Improved image quality and dose reduction in abdominal CT with deep-learning reconstruction algorithm: a phantom study. 2023

Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
Department of Medical Imaging, CHU Nîmes, Univ Montpellier, Nîmes Medical Imaging Group, EA 2992, Bd. Prof Robert Debré, 30029, Nîmes Cedex 9, France. joel.greffier@chu-nimes.fr.

OBJECTIVE To assess the impact of a new artificial intelligence deep-learning reconstruction (Precise Image; AI-DLR) algorithm on image quality against a hybrid iterative reconstruction (IR) algorithm in abdominal CT for different clinical indications. METHODS Acquisitions on phantoms were performed at 5 dose levels (CTDIvol: 13/11/9/6/1.8 mGy). Raw data were reconstructed using level 4 of iDose4 (i4) and 3 levels of AI-DLR (Smoother/Smooth/Standard). Noise power spectrum (NPS), task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a liver metastasis (LM) and hepatocellular carcinoma at portal (HCCp) and arterial (HCCa) phases. Image quality was subjectively assessed on an anthropomorphic phantom by 2 radiologists. RESULTS From Standard to Smoother levels, noise magnitude and average NPS spatial frequency decreased and the detectability (d') of all simulated lesions increased. For both inserts, TTF values were similar for all three AI-DLR levels from 13 to 6 mGy but decreased from Standard to Smoother levels at 1.8 mGy. Compared to the i4 used in clinical practice, d' values were higher using the Smoother and Smooth levels and close for the Standard level. For all dose levels, except at 1.8 mGy, radiologists considered images satisfactory for clinical use for the 3 levels of AI-DLR, but rated images too smooth using the Smoother level. CONCLUSIONS Use of the Smooth and Smoother levels of AI-DLR reduces the image noise and improves the detectability of lesions and spatial resolution for standard and low-dose levels. Using the Smooth level is apparently the best compromise between the lowest dose level and adequate image quality. CONCLUSIONS • Evaluation of the impact of a new artificial intelligence deep-learning reconstruction (AI-DLR) on image quality and dose compared to a hybrid iterative reconstruction (IR) algorithm. • The Smooth and Smoother levels of AI-DLR reduced the image noise and improved the detectability of lesions and spatial resolution for standard and low-dose levels. • The Smooth level seems the best compromise between the lowest dose level and adequate image quality.

