scholarly journals Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications

2021 ◽  
Vol 7 (3) ◽  
pp. 44
Author(s):  
Johannes Leuschner ◽  
Maximilian Schmidt ◽  
Poulami Somanya Ganguly ◽  
Vladyslav Andriiashen ◽  
Sophia Bethany Coban ◽  
...  
Keyword(s):  
Deep Learning ◽  
Low Dose ◽  
Signal To Noise Ratio ◽  
Structural Similarity ◽  
Measurement Model ◽  
Training Data ◽  
Data Driven ◽  
Reconstruction Methods ◽  
Reconstruction Quality ◽  
Public Datasets

The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a data challenge that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed.

ANALISIS SENSITIVITAS VIDEO MPEG-4 BERDASARKAN STRUKTUR FRAME PADA TRANSMISI DVB-T

2020 ◽  
Vol 25 (2) ◽  
pp. 86-97
Author(s):  
Sandy Suryo Prayogo ◽  
Tubagus Maulana Kusuma
Keyword(s):  
Deep Learning ◽  
Bit Error Rate ◽  
Error Rate ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Signal To Noise ◽  
Structural Similarity Index ◽  
Noise Ratio

DVB merupakan standar transmisi televisi digital yang paling banyak digunakan saat ini. Unsur terpenting dari suatu proses transmisi adalah kualitas gambar dari video yang diterima setelah melalui proses transimisi tersebut. Banyak faktor yang dapat mempengaruhi kualitas dari suatu gambar, salah satunya adalah struktur frame dari video. Pada tulisan ini dilakukan pengujian sensitifitas video MPEG-4 berdasarkan struktur frame pada transmisi DVB-T. Pengujian dilakukan menggunakan simulasi matlab dan simulink. Digunakan juga ffmpeg untuk menyediakan format dan pengaturan video akan disimulasikan. Variabel yang diubah dari video adalah bitrate dan juga group-of-pictures (GOP), sedangkan variabel yang diubah dari transmisi DVB-T adalah signal-to-noise-ratio (SNR) pada kanal AWGN di antara pengirim (Tx) dan penerima (Rx). Hasil yang diperoleh dari percobaan berupa kualitas rata-rata gambar pada video yang diukur menggunakan metode pengukuran structural-similarity-index (SSIM). Dilakukan juga pengukuran terhadap jumlah bit-error-rate BER pada bitstream DVB-T. Percobaan yang dilakukan dapat menunjukkan seberapa besar sensitifitas bitrate dan GOP dari video pada transmisi DVB-T dengan kesimpulan semakin besar bitrate maka akan semakin buruk nilai kualitas gambarnya, dan semakin kecil nilai GOP maka akan semakin baik nilai kualitasnya. Penilitian diharapkan dapat dikembangkan menggunakan deep learning untuk memperoleh frame struktur yang tepat di kondisi-kondisi tertentu dalam proses transmisi televisi digital.

scholarly journals Computing 3D Phase-Type Holograms Based on Deep Learning Method

Photonics ◽  
2021 ◽  
Vol 8 (7) ◽  
pp. 280
Author(s):  
Huadong Zheng ◽  
Jianbin Hu ◽  
Chaojun Zhou ◽  
Xiaoxi Wang
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Contrast Ratio ◽  
Angular Spectrum ◽  
Structural Similarity ◽  
Computational Time ◽  
Experimental Investigations ◽  
Training Strategy ◽  
Holographic Display ◽  
Phase Type

Computer holography is a technology that use a mathematical model of optical holography to generate digital holograms. It has wide and promising applications in various areas, especially holographic display. However, traditional computational algorithms for generation of phase-type holograms based on iterative optimization have a built-in tradeoff between the calculating speed and accuracy, which severely limits the performance of computational holograms in advanced applications. Recently, several deep learning based computational methods for generating holograms have gained more and more attention. In this paper, a convolutional neural network for generation of multi-plane holograms and its training strategy is proposed using a multi-plane iterative angular spectrum algorithm (ASM). The well-trained network indicates an excellent ability to generate phase-only holograms for multi-plane input images and to reconstruct correct images in the corresponding depth plane. Numerical simulations and optical reconstructions show that the accuracy of this method is almost the same with traditional iterative methods but the computational time decreases dramatically. The result images show a high quality through analysis of the image performance indicators, e.g., peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and contrast ratio. Finally, the effectiveness of the proposed method is verified through experimental investigations.

