Visualization of Large Collections of Medical Images: Problem Denition Jorge Camargo April 19, 2009
The large amount of visual and multimedia data is growing exponentially thanks to the development of Internet and to the easy of producing and publishing multimedia data. This generates two main problems: how to nd eciently and eectively the information needed, and how to extract knowledge from the data. The problem has been mainly addressed from the Information Retrieval (IR) perspective, and this approach has been very useful dealing with textual data [1]. However, there are still a huge amount of work to do on other kind of non-textual data, such as images. Information visualization techniques [3] are an interesting alternative to address the problem in the case of large collection of images. Information visualization techniques oer ways to reveal hidden information (complex relationships) in a visual representation and allow users to seek information in a more ecient way [4]. Thanks to the human visual capacity for learning and identifying patterns, visualization is a good alternative to deal with this kind of problems. However, the visualization itself is a hard problem; one of the main challenges is how to nd low-dimensional, simple representations that faithfully represent the complete dataset and the relationships among data objects [2]. The majority of existent approaches use a 2D grid layout for visualizing results. The main problem of this kind of visualization is that it does not make explicit the relationships among the presented images and only a portion of the results is shown to the user. In the original space images are represented by many dimensions and how to reduce them such as we can visualize them in a two dimensions space? Assume that we have a way for visualizing the collection, how to display a summary of the entire collection? It is not possible to show the entire collection in a computer screen so how to select and visualize a image subset to the user that represents the entire collection? Once we have a way to visualize and summarize the collection, how we allow users to explore the images in a intuitive way? Finally, how to evaluate the performance of the techniques used to solve the mentioned issues? On the other hand, medical image collection visualization is an unexplored area that oers interesting and challenging problems. First of all, the amount of medical images that is produced routinely in health centers demand eective and ecient techniques for searching, exploration and retrieval. Second, these images have a good amount of semantic, domain-specic content that has to be 1
modeled in order to build eective medical decision support systems. Visualization tools are necessary in health centers to assist diagnosis tasks eectively and eciently. For instance, a medical doctor may have a diagnostic image and wants to nd similar images associated to other cases that helps him to assess the current case. Previously, the doctor would need to sequentially traverse the image database looking for similar images, a process that could be unfeasible for moderately large data bases. Information visualization methods coupled with machine learning techniques may provide meaningful representation of medical image collections. In this work I propose to nd suitable solutions to above issues, to apply them to medical context, and to evaluate them by physicians.
References [1] A. Del Bimbo. A perspective view on visual information retrieval systems.
Content-Based Access of Image and Video Libraries, 1998. Proceedings. IEEE Workshop on, pages 108109, Jun 1998.
[2] G. P. Nguyen and M. Worring. Interactive access to large image collections using similarity-based visualization. Journal of Visual Languages & Computing, 19(2):203224, April 2008. [3] Jock D.Mackinlay Stuart K. Card and Ben Shneiderman. Readings in Information Visualization: Using Vision to Think. Morgan Kaufmann Publishers, 1999. [4] Jin Zhang.
Visualization for Information Retrieval. Springer, 2008.
2