A robust and automatic CT-3D ultrasound registration method based on segmentation, context and edge hybrid metric.

Researchers

Journal

Modalities

Models

Abstract

The fusion of computed tomography (CT) and ultrasound (US) image can enhance lesion detection ability and improve the success rate of liver interventional radiology. The image based fusion methods encounter the challenge of registration initialization due to the random scanning pose and limited field of view of ultrasound. Existing automatic methods those used vessel geometric information and intensity based metric are sensitive to parameters and have low success rate. The learning based methods require a large number of registered datasets for training.The aim of this study is to provide a fully automatic and robust US-3D CT registration method without registered training data and user-specified parameters assisted by the revolutionary deep learning based segmentation, which can further be used for preparing training samples for the study of learning based methods.We propose a fully automatic CT-3D US registration method by two improved registration metrics. We propose to use 3D U-Net based multi-organ segmentation of ultrasound and CT to assist the conventional registration. The rigid transform is searched in the space of any paired vessel bifurcation planes where the best transform is decided by a segmentation overlap metric which is more related to the segmentation precision than Dice coefficient. In non-rigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy ultrasound voxels to guide the B-spline transform registration. We evaluate our method on 42 paired CT-3D US datasets scanned with two different US devices from two hospitals. We compared our methods with other exsiting methods with both quantitative measures of target registration error (TRE) & the Jacobian determinent with paired t-test and qualitative registration imaging results.The results show that our method achieves fully automatic rigid registration TRE of 4.895 mm, deformable registration TRE of 2.995 mm in average, which outperforms state-of-the-art automatic linear methods and non-linear registration metrics with paried t-test’s P value less than 0.05. The proposed overlap metric achieves better results than SSD (Self similarity description), EM (edge matching) and BM (block matching) with P values of 1.624E-10, 4.235E-9, and 0.002, respectively. The proposed hybrid edge and context based metric outperforms context-only, edge-only and intensity statistics-only based metrics with P values of 0.023, 3.81E-5, and 1.38E-15, respectively. The 3D ultrasound segmentation has achieved mean Dice similarity coefficient (DSC) of 0.799, 0.724, 0.788, and precision of 0.871, 0.769, 0.862 for gallbladder, vessel, and branch vessel, respectively.The deep learning based ultrasound segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient based metrics, hybrid context and edge image similarity metric contributes to robust and accurate registration. This article is protected by copyright. All rights reserved.This article is protected by copyright. All rights reserved.