ROI-BASED 3D HUMAN BRAIN MAGNETIC RESONANCE IMAGES COMPRESSION USING ADAPTIVE MESH DESIGN AND REGION-BASED DISCRETE WAVELET TRANSFORM

2010 ◽  
Vol 08 (03) ◽  
pp. 407-430 ◽  
Author(s):  
EMAD FATEMIZADEH ◽  
PARISA SHOOSHTARI
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Compression Ratio ◽  
Medical Images ◽  
Region Of Interest ◽  
Adaptive Mesh ◽  
Magnetic Resonance Images ◽  
Discrete Wavelet ◽  
Object Based ◽  
The Difference

Due to the large volume required for medical images for transmission and archiving purposes, the compression of medical images is known as one of the main concepts of medical image processing. Lossless compression methods have the drawback of a low compression ratio. In contrast, lossy methods have a higher compression ratio and suffer from lower quality of the reconstructed images in the receiver. Recently, some selective compression methods have been proposed in which the main image is divided into two separate regions: Region of Interest (ROI), which should be compressed in a lossless manner, and Region of Background (ROB), which is compressed in a lossy manner with a lower quality. In this research, we introduce a new selective compression method to compress 3D brain MR images. To this aim, we design an adaptive mesh on the first slice and estimate the gray levels of the next slices by computing the mesh element's deformations. After computing the residual image, which is the difference between the main image and the estimated one, we transform it to the wavelet domain using a region-based discrete wavelet transform (RBDWT). Finally, the wavelet coefficients are coded by an object-based SPIHT coder.

Detection of Defects in Welded Structures With Complex Geometry Using Statistical Method Based on Discrete Wavelet Transform

2009 ◽  
Author(s):  
Tsun-Yen Wu ◽  
I. Charles Ume ◽  
Matthew D. Rogge
Keyword(s):  
Wavelet Transform ◽  
Energy Distribution ◽  
Discrete Wavelet Transform ◽  
Statistical Method ◽  
Defect Detection ◽  
Complex Geometry ◽  
Inspection System ◽  
Discrete Wavelet ◽  
Electromagnetic Acoustic Transducer ◽  
The Difference

In this paper, an inspection system and a defect detection method are presented. A welded sample with complex geometry was placed on an inspection system and inspected by generating ultrasound on one side of the weld and receiving on the other with an electromagnetic acoustic transducer (EMAT) sensor. Ultrasonic signals along the weld were acquired at locations with 1 mm distance between inspections. In order to detect the presence of defects, a statistical method based on Discrete Wavelet Transform (DWT) is implemented. Energy of each location along the weld is calculated and useful information indicating presence of defects is extracted by DWT using different mother wavelets. By comparing the energy distribution obtained from a particular sample, or a target, with a baseline energy distribution, defect locations are predicted. The baseline energy distribution is obtained by averaging energy distributions calculated for all inspected samples. The difference between a target and the reference is viewed as an indication of presence of defects. The results showed that the method can isolate signal changes that were caused by defects. Comparison to destructive cut-checks shows the accuracy of defect detection is high.

Shift-invariant discrete wavelet transform-based sparse fusion of medical images

2021 ◽  
Author(s):  
M. Munawwar Iqbal Ch ◽  
M. Mohsin Riaz ◽  
Naima Iltaf ◽  
Abdul Ghafoor ◽  
Nuwayrah Jawaid Saghir
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Medical Images ◽  
Discrete Wavelet

scholarly journals Deep Learning-based Histopathological Segmentation for Whole Slide Images of Colorectal Cancer in a Compressed Domain

2021 ◽  
Author(s):  
Hyeongsub Kim ◽  
Hongjoon Yoon ◽  
Nishant Thakur ◽  
Gyoyeon Hwang ◽  
Eun Jung Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Wavelet Transform ◽  
High Resolution ◽  
Discrete Wavelet Transform ◽  
Region Of Interest ◽  
Principal Component ◽  
Spatial Domain ◽  
Discrete Wavelet ◽  
Compressed Domain ◽  
Segmentation Approach

Abstract Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score was 0.852 ± 0.086 and the pixel accuracy was 0.962 ± 0.027. We can train the networks for the high-resolution image (magnification x20) compared to the result in the spatial domain (magnification x10) in same the region of interest (6.25 × 10^2 um^2). The average Dice score and pixel accuracy are significantly increased by 6.4 % and 1.6 %, respectively. We believe that our approach has great potential for accurate diagnosis in pathology.

Sign in / Sign up

Export Citation Format

Share Document