Automated registration of 3D ultrasound and CT/MR images for liver

Haque, Hasnine A; Omi, Yasuo; Ruskó, László; Annangi, Pavan; Kazuyuki, Ohmura

doi:10.1109/ultsym.2016.7728738

Cited by 2 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The automatic rigid registration is based on vessel bifurcation features proposed by Haque et al 12 . For every Y‐like vessel bifurcation, the bifurcation point and its three connected directional branches lead to six bifurcation spaces, each of which is defined by two ordered branch vessel vectors u and v and the bifurcation point p .…”

Section: Methodsmentioning

confidence: 99%

“…The matching criteria computation for all possible combinations can be processed concurrently. To decide the best match, the original method 12 used the SSD and cross‐correlation coefficient (CCC) calculated on a 3D region

{64 \times 64 \times 64}

centered on bifurcations point. As was mentioned previously, such intensity‐based metric is not robust.…”

Section: Methodsmentioning

confidence: 99%

“…We used our deep learning segmentation results in all methods for more fair and convenient comparison. The implementation details of registration algorithms were SSD: Our rigid registration process was similar to the method proposed by Haque et al 12 . The difference was that they used a SSD calculated on the intensity image slice in the bifurcation plane. Edge matching (EM): The method proposed by Nam et al 11 .…”

Section: Methodsmentioning

confidence: 99%

“…In rigid registration, we also compared the proposed metric

L_s

with the original Dice similarity coefficient (DSC) and other metrics such as CC, 12 MCC 7 used by existing methods. Besides, we will also compare multilabel mask with the vessel‐only mask to demonstrate the usefulness of gallbladder mask.…”

Section: Methodsmentioning

confidence: 99%

“…Based on the previous studies, we use the traditional geometrical information of liver vessel for automatic rigid registration based on the method by Haque et al 12 . that do not require any registered samples for training.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Zhao

Dai

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundThe 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 US. 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.PurposeThe 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.MethodsWe 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 US 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 nonrigid registration phase, we propose a hybrid context and edge based image similarity metric with a simple mask that can remove most noisy US 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) and the Jacobian determinent with paired t‐test and qualitative registration imaging results.ResultsThe 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 nonlinear registration metrics with paired t‐test's p value less than 0.05. The proposed overlap metric achieves better results than self similarity description (SSD), edge matching (EM), and block matching (BM) 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 US 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.ConclusionsThe deep learning‐based US segmentation can achieve satisfied result to assist robust conventional rigid registration. The Dice similarity coefficient‐based metrics, hybrid context, and edge image similarity metric contribute to robust and accurate registration.

show abstract

Section: Methodsmentioning

confidence: 99%