BISC(Berkeley
Initiative in Soft Computing) is in the process of forming a
specialinterest group in Medical Imaging (BISC-MED).
The purpose of this group is to facilitate communication between people who have interests in soft computing techniques and medical imaging.
In part, applying soft computing to medical imaging involves an acceptanceof impreciseness is an implicit aspect of: data, data structures, and extractedinformation.
The inital aspects of BISC-MED will be to: (a) develop a list of peopleinterested in this area so they can informally communicate through internet,(b) build a bibliography directed toward softcomputing and medical imaging,(c) provide a bulletin of web links of interest.
If you are interested in joining this group, please read the group announcementthat can be reached by toggling the BISC-MED DataBaselink.
The chairman for this group is Yutaka Hata.
Medical imaging has evolved at an explosive rate in the past few years.High-resolution, three-dimensional anatomical information can now be obtainedin a routine manner with magnetic resonance imaging(MRI) and computer-aidedtomography(CT). Three-dimensional functional imaging of blood flow and metabolicinformation can be obtained from positron emission tomography(PET) images, and functional four-dimensional electrophysiology (EEG) and evoked potentialinformation can be obtained using high-speed computers.
In the context of medical imaging, soft computing technique appears asa power framework since it provides tools adapted to this task. Its mainproperties are:
1. It provides a way to represent and manipulate imprecise and uncertaininformation.
2. It will be able to demonstrate knowledge of Medical doctors.
3. It is well adapted to image processing since the natural spatial interpretationof soft computing leads to efficient representations of imprecise or implicitstructures or classes in pictures.
Especially, a mixture of pattern recognition and SC-aided expert systemtechniques lead to successful tasks to segmentation of regions of interestsand to give enhanced anatomical and functional resolution.
This explosion of new techniques also emphasizes the need to integrate andfocus the efforts of scientists and clinicians to facilitate communication,establish standards, and develop training programs.
Soft computing is a consortium of methodologies that exploit a tolerancefor imprecision, uncertainty and partial truth. Results are achieved withtractability, robustness and a rapport with reality. These results are oftenbetter than that what is achieved through the exclusive use of conventional(hard) computing.
The principal members of soft computing are for the most part synergisticand complementary. The main ideas of soft computing were brought forth bythe confluence of fuzzy logic, neural networks, and probabilistic reasoning.Other ingredients include evolutionary algorithms, rough sets, chaos theory,belief networks and, although only partially, learning theory.
In soft computing, each constituent contributes a distinct methodology foraddressing problems in its domain. This is done in a complementary, ratherthan competitive way. clickhere for a definition of soft computing in greater detail
This page and all other BISC Medical Imaging pages are going through
significantmodification, definition, and development. Suggestions and
comments arevery welcome.