of insufficient and unbalanced clinical data of meningioma images, we use an oversampling technique which allows us to considerably improve the accuracy of classification. Experiments on large clinical datasets show that our model can achieve quite high accuracy (i.e., as high as 83.33%) for the classification of meningioma images.

scholarly journals Interpolation Consistency Training for Semi-supervised Learning

2019 ◽  
Author(s):  
Vikas Verma ◽  
Alex Lamb ◽  
Juho Kannala ◽  
Yoshua Bengio ◽  
David Lopez-Paz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Supervised Learning ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Data Distribution ◽  
Network Architectures ◽  
Low Density ◽  
Decision Boundary ◽  
Classification Problems

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark dataset.

scholarly journals Confidence-Calibrated Human Activity Recognition

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6566
Author(s):  
Debaditya Roy ◽  
Sarunas Girdzijauskas ◽  
Serghei Socolovschi
Keyword(s):  
Neural Network ◽  
Activity Recognition ◽  
State Of The Art ◽  
Wearable Sensors ◽  
Window Size ◽  
Well Being ◽  
The State ◽  
Calibration Error ◽  
Network Architectures ◽  
Neural Network Architectures

Wearable sensors are widely used in activity recognition (AR) tasks with broad applicability in health and well-being, sports, geriatric care, etc. Deep learning (DL) has been at the forefront of progress in activity classification with wearable sensors. However, most state-of-the-art DL models used for AR are trained to discriminate different activity classes at high accuracy, not considering the confidence calibration of predictive output of those models. This results in probabilistic estimates that might not capture the true likelihood and is thus unreliable. In practice, it tends to produce overconfident estimates. In this paper, the problem is addressed by proposing deep time ensembles, a novel ensembling method capable of producing calibrated confidence estimates from neural network architectures. In particular, the method trains an ensemble of network models with temporal sequences extracted by varying the window size over the input time series and averaging the predictive output. The method is evaluated on four different benchmark HAR datasets and three different neural network architectures. Across all the datasets and architectures, our method shows an improvement in calibration by reducing the expected calibration error (ECE)by at least 40%, thereby providing superior likelihood estimates. In addition to providing reliable predictions our method also outperforms the state-of-the-art classification results in the WISDM, UCI HAR, and PAMAP2 datasets and performs as good as the state-of-the-art in the Skoda dataset.

scholarly journals A Convolutional Neural Networks Based Method for Anthracnose Infected Walnut Tree Leaves Identification

2020 ◽  
Vol 10 (2) ◽  
pp. 469 ◽  
Author(s):  
Athanasios Anagnostis ◽  
Gavriela Asiminari ◽  
Elpiniki Papageorgiou ◽  
Dionysis Bochtis
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Initial Step ◽  
Machine Learning Algorithms ◽  
Site Classification ◽  
Network Architectures ◽  
Tree Leaves ◽  
Mode A

Anthracnose is a fungal disease that infects a large number of trees worldwide, damages intensively the canopy, and spreads with ease to neighboring trees, resulting in the potential destruction of whole crops. Even though it can be treated relatively easily with good sanitation, proper pruning and copper spraying, the main issue is the early detection for the prevention of spreading. Machine learning algorithms can offer the tools for the on-site classification of healthy and affected leaves, as an initial step towards managing such diseases. The purpose of this study was to build a robust convolutional neural network (CNN) model that is able to classify images of leaves, depending on whether or not these are infected by anthracnose, and therefore determine whether a tree is infected. A set of images were used both in grayscale and RGB mode, a fast Fourier transform was implemented for feature extraction, and a CNN architecture was selected based on its performance. Finally, the best performing method was compared with state-of-the-art convolutional neural network architectures.

scholarly journals Klasifikasi Data Berat Bayi Lahir Menggunakan Weighted Probabilistic Neural Network (WPNN) (Studi Kasus di Rumah Sakit Islam Sultan Agung Semarang)

