Towards an Optimal Interest Point Detector for Measurements in Ultrasound Images

Abstract

This paper focuses on the comparison of different interest point detectors and their utilization for measurements in ultrasound (US) images. Certain medical examinations are based on speckle tracking which strongly relies on features that can be reliably tracked frame to frame. Only significant features (interest points) resistant to noise and brightness changes within US images are suitable for accurate long-lasting tracking. We compare three interest point detectors -Harris-Laplace, Difference of Gaussian (DoG) and Fast Hessian -and identify the most suitable one for use in US images on the basis of an objective criterion. Repeatability rate is assumed to be an objective quality measure for comparison. We have measured repeatability in images corrupted by different types of noise (speckle noise, Gaussian noise) and for changes in brightness. The Harris-Laplace detector outperformed its competitors and seems to be a sound option when choosing a suitable interest point detector for US images. However, it has to be noted that Fast Hessian and DoG detectors achieved better results in terms of processing speed.

Deep learning robotic guidance for autonomous vascular access

“…The second network (Fig. 2d) was pre-trained on two public US image datasets 63,64 and fine-tuned on previously acquired transverse 2D US images of peripheral upper-extremity vessels from nine subjects using two clinical US transducers (L18-10L30H-4, Telemed Ultrasound and SeeMore Near-Field 7.5/24 MHz, Interson) 59 . Inputs were two-channel tensors with dimensions 512 × 416 × 2 containing B-mode and CDIs.…”