Data-driven method for training data selection for deep learning

2021 ◽  
Author(s):  
C. Lacombe ◽  
I. Hammoud ◽  
J. Messud ◽  
H. Peng ◽  
T. Lesieur ◽  
...  
Keyword(s):  
Deep Learning ◽  
Training Data ◽  
Data Selection ◽  
Data Driven ◽  
Selection For ◽  
Training Data Selection

scholarly journals On the objectivity, reliability, and validity of deep learning enabled bioimage analyses

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Dennis Segebarth ◽  
Matthias Griebel ◽  
Nikolai Stein ◽  
Cora R von Collenberg ◽  
Corinna Martin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Biological Effects ◽  
Reliability And Validity ◽  
Ground Truth ◽  
Training Data ◽  
Model Organisms ◽  
Data Annotation ◽  
Bioimage Analysis ◽  
Model Training

Bioimage analysis of fluorescent labels is widely used in the life sciences. Recent advances in deep learning (DL) allow automating time-consuming manual image analysis processes based on annotated training data. However, manual annotation of fluorescent features with a low signal-to-noise ratio is somewhat subjective. Training DL models on subjective annotations may be instable or yield biased models. In turn, these models may be unable to reliably detect biological effects. An analysis pipeline integrating data annotation, ground truth estimation, and model training can mitigate this risk. To evaluate this integrated process, we compared different DL-based analysis approaches. With data from two model organisms (mice, zebrafish) and five laboratories, we show that ground truth estimation from multiple human annotators helps to establish objectivity in fluorescent feature annotations. Furthermore, ensembles of multiple models trained on the estimated ground truth establish reliability and validity. Our research provides guidelines for reproducible DL-based bioimage analyses.

A Deep Learning Method for Limited-View Intravascular Photoacoustic Image Reconstruction

2020 ◽  
Vol 10 (11) ◽  
pp. 2707-2713
Author(s):  
Zheng Sun ◽  
Xiangyang Yan
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Imaging Modality ◽  
Image Data ◽  
Structural Similarity ◽  
Simulated Image ◽  
Cross Sectional ◽  
Data Set ◽  
Reconstruction Methods ◽  
Under Sampling

Intravascular photoacoustic tomography (IVPAT) is a newly developed imaging modality in the interventional diagnosis and treatment of coronary artery diseases. Incomplete acoustic measurement caused by limitedview scanning of the detector in the vascular lumen results in under-sampling artifacts and distortion in the images reconstructed by using the standard reconstruction methods. A method for limited-view IVPAT image reconstruction based on deep learning is presented in this paper. A convolutional neural network (CNN) is constructed and trained with computer-simulated image data set. Then, the trained CNN is used to optimize the cross-sectional images of the vessel which are recovered from the incomplete photoacoustic measurements by using the standard time-reversal (TR) algorithm to obtain the images with the improved quality. Results of numerical demonstration indicate that the method can effectively reduce the image distortion and artifacts caused by the limited-view detection. Furthermore, it is superior to the compressed sensing (CS) method in recovering the unmeasured information of the imaging target with the structural similarity around 10% higher than CS reconstruction.

scholarly journals Deep Learning Image Processing Enables 40% Faster Spinal MR Scans Which Match or Exceed Quality of Standard of Care

2021 ◽  
Author(s):  
S. Bash ◽  
B. Johnson ◽  
W. Gibbs ◽  
T. Zhang ◽  
A. Shankaranarayanan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Standard Of Care ◽  
Structural Similarity ◽  
Image Features ◽  
Scan Time ◽  
Magnetic Resonance Imaging Mri ◽  
Display Order ◽  
Spine Mri

