Literature DB >> 18683566

Development and evaluation of a novel lossless image compression method (AIC: artificial intelligence compression method) using neural networks as artificial intelligence.

Hiroshi Fukatsu1, Shinji Naganawa, Shinnichiro Yumura.   

Abstract

PURPOSE: This study was aimed to validate the performance of a novel image compression method using a neural network to achieve a lossless compression. The encoding consists of the following blocks: a prediction block; a residual data calculation block; a transformation and quantization block; an organization and modification block; and an entropy encoding block. The predicted image is divided into four macro-blocks using the original image for teaching; and then redivided into sixteen sub-blocks. The predicted image is compared to the original image to create the residual image. The spatial and frequency data of the residual image are compared and transformed.
MATERIALS AND METHODS: Chest radiography, computed tomography (CT), magnetic resonance imaging, positron emission tomography, radioisotope mammography, ultrasonography, and digital subtraction angiography images were compressed using the AIC lossless compression method; and the compression rates were calculated.
RESULTS: The compression rates were around 15:1 for chest radiography and mammography, 12:1 for CT, and around 6:1 for other images. This method thus enables greater lossless compression than the conventional methods.
CONCLUSION: This novel method should improve the efficiency of handling of the increasing volume of medical imaging data.

Mesh:

Year:  2008        PMID: 18683566     DOI: 10.1007/s11604-007-0205-8

Source DB:  PubMed          Journal:  Radiat Med        ISSN: 0288-2043


  15 in total

Review 1.  Data explosion: the challenge of multidetector-row CT.

Authors:  G D Rubin
Journal:  Eur J Radiol       Date:  2000-11       Impact factor: 3.528

2.  Statistical mechanics of lossy data compression using a nonmonotonic perceptron.

Authors:  Tadaaki Hosaka; Yoshiyuki Kabashima; Hidetoshi Nishimori
Journal:  Phys Rev E Stat Nonlin Soft Matter Phys       Date:  2002-12-18

3.  Optimization of wavelet decomposition for image compression and feature preservation.

Authors:  Shih-Chung B Lo; Huai Li; Matthew T Freedman
Journal:  IEEE Trans Med Imaging       Date:  2003-09       Impact factor: 10.048

4.  Wavelet compression of medical imagery.

Authors:  E Reiter
Journal:  Telemed J       Date:  1996

5.  Managing the CT data explosion: initial experiences of archiving volumetric datasets in a mini-PACS.

Authors:  Kyoung Ho Lee; Hak Jong Lee; Jae Hyoung Kim; Heung Sik Kang; Kyung Won Lee; Helen Hong; Ho Jun Chin; Kyoo Seob Ha
Journal:  J Digit Imaging       Date:  2005-09       Impact factor: 4.056

6.  JPEG compression history estimation for color images.

Authors:  Ramesh Neelamani; Ricardo de Queiroz; Zhigang Fan; Sanjeeb Dash; Richard G Baraniuk
Journal:  IEEE Trans Image Process       Date:  2006-06       Impact factor: 10.856

7.  Perceptually lossless medical image coding.

Authors:  David Wu; Damian M Tan; Marilyn Baird; John DeCampo; Chris White; Hong Ren Wu
Journal:  IEEE Trans Med Imaging       Date:  2006-03       Impact factor: 10.048

8.  Compression of digital chest radiographs with a mixture of principal components neural network: evaluation of performance.

Authors:  R D Dony; C L Coblentz; C Nabmias; S Haykin
Journal:  Radiographics       Date:  1996-11       Impact factor: 5.333

9.  Artificial intelligence: its use in medical diagnosis.

Authors:  R Scott
Journal:  J Nucl Med       Date:  1993-03       Impact factor: 10.057

10.  Acute pulmonary embolism: artificial neural network approach for diagnosis.

Authors:  G D Tourassi; C E Floyd; H D Sostman; R E Coleman
Journal:  Radiology       Date:  1993-11       Impact factor: 11.105

View more
  1 in total

1.  A multicenter observer performance study of 3D JPEG2000 compression of thin-slice CT.

Authors:  Bradley J Erickson; Elizabeth Krupinski; Katherine P Andriole
Journal:  J Digit Imaging       Date:  2009-07-15       Impact factor: 4.056

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.