Book ChapterDOI
Image Preprocessing for Pathological Brain Detection
Shuihua Wang,Yudong Zhang,Zhengchao Dong,Preetha Phillips,Preetha Phillips +4 more
- pp 29-44
Reads0
Chats0
TLDR
This chapter first introduces the concept of k-space, where the acquired signal lies, and reconstruction is necessary to transform it to spatial space, which can help improve the visual quality of magnetic brain images.Abstract:
Image preprocessing is quite important This chapter first introduces the concept of k-space, where the acquired signal lies First, reconstruction is necessary to transform it to spatial space Then, image denoising techniques are required Magnetic resonance images are contaminated by Rician noise in addition to common Gaussian noise Several denoising methods are introduced here A brain extraction tool is introduced to strip the skull and preserve only brain tissues The inter-class variance-based slice selection method is discussed, which aims to select one/several distinguishing slice(s) Spatial normalization is necessary, as it can transform a brain image to match a template Rigid and non-rigid normalization methods are introduced The intensity of normalization can improve image compatibility and facilitate comparability of scans with different settings Finally, image enhancement is introduced, which can help improve the visual quality of magnetic brain images Histogram equalization and contrast-limited adaptive histogram equalization methods are presentedread more
Citations
More filters
Journal ArticleDOI
Performance enhancement of image segmentation analysis for multi-grade tumour classification in MRI image
TL;DR: In this paper, the authors used hybrid wavelet Hadamard transform and grey-level co-occurrence matrix for feature extraction, which is an easy greedy search algorithm for feature selection.
References
More filters
Journal ArticleDOI
Fast robust automated brain extraction
TL;DR: An automated method for segmenting magnetic resonance head images into brain and non‐brain has been developed and described and examples of results and the results of extensive quantitative testing against “gold‐standard” hand segmentations, and two other popular automated methods.
Journal ArticleDOI
Improved optimization for the robust and accurate linear registration and motion correction of brain images
Journal ArticleDOI
Age-specific CT and MRI templates for spatial normalization.
Chris Rorden,Leonardo Bonilha,Julius Fridriksson,Benjamin Bender,Hans-Otto Karnath,Hans-Otto Karnath +5 more
TL;DR: Specialized templates that allow normalization algorithms to be applied to stroke-aged populations are introduced and a MRI template is derived that approximately matches the shape of the CT template.
Journal ArticleDOI
Deep MRI brain extraction: A 3D convolutional neural network for skull stripping
Jens Kleesiek,Gregor Urban,Alexander Hubert,Daniel Schwarz,Klaus H. Maier-Hein,Martin Bendszus,Armin Biller +6 more
TL;DR: A 3D convolutional deep learning architecture to address shortcomings of existing methods, not limited to non-enhanced T1w images, and may prove useful for large-scale studies and clinical trials.
Journal ArticleDOI
Detection of subjects and brain regions related to Alzheimer's disease using 3D MRI scans based on eigenbrain and machine learning.
Yudong Zhang,Zhengchao Dong,Preetha Phillips,Shuihua Wang,Shuihua Wang,Genlin Ji,Jiquan Yang,Ti-Fei Yuan +7 more
TL;DR: The proposed eigenbrain method was effective in AD subject prediction and discriminant brain-region detection in MRI scanning and was coherent with existing literatures.