A Split-and-Merge-Based Uterine Fibroid Ultrasound Image Segmentation Method in HIFU Therapy

Abstract

High-intensity focused ultrasound (HIFU) therapy has been used to treat uterine fibroids widely and successfully. Uterine fibroid segmentation plays an important role in positioning the target region for HIFU therapy. Presently, it is completed by physicians manually, reducing the efficiency of therapy. Thus, computer-aided segmentation of uterine fibroids benefits the improvement of therapy efficiency. Recently, most computer-aided ultrasound segmentation methods have been based on the framework of contour evolution, such as snakes and level sets. These methods can achieve good performance, although they need an initial contour that influences segmentation results. It is difficult to obtain the initial contour automatically; thus, the initial contour is always obtained manually in many segmentation methods. A split-and-merge-based uterine fibroid segmentation method, which needs no initial contour to ensure less manual intervention, is proposed in this paper. The method first splits the image into many small homogeneous regions called superpixels. A new feature representation method based on texture histogram is employed to characterize each superpixel. Next, the superpixels are merged according to their similarities, which are measured by integrating their Quadratic-Chi texture histogram distances with their space adjacency. Multi-way Ncut is used as the merging criterion, and an adaptive scheme is incorporated to decrease manual intervention further. The method is implemented using Matlab on a personal computer (PC) platform with Intel Pentium Dual-Core CPU E5700. The method is validated on forty-two ultrasound images acquired from HIFU therapy. The average running time is 9.54 s. Statistical results showed that SI reaches a value as high as 87.58%, and normHD is 5.18% on average. It has been demonstrated that the proposed method is appropriate for segmentation of uterine fibroids in HIFU pre-treatment imaging and planning.

Full coverage path planning algorithm for MRgFUS therapy

“…The-wide adaption of HIFU in the clinical management of uterine fibroids has led scientists to the development of more advanced planning and guiding tools for this specific application. Xu et al 12 proposed an automatic segmentation method for uterine fibroids on US images. The developed algorithm involves dividing the image into smaller regions called superpixels that are characterised using a texture histogram-based feature representation method and finally merging them again based on their similarities, meaning that the tumour's pixels will be merged together since they have similar texture.…”

“…The developed algorithm involves dividing the image into smaller regions called superpixels that are characterised using a texture histogram-based feature representation method and finally merging them again based on their similarities, meaning that the tumour's pixels will be merged together since they have similar texture. 12 Recently, Ning et al 7 proposed an image guidance system featuring tools for automatic detection and segmentation of lesions on MR images through a CNN multi-stage segmentation. Notably, the developed system also enables intraoperative lesion tracking on US images.…”

“…The‐wide adaption of HIFU in the clinical management of uterine fibroids has led scientists to the development of more advanced planning and guiding tools for this specific application. Xu et al 12 . proposed an automatic segmentation method for uterine fibroids on US images.…”

“…Advantageously, the proposed algorithm is specifically dedicated to path planning of MRgFUS robotic devices, whereas authors in previous studies developed planning tools for US‐guided therapy 7 , 12 or examined the performance of already existing segmentation tools. 13 With the proposed algorithm, the whole procedure from the lesion segmentation stage and distribution of foci to path execution is implemented in the MRI setting.…”

Adaptive localised region and edge‐based active contour model using shape constraint and sub‐global information for uterine fibroid segmentation in ultrasound‐guided HIFU therapy

“…The accurate, robust and efficient uterine fibroids segmentation in the guidance ultrasound images of HIFU therapy is essential for the definition of intra‐operative planning of the surgery [5]. Unfortunately, the ultrasound image in HIFU therapy is of poor quality with severely low signal‐to‐noise ratio (SNR), weak boundary and heterogeneous image intensities due to the interference of deaerated water when imaging by type‐B ultrasound during the treatment, which brings enormous difficulties in accurately and efficiently segmenting uterine fibroids with robustness [6–8].…”