• Corpus ID: 239049963

A New Automatic Change Detection Frame-work Based on Region Growing and Weighted Local Mutual Information: Analysis of Breast Tumor Response to Chemotherapy in Serial MR Images

  title={A New Automatic Change Detection Frame-work Based on Region Growing and Weighted Local Mutual Information: Analysis of Breast Tumor Response to Chemotherapy in Serial MR Images},
  author={Narges Norouzi and Reza Azmi and Nooshin Noshiri and Robab Anbiaee},
The automatic analysis of subtle changes between longitudinal MR images is an important task as it is still a challenging issue in scope of the breast medical image processing. In this paper we propose an effective automatic change detection framework composed of two phases since previously used methods have features with low distinctive power. First, in the preprocessing phase an intensity normalization method is suggested based on Hierarchical Histogram Matching (HHM) that is more robust to… 


Automatic change detection in multimodal serial MRI: application to multiple sclerosis lesion evolution
An automatic image processing system that outperforms the human expert, detecting many lesion evolutions that are missed by the expert, including small, subtle changes.
Change detection of medical images using dictionary learning techniques and principal component analysis
Experimental results with both simulated and real MRI scans show that the improved EigenBlockCD-2 algorithm outperforms the previous methods and shows the advantages of the L2 norm over the L1 norm both theoretically and numerically.
A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images
  • R. Azmi, N. Norozi
  • Computer Science, Medicine
    Journal of medical signals and sensors
  • 2011
Improved-Markov Random Field (I-MRF) method for breast lesion segmentation in MR images is presented, which doesn’t use the Iterative Conditional Mode (ICM) method or Simulated Annealing (SA) for class membership estimation of each pixel.
IMPST: A New Interactive Self-Training Approach to Segmentation Suspicious Lesions in Breast MRI
Experimental results show that performance of segmentation in this approach is higher than supervised and unsupervised methods such as K nearest neighbors, Bayesian, Support Vector Machine, and Fuzzy c-Means.
A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies
This paper presents an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies and believes that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.
Part 1. Automated Change Detection and Characterization in Serial MR Studies of Brain-Tumor Patients
An algorithm which would quantitatively compare serial magnetic resonance imaging studies of brain-tumor patients and a standard classify–subtract algorithm were constructed, and the novel algorithm achieved perfect specificity in seven of the nine experiments.
Brain tissue segmentation in MR images based on a hybrid of MRF and social algorithms
A novel method based on MRF and a hybrid of social algorithms that contain an ant colony optimization (ACO) and a Gossiping algorithm which can be used for segmenting single and multispectral MRIs in real time environments is proposed.
A non-parametric approach to automatic change detection in MRI images of the brain
  • H. Seo, P. Milanfar
  • Mathematics, Computer Science
    2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
  • 2009
A novel approach to change detection between two brain MRI scans (reference and target) that uses a single modality to find subtle changes; and does not require prior knowledge of the type of changes to be sought.
Breast Density Analysis Using an Automatic Density Segmentation Algorithm
An automated approach for breast density segmentation in mammographic images based on a supervised pixel-based classification and using textural and morphological features is presented to show the feasibility of an automatic algorithm and prove its potential application to the study of breast density evolution in longitudinal studies.
Development of a quantitative method for analysis of breast density based on three-dimensional breast MRI.
Results suggest that the technique based on three-dimensional MRI can achieve reasonable consistency to be applied in longitudinal follow-up studies to detect small changes, and may provide a reliable method for evaluating the change of breast density for risk management of women.