Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Best of 2016 Recommended by Editor Recommended by Reviewer Recommended by Reader
Search
Tractome: a visual data mining tool for brain connectivity analysis
Porro-Muñoz D., Olivetti E., Sharmin N., Nguyen T., Garyfallidis E., Avesani P. Data Mining and Knowledge Discovery29 (5):1258-1279,2015.Type:Article
Date Reviewed: Oct 21 2015

Brain imaging has revolutionized neuroscience and related areas such as neurogenetics by providing detailed measures of brain structure and function that can be used to advance our understanding of neuroanatomy and neurophysiology. This paper discusses the use of diffusion magnetic resonance imaging (dMRI), which provides unique insights into the connectivity of the brain that is critical for normal function. The collective connections measured using dMRI are called brain tactography. The paper introduces Tractome as a visual data mining tool for enabling users to visually explore brain tactography data for the purpose of understanding the data as a whole and for the identification of important anatomical variations.

The core concept of Tractome and visual data mining more generally is putting the human at the center of the discovery process. This is in contrast to most systems that put an algorithm or software at the center, with the user left to consume processed information. Tractome has a workflow that consists of the following steps. First, the tactography data is clustered to present a simplified visual representation of the data to the user. This allows the user to identify and focus on the important pieces of information. At any time the user can focus on the detailed data, thus providing access to all of the data as necessary. Interesting subsets of data can be selected and further refined using clustering. Important pieces of information can be isolated and returned, thus generating knowledge as output. The authors stress the interactive nature of the Tractome tool that allows the human to drive the visual analysis.

The authors provide some real-data examples of Tractome use that should be convincing for potential users. The descriptions of the method and its workflow are clear and should be helpful for those hoping to adopt the software. This paper is a nice example of the rapid development of visual analytics as a discipline. The Tractome software integrates the three parts of visual analytics: analysis, human-computer interaction, and visualization. Given the rapid integration of new technology and methods into visual analytics, it would have been nice to see some discussion about how Tractome could take advantage of approaches such as virtual reality or 3D printing. Would implementing Tractome using a video game engine provide any benefit? The base functionality of Tractome is there. Future extensions into other mediums will be interesting to see.

Reviewer:  Jason Moore Review #: CR143876 (1601-0075)
Bookmark and Share
  Editor Recommended
Featured Reviewer
 
 
Data Mining (H.2.8 ... )
 
 
Biology And Genetics (J.3 ... )
 
 
Artificial Intelligence (I.2 )
 
Would you recommend this review?
yes
no
Other reviews under "Data Mining": Date
Feature selection and effective classifiers
Deogun J. (ed), Choubey S., Raghavan V. (ed), Sever H. (ed) Journal of the American Society for Information Science 49(5): 423-434, 1998. Type: Article
May 1 1999
Rule induction with extension matrices
Wu X. (ed) Journal of the American Society for Information Science 49(5): 435-454, 1998. Type: Article
Jul 1 1998
Predictive data mining
Weiss S., Indurkhya N., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998. Type: Book (9781558604032)
Feb 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy