Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Big Data in Medical Imaging

No description
by

Mamtha Kashyap

on 30 July 2014

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Big Data in Medical Imaging

Breast Cancer Diagnosis Techniques
MAMMOGRAPHY
PROPOSED METHODOLOGY
Image segmentation

Feature Extraction

Feature selection

Discretization

Pattern extraction

Pattern clustering

Conclusion
Real time use of this proposed system can revolutionize the way breast cancer is treated
Big Data in Medical Imaging

Team Name: TechKnuckled
Mamtha Lakshminarasimhan
Miti Kadia
Sharanya Jayabalan
Shirley Xiao

Helps analyze mammograms on a large scale.
Eliminates Human Error
But could not handle heterogeneous images
Image Segmentation
FEATURE EXTRACTION
Reduce the ROIs of the image into 16x16.

Identify the co-occurrence matrix M(d,θ) where d is the distances 1,2,3,4,5 and θ is the directions of 0, 45, 90, 135.

Calculate twenty 16x16 matrices.

For each matrix, the seven features are calculated, producing a feature vector of 140 elements to represent each image.

Features
DISCRETIZATION
Sort the data for the given feature in ascending order.
Define cut points so that every value of the feature is in separate interval.
Repeat until there are no more features.

PATTERN EXTRACTION
Discover high-order patterns or event associations

Standardized residual is used to select the compound set as a Pattern.

PATTERN CLUSTERING
Discover qualitative and quantitative patterns
Pattern-induced data clusters are produced
Number of constant clusters reduced by merging clusters
No within cluster variations

HIPI API & IMAGE MINING
The Problem
How does Big Data come into picture?
System Requirements for Hadoop Cluster
Computer Aided Diagnostic (CAD) System
Early detection is key for combating breast cancer.
Optimize all previous mammography information from heterogeneous sources to provide a unified data source.
Big Data, specifically Hadoop Framework can help solve this problem
The data centers can be anywhere as Hadoop is distributed.
QUESTIONS ???
THANK YOU !!!
CONTRIBUTIONS
Mamtha L.
Miti K.
Sharanya J.
Shirley X.
Proposed Methodology and Hadoop
Big Data and Hadoop
Proposed Methodology and MapReduce
MapReduce and Literature Review
Mammogram image
Full transcript