scholarly journals Super-resolution Ultrasound Imaging Scheme Based on a Symmetric Series Convolutional Neural Network

2021 ◽  
Author(s):  
Lakpa Dorje Tamang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Ultrasound Image ◽  
Similarity Index ◽  
Super Resolution ◽  
Input Image ◽  
Feature Maps ◽  
Proposed Model ◽  
Reconstruction Performance

In this paper, we propose a symmetric series convolutional neural network (SS-CNN), which is a novel deep convolutional neural network (DCNN)-based super-resolution (SR) technique for ultrasound medical imaging. The proposed model comprises two parts: a feature extraction network (FEN) and an up-sampling layer. In the FEN, the low-resolution (LR) counterpart of the ultrasound image passes through a symmetric series of two different DCNNs. The low-level feature maps obtained from the subsequent layers of both DCNNs are concatenated in a feed forward manner, aiding in robust feature extraction to ensure high reconstruction quality. Subsequently, the final concatenated features serve as an input map to the latter 2D convolutional layers, where the textural information of the input image is connected via skip connections. The second part of the proposed model is a sub-pixel convolutional (SPC) layer, which up-samples the output of the FEN by multiplying it with a multi-dimensional kernel followed by a periodic shuffling operation to reconstruct a high-quality SR ultrasound image. We validate the performance of the SS-CNN with publicly available ultrasound image datasets. Experimental results show that the proposed model achieves an exquisite reconstruction performance of ultrasound image over the conventional methods in terms of peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM), while providing compelling SR reconstruction time.

scholarly journals Super-resolution Ultrasound Imaging Scheme Based on a Symmetric Series Convolutional Neural Network

2021 ◽  
Author(s):  
Lakpa Dorje Tamang
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Ultrasound Image ◽  
Similarity Index ◽  
Super Resolution ◽  
Input Image ◽  
Feature Maps ◽  
Proposed Model ◽  
Reconstruction Performance

In this paper, we propose a symmetric series convolutional neural network (SS-CNN), which is a novel deep convolutional neural network (DCNN)-based super-resolution (SR) technique for ultrasound medical imaging. The proposed model comprises two parts: a feature extraction network (FEN) and an up-sampling layer. In the FEN, the low-resolution (LR) counterpart of the ultrasound image passes through a symmetric series of two different DCNNs. The low-level feature maps obtained from the subsequent layers of both DCNNs are concatenated in a feed forward manner, aiding in robust feature extraction to ensure high reconstruction quality. Subsequently, the final concatenated features serve as an input map to the latter 2D convolutional layers, where the textural information of the input image is connected via skip connections. The second part of the proposed model is a sub-pixel convolutional (SPC) layer, which up-samples the output of the FEN by multiplying it with a multi-dimensional kernel followed by a periodic shuffling operation to reconstruct a high-quality SR ultrasound image. We validate the performance of the SS-CNN with publicly available ultrasound image datasets. Experimental results show that the proposed model achieves an exquisite reconstruction performance of ultrasound image over the conventional methods in terms of peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM), while providing compelling SR reconstruction time.

scholarly journals Underwater Object Detection and Reconstruction Based on Active Single-Pixel Imaging and Super-Resolution Convolutional Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 313
Author(s):  
Mengdi Li ◽  
Anumol Mathai ◽  
Stephen L. H. Lau ◽  
Jian Wei Yam ◽  
Xiping Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Similarity Index ◽  
Super Resolution ◽  
Inspection System ◽  
Underwater Environment ◽  
Reconstruction Performance ◽  
Underwater Object ◽  
The Impact ◽  
Single Pixel

