Authors:
Simone Damiani
1
;
2
;
Manuela Imbriani
1
;
3
;
Francesca Lizzi
2
;
Mariagrazia Quattrocchi
3
;
Alessandra Retico
2
;
Sara Saponaro
2
;
Camilla Scapicchio
2
;
Alessandro Tofani
3
;
Arman Zafaranchi
1
;
2
;
4
;
Maria Irene Tenerani
1
;
2
and
Maria Evelina Fantacci
1
;
2
Affiliations:
1
Department of Physics, University of Pisa, Pisa, Italy
;
2
National Institute for Nuclear Physics, Pisa Division, Italy
;
3
Medical Physics Department, Azienda Toscana Nord Ovest Area Nord, Lucca, Italy
;
4
Department of Computer Science, University of Pisa, Pisa, Italy
Keyword(s):
Denoising, Chest Low Dose Computed Tomography, Convolutional Autoencoder, Phantom, Lung Cancer, Deep Learning.
Abstract:
Low Dose Computed Tomography (LDCT) has proven to be an optimal clinical exploration method for early diagnosis of lung cancer in asymptomatic but high-risk population; however, this methodology suffers from a considerable increase in image noise with respect to Standard Dose Computed Tomography (CT) scans. Several approaches, both conventional and Deep Learning (DL) based, have been developed to mitigate this problem while preserving the visibility of the radiological signs of pathology. This study aims to exploit the possibility of using DL-based methods for the denoising of LDCTs, using a Convolutional Autoencoder and a paired low-dose and high-dose scans (LD/HD) dataset of phantom images. We used twelve acquisitions of the Catphan-500® phantom, each containing 130 slices, acquired with two CT scanners, two dose levels and reconstructed using the Filtered BackProjection algorithm. The proposed architecture, trained with a com-bined loss function, shows promising results for both n
oise magnitude reduction and Contrast-to-Noise Ratio enhancement when compared with HD reference images. These preliminary results, while encouraging, leave a wide margin for improvement and need to be replicated first on phantoms with more complex structures, secondly on images reconstructed with Iterative Reconstruction algorithms and then translated to LDCTs of real patients.
(More)