Optical coherence tomography image denoising using a generative adversarial network with speckle modulation.
Ontology highlight
ABSTRACT:
SUBMITTER: Dong Z
PROVIDER: S-EPMC8258757 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundLow-dose computed tomography (LDCT) is a diagnostic imaging technique designed to minimize radiation exposure to the patient. However, this reduction in radiation may compromise computed tomography (CT) image quality, adversely impacting clinical diagnoses. Various advanced LDCT methods have emerged to mitigate this challenge, relying on well-matched LDCT and normal-dose CT (NDCT) image pairs for training. Nevertheless, these methods often face difficulties in distinguishing image details from nonuniformly distributed noise, limiting their denoising efficacy. Additionally, acquiring suitably paired datasets in the medical domain poses challenges, further constraining their applicability. Hence, the objective of this study was to develop an innovative denoising framework for LDCT images employing unpaired data.MethodsIn this paper, we propose a LDCT denoising network (DNCNN) that alleviates the need for aligning LDCT and NDCT images. Our approach employs generative adversarial networks (GANs) to learn and model the noise present in LDCT images, establishing a mapping from the pseudo-LDCT to the actual NDCT domain without the need for paired CT images.ResultsWithin the domain of weakly supervised methods, our proposed model exhibited superior objective metrics on the simulated dataset when compared to CycleGAN and selective kernel-based cycle-consistent GAN (SKFCycleGAN): the peak signal-to-noise ratio (PSNR) was 43.9441, the structural similarity index measure (SSIM) was 0.9660, and the visual information fidelity (VIF) was 0.7707. In the clinical dataset, we conducted a visual effect analysis by observing various tissues through different observation windows. Our proposed method achieved a no-reference structural sharpness (NRSS) value of 0.6171, which was closest to that of the NDCT images (NRSS =0.6049), demonstrating its superiority over other denoising techniques in preserving details, maintaining structural integrity, and enhancing edge contrast.ConclusionsThrough extensive experiments on both simulated and clinical datasets, we demonstrated the superior efficacy of our proposed method in terms of denoising quality and quantity. Our method exhibits superiority over both supervised techniques, including block-matching and 3D filtering (BM3D), residual encoder-decoder convolutional neural network (RED-CNN), and Wasserstein generative adversarial network-VGG (WGAN-VGG), and over weakly supervised approaches, including CycleGAN and SKFCycleGAN.
| S-EPMC11320552 | biostudies-literature
Project description:Optical coherence tomography (OCT) suffers from speckle noise due to the high spatial coherence of the utilized light source, leading to significant reductions in image quality and diagnostic capabilities. In the past, angular compounding techniques have been applied to suppress speckle noise. However, existing image registration methods usually guarantee pure angular compounding only within a relatively small field of view in the focal region, but produce spatial averaging in the other regions, resulting in resolution loss and image blur. This work develops an image registration model to correctly localize the real-space location of every pixel in an OCT image, for all depths. The registered images captured at different angles are fused into a speckle-reduced composite image. Digital focusing, based on the convolution of the complex OCT images and the conjugate of the point spread function (PSF), is studied to further enhance lateral resolution and contrast. As demonstrated by experiments, angular compounding with our improved image registration techniques and digital focusing, can effectively suppress speckle noise, enhance resolution and contrast, and reveal fine structures in ex-vivo imaged tissue.
| S-EPMC7002526 | biostudies-literature
Project description:Optical coherence tomography (OCT) is a powerful biomedical imaging technology that relies on the coherent detection of backscattered light to image tissue morphology in vivo. As a consequence, OCT is susceptible to coherent noise (speckle noise), which imposes significant limitations on its diagnostic capabilities. Here we show speckle-modulating OCT (SM-OCT), a method based purely on light manipulation that virtually eliminates speckle noise originating from a sample. SM-OCT accomplishes this by creating and averaging an unlimited number of scans with uncorrelated speckle patterns without compromising spatial resolution. Using SM-OCT, we reveal small structures in the tissues of living animals, such as the inner stromal structure of a live mouse cornea, the fine structures inside the mouse pinna, and sweat ducts and Meissner's corpuscle in the human fingertip skin-features that are otherwise obscured by speckle noise when using conventional OCT or OCT with current state of the art speckle reduction methods.