Due to medium scattering, absorption, and complex light interactions, capturing objects from the underwater environment has always been a difficult task. Single-pixel imaging (SPI) is an efficient imaging approach that can obtain spatial object information under low-light conditions. In this paper, we propose a single-pixel object inspection system for the underwater environment based on compressive sensing super-resolution convolutional neural network (CS-SRCNN). With the CS-SRCNN algorithm, image reconstruction can be achieved with 30% of the total pixels in the image. We also investigate the impact of compression ratios on underwater object SPI reconstruction performance. In addition, we analyzed the effect of peak signal to noise ratio (PSNR) and structural similarity index (SSIM) to determine the image quality of the reconstructed image. Our work is compared to the SPI system and SRCNN method to demonstrate its efficiency in capturing object results from an underwater environment. The PSNR and SSIM of the proposed method have increased to 35.44% and 73.07%, respectively. This work provides new insight into SPI applications and creates a better alternative for underwater optical object imaging to achieve good quality.

scholarly journals Visual Interpretation of Convolutional Neural Network Predictions in Classifying Medical Image Modalities

Diagnostics ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 38 ◽  
Author(s):  
Incheol Kim ◽  
Sivaramakrishnan Rajaraman ◽  
Sameer Antani
Keyword(s):  
Neural Network ◽  
Information Retrieval ◽  
Convolutional Neural Network ◽  
Visual Information ◽  
Medical Image ◽  
Input Image ◽  
Visual Interpretation ◽  
Feature Maps ◽  
Novel Method ◽  
Series Of Experiments

Deep learning (DL) methods are increasingly being applied for developing reliable computer-aided detection (CADe), diagnosis (CADx), and information retrieval algorithms. However, challenges in interpreting and explaining the learned behavior of the DL models hinders their adoption and use in real-world systems. In this study, we propose a novel method called “Class-selective Relevance Mapping” (CRM) for localizing and visualizing discriminative regions of interest (ROI) within a medical image. Such visualizations offer improved explanation of the convolutional neural network (CNN)-based DL model predictions. We demonstrate CRM effectiveness in classifying medical imaging modalities toward automatically labeling them for visual information retrieval applications. The CRM is based on linear sum of incremental mean squared errors (MSE) calculated at the output layer of the CNN model. It measures both positive and negative contributions of each spatial element in the feature maps produced from the last convolution layer leading to correct classification of an input image. A series of experiments on a “multi-modality” CNN model designed for classifying seven different types of image modalities shows that the proposed method is significantly better in detecting and localizing the discriminative ROIs than other state of the art class-activation methods. Further, to visualize its effectiveness we generate “class-specific” ROI maps by averaging the CRM scores of images in each modality class, and characterize the visual explanation through their different size, shape, and location for our multi-modality CNN model that achieved over 98% performance on a dataset constructed from publicly available images.

scholarly journals AFibNet: An Implementation of Atrial Fibrillation Detection With Convolutional Neural Network

2021 ◽  
Author(s):  
Bambang Tutuko ◽  
Siti Nurmaini ◽  
Alexander Edo Tondas ◽  
Muhammad Naufal Rachmatullah ◽  
Annisa Darmawahyuni ◽  
...  
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Convolutional Neural Network ◽  
Learning System ◽  
Single Frequency ◽  
Feature Maps ◽  
Proposed Model ◽  
Unseen Data ◽  
Specific Device ◽  
Model Formation

Abstract Background: Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R-R intervals to determine the Heart Rate Variability (HRV). An accurate HRV is the gold standard for predicting the AF condition. Hence, we propose a DL approach to analyze massive amounts of ECG raw data in a broad range of devices to overcome a current challenge.Results: This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8,232 records based on three datasets and tested with 3,610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity. When tested with unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity in 0.02 seconds for one instance when processed in theDL-Cloud System.Conclusions: These findings demonstrate that the proposed model approach can used in a broad range of devices and validated to unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment.

scholarly journals Super Resolution pada Citra Udara menggunakan Convolutional Neural Network

2021 ◽  
Vol 9 (1) ◽  
pp. 71
Author(s):  
MUHAMMAD EFAN ABDULFATTAH ◽  
LEDYA NOVAMIZANTI ◽  
SYAMSUL RIZAL
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Unmanned Aerial Vehicle ◽  
Super Resolution ◽  
Image Features ◽  
Scale Factor ◽  
Aerial Imagery ◽  
Aerial Vehicle

