skip to main content

Explore Research Products in the NSF-PAR

Title: High Impulse Noise Intensity Removal in Natural Images Using Convolutional Neural Network
This paper introduces a new image smoothing filter based on a feed-forward convolutional neural network (CNN) in presence of impulse noise. This smoothing filter integrates a very deep architecture, a regularization method, and a batch normalization process. This fully integrated approach yields an effectively denoised and smoothed image yielding a high similarity measure with the original noise free image. Specific structural metrics are used to assess the denoising process and how effective was the removal of the impulse noise. This CNN model can also deal with other noise levels not seen during the training phase. The proposed CNN model is constructed through a 20-layer network using 400 images from the Berkeley Segmentation Dataset (BSD) in the training phase. Results are obtained using the standard testing set of 8 natural images not seen in the training phase. The merits of this proposed method are weighed in terms of high similarity measure and structural metrics that conform to the original image and compare favorably to the different results obtained using state-of-art denoising filters.  more » « less
Award ID(s):
1920182 1532061
NSF-PAR ID:
10185414
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
IEEE 10th Annual Computing and Communication Workshop and Conference (CCWC)
Page Range / eLocation ID:
0673 to 0677
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ( , PLOS ONE)
    Yap, Pew-Thian (Ed.)
    Diffusion weighted imaging (DWI) with multiple, high b-values is critical for extracting tissue microstructure measurements; however, high b-value DWI images contain high noise levels that can overwhelm the signal of interest and bias microstructural measurements. Here, we propose a simple denoising method that can be applied to any dataset, provided a low-noise, single-subject dataset is acquired using the same DWI sequence. The denoising method uses a one-dimensional convolutional neural network (1D-CNN) and deep learning to learn from a low-noise dataset, voxel-by-voxel. The trained model can then be applied to high-noise datasets from other subjects. We validated the 1D-CNN denoising method by first demonstrating that 1D-CNN denoising resulted in DWI images that were more similar to the noise-free ground truth than comparable denoising methods, e.g., MP-PCA, using simulated DWI data. Using the same DWI acquisition but reconstructed with two common reconstruction methods, i.e. SENSE1 and sum-of-square, to generate a pair of low-noise and high-noise datasets, we then demonstrated that 1D-CNN denoising of high-noise DWI data collected from human subjects showed promising results in three domains: DWI images, diffusion metrics, and tractography. In particular, the denoised images were very similar to a low-noise reference image of that subject, more than the similarity between repeated low-noise images (i.e. computational reproducibility). Finally, we demonstrated the use of the 1D-CNN method in two practical examples to reduce noise from parallel imaging and simultaneous multi-slice acquisition. We conclude that the 1D-CNN denoising method is a simple, effective denoising method for DWI images that overcomes some of the limitations of current state-of-the-art denoising methods, such as the need for a large number of training subjects and the need to account for the rectified noise floor. 
    more » « less
  2. ; ; ; ; ( , The Astrophysical Journal Supplement Series)
    Abstract The quality of solar images plays an important role in the analysis of small events in solar physics. Therefore, the improvement of image resolution based on super-resolution (SR) reconstruction technology has aroused the interest of many researchers. In this paper, an improved conditional denoising diffusion probability model (ICDDPM) based on the Markov chain is proposed for the SR reconstruction of solar images. This method reconstructs high-resolution (HR) images from low-resolution images by learning a reverse process that adds noise to HR images. To verify the effectiveness of the method, images from the Goode Solar Telescope at the Big Bear Solar Observatory and the Helioseismic and Magnetic Imager (HMI) on the Solar Dynamics Observatory are used to train a network, and the spatial resolution of reconstructed images is 4 times that of the original HMI images. The experimental results show that the performance based on ICDDPM is better than the previous work in subject judgment and object evaluation indexes. The reconstructed images of this method have higher subjective vision quality and better consistency with the HMI images. And the structural similarity and rms index results are also higher than the compared method, demonstrating the success of the resolution improvement using ICDDPM. 
    more » « less
  3. ; ; ; ( , 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS))
    Data fusion techniques have gained special interest in remote sensing due to the available capabilities to obtain measurements from the same scene using different instruments with varied resolution domains. In particular, multispectral (MS) and hyperspectral (HS) imaging fusion is used to generate high spatial and spectral images (HSEI). Deep learning data fusion models based on Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN) have been developed to achieve such task.In this work, we present a Multi-Level Propagation Learning Network (MLPLN) based on a LSTM model but that can be trained with variable data sizes in order achieve the fusion process. Moreover, the MLPLN provides an intrinsic data augmentation feature that reduces the required number of training samples. The proposed model generates a HSEI by fusing a high-spatial resolution MS image and a low spatial resolution HS image. The performance of the model is studied and compared to existing CNN and LSTM approaches by evaluating the quality of the fused image using the structural similarity metric (SSIM). The results show that an increase in the SSIM is still obtained while reducing of the number of training samples to train the MLPLN model. 
