Segmentation-guided multi-modal registration of liver images for dose estimation in SIRT

Abstract

Purpose Selective internal radiation therapy (SIRT) requires a good liver registration of multi-modality images to obtain precise dose prediction and measurement. This study investigated the feasibility of liver registration of CT and MR images, guided by segmentation of the liver and its landmarks. The influence of the resulting lesion registration on dose estimation was evaluated. Methods The liver segmentation was done with a convolutional neural network (CNN), and the landmarks were segmented manually. Our image-based registration software and its liver-segmentation-guided extension (CNN-guided) were tuned and evaluated with 49 CT and 26 MR images from 20 SIRT patients. Each liver registration was evaluated by the root mean square distance (RMSD) of mean surface distance between manually delineated liver contours and mass center distance between manually delineated landmarks (lesions, clips, etc.). The root mean square of RMSDs (RRMSD) was used to evaluate all liver registrations. The CNN-guided registration was further extended by incorporating landmark segmentations (CNN&LM-guided) to assess the value of additional landmark guidance. To evaluate the influence of segmentation-guided registration on dose estimation, mean dose and volume percentages receiving at least 70 Gy (V70) estimated on the 99mTc-labeled macro-aggregated albumin (99mTc-MAA) SPECT were computed, either based on lesions from the reference 99mTc-MAA CT (reference lesions) or from the registered floating CT or MR images (registered lesions) using the CNN- or CNN&LM-guided algorithms. Results The RRMSD decreased for the floating CTs and MRs by 1.0 mm (11%) and 3.4 mm (34%) using CNN guidance for the image-based registration and by 2.1 mm (26%) and 1.4 mm (21%) using landmark guidance for the CNN-guided registration. The quartiles for the relative mean dose difference (the V70 difference) between the reference and registered lesions and their correlations [25th, 75th; r] are as follows: [− 5.5% (− 1.3%), 5.6% (3.4%); 0.97 (0.95)] and [− 12.3% (− 2.1%), 14.8% (2.9%); 0.96 (0.97)] for the CNN&LM- and CNN-guided CT to CT registrations, [− 7.7% (− 6.6%), 7.0% (3.1%); 0.97 (0.90)] and [− 15.1% (− 11.3%), 2.4% (2.5%); 0.91 (0.78)] for the CNN&LM- and CNN-guided MR to CT registrations. Conclusion Guidance by CNN liver segmentations and landmarks markedly improves the performance of the image-based registration. The small mean dose change between the reference and registered lesions demonstrates the feasibility of applying the CNN&LM- or CNN-guided registration to volume-level dose prediction. The CNN&LM- and CNN-guided registrations for CTs can be applied to voxel-level dose prediction according to their small V70 change for most lesions. The CNN-guided MR to CT registration still needs to incorporate landmark guidance for smaller change of voxel-level dose estimation.

CT-MRI liver registration for selective internal radiation therapy

“…Since the tumor cannot be directly registered, the registration is done on the liver, thus requiring radiologists to manually delineate the liver on the CT in order to evaluate and potentially refine the quality of the registration. As registration has proven to be a tedious and time-consuming task for clinicians, 5,6 various semi-automatic and fully automatic liver registration methods have been studied and can be found in the literature. Conventional registration methods can be categorized 7 based on image dimensionality (2D, 3D, or 4D), modalities involved (mono-or multimodal), transformation models (rigid or non-rigid), and the fundamental approach used, whether feature-based or intensity-based.…”

“…Conventional registration methods can be categorized 7 based on image dimensionality (2D, 3D, or 4D), modalities involved (mono-or multimodal), transformation models (rigid or non-rigid), and the fundamental approach used, whether feature-based or intensity-based. Featurebased methods use landmarks such as feature points, 6 vessel 8, 9 or segmentations 5,10 to guide the registration by minimizing the distance of the features between the two images. In intensity-based approaches, 5,9,[11][12][13] the voxels of the two images are mapped based on their intensities, and the goal is to minimize the distance between the mapped voxels.…”

“…Featurebased methods use landmarks such as feature points, 6 vessel 8, 9 or segmentations 5,10 to guide the registration by minimizing the distance of the features between the two images. In intensity-based approaches, 5,9,[11][12][13] the voxels of the two images are mapped based on their intensities, and the goal is to minimize the distance between the mapped voxels. In multimodal tasks, the intensity mapping can be challenging due to differences in intensity scales and contrast variations between the modalities.…”

“…They use the bounding boxes of the liver segmentation masks in order to limit the sampling in the region of interest and it's surroundings. Tang et al 5 make use of a convolutional neural network (CNN) to automatically generate the liver segmentation masks that they use in a segmentation-based registration task, in combination with manually extracted landmarks.…”