ABSTRAKBencana di Indonesia didominasi oleh bencana hidrometeorologi yang mengakibatkan kerusakan dalam skala besar. Melalui pemetaan, penanganan yang menyeluruh dapat dilakukan guna membantu analisa dan penindakan selanjutnya. Unmanned Aerial Vehicle (UAV) dapat digunakan sebagai alat bantu pemetaan dari udara. Namun, karena faktor kamera maupun perangkat pengolah citra yang tidak memenuhi spesifikasi, hasilnya menjadi kurang informatif. Penelitian ini mengusulkan Super Resolution pada citra udara berbasis Convolutional Neural Network (CNN) dengan model DCSCN. Model terdiri atas Feature Extraction Network untuk mengekstraksi ciri citra, dan Reconstruction Network untuk merekonstruksi citra. Performa DCSCN dibandingkan dengan Super Resolution CNN (SRCNN). Eksperimen dilakukan pada dataset Set5 dengan nilai scale factor 2, 3 dan 4. Secara berurutan SRCNN menghasilkan nilai PSNR dan SSIM sebesar 36.66 dB / 0.9542, 32.75 dB / 0.9090 dan 30.49 dB / 0.8628. Performa DCSCN meningkat menjadi 37.614dB / 0.9588, 33.86 dB / 0.9225 dan 31.48 dB / 0.8851.Kata kunci: citra udara, deep learning, super resolution ABSTRACTDisasters in Indonesia are dominated by hydrometeorological disasters, which cause large-scale damage. Through mapping, comprehensive handling can be done to help the analysis and subsequent action. Unmanned Aerial Vehicle (UAV) can be used as an aerial mapping tool. However, due to the camera and image processing devices that do not meet specifications, the results are less informative. This research proposes Super Resolution on aerial imagery based on Convolutional Neural Network (CNN) with the DCSCN model. The model consists of Feature Extraction Network for extracting image features and Reconstruction Network for reconstructing images. DCSCN's performance is compared to CNN Super Resolution (SRCNN). Experiments were carried out on the Set5 dataset with scale factor values 2, 3, and 4. The SRCNN sequentially produced PSNR and SSIM values of 36.66dB / 0.9542, 32.75dB / 0.9090 and 30.49dB / 0.8628. DCSCN's performance increased to 37,614dB / 0.9588, 33.86dB / 0.9225 and 31.48dB / 0.8851.Keywords: aerial imagery, deep learning, super resolution

scholarly journals Super resolution convolutional neural network for feature extraction in spectroscopic data

2020 ◽  
Vol 91 (3) ◽  
pp. 033905
Author(s):  
Han Peng ◽  
Xiang Gao ◽  
Yu He ◽  
Yiwei Li ◽  
Yuchen Ji ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Spectroscopic Data ◽  
Super Resolution

scholarly journals Image Super-Resolution for MRI Images using 3D Faster Super-Resolution Convolutional Neural Network architecture

2020 ◽  
Vol 32 ◽  
pp. 03044
Author(s):  
Vanita Mane ◽  
Suchit Jadhav ◽  
Praneya Lal
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Brain Mri ◽  
Super Resolution ◽  
Structural Mri ◽  
Reconstruction Performance ◽  
Human Connectome Project ◽  
Image Super Resolution

Single image super-resolution using deep learning techniques has shown very high reconstruction performance over the last few years. We propose a novel three-dimensional convolutional neural network called 3D FSRCNN based on FSRCNN, which reinstates the high-resolution quality of structural MRI. The 3D neural network generates output brain images of high-resolution (HR) from a low-resolution (LR) input image. A simple design ensures less time complexity and high reconstruction quality. The network is trained using T1-weighted structural MRI images from the human connectome project dataset which is a large publicly available brain MRI database.