2017 ◽  
Vol 10 (1) ◽  
pp. 61
Author(s):  
Hasbi Yasin ◽  
Dwi Ispriyansti
Keyword(s):  
Neural Network ◽  
Low Birthweight ◽  
Probabilistic Neural Network ◽  
High Accuracy ◽  
Training Data ◽  
World Health ◽  
Model Accuracy ◽  
Health Organization ◽  
Very High ◽  
Length Of Gestation

Low Birthweight (LBW) is one of the causes of infant mortality. Birthweight is the weight of babies who weighed within one hour after birth. Low birthweight has been defined by the World Health Organization (WHO) as weight at birth of less than 2,500 grams (5.5 pounds). There are several factors that influence the BWI such as maternal age, length of gestation, body weight, height, blood pressure, hemoglobin and parity. This study uses a Weighted Probabilistic Neural Network (WPNN) to classify the birthweight in RSI Sultan Agung Semarang based on these factors. The results showed that the birthweight classification using WPNN models have a very high accuracy. This is shown by the model accuracy of 98.75% using the training data and 94.44% using the testing data.Keywords:Birthweight, Classification, LBW, WPNN.

scholarly journals AI-Based Video Clipping of Soccer Events

2021 ◽  
Vol 3 (4) ◽  
pp. 990-1008
Author(s):  
Joakim Olav Valand ◽  
Haris Kadragic ◽  
Steven Alexander Hicks ◽  
Vajira Lasantha Thambawita ◽  
Cise Midoglu ◽  
...  
Keyword(s):  
Neural Network ◽  
Gold Standard ◽  
Boundary Detection ◽  
High Accuracy ◽  
Time Interval ◽  
Network Architectures ◽  
Considerable Potential ◽  
Current Gold Standard ◽  
Neural Network Architectures ◽  
Human Operators

The current gold standard for extracting highlight clips from soccer games is the use of manual annotations and clippings, where human operators define the start and end of an event and trim away the unwanted scenes. This is a tedious, time-consuming, and expensive task, to the extent of being rendered infeasible for use in lower league games. In this paper, we aim to automate the process of highlight generation using logo transition detection, scene boundary detection, and optional scene removal. We experiment with various approaches, using different neural network architectures on different datasets, and present two models that automatically find the appropriate time interval for extracting goal events. These models are evaluated both quantitatively and qualitatively, and the results show that we can detect logo and scene transitions with high accuracy and generate highlight clips that are highly acceptable for viewers. We conclude that there is considerable potential in automating the overall soccer video clipping process.

scholarly journals A New Classification Approach with Deep Mask R-CNN for Synthetic Aperture Radar Image Segmentation

2020 ◽  
Vol 26 (6) ◽  
pp. 52-57
Author(s):  
Ridvan Yayla ◽  
Baha Sen
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Synthetic Aperture Radar ◽  
High Accuracy ◽  
Synthetic Aperture ◽  
Classification Approach ◽  
Radar Images ◽  
Learning Techniques ◽  
Segmentation Methods ◽  
Aperture Radar

In this paper, a hybrid classification approach which is combined with a more deep mask region-convolutional neural network and sparsity driven despeckling algorithm is proposed for synthetic aperture radar (SAR) image segmentation instead of the classical segmentation methods. In satellite technology, synthetic aperture radar images are strongly used for a lot of areas, such as evaluating air conditions, determining agricultural fields, climatic changes, and as a target in the military. Synthetic aperture radar images must be segmented to each meaningful point in the image for a quality segmentation process. In contrast, synthetic aperture radar images have a lot of noisy speckles and these speckles should be also reduced for a quality segmentation. Current studies show that deep learning techniques are widely used for segmentation methods. High accuracy and fast results can be obtained with deep learning techniques for image segmentation. Mask region-convolutional neural network can not only separate each meaningful field in the image, but it can also generate a high accuracy prediction for each meaningful field of synthetic aperture radar images. The study shows that smoothed SAR images can be classified as multiple regions with deep neural networks.

Sign in / Sign up

Export Citation Format

Share Document