| S-EPMC5481831 | biostudies-literature
Project description:BackgroundGenerative adversarial network (GAN)-based synthetic images can be viable solutions to current supervised deep learning challenges. However, generating highly realistic images is a prerequisite for these approaches.ObjectiveThe aim of this study was to investigate and validate the unsupervised synthesis of highly realistic body computed tomography (CT) images by using a progressive growing GAN (PGGAN) trained to learn the probability distribution of normal data.MethodsWe trained the PGGAN by using 11,755 body CT scans. Ten radiologists (4 radiologists with <5 years of experience [Group I], 4 radiologists with 5-10 years of experience [Group II], and 2 radiologists with >10 years of experience [Group III]) evaluated the results in a binary approach by using an independent validation set of 300 images (150 real and 150 synthetic) to judge the authenticity of each image.ResultsThe mean accuracy of the 10 readers in the entire image set was higher than random guessing (1781/3000, 59.4% vs 1500/3000, 50.0%, respectively; P<.001). However, in terms of identifying synthetic images as fake, there was no significant difference in the specificity between the visual Turing test and random guessing (779/1500, 51.9% vs 750/1500, 50.0%, respectively; P=.29). The accuracy between the 3 reader groups with different experience levels was not significantly different (Group I, 696/1200, 58.0%; Group II, 726/1200, 60.5%; and Group III, 359/600, 59.8%; P=.36). Interreader agreements were poor (κ=0.11) for the entire image set. In subgroup analysis, the discrepancies between real and synthetic CT images occurred mainly in the thoracoabdominal junction and in the anatomical details.ConclusionsThe GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; however, it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details.
| S-EPMC8077702 | biostudies-literature
Project description:Speckle noise limits the diagnostic capabilities of optical coherence tomography (OCT) images, causing both a reduction in contrast and a less accurate assessment of the microstructural morphology of the tissue. We present a speckle-noise reduction method for OCT volumes that exploits the advantages of adaptive-noise wavelet thresholding with a wavelet compounding method applied to several frames acquired from consecutive positions. The method takes advantage of the wavelet representation of the speckle statistics, calculated properly from a homogeneous sample or a region of the noisy volume. The proposed method was first compared quantitatively with different state-of-the-art approaches by being applied to three different clinical dermatological OCT volumes with three different OCT settings. The method was also applied to a public retinal spectral-domain OCT dataset to demonstrate its applicability to different imaging modalities. The results based on four different metrics demonstrate that the proposed method achieved the best performance among the tested techniques in suppressing noise and preserving structural information. The proposed OCT denoising technique has the potential to adapt to different image OCT settings and noise environments and to improve image quality prior to clinical diagnosis based on visual assessment.
| S-EPMC8211087 | biostudies-literature
Project description:We record Optical coherence tomography (OCT) images of various textile fabrics. Each textile fabric consisted of one material only: wool, cotton or polyester. We took OCT images from three different fabrics for each material type giving a total of 9 different fabrics. We scan each material at least a hundred times at different places on each surface. In order to have approximately consistent data between samples, the scans for each image were fixed to 2 mm scan length and saved in a portable network format. We divide the material data into three categories. Groups 1, 2, and 3 consisted only of cotton, wool, and polyester fabrics, respectively. These were placed in folders, becoming the labelled dataset for deep learning training classes. We publish this OCT fabric image dataset publicly. Researchers can utilize the data to train deep learning networks, test existing machine learning algorithms, or develop new systems for automated material classification and recycling.
