基于实时灰度Hough变换的超声图像针状物体检测

实时针状物体分割、跟踪技术是图像导引手术治疗过程中的一项关键技术,针分割结果直接关系到手术的成败.以灰度Hough变换为基础,提出了一种在二维超声图像中检测插入软组织中针的自动跟踪技术--实时灰度Hough变换技术.该技术不需要二值化,它由粗-精搜索策略和改进的基于相位编组方法的灰度Hough变换两部分组成.用患者乳腺活检超声图像进行了实验,其结果表明,方法在没有外部硬件加速的情况下,在PC机上就能够实时、准确地检测出活检针,其方向误差为1°左右,位置误差在0.5mm以内,完全可以满足超声图像导引手术治疗与活检的需要.

Needle Segmentation in US Images Based on Real-time Gray-scale Hough Transformation

Real-time needle segmentation and tracking are very important technique in image-guided surgery, biopsy, and therapy.We proposed a needle segmentation technique based on a Real-Time Gray-Scale Hough Transform (RTGHT), which is composed of an improved Gray Hough transformation using phase-grouping algorithm with the coarse-fine searching strategy.Furthermore, the RTGHT technique was evaluated by patient breast biopsy images.Experiments with patient breast biopsy ultrasound (US) image sequences showed that our approach can segment the biopsy needle in real time with the angular rms error of about 1° and the position rms error of about 0.5 mm on an affordable PC com-puter without the help of specially designed hardware.It can be applied in image-guided surgery and therapy.