In this paper, we present a novel method for selective compression of medical images. In our scheme, regions of interest (ROIs) are differentiated from the background by detecting relevant features such as edges, texture and clusters. A detection map is created for ROIs so that the coding system can use it to assign proper bit rates in the process of quantization. The localized, multiresolution representation of the wavelet coefficients makes it easy to allocate different bit rates to complex, adjacent ROIs in the process of successive approximation quantization of wavelet coefficients. For maximum flexibility and efficiency in selective allocation of bit rates, we use an intraband coding scheme, compact quadtree, instead of the conventional interband approaches. By adjusting the amplitudes of the wavelet coefficients in ROIs, one can smoothly preserve multiple ROIs with virtual no coding overhead. Experimental results on digital mammographical images show that minute microcalcifications can be perfectly preserved while their background is compressed at very high ratios, i.e., over 100 to 1.
[1]
Janice C. Honeyman-Buck,et al.
Hexagonal wavelet processing of digital mammography
,
1993
.
[2]
D R Dance,et al.
Segmentation of mammograms using multiple linked self-organizing neural networks.
,
1995,
Medical physics.
[3]
I. Daubechies,et al.
Biorthogonal bases of compactly supported wavelets
,
1992
.
[4]
Huai Li,et al.
Artificial convolution neural network for medical image pattern recognition
,
1995,
Neural Networks.
[5]
Michel Barlaud,et al.
Image coding using wavelet transform
,
1992,
IEEE Trans. Image Process..
[6]
Vance Faber,et al.
Perfect reconstruction with critically sampled filter banks and linear boundary conditions
,
1995,
IEEE Trans. Signal Process..
[7]
D. Betal.
Extraction of microcalcifications from digital mammograms using mathematical morphology
,
1993
.
[8]
Michael Unser,et al.
Texture classification and segmentation using wavelet frames
,
1995,
IEEE Trans. Image Process..