Abnormal Event Detection in a Surveillance Scene Using Convolutional Neural Network

2021 ◽  
Vol 11 (4) ◽  
pp. 1-20
Author(s):  
Kinjal V. Joshi ◽  
Narendra M. Patel
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Event Detection ◽  
Characteristic Curve ◽  
Research Area ◽  
Support Vector ◽  
Abnormal Event Detection ◽  
Proposed Model ◽  
Benchmark Datasets

Automatic abnormal event detection in a surveillance scene is very significant because of more consciousness about public safety. Because of usefulness and complexity, currently, it is an open research area. In this manuscript, the authors have proposed a novel convolutional neural network (CNN) model to detect an abnormal event in a surveillance scene. In this work, CNN is used in two ways. Firstly, it is used for both feature extraction and classification. In a second way, CNN is used for feature extraction, and support vector machine (SVM) is used for classification. Without any pre-processing, the proposed model gives better results compared to state-of-the-art methods. Experiments are carried out on four different publicly available benchmark datasets and one combined dataset, which contains all images of four datasets. The performance is measured by accuracy and area under the ROC (receiver operating characteristic) curve (AUC). The experimental results determine the efficacy of the proposed model.

scholarly journals Fault Diagnosis and Fault Frequency Determination of Permanent Magnet Synchronous Motor Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3608
Author(s):  
Chiao-Sheng Wang ◽  
I-Hsi Kao ◽  
Jau-Woei Perng
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Permanent Magnet ◽  
Support Vector ◽  
One Dimensional ◽  
Proposed Model ◽  
Wide Range ◽  
Fault State

The early diagnosis of a motor is important. Many researchers have used deep learning to diagnose motor applications. This paper proposes a one-dimensional convolutional neural network for the diagnosis of permanent magnet synchronous motors. The one-dimensional convolutional neural network model is weakly supervised and consists of multiple convolutional feature-extraction modules. Through the analysis of the torque and current signals of the motors, the motors can be diagnosed under a wide range of speeds, variable loads, and eccentricity effects. The advantage of the proposed method is that the feature-extraction modules can extract multiscale features from complex conditions. The number of training parameters was reduced so as to solve the overfitting problem. Furthermore, the class feature map was proposed to automatically determine the frequency component that contributes to the classification using the weak learning method. The experimental results reveal that the proposed model can effectively diagnose three different motor states—healthy state, demagnetization fault state, and bearing fault state. In addition, the model can detect eccentric effects. By combining the current and torque features, the classification accuracy of the proposed model is up to 98.85%, which is higher than that of classical machine-learning methods such as the k-nearest neighbor and support vector machine.

scholarly journals SFRNet: Feature Extraction-Fusion Steganalysis Network Based on Squeeze-and-Excitation Block and RepVgg Block

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Guiyong Xu ◽  
Yang Xu ◽  
Sicong Zhang ◽  
Xiaoyao Xie
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Detection Accuracy ◽  
Image Size ◽  
Feature Maps ◽  
Accuracy Rate ◽  
Excellent Performance ◽  
Training Time

In the era of big data, convolutional neural network (CNN) has been widely used in the field of image classification and has achieved excellent performance. More and more researchers are beginning to combine deep neural networks with steganalysis to improve performance in recent years. However, most of the steganalysis algorithm based on the convolutional neural network has only run test against the WOW and S-UNIWARD algorithms; meanwhile, their versatility is insufficient due to long training time and the limit of image size. This paper proposes a new network architecture, called SFRNet, to solve these problems. The feature extraction and fusion layer can extract more features from the digital image. The RepVgg block is used to accelerate the inference and increase memory utilization. The SE block improves the detection accuracy rate because it can learn feature weights to make effective feature maps with significant weights and invalid or ineffective feature maps with small weights. Experimental results show that the SFRNet has achieved excellent performance in the detection accuracy rate against four state-of-the-art steganography algorithms in the spatial domain, e.g., HUGO, WOW, S-UNIWARD, and MiPOD, under different payloads. The SFRNet detection accuracy rate achieves 89.6% against S-UNIWARD algorithm with the payload of 0.4bpp and 72.5% at 0.2bpp. As the same time, the training time of our network is greatly reduced by 35% compared with Yedroudj-Net.

Sign in / Sign up

Export Citation Format

Share Document