Abstract Objective This prospective multicenter multireader study evaluated the performance of 40% scan-time reduced spinal magnetic resonance imaging (MRI) reconstructed with deep learning (DL). Methods A total of 61 patients underwent standard of care (SOC) and accelerated (FAST) spine MRI. DL was used to enhance the accelerated set (FAST-DL). Three neuroradiologists were presented with paired side-by-side datasets (666 series). Datasets were blinded and randomized in sequence and left-right display order. Image features were preference rated. Structural similarity index (SSIM) and per pixel L1 was assessed for the image sets pre and post DL-enhancement as a quantitative assessment of image integrity impact. Results FAST-DL was qualitatively better than SOC for perceived signal-to-noise ratio (SNR) and artifacts and equivalent for other features. Quantitative SSIM was high, supporting the absence of image corruption by DL processing. Conclusion DL enables 40% spine MRI scan time reduction while maintaining diagnostic integrity and image quality with perceived benefits in SNR and artifact reduction, suggesting potential for clinical practice utility.

scholarly journals SARA-GAN: Self-Attention and Relative Average Discriminator Based Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction

2020 ◽  
Vol 14 ◽  
Author(s):  
Zhenmou Yuan ◽  
Mingfeng Jiang ◽  
Yaming Wang ◽  
Bo Wei ◽  
Yongming Li ◽  
...  
Keyword(s):  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Attention Mechanism ◽  
Generative Adversarial Networks ◽  
Reconstruction Method ◽  
Mri Imaging ◽  
Adversarial Networks ◽  
Reconstruction Methods ◽  
Mri Reconstruction

Research on undersampled magnetic resonance image (MRI) reconstruction can increase the speed of MRI imaging and reduce patient suffering. In this paper, an undersampled MRI reconstruction method based on Generative Adversarial Networks with the Self-Attention mechanism and the Relative Average discriminator (SARA-GAN) is proposed. In our SARA-GAN, the relative average discriminator theory is applied to make full use of the prior knowledge, in which half of the input data of the discriminator is true and half is fake. At the same time, a self-attention mechanism is incorporated into the high-layer of the generator to build long-range dependence of the image, which can overcome the problem of limited convolution kernel size. Besides, spectral normalization is employed to stabilize the training process. Compared with three widely used GAN-based MRI reconstruction methods, i.e., DAGAN, DAWGAN, and DAWGAN-GP, the proposed method can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measure(SSIM), and the details of the reconstructed image are more abundant and more realistic for further clinical scrutinization and diagnostic tasks.

scholarly journals PSIC-Net: Pixel-Wise Segmentation and Image-Wise Classification Network for Surface Defects

Machines ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 221
Author(s):  
Linjian Lei ◽  
Shengli Sun ◽  
Yue Zhang ◽  
Huikai Liu ◽  
Wenjun Xu
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Surface Defect ◽  
Performance Metrics ◽  
Surface Defects ◽  
Training Data ◽  
Detection Methods ◽  
Detection Technology ◽  
Surface Defect Detection ◽  
Public Datasets

Recent years have witnessed the widespread research of the surface defect detection technology based on machine vision, which has spawned various effective detection methods. In particular, the rise of deep learning has allowed the surface defect detection technology to develop further. However, these methods based on deep learning still have some drawbacks. For example, the size of the sample data is not large enough to support deep learning; the location and recognition of surface defects are not accurate enough; the real-time performance of segmentation and classification is not satisfactory. In the context, this paper proposes an end-to-end convolutional neural network model: the pixel-wise segmentation and image-wise classification network (PSIC-Net). With the innovative design of a three-stage network structure, improved loss function and a two-step training mode, PSIC-Net can accurately and quickly segment and classify surface defects with a small dataset of training data. This model was evaluated with three public datasets, and compared with the most advanced defect detection methods. All the performance metrics prove the effectiveness and advancement of PSIC-Net.

