A New Framework to Automatically Select Noise Model for Rician Noise Estimation in MR Images

2012 ◽  
Author(s):  
Nivitha Varghees V. ◽  
M. Sabarimalai Manikandan ◽  
Rolant Gini ◽  
K.P. Soman
Keyword(s):  
Noise Estimation ◽  
Noise Model ◽  
Rician Noise ◽  
Mr Images ◽  
New Framework

scholarly journals Object-based Rician Noise Estimation for MR Images

NeuroImage ◽  
2009 ◽  
Vol 47 ◽  
pp. S81
Author(s):  
P. Coupé ◽  
J.V. Manjón ◽  
E. Gedamu ◽  
D. Arnold ◽  
M. Robles ◽  
...  
Keyword(s):  
Noise Estimation ◽  
Rician Noise ◽  
Mr Images ◽  
Object Based

scholarly journals An Object-Based Method for Rician Noise Estimation in MR Images

2009 ◽  
pp. 601-608
Author(s):  
Pierrick Coupé ◽  
José V. Manjón ◽  
Elias Gedamu ◽  
Douglas Arnold ◽  
Montserrat Robles ◽  
...  
Keyword(s):  
Noise Estimation ◽  
Rician Noise ◽  
Mr Images ◽  
Object Based

scholarly journals Robust Rician noise estimation for MR images

2010 ◽  
Vol 14 (4) ◽  
pp. 483-493 ◽  
Author(s):  
Pierrick Coupé ◽  
José V. Manjón ◽  
Elias Gedamu ◽  
Douglas Arnold ◽  
Montserrat Robles ◽  
...  
Keyword(s):  
Noise Estimation ◽  
Rician Noise ◽  
Mr Images

scholarly journals KCB-Net: A 3D Knee Cartilage and Bone Segmentation Network via Sparse Annotation

2021 ◽  
Author(s):  
Yaopeng Peng ◽  
Hao Zheng ◽  
Fahim Zaman ◽  
Lichun Zhang ◽  
Xiaodong Wu ◽  
...  
Keyword(s):  
Medical Image Segmentation ◽  
Small Subset ◽  
Bone Segmentation ◽  
Knee Cartilage ◽  
Mr Images ◽  
3D Images ◽  
Articular Damage ◽  
Primal Dual ◽  
Model Training ◽  
New Framework

<div>Knee cartilage and bone segmentation is critical for physicians to analyze and diagnose articular damage and knee osteoarthritis (OA). Deep learning (DL) methods for medical image segmentation have largely outperformed traditional methods, but they often need large amounts of annotated data for model training, which is very costly and time-consuming for medical experts, especially on 3D images. In this paper, we report a new knee cartilage and bone segmentation framework, KCB-Net, for 3D MR images based on sparse annotation. KCB-Net selects a small subset of slices from 3D images for annotation, and seeks to bridge the performance gap between sparse annotation and full annotation. Specifically, it first identifies a subset of the most effective and representative slices with an unsupervised scheme; it then trains an ensemble model using the annotated slices; next, it self-trains the model using 3D images containing pseudo-labels generated by the ensemble method and improved by a bi-directional hierarchical earth mover’s distance (bi-HEMD) algorithm; finally, it fine-tunes the segmentation results using the primal-dual Internal Point Method (IPM). Experiments on two 3D MR knee joint datasets (the Iowa dataset and iMorphics dataset) show that our new framework outperforms state-of-the-art methods on full annotation, and yields high quality results even for annotation ratios as low as 5%.<br></div>

scholarly journals Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2918 ◽  
Author(s):  
Houqiang Yu ◽  
Mingyue Ding ◽  
Xuming Zhang
Keyword(s):  
Similarity Index ◽  
Similarity Measures ◽  
Noise Removal ◽  
Human Vision ◽  
Rician Noise ◽  
Mr Images ◽  
Laplacian Eigenmaps ◽  
Nonlocal Means ◽  
Output Layer ◽  
Denoised Image

Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).

Denoising of MR images with Rician noise using a wider neural network and noise range division

2019 ◽  
Vol 64 ◽  
pp. 154-159 ◽  
Author(s):  
Xuexiao You ◽  
Ning Cao ◽  
Hao Lu ◽  
Minghe Mao ◽  
Wei Wanga,
Keyword(s):  
Neural Network ◽  
Rician Noise ◽  
Mr Images
Sign in / Sign up

Export Citation Format

Share Document