| S-EPMC9679701 | biostudies-literature
Project description:This study proposed an end-to-end unsupervised medical fusion generative adversarial network, MedFusionGAN, to fuse computed tomography (CT) and high-resolution isotropic 3D T1-Gd Magnetic resonance imaging (MRI) image sequences to generate an image with CT bone structure and MRI soft tissue contrast to improve target delineation and to reduce the radiotherapy planning time. We used a publicly available multicenter medical dataset (GLIS-RT, 230 patients) from the Cancer Imaging Archive. To improve the models generalization, we consider different imaging protocols and patients with various brain tumor types, including metastases. The proposed MedFusionGAN consisted of one generator network and one discriminator network trained in an adversarial scenario. Content, style, and L1 losses were used for training the generator to preserve the texture and structure information of the MRI and CT images. The MedFusionGAN successfully generates fused images with MRI soft-tissue and CT bone contrast. The results of the MedFusionGAN were quantitatively and qualitatively compared with seven traditional and eight deep learning (DL) state-of-the-art methods. Qualitatively, our method fused the source images with the highest spatial resolution without adding the image artifacts. We reported nine quantitative metrics to quantify the preservation of structural similarity, contrast, distortion level, and image edges in fused images. Our method outperformed both traditional and DL methods on six out of nine metrics. And it got the second performance rank for three and two quantitative metrics when compared with traditional and DL methods, respectively. To compare soft-tissue contrast, intensity profile along tumor and tumor contours of the fusion methods were evaluated. MedFusionGAN provides a more consistent, better intensity profile, and a better segmentation performance. The proposed end-to-end unsupervised method successfully fused MRI and CT images. The fused image could improve targets and OARs delineation, which is an important aspect of radiotherapy treatment planning.
| S-EPMC10704723 | biostudies-literature
Project description:In this paper, we make contact with the field of compressive sensing and present a development and generalization of tools and results for reconstructing irregularly sampled tomographic data. In particular, we focus on denoising Spectral-Domain Optical Coherence Tomography (SDOCT) volumetric data. We take advantage of customized scanning patterns, in which, a selected number of B-scans are imaged at higher signal-to-noise ratio (SNR). We learn a sparse representation dictionary for each of these high-SNR images, and utilize such dictionaries to denoise the low-SNR B-scans. We name this method multiscale sparsity based tomographic denoising (MSBTD). We show the qualitative and quantitative superiority of the MSBTD algorithm compared to popular denoising algorithms on images from normal and age-related macular degeneration eyes of a multi-center clinical trial. We have made the corresponding data set and software freely available online.
| S-EPMC3342198 | biostudies-other
Project description:We present a new technique for the correction of nonuniform rotation distortion in catheter-based optical coherence tomography (OCT), based on the statistics of speckle between A-lines using intensity-based dynamic light scattering. This technique does not rely on tissue features and can be performed on single frames of data, thereby enabling real-time image correction. We demonstrate its suitability in a gastrointestinal (GI) balloon-catheter OCT system, determining the actual rotational speed with high temporal resolution, and present corrected cross-sectional and en face views showing significant enhancement of image quality.
| S-EPMC4720487 | biostudies-literature
Project description:Proteins are complex macromolecules accountable for the biological processes in the cell. In biomedical research, the images of protein are extensively used in medicine. The rate at which these images are produced makes it difficult to evaluate them manually and hence there exists a need to automate the system. The quality of images is still a major issue. In this paper, we present the use of different image enhancement techniques that improves the contrast of these images. Besides the quality of images, the challenge of gathering such datasets in the field of medicine persists. We use generative adversarial networks for generating synthetic samples to ameliorate the results of CNN. The performance of the synthetic data augmentation was compared with the classic data augmentation on the classification task, an increase of 2.7% in Macro F1 and 2.64% in Micro F1 score was observed. Our best results were obtained by the pretrained Inception V4 model that gave a fivefold cross-validated macro F1 of 0.603. The achieved results are contrasted with the existing work and comparisons show that the proposed method outperformed.
| S-EPMC7438425 | biostudies-literature