File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: MR to ultrasound image registration with segmentation-based learning for HDR prostate brachytherapy

TitleMR to ultrasound image registration with segmentation-based learning for HDR prostate brachytherapy
Authors
Keywordsdeep learning
MR to US image registration
prostate brachytherapy
segmentation
weak supervision
Issue Date1-Jun-2021
PublisherWiley
Citation
Medical Physics, 2021, v. 48, n. 6, p. 3074-3083 How to Cite?
AbstractPurpose: Propagation of contours from high-quality magnetic resonance (MR) images to treatment planning ultrasound (US) images with severe needle artifacts is a challenging task, which can greatly aid the organ contouring in high dose rate (HDR) prostate brachytherapy. In this study, a deep learning approach was developed to automatize this registration procedure for HDR brachytherapy practice. Methods: Because of the lack of training labels and difficulty of accurate registration from inferior image quality, a new segmentation-based registration framework was proposed for this multi-modality image registration problem. The framework consisted of two segmentation networks and a deformable registration network, based on the weakly -supervised registration strategy. Specifically, two 3D V-Nets were trained for the prostate segmentation on the MR and US images separately, to generate the weak supervision labels for the registration network training. Besides the image pair, the corresponding prostate probability maps from the segmentation were further fed to the registration network to predict the deformation matrix, and an augmentation method was designed to randomly scale the input and label probability maps during the registration network training. The overlap between the deformed and fixed prostate contours was analyzed to evaluate the registration accuracy. Three datasets were collected from our institution for the MR and US image segmentation networks, and the registration network learning, which contained 121, 104, and 63 patient cases, respectively. Results: The mean Dice similarity coefficient (DSC) results of the two prostate segmentation networks are 0.86 ± 0.05 and 0.90 ± 0.03, for MR images and the US images after the needle insertion, respectively. The mean DSC, center-of-mass (COM) distance, Hausdorff distance (HD), and averaged symmetric surface distance (ASSD) results for the registration of manual prostate contours were 0.87 ± 0.05, 1.70 ± 0.89 mm, 7.21 ± 2.07 mm, 1.61 ± 0.64 mm, respectively. By providing the prostate probability map from the segmentation to the registration network, as well as applying the random map augmentation method, the evaluation results of the four metrics were all improved, such as an increase in DSC from 0.83 ± 0.08 to 0.86 ± 0.06 and from 0.86 ± 0.06 to 0.87 ± 0.05, respectively. Conclusions: A novel segmentation-based registration framework was proposed to automatically register prostate MR images to the treatment planning US images with metal artifacts, which not only largely saved the labor work on the data preparation, but also improved the registration accuracy. The evaluation results showed the potential of this approach in HDR prostate brachytherapy practice.
Persistent Identifierhttp://hdl.handle.net/10722/345839
ISSN
2023 Impact Factor: 3.2
2023 SCImago Journal Rankings: 1.052

 

DC FieldValueLanguage
dc.contributor.authorChen, Yizheng-
dc.contributor.authorXing, Lei-
dc.contributor.authorYu, Lequan-
dc.contributor.authorLiu, Wu-
dc.contributor.authorPooya Fahimian, Benjamin-
dc.contributor.authorNiedermayr, Thomas-
dc.contributor.authorBagshaw, Hilary P-
dc.contributor.authorBuyyounouski, Mark-
dc.contributor.authorHan, Bin-
dc.date.accessioned2024-09-04T07:05:51Z-
dc.date.available2024-09-04T07:05:51Z-
dc.date.issued2021-06-01-
dc.identifier.citationMedical Physics, 2021, v. 48, n. 6, p. 3074-3083-
dc.identifier.issn0094-2405-
dc.identifier.urihttp://hdl.handle.net/10722/345839-
dc.description.abstractPurpose: Propagation of contours from high-quality magnetic resonance (MR) images to treatment planning ultrasound (US) images with severe needle artifacts is a challenging task, which can greatly aid the organ contouring in high dose rate (HDR) prostate brachytherapy. In this study, a deep learning approach was developed to automatize this registration procedure for HDR brachytherapy practice. Methods: Because of the lack of training labels and difficulty of accurate registration from inferior image quality, a new segmentation-based registration framework was proposed for this multi-modality image registration problem. The framework consisted of two segmentation networks and a deformable registration network, based on the weakly -supervised registration strategy. Specifically, two 3D V-Nets were trained for the prostate segmentation on the MR and US images separately, to generate the weak supervision labels for the registration network training. Besides the image pair, the corresponding prostate probability maps from the segmentation were further fed to the registration network to predict the deformation matrix, and an augmentation method was designed to randomly scale the input and label probability maps during the registration network training. The overlap between the deformed and fixed prostate contours was analyzed to evaluate the registration accuracy. Three datasets were collected from our institution for the MR and US image segmentation networks, and the registration network learning, which contained 121, 104, and 63 patient cases, respectively. Results: The mean Dice similarity coefficient (DSC) results of the two prostate segmentation networks are 0.86 ± 0.05 and 0.90 ± 0.03, for MR images and the US images after the needle insertion, respectively. The mean DSC, center-of-mass (COM) distance, Hausdorff distance (HD), and averaged symmetric surface distance (ASSD) results for the registration of manual prostate contours were 0.87 ± 0.05, 1.70 ± 0.89 mm, 7.21 ± 2.07 mm, 1.61 ± 0.64 mm, respectively. By providing the prostate probability map from the segmentation to the registration network, as well as applying the random map augmentation method, the evaluation results of the four metrics were all improved, such as an increase in DSC from 0.83 ± 0.08 to 0.86 ± 0.06 and from 0.86 ± 0.06 to 0.87 ± 0.05, respectively. Conclusions: A novel segmentation-based registration framework was proposed to automatically register prostate MR images to the treatment planning US images with metal artifacts, which not only largely saved the labor work on the data preparation, but also improved the registration accuracy. The evaluation results showed the potential of this approach in HDR prostate brachytherapy practice.-
dc.languageeng-
dc.publisherWiley-
dc.relation.ispartofMedical Physics-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectdeep learning-
dc.subjectMR to US image registration-
dc.subjectprostate brachytherapy-
dc.subjectsegmentation-
dc.subjectweak supervision-
dc.titleMR to ultrasound image registration with segmentation-based learning for HDR prostate brachytherapy-
dc.typeArticle-
dc.identifier.doi10.1002/mp.14901-
dc.identifier.pmid33905566-
dc.identifier.scopuseid_2-s2.0-85105806430-
dc.identifier.volume48-
dc.identifier.issue6-
dc.identifier.spage3074-
dc.identifier.epage3083-
dc.identifier.eissn2473-4209-
dc.identifier.issnl0094-2405-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats