Principles of Image Cross-Validation (ICV): Representative Segmentation of Image Data Structures

2007 ◽  
pp. 155-180 ◽  
Author(s):  
Kim H. Esbensen ◽  
Thorbjrn T. Lied
Keyword(s):  
Data Structures ◽  
Cross Validation ◽  
Image Data

Cross-Validation and Nested Data Structures

NIR news ◽  
2011 ◽  
Vol 22 (2) ◽  
pp. 17-20 ◽  
Author(s):  
Tom Fearn
Keyword(s):  
Data Structures ◽  
Cross Validation ◽  
Nested Data

Introduction to Image Steganography and Steganalysis

2013 ◽  
pp. 209-237
Author(s):  
Michiharu Niimi ◽  
Hideki Noda
Keyword(s):  
Image Segmentation ◽  
Data Structures ◽  
Information Hiding ◽  
Image Data ◽  
Complexity Measure ◽  
Image Steganography ◽  
The Internet ◽  
Reversible Information Hiding ◽  
Bit Plane ◽  
Steganalysis Method

This chapter reviews information hiding methods, with a focus on steganography and steganalysis. First, the authors summarize image data structures and image formats required by computers and the Internet. They then introduce several information hiding methods based on image formats including lossless (non-compression based), limited color-based image data, JPEG, and JPEG2000. The authors describe a steganographic method in detail, which is based on image segmentation using a complexity measure. They also introduce a method for applying this to palette-based image formats, reversible information hiding for grayscale images, and JPEG2000 steganography. The steganographic methods for JPEG and JPEG2000 described in this chapter give particular consideration to the naturalness of cover data. In the steganalysis section, the authors introduce two methods, i.e., a specific steganalysis method for LSB steganography and Bit-Plane Complexity Segmentation (BPCS) stegnography.

Image Data Structures

1984 ◽  
pp. 49-49
Author(s):  
Alan Bundy ◽  
Lincoln Wallen
Keyword(s):  
Data Structures ◽  
Image Data

Automated artificial intelligence quantification of fibroglandular tissue on breast MRI.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e12071-e12071
Author(s):  
Ruquaiyah Takhtawala ◽  
Nataly Tapia Negrete ◽  
Madeleine Shaver ◽  
Turkay Kart ◽  
Yang Zhang ◽  
...  
Keyword(s):  
Cross Validation ◽  
Pearson Correlation ◽  
Image Data ◽  
Breast Mri ◽  
Ground Truth ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Tissue Segmentation ◽  
Fibroglandular Tissue ◽  
Institutional Review

e12071 Background: The objective of this study is to examine if a convolutional neural network can be utilized to automate breast fibroglandular tissue segmentation, a risk factor for breast cancer, on MRIs. Methods: This institutional review board approved study assessed retrospectively acquired MRI T1 pre-contrast image data for 238 patients. Ground truth parameters were derived through manual segmentation. A hybrid 3D/2D U-Net architecture was developed for fibroglandular tissue segmentation. The network was trained with T1 pre-contrast MRI data and their corresponding ground-truth labels. The analysis was started with image pre-processing. Each MRI volume was re-sampled and normalized using z-scores. Convolution operations reduced 3D volumes into a 2D slice in the contracting arm of the U-Net architecture. Results: A 5-fold cross validation was performed and the Dice similarity coefficient was used to assess the accuracy of fibroglandular tissue segmentation. Cross-validation results showed that the automated hybrid CNN approach resulted in a Dice similarity coefficient of 0.848 and a Pearson correlation of 0.961 in comparison to the ground-truth for fibroglandular breast tissue segmentation, which demonstrates high accuracy. Conclusions: The results demonstrate significant application of deep learning in accurately automating segmentation of breast fibroglandular tissue.

PARALLEL CREATION OF LINEAR OCTREES FROM QUADTREE SLICES

1994 ◽  
Vol 04 (04) ◽  
pp. 447-453
Author(s):  
L.K. SWIFT ◽  
T. JOHNSON ◽  
P.E. LIVADAS
Keyword(s):  
Data Structure ◽  
Parallel Algorithm ◽  
Data Structures ◽  
Linear Form ◽  
Image Data ◽  
Three Dimensions ◽  
Two Dimensional ◽  
Hierarchical Data ◽  
Intermediate Data ◽  
Linear Octree

Quadtrees and octrees are hierarchical data structures for efficiently storing image data. Quadtrees represent two dimensional images, while octrees are a generalization to three dimensions. The linear form of each is an abstraction of the tree structure to reduce storage requirements. We have developed a parallel algorithm to efficiently create a linear octree from quadtree slices of an object without the use of an intermediate data structure. We also propose the d-slice, which is a generalization of an octree, and which efficiently represents non-cubic volumes.

Sign in / Sign up

Export Citation Format

Share Document