scholarly journals Deep learning-based enhancement of epigenomics data with AtacWorks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Avantika Lal ◽  
Zachary D. Chiang ◽  
Nikolai Yakovenko ◽  
Fabiana M. Duarte ◽  
Johnny Israeli ◽  
...  
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Cell Types ◽  
Chromatin Accessibility ◽  
Training Data ◽  
Regulatory Regions ◽  
Hematopoietic Stem ◽  
Sequencing Coverage ◽  
Lineage Priming ◽  
Low Coverage

AbstractATAC-seq is a widely-applied assay used to measure genome-wide chromatin accessibility; however, its ability to detect active regulatory regions can depend on the depth of sequencing coverage and the signal-to-noise ratio. Here we introduce AtacWorks, a deep learning toolkit to denoise sequencing coverage and identify regulatory peaks at base-pair resolution from low cell count, low-coverage, or low-quality ATAC-seq data. Models trained by AtacWorks can detect peaks from cell types not seen in the training data, and are generalizable across diverse sample preparations and experimental platforms. We demonstrate that AtacWorks enhances the sensitivity of single-cell experiments by producing results on par with those of conventional methods using ~10 times as many cells, and further show that this framework can be adapted to enable cross-modality inference of protein-DNA interactions. Finally, we establish that AtacWorks can enable new biological discoveries by identifying active regulatory regions associated with lineage priming in rare subpopulations of hematopoietic stem cells.

scholarly journals Deep Learning-Based Stacked Denoising and Autoencoder for ECG Heartbeat Classification

Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 135 ◽  
Author(s):  
Siti Nurmaini ◽  
Annisa Darmawahyuni ◽  
Akhmad Noviar Sakti Mukti ◽  
Muhammad Naufal Rachmatullah ◽  
Firdaus Firdaus ◽  
...  
Keyword(s):  
Deep Learning ◽  
Signal To Noise Ratio ◽  
Stress Test ◽  
Feature Learning ◽  
Feature Representation ◽  
Training Data ◽  
Fine Tuning ◽  
Noninvasive Test ◽  
Heartbeat Classification ◽  
Unseen Data

The electrocardiogram (ECG) is a widely used, noninvasive test for analyzing arrhythmia. However, the ECG signal is prone to contamination by different kinds of noise. Such noise may cause deformation on the ECG heartbeat waveform, leading to cardiologists’ mislabeling or misinterpreting heartbeats due to varying types of artifacts and interference. To address this problem, some previous studies propose a computerized technique based on machine learning (ML) to distinguish between normal and abnormal heartbeats. Unfortunately, ML works on a handcrafted, feature-based approach and lacks feature representation. To overcome such drawbacks, deep learning (DL) is proposed in the pre-training and fine-tuning phases to produce an automated feature representation for multi-class classification of arrhythmia conditions. In the pre-training phase, stacked denoising autoencoders (DAEs) and autoencoders (AEs) are used for feature learning; in the fine-tuning phase, deep neural networks (DNNs) are implemented as a classifier. To the best of our knowledge, this research is the first to implement stacked autoencoders by using DAEs and AEs for feature learning in DL. Physionet’s well-known MIT-BIH Arrhythmia Database, as well as the MIT-BIH Noise Stress Test Database (NSTDB). Only four records are used from the NSTDB dataset: 118 24 dB, 118 −6 dB, 119 24 dB, and 119 −6 dB, with two levels of signal-to-noise ratio (SNRs) at 24 dB and −6 dB. In the validation process, six models are compared to select the best DL model. For all fine-tuned hyperparameters, the best model of ECG heartbeat classification achieves an accuracy, sensitivity, specificity, precision, and F1-score of 99.34%, 93.83%, 99.57%, 89.81%, and 91.44%, respectively. As the results demonstrate, the proposed DL model can extract high-level features not only from the training data but also from unseen data. Such a model has good application prospects in clinical practice.

Sign in / Sign up

Export Citation Format

Share Document