FZUImageReg: A toolbox for medical image registration and dose fusion in cervical cancer radiotherapy

Abstract

The combination external-beam radiotherapy and high-dose-rate brachytherapy is a standard form of treatment for patients with locally advanced uterine cervical cancer. Personalized radiotherapy in cervical cancer requires efficient and accurate dose planning and assessment across these types of treatment. To achieve radiation dose assessment, accurate mapping of the dose distribution from HDR-BT onto EBRT is extremely important. However, few systems can achieve robust dose fusion and determine the accumulated dose distribution during the entire course of treatment. We have therefore developed a toolbox (FZUImageReg), which is a user-friendly dose fusion system based on hybrid image registration for radiation dose assessment in cervical cancer radiotherapy. The main part of the software consists of a collection of medical image registration algorithms and a modular design with a user-friendly interface, which allows users to quickly configure, test, monitor, and compare different registration methods for a specific application. Owing to the large deformation, the direct application of conventional state-of-the-art image registration methods is not sufficient for the accurate alignment of EBRT and HDR-BT images. To solve this problem, a multi-phase non-rigid registration method using local landmark-based free-form deformation is proposed for locally large deformation between EBRT and HDR-BT images, followed by intensity-based free-form deformation. With the transformation, the software also provides a dose mapping function according to the deformation field. The total dose distribution during the entire course of treatment can then be presented. Experimental results clearly show that the proposed system can achieve accurate registration between EBRT and HDR-BT images and provide radiation dose warping and fusion results for dose assessment in cervical cancer radiotherapy in terms of high accuracy and efficiency.

Fig 1. Flowchart and strategy of registration of EBRT and HDR-BT images in cervical cancer.

Fig 2. Scheme of dose accumulation between EBRT and HDR-BT.

Fig 3. Framework and workflow of FZUImageReg system.

Fig 4. Denoising of HDR-BT images by median filter.

(a) HDR-BT image with uneven bright voxels before denoising. (b) HDR-BT image after denoising.

Fig 5. Correction of locally large deformation between EBRT and HDR-BT images by LFFD.

(a) EBRT images used as a reference. (b) HDR-BT image with locally large deformation induced by the brachytherapy applicator. (c) and (d) Corresponding EBRT and HDR-BT image with manual landmarks. (e) HDR-BT image after correction of locally large deformation by LFFD. (f) and (g) Corresponding difference images before and after correction. (h) Deformation grid of LFFD, in which the ROIs are defined by the red rectangles.

Fig 6. Screenshot of the proposed FZUImageReg system.

(a) Main window interfaces of FZUImageReg (b) Point set registration panel (PointReg). (c) Automatic image registration panel (ImageReg).

Fig 7. Original clinical data of one cervical cancer patient.

(a) EBRT CT image. (b) HDR-BT CT image.

Fig 8. Coarse registration between EBRT and HDR-BT CT images for better initialization.

(a) EBRT images used as a reference. (The four marked points inside the image were used for point set rigid registration.) (b) HDR-BT image before initialization. (c) Difference images between EBRT and HDR-BT before initialization. (d) HDR-BT image with four marked points used for point set rigid registration. (e) HDR-BT image after intensity-based rigid, and affine (f) registration. The corresponding difference images between EBRT and HDR-BT after point set rigid, intensity-based rigid, and affine registration are shown in (g)–(i).

Fig 9. Comparison of registration results using FFD and LFFD+FFD non-rigid registration respectively.

(a) EBRT image used as a reference. (b) Initialized HDR-BT image before non-rigid registration. (c) HDR-BT image after (FFD) non-rigid registration. (d) HDR-BT image after (LFFD+FFD) non-rigid registration. The corresponding difference images are shown in (e) and (f).

Fig 10. EBRT and HDR-BT dose accumulation in cervical cancer.

(a) EBRT dose distribution used as a reference. The first, second, and third HDR-BT dose distributions and the accumulated dose distributions after affine and non-rigid (LFFD+FFD) registration are shown in columns (b)–(d).

Fig 11. Validation of alignment of images by mapping contours of important organs.

The contours of the pelvis, bladder, and rectum are delineated by an expert on both EBRT (a) and HDR-BT images (b). Alignment of both contours images without registration (c), and after affine (d), FFD (e), and LFFD+FFD registration (f).

Fig 12. Mapping of three HDR-BT images onto a reference EBRT image using (LFFD+FFD) non-rigid registration.

(a) EBRT image used as a reference. The first, second, and third HDR-BT images, registration result, and the corresponding difference image between EBRT and HDR-BT are shown in columns (b)–(d).