UI MeSH Term Description Entries
D011829 Radiation Dosage The amount of radiation energy that is deposited in a unit mass of material, such as tissues of plants or animal. In RADIOTHERAPY, radiation dosage is expressed in gray units (Gy). In RADIOLOGIC HEALTH, the dosage is expressed by the product of absorbed dose (Gy) and quality factor (a function of linear energy transfer), and is called radiation dose equivalent in sievert units (Sv). Sievert Units,Dosage, Radiation,Gray Units,Gy Radiation,Sv Radiation Dose Equivalent,Dosages, Radiation,Radiation Dosages,Units, Gray,Units, Sievert
D011857 Radiographic Image Interpretation, Computer-Assisted Computer systems or networks designed to provide radiographic interpretive information. Computer Assisted Radiographic Image Interpretation,Computer-Assisted Radiographic Image Interpretation,Radiographic Image Interpretation, Computer Assisted
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D000077321 Deep Learning Supervised or unsupervised machine learning methods that use multiple layers of data representations generated by nonlinear transformations, instead of individual task-specific ALGORITHMS, to build and train neural network models. Hierarchical Learning,Learning, Deep,Learning, Hierarchical
D000084862 Drug Tapering Gradual discontinuation or reduction of a therapeutic dose of a particular drug over a period of time. Dose Reduction,Dose Tapering,Dose Reductions,Dose Taperings,Reduction, Dose,Reductions, Dose,Tapering, Dose,Tapering, Drug,Taperings, Dose
D000465 Algorithms A procedure consisting of a sequence of algebraic formulas and/or logical steps to calculate or determine a given task. Algorithm
D001185 Artificial Intelligence Theory and development of COMPUTER SYSTEMS which perform tasks that normally require human intelligence. Such tasks may include speech recognition, LEARNING; VISUAL PERCEPTION; MATHEMATICAL COMPUTING; reasoning, PROBLEM SOLVING, DECISION-MAKING, and translation of language. AI (Artificial Intelligence),Computer Reasoning,Computer Vision Systems,Knowledge Acquisition (Computer),Knowledge Representation (Computer),Machine Intelligence,Computational Intelligence,Acquisition, Knowledge (Computer),Computer Vision System,Intelligence, Artificial,Intelligence, Computational,Intelligence, Machine,Knowledge Representations (Computer),Reasoning, Computer,Representation, Knowledge (Computer),System, Computer Vision,Systems, Computer Vision,Vision System, Computer,Vision Systems, Computer
D014057 Tomography, X-Ray Computed Tomography using x-ray transmission and a computer algorithm to reconstruct the image. CAT Scan, X-Ray,CT Scan, X-Ray,Cine-CT,Computerized Tomography, X-Ray,Electron Beam Computed Tomography,Tomodensitometry,Tomography, Transmission Computed,X-Ray Tomography, Computed,CAT Scan, X Ray,CT X Ray,Computed Tomography, X-Ray,Computed X Ray Tomography,Computerized Tomography, X Ray,Electron Beam Tomography,Tomography, X Ray Computed,Tomography, X-Ray Computer Assisted,Tomography, X-Ray Computerized,Tomography, X-Ray Computerized Axial,Tomography, Xray Computed,X Ray Computerized Tomography,X Ray Tomography, Computed,X-Ray Computer Assisted Tomography,X-Ray Computerized Axial Tomography,Beam Tomography, Electron,CAT Scans, X-Ray,CT Scan, X Ray,CT Scans, X-Ray,CT X Rays,Cine CT,Computed Tomography, Transmission,Computed Tomography, X Ray,Computed Tomography, Xray,Computed X-Ray Tomography,Scan, X-Ray CAT,Scan, X-Ray CT,Scans, X-Ray CAT,Scans, X-Ray CT,Tomographies, Computed X-Ray,Tomography, Computed X-Ray,Tomography, Electron Beam,Tomography, X Ray Computer Assisted,Tomography, X Ray Computerized,Tomography, X Ray Computerized Axial,Transmission Computed Tomography,X Ray Computer Assisted Tomography,X Ray Computerized Axial Tomography,X Ray, CT,X Rays, CT,X-Ray CAT Scan,X-Ray CAT Scans,X-Ray CT Scan,X-Ray CT Scans,X-Ray Computed Tomography,X-Ray Computerized Tomography,Xray Computed Tomography
D019047 Phantoms, Imaging Devices or objects in various imaging techniques used to visualize or enhance visualization by simulating conditions encountered in the procedure. Phantoms are used very often in procedures employing or measuring x-irradiation or radioactive material to evaluate performance. Phantoms often have properties similar to human tissue. Water demonstrates absorbing properties similar to normal tissue, hence water-filled phantoms are used to map radiation levels. Phantoms are used also as teaching aids to simulate real conditions with x-ray or ultrasonic machines. (From Iturralde, Dictionary and Handbook of Nuclear Medicine and Clinical Imaging, 1990) Phantoms, Radiographic,Phantoms, Radiologic,Radiographic Phantoms,Radiologic Phantoms,Phantom, Radiographic,Phantom, Radiologic,Radiographic Phantom,Radiologic Phantom,Imaging Phantom,Imaging Phantoms,Phantom, Imaging

Related Publications

Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
July 2020, European radiology,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
October 2021, Medical physics,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
August 2022, Medical physics,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
February 2022, European radiology,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
June 2022, European radiology,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
July 2021, Journal of applied clinical medical physics,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
January 2022, Quantitative imaging in medicine and surgery,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
July 2022, Physics in medicine and biology,
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
January 2021, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB),
Joël Greffier, and Quentin Durand, and Julien Frandon, and Salim Si-Mohamed, and Maeliss Loisy, and Fabien de Oliveira, and Jean-Paul Beregi, and Djamel Dabli
January 2021, Journal of X-ray science and technology,
Copied contents to your clipboard!