Biyopsi iğnelerinin gabor filtresi kullanılarak 2B ultrason görüntülerinde lokalize edilmesi

Needle Biopsies are common medical procedures to remove tissue samples from the body to be examined for diseases. During these procedures, the needle and its tip are tracked using medical imaging devices to avoid damage to the tissues and to get samples from the targeted site. Ultrasound (US) is a common imaging method to localize the needles because it does not have any known side effects and provides a larger workspace. However, excessive artifacts and low resolution of the US images make it difficult to localize the needles in the biopsies. A possible solution to this problem is to detect the needle and its tip using an image processing algorithm. In this thesis, a novel needle localization method is proposed for 2D US images based on the Gabor filter. This method enhances the needle outline to localize the needle, while suppressing other structures in the US images. The needle tip is localized in real-time and the estimation noise is reduced using the Kalman filter. Using the bin packing method, the processing time is reduced by 56%, without a GPU. Also, a simulation study to understand the accuracy of the system within different mediums is conducted. The proposed needle localization scheme was tested using various phantoms. An external sensor was used to evaluate the accuracy of the needle insertion angle estimation and the needle tip localization methods. The Root mean square (RMS) error of the needle insertion angle was 2.29° ; and the RMS error of the needle tip position was 1.17 mm. The results showed that this localization scheme can be used in the US image guided percutaneous needle procedures.