An iterative multi‐path fully convolutional neural network for automatic cardiac segmentation in cine MR images.
Saved in:
| Title: | An iterative multi‐path fully convolutional neural network for automatic cardiac segmentation in cine MR images. |
|---|---|
| Authors: | Ma, Zongqing1 (AUTHOR), Wu, Xi2 (AUTHOR), Wang, Xin3 (AUTHOR), Song, Qi3 (AUTHOR), Yin, Youbing3 (AUTHOR), Cao, Kunlin3 (AUTHOR), Wang, Yan1 (AUTHOR) wangyanscu@hotmail.com, Zhou, Jiliu1,2 (AUTHOR) zhoujl@cuit.edu.cn |
| Source: | Medical Physics. Dec2019, Vol. 46 Issue 12, p5652-5665. 14p. |
| Subjects: | Artificial neural networks, Magnetic resonance imaging, Left heart ventricle, Magnetic resonance, Heart diseases |
| Abstract: | Purpose: Segmentation of the left ventricle (LV), right ventricle (RV) cavities and the myocardium (MYO) from cine cardiac magnetic resonance (MR) images is an important step for diagnosis and monitoring cardiac diseases. Spatial context information may be highly beneficial for segmentation performance improvement. To this end, this paper proposes an iterative multi‐path fully convolutional network (IMFCN) to effectively leverage spatial context for automatic cardiac segmentation in cine MR images. Methods: To effectively leverage spatial context information, the proposed IMFCN explicitly models the interslice spatial correlations using a multi‐path late fusion strategy. First, the contextual inputs including both the adjacent slices and the already predicted mask of the above adjacent slice are processed by independent feature‐extraction paths. Then, an atrous spatial pyramid pooling (ASPP) module is employed at the feature fusion process to combine the extracted high‐level contextual features in a more effective way. Finally, deep supervision (DS) and batch‐wise class re‐weighting mechanism are utilized to enhance the training of the proposed network. Results: The proposed IMFCN was evaluated and analyzed on the MICCAI 2017 automatic cardiac diagnosis challenge (ACDC) dataset. On the held‐out training dataset reserved for testing, our method effectively improved its counterparts that without spatial context and that with spatial context but using an early fusion strategy. On the 50 subjects test dataset, our method achieved Dice similarity coefficient of 0.935, 0.920, and 0.905, and Hausdorff distance of 7.66, 12.10, and 8.80 mm for LV, RV, and MYO, respectively, which are comparable or even better than the state‐of‐the‐art methods of ACDC Challenge. In addition, to explore the applicability to other datasets, the proposed IMFCN was retrained on the Sunnybrook dataset for LV segmentation and also produced comparable performance to the state‐of‐the‐art methods. Conclusions: We have presented an automatic end‐to‐end fully convolutional architecture for accurate cardiac segmentation. The proposed method provides an effective way to leverage spatial context in a two‐dimensional manner and results in precise and consistent segmentation results. [ABSTRACT FROM AUTHOR] |
| Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 140232249 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: An iterative multi‐path fully convolutional neural network for automatic cardiac segmentation in cine MR images. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Ma%2C+Zongqing%22">Ma, Zongqing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Xi%22">Wu, Xi</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Xin%22">Wang, Xin</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Song%2C+Qi%22">Song, Qi</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yin%2C+Youbing%22">Yin, Youbing</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cao%2C+Kunlin%22">Cao, Kunlin</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Yan%22">Wang, Yan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wangyanscu@hotmail.com</i><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Jiliu%22">Zhou, Jiliu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> zhoujl@cuit.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Dec2019, Vol. 46 Issue 12, p5652-5665. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+resonance+imaging%22">Magnetic resonance imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Left+heart+ventricle%22">Left heart ventricle</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+resonance%22">Magnetic resonance</searchLink><br /><searchLink fieldCode="DE" term="%22Heart+diseases%22">Heart diseases</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Purpose: Segmentation of the left ventricle (LV), right ventricle (RV) cavities and the myocardium (MYO) from cine cardiac magnetic resonance (MR) images is an important step for diagnosis and monitoring cardiac diseases. Spatial context information may be highly beneficial for segmentation performance improvement. To this end, this paper proposes an iterative multi‐path fully convolutional network (IMFCN) to effectively leverage spatial context for automatic cardiac segmentation in cine MR images. Methods: To effectively leverage spatial context information, the proposed IMFCN explicitly models the interslice spatial correlations using a multi‐path late fusion strategy. First, the contextual inputs including both the adjacent slices and the already predicted mask of the above adjacent slice are processed by independent feature‐extraction paths. Then, an atrous spatial pyramid pooling (ASPP) module is employed at the feature fusion process to combine the extracted high‐level contextual features in a more effective way. Finally, deep supervision (DS) and batch‐wise class re‐weighting mechanism are utilized to enhance the training of the proposed network. Results: The proposed IMFCN was evaluated and analyzed on the MICCAI 2017 automatic cardiac diagnosis challenge (ACDC) dataset. On the held‐out training dataset reserved for testing, our method effectively improved its counterparts that without spatial context and that with spatial context but using an early fusion strategy. On the 50 subjects test dataset, our method achieved Dice similarity coefficient of 0.935, 0.920, and 0.905, and Hausdorff distance of 7.66, 12.10, and 8.80 mm for LV, RV, and MYO, respectively, which are comparable or even better than the state‐of‐the‐art methods of ACDC Challenge. In addition, to explore the applicability to other datasets, the proposed IMFCN was retrained on the Sunnybrook dataset for LV segmentation and also produced comparable performance to the state‐of‐the‐art methods. Conclusions: We have presented an automatic end‐to‐end fully convolutional architecture for accurate cardiac segmentation. The proposed method provides an effective way to leverage spatial context in a two‐dimensional manner and results in precise and consistent segmentation results. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Medical Physics is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=140232249 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1002/mp.13859 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 5652 Subjects: – SubjectFull: Artificial neural networks Type: general – SubjectFull: Magnetic resonance imaging Type: general – SubjectFull: Left heart ventricle Type: general – SubjectFull: Magnetic resonance Type: general – SubjectFull: Heart diseases Type: general Titles: – TitleFull: An iterative multi‐path fully convolutional neural network for automatic cardiac segmentation in cine MR images. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Ma, Zongqing – PersonEntity: Name: NameFull: Wu, Xi – PersonEntity: Name: NameFull: Wang, Xin – PersonEntity: Name: NameFull: Song, Qi – PersonEntity: Name: NameFull: Yin, Youbing – PersonEntity: Name: NameFull: Cao, Kunlin – PersonEntity: Name: NameFull: Wang, Yan – PersonEntity: Name: NameFull: Zhou, Jiliu IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2019 Type: published Y: 2019 Identifiers: – Type: issn-print Value: 00942405 Numbering: – Type: volume Value: 46 – Type: issue Value: 12 Titles: – TitleFull: Medical Physics Type: main |
| ResultId | 1 |
