Tucker Decomposition Based Lossless Image Compression for 3D Medical Image

The successful operation of a telecommunication system depends on the maintaining and transferring of high compression three-dimension medical images that produce reconstructions of excellent quality after decompression. To address this issue, we presented a Tucker Decomposition based lossless image...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computation System and Information Technology for Sustainable Solutions (CSITSS), International Conference on s. 1 - 6
Hlavní autoři: Makandar, Aziz, Biradar, Rekha
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 07.11.2024
Témata:
3D medical image
Adaptive Binary Range Coder (ABRC)
Biomedical imaging
Image coding
Image reconstruction
PSNR
Selective Bounding Volume (SBV)
Telecommunications
Tensors
Three-dimensional displays
Transform coding
Tucker Decomposition
VOI
Volume measurement
ISSN:2767-1097
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The successful operation of a telecommunication system depends on the maintaining and transferring of high compression three-dimension medical images that produce reconstructions of excellent quality after decompression. To address this issue, we presented a Tucker Decomposition based lossless image compression for three-dimension medical image. Tucker decomposition, the extended form of Singular Value Decomposition (SVD), can handle high dimensional information; SVD is limited to two dimensions. Use the Selective Bounding volume (SBV) to find and retrieve the Volume of Interest (VOI). Tucker decomposition is used to break down the extracted volume of interest (VOI) into its component major tensor, coefficient matrices, and distinct parameters. subsequently, an Adaptive Binary Range Coder (ABRC) is utilized for compress these values. By inverting the compression procedure and integrating the uncompressed VOI with the surrounding area employing the bound volume coordinates connected to the compressed three-dimensional image, the final uncompressed VOI is produced. utilizing a range of 3D medical images obtained through different forms of imaging, the proposed approach's performance was assessed using analytical evaluation metrics like the Compression Ratio (CR), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Measure (SSIM). The proposed compression methodology produces consistently high-quality image compressions and produces larger-scale results, as shown by the method's outcome.
ISSN:2767-1097
DOI:10.1109/CSITSS64042.2024.10816987