Temporal and volumetric denoising via quantile sparse image prior
This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and compu...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2020
|
| Online Access: | https://hdl.handle.net/1721.1/124794 |
| _version_ | 1826197346054045696 |
|---|---|
| author | Fujimoto, James G. |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Fujimoto, James G. |
| author_sort | Fujimoto, James G. |
| collection | MIT |
| description | This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show different noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the other hand has a lower resolution and shows high-frequency noise. For the purpose of denoising, we propose a variational framework based on the QuaSI prior and a Huber data fidelity model that can handle 3-D and 3-D+t data. Efficient optimization is facilitated through the use of an alternating direction method of multipliers (ADMM) scheme and the linearization of the quantile filter. Experiments on multiple datasets emphasize the excellent performance of the proposed method. ©2018 |
| first_indexed | 2024-09-23T10:46:16Z |
| format | Article |
| id | mit-1721.1/124794 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:46:16Z |
| publishDate | 2020 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1247942020-10-15T06:25:31Z Temporal and volumetric denoising via quantile sparse image prior Fujimoto, James G. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Research Laboratory of Electronics This paper introduces an universal and structure-preserving regularization term, called quantile sparse image (QuaSI) prior. The prior is suitable for denoising images from various medical imaging modalities. We demonstrate its effectiveness on volumetric optical coherence tomography (OCT) and computed tomography (CT) data, which show different noise and image characteristics. OCT offers high-resolution scans of the human retina but is inherently impaired by speckle noise. CT on the other hand has a lower resolution and shows high-frequency noise. For the purpose of denoising, we propose a variational framework based on the QuaSI prior and a Huber data fidelity model that can handle 3-D and 3-D+t data. Efficient optimization is facilitated through the use of an alternating direction method of multipliers (ADMM) scheme and the linearization of the quantile filter. Experiments on multiple datasets emphasize the excellent performance of the proposed method. ©2018 2020-04-22T16:18:49Z 2020-04-22T16:18:49Z 2019-10-02T12:56:51Z Article http://purl.org/eprint/type/JournalArticle 1361-8423 1361-8415 https://hdl.handle.net/1721.1/124794 Schirrmacher, Franziska, et al., "Temporal and volumetric denoising via quantile sparse image prior." Medical image analysis 48 (August 2018): p.131-46 doi 10.1016/J.MEDIA.2018.06.002 ©2018 Author(s) en 10.1016/J.MEDIA.2018.06.002 Medical image analysis Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV PMC |
| spellingShingle | Fujimoto, James G. Temporal and volumetric denoising via quantile sparse image prior |
| title | Temporal and volumetric denoising via quantile sparse image prior |
| title_full | Temporal and volumetric denoising via quantile sparse image prior |
| title_fullStr | Temporal and volumetric denoising via quantile sparse image prior |
| title_full_unstemmed | Temporal and volumetric denoising via quantile sparse image prior |
| title_short | Temporal and volumetric denoising via quantile sparse image prior |
| title_sort | temporal and volumetric denoising via quantile sparse image prior |
| url | https://hdl.handle.net/1721.1/124794 |
| work_keys_str_mv | AT fujimotojamesg temporalandvolumetricdenoisingviaquantilesparseimageprior |