X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods
In this work, an innovative approach is proposed for three-dimensional (3D) organ volume reconstruction from a single planar X-ray, namely X2V network. Such capability holds pivotal clinical potential, especially in real-time image-guided radiotherapy, computer-aided surgery, and patient follow-up s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10493004/ |
| _version_ | 1797206091978768384 |
|---|---|
| author | Gokce Guven Hasan F. Ates H. Fatih Ugurdag |
| author_facet | Gokce Guven Hasan F. Ates H. Fatih Ugurdag |
| author_sort | Gokce Guven |
| collection | DOAJ |
| description | In this work, an innovative approach is proposed for three-dimensional (3D) organ volume reconstruction from a single planar X-ray, namely X2V network. Such capability holds pivotal clinical potential, especially in real-time image-guided radiotherapy, computer-aided surgery, and patient follow-up sessions. Traditional methods for 3D volume reconstruction from X-rays often require the utilization of statistical 3D organ templates, which are employed in 2D/3D registration. However, these methods may not accurately account for the variation in organ shapes across different subjects. Our X2V model overcomes this problem by leveraging neural implicit representation. A vision transformer model is integrated as an encoder network, specifically designed to direct and enhance attention to particular regions within the X-ray image. The reconstructed meshes exhibit a similar topology to the ground truth organ volume, demonstrating the ability of X2V in accurately capturing the 3D structure from a 2D image. The effectiveness of X2V is evaluated on lung X-rays using several metrics, including volumetric Intersection over Union (IoU). X2V outperforms the state-of-the-art method in the literature for lungs (DeepOrganNet) by about 7-9% achieving IoU’s between 0.892-0.942 versus DeepOrganNet’s IoU of 0.815-0.888. |
| first_indexed | 2024-04-24T09:01:31Z |
| format | Article |
| id | doaj.art-1f2c2b65438e4cd298a0be3a0acf6d3b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T09:01:31Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1f2c2b65438e4cd298a0be3a0acf6d3b2024-04-15T23:00:22ZengIEEEIEEE Access2169-35362024-01-0112508985091010.1109/ACCESS.2024.338566810493004X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit MethodsGokce Guven0Hasan F. Ates1https://orcid.org/0000-0002-6842-1528H. Fatih Ugurdag2https://orcid.org/0000-0002-6256-0850Department of Computer Science, Özyeğin Üniversitesi, Istanbul, TurkeyDepartment of Computer Science, Özyeğin Üniversitesi, Istanbul, TurkeyDepartment of Electrical and Electronics Engineering, Özyeğin Üniversitesi, Istanbul, TurkeyIn this work, an innovative approach is proposed for three-dimensional (3D) organ volume reconstruction from a single planar X-ray, namely X2V network. Such capability holds pivotal clinical potential, especially in real-time image-guided radiotherapy, computer-aided surgery, and patient follow-up sessions. Traditional methods for 3D volume reconstruction from X-rays often require the utilization of statistical 3D organ templates, which are employed in 2D/3D registration. However, these methods may not accurately account for the variation in organ shapes across different subjects. Our X2V model overcomes this problem by leveraging neural implicit representation. A vision transformer model is integrated as an encoder network, specifically designed to direct and enhance attention to particular regions within the X-ray image. The reconstructed meshes exhibit a similar topology to the ground truth organ volume, demonstrating the ability of X2V in accurately capturing the 3D structure from a 2D image. The effectiveness of X2V is evaluated on lung X-rays using several metrics, including volumetric Intersection over Union (IoU). X2V outperforms the state-of-the-art method in the literature for lungs (DeepOrganNet) by about 7-9% achieving IoU’s between 0.892-0.942 versus DeepOrganNet’s IoU of 0.815-0.888.https://ieeexplore.ieee.org/document/10493004/3D reconstructionX-ray3D organ topologyneural implicit methodsvision transformers |
| spellingShingle | Gokce Guven Hasan F. Ates H. Fatih Ugurdag X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods IEEE Access 3D reconstruction X-ray 3D organ topology neural implicit methods vision transformers |
| title | X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods |
| title_full | X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods |
| title_fullStr | X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods |
| title_full_unstemmed | X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods |
| title_short | X2V: 3D Organ Volume Reconstruction From a Planar X-Ray Image With Neural Implicit Methods |
| title_sort | x2v 3d organ volume reconstruction from a planar x ray image with neural implicit methods |
| topic | 3D reconstruction X-ray 3D organ topology neural implicit methods vision transformers |
| url | https://ieeexplore.ieee.org/document/10493004/ |
| work_keys_str_mv | AT gokceguven x2v3dorganvolumereconstructionfromaplanarxrayimagewithneuralimplicitmethods AT hasanfates x2v3dorganvolumereconstructionfromaplanarxrayimagewithneuralimplicitmethods AT hfatihugurdag x2v3dorganvolumereconstructionfromaplanarxrayimagewithneuralimplicitmethods |