Repository logo
 

INSIDEnet: Interpretable NonexpanSIve Data-Efficient network for denoising in grating interferometry breast CT.

Simple item page
cam.issuedOnline2022-03-24
dc.contributor.authorvan Gogh, Stefano
dc.contributor.authorWang, Zhentian
dc.contributor.authorRawlik, Michał
dc.contributor.authorEtmann, Christian
dc.contributor.authorMukherjee, Subhadip
dc.contributor.authorSchönlieb, Carola-Bibiane
dc.contributor.authorAngst, Florian
dc.contributor.authorBoss, Andreas
dc.contributor.authorStampanoni, Marco
dc.date.accessioned2022-03-31T18:01:34Z
dc.date.available2022-03-31T18:01:34Z
dc.date.issued2022-06
dc.date.submitted2021-08-09
dc.date.updated2022-03-31T18:01:33Z
dc.descriptionFunder: Promedica Stiftung; Id: http://dx.doi.org/10.13039/501100008307
dc.descriptionFunder: Swisslos Lottery Fund of Kanton Aargau
dc.description.abstractPURPOSE: Breast cancer is the most common malignancy in women. Unfortunately, current breast imaging techniques all suffer from certain limitations: they are either not fully three dimensional, have an insufficient resolution or low soft-tissue contrast. Grating interferometry breast computed tomography (GI-BCT) is a promising X-ray phase contrast modality that could overcome these limitations by offering high soft-tissue contrast and excellent three-dimensional resolution. To enable the transition of this technology to clinical practice, dedicated data-processing algorithms must be developed in order to effectively retrieve the signals of interest from the measured raw data. METHODS: This article proposes a novel denoising algorithm that can cope with the high-noise amplitudes and heteroscedasticity which arise in GI-BCT when operated in a low-dose regime to effectively regularize the ill-conditioned GI-BCT inverse problem. We present a data-driven algorithm called INSIDEnet, which combines different ideas such as multiscale image processing, transform-domain filtering, transform learning, and explicit orthogonality to build an Interpretable NonexpanSIve Data-Efficient network (INSIDEnet). RESULTS: We apply the method to simulated breast phantom datasets and to real data acquired on a GI-BCT prototype and show that the proposed algorithm outperforms traditional state-of-the-art filters and is competitive with deep neural networks. The strong inductive bias given by the proposed model's architecture allows to reliably train the algorithm with very limited data while providing high model interpretability, thus offering a great advantage over classical convolutional neural networks (CNNs). CONCLUSIONS: The proposed INSIDEnet is highly data-efficient, interpretable, and outperforms state-of-the-art CNNs when trained on very limited training data. We expect the proposed method to become an important tool as part of a dedicated plug-and-play GI-BCT reconstruction framework, needed to translate this promising technology to the clinics.
dc.identifier.doi10.17863/CAM.83045
dc.identifier.eissn2473-4209
dc.identifier.issn0094-2405
dc.identifier.othermp15595
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/335614
dc.languageen
dc.language.isoeng
dc.publisherWiley
dc.publisher.urlhttp://dx.doi.org/10.1002/mp.15595
dc.subjectbreast CT
dc.subjectimage denoising
dc.subjectinterpretable machine learning
dc.subjectAlgorithms
dc.subjectFemale
dc.subjectHumans
dc.subjectImage Processing, Computer-Assisted
dc.subjectInterferometry
dc.subjectPhantoms, Imaging
dc.subjectSignal-To-Noise Ratio
dc.subjectThorax
dc.subjectTomography, X-Ray Computed
dc.titleINSIDEnet: Interpretable NonexpanSIve Data-Efficient network for denoising in grating interferometry breast CT.
dc.typeArticle
dcterms.dateAccepted2022-01-07
prism.publicationNameMed Phys
pubs.funder-project-idETH‐Research Commission (ETH‐12 20‐2)
pubs.funder-project-idSNF (CRSII5 183568)
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
rioxxterms.versionVoR
rioxxterms.versionofrecord10.1002/mp.15595

Files

Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
mp.15595.pdf
Size:
8.33 MB
Format:
Adobe Portable Document Format
Description:
Published version
Licence
http://creativecommons.org/licenses/by-nc-nd/4.0/
Download
No Thumbnail Available
Name:
mp.15595.xml
Size:
11.62 KB
Format:
Extensible Markup Language
Description:
Bibliographic metadata
Licence
http://creativecommons.org/licenses/by-nc-nd/4.0/
Download

Collections

Jisc Publications Router