    more » « less
  4. ; ; ; ; ; ; ; ; ( , Biomedical Optics Express)
    Traditionally, a high-performance microscope with a large numerical aperture is required to acquire high-resolution images. However, the images’ size is typically tremendous. Therefore, they are not conveniently managed and transferred across a computer network or stored in a limited computer storage system. As a result, image compression is commonly used to reduce image size resulting in poor image resolution. Here, we demonstrate custom convolution neural networks (CNNs) for both super-resolution image enhancement from low-resolution images and characterization of both cells and nuclei from hematoxylin and eosin (H&E) stained breast cancer histopathological images by using a combination of generator and discriminator networks so-called super-resolution generative adversarial network-based on aggregated residual transformation (SRGAN-ResNeXt) to facilitate cancer diagnosis in low resource settings. The results provide high enhancement in image quality where the peak signal-to-noise ratio and structural similarity of our network results are over 30 dB and 0.93, respectively. The derived performance is superior to the results obtained from both the bicubic interpolation and the well-known SRGAN deep-learning methods. In addition, another custom CNN is used to perform image segmentation from the generated high-resolution breast cancer images derived with our model with an average Intersection over Union of 0.869 and an average dice similarity coefficient of 0.893 for the H&E image segmentation results. Finally, we propose the jointly trained SRGAN-ResNeXt and Inception U-net Models, which applied the weights from the individually trained SRGAN-ResNeXt and inception U-net models as the pre-trained weights for transfer learning. The jointly trained model’s results are progressively improved and promising. We anticipate these custom CNNs can help resolve the inaccessibility of advanced microscopes or whole slide imaging (WSI) systems to acquire high-resolution images from low-performance microscopes located in remote-constraint settings. 
    more » « less
  5. ; ; ; ; ; ; ; ; ( , Society for Imaging Informatics in Medicine (SIIM) Annual Meeting)
    Introduction Multi-series CT (MSCT) scans, including non-contrast CT (NCCT), CT Perfusion (CTP), and CT Angiography (CTA), are widely used in acute stroke imaging. While each scan has its advantage in disease diagnosis, the varying image resolution of different series hinders the ability of the radiologist to discern subtle suspicious findings. Besides, higher image quality requires high radiation doses, leading to increases in health risks such as cataract formation and cancer induction. Thus, it is highly crucial to develop an approach to improve MSCT resolution and to lower radiation exposure. Hypothesis MSCT imaging of the same patient is highly correlated in structural features, the transferring and integration of the shared and complementary information from different series are beneficial for achieving high image quality. Methods We propose TL-GAN, a learning-based method by using Transfer Learning (TL) and Generative Adversarial Network (GAN) to reconstruct high-quality diagnostic images. Our TL-GAN method is evaluated on 4,382 images collected from nine patients’ MSCT scans, including 415 NCCT slices, 3,696 CTP slices, and 271 CTA slices. We randomly split the nine patients into a training set (4 patients), a validation set (2 patients), and a testing set (3 patients). In preprocessing, we remove the background and skull and visualize in brain window. The low-resolution images (1/4 of the original spatial size) are simulated by bicubic down-sampling. For training without TL, we train different series individually, and for with TL, we follow the scanning sequence (NCCT, CTP, and CTA) by finetuning. Results The performance of TL-GAN is evaluated by the peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) index on 184 NCCT, 882 CTP, and 107 CTA test images. Figure 1 provides both visual (a-c) and quantity (d-f) comparisons. Through TL-GAN, there is a significant improvement with TL than without TL (training from scratch) for NCCT, CTP, and CTA images, respectively. These significances of performance improvement are evaluated by one-tailed paired t-tests (p < 0.05). We enlarge the regions of interest for detail visual comparisons. Further, we evaluate the CTP performance by calculating the perfusion maps, including cerebral blood flow (CBF) and cerebral blood volume (CBV). The visual comparison of the perfusion maps in Figure 2 demonstrate that TL-GAN is beneficial for achieving high diagnostic image quality, which are comparable to the ground truth images for both CBF and CBV maps. Conclusion Utilizing TL-GAN can effectively improve the image resolution for MSCT, provides radiologists more image details for suspicious findings, which is a practical solution for MSCT image quality enhancement. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email