|
| Characteristic of the Dominant Follicle in Unstimulated Cycles |
| Leader: |
Prof. Dr. Veljko Vlaisavljevic (Teaching Hospital of
Maribor) |
| Participants: |
Prof. Dr. Damjan
Zazula, Dr. Dean Korošec, Dr. Božidar Potocnik, Jurij Munda, Nicolas Sergent
(Ecole Centrale de Nantes, France) |
| Project partners: |
Teaching Hospital of Maribor |
| Financed by: |
Slovenian Ministry of Science and Technology |
| Duration: |
2000 to 2002 |
This project was accepted in 2000 for a duration of two and half years. As project partners, we will develop computer-based procedures for the interpretation of ovarian B-ultrasound and Doppler images. The problem is very complex, especially because we are dealing with automated object recognition in extra noisy environments.
At the moment our research is towards computer-assisted estimation of blood quantity around a dominant follicle. The blood quantity is a very interesting parameter for physicians, because it can reveal abnormal situations in the ovary. It can even predict a subsequent follicular response in an "In Vitro Fertilization" program. The dominant follicle is supposed to be the most fed by blood, and too much or too less quantity of blood around
the dominant follicle can trouble its normal development. Gynaecologists can visualize a blood flow or the resilience in the vessels by means of Doppler images. However, they are unable to estimate the blood quantity.
In the first project year, we developed a prototype for automated estimation of blood quantity in a 5 mm pass around the dominant follicle. This procedure is the first known systematic approach to the above-mentioned problem. Our procedure is a combination of several sophisticated digital image processing routines ranging from image colour channel splitting,
thresholding, cellular neural networks used for follicle detection, to prediction routines and statistical tools. After processing the entire Doppler image sequence (usually around 500 images) quantitative results are obtained. Location, importance and other quantitative indexes are determined for each blood vessel in a 5 mm pass around the dominant follicle. Finally, a 3D reconstruction model of these blood vessels is built.
We analysed approximately 100 patients in the first project year using our tool.
See also "Quantitative and automated estimation of blood around the follicle in the ovary". |
|
