EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Spatial resolution, noise properties, and detectability index of a deep learning reconstruction algorithm for dual‐energy CT of the abdomen

Daniel Thor, Rebecca Titternes, Gavin Poludniowski

Medical Physics · 2023

DOI: 10.1002/mp.16300 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Daniel Thor and 2 co-authors. Institution: Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Stockholm, Sweden. Major MEDLