Exjobbsförslag från företag

Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.

Förslaget inkom 2003-09-25

Analyzing ultrasound data using neural networks

OBS! ANSÖKNINGSTIDEN FÖR DETTA EXJOBB HAR LÖPT UT.
A very big multicenter study called Myocardial Doppler in Stress Echocardiography (MYDISE) has been performed in hospitals across Europe. In this study more than 1 000 patients and normal control persons underwent standard dobutamine stress echocardiography, that is, they were given dobutamine to increase the heart rate and then different parameters such as peak systolic velocities were measured using ultrasound.

The dataset has been analyzed with traditional statistical methods, but we feel that there is more to find in this dataset, and that new relations within the data can be found using neural networks. Maybe we can create a neural network which can be fed with different echocardiographical parameters and then predict where in the heart the problem is?

The work will be done using the Matlab Neural Networks Toolbox. Some experience in and knowledge of neural networks is required, and it is preferable with some experience in matlab programming.

The work will be done at the Division of Medical Engineering in Huddinge, Stockholm.

For more information, see: http://www.labtek.ki.se/medtek


  GÅ TILL XJOBB.NU FÖR FULLSTÄNDIG INFO OM DETTA EXJOBB




Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.