Herself’s Artificial Intelligence

I hadn’t heard anything about wavlets in several years and then this news story caught my eye.

. . .Meningiomas are tumours of the brain and nervous system and they account for 20% of all brain tumours. Doctors have a major problem of discriminating between the four different subtypes of meningiomas but doctors face three key problems in making such a diagnois:

– The work can be painstakingly slow requiring up to two hours of analysis and expert consideration of a full “slide” of information.

– The finest tumour specialists (histopathologists) can at times come up with completely contradictory findings based on slight variations in their method of analysis.

– Currently the slides that specialists examine contain a few million pixels of data and the task of tumour diagnosis is painstakingly slow already. This problem is quite literally growing as medical equipment is coming on stream that can produce slides with hundreds of millions pixel resolution.

. . .

Now researchers in the University of Warwick’s Department of Computer Science have devised a method of using “wavelets” to provide an automated analysis of the varying texture of the tumours and guidance to doctor’s within seconds of being presented the data.

[ read more Wavelets crunch through doctor’s day to long struggle to diagnose brain tumors

Maybe wavelets are about to make a bigger splash in the world of artificial intelligence?

Learn more:
An introduction to wavelets
A really friendly guide to wavelets
Tutorial on continuous wavelet analysis
Wavelet ( Wolfram site )
Wavelets
Wavelets for computer graphics

Code:
WAILI - Wavelets C++ library ( open source )
PyWavelets - Python library ( open source )
Wavelets in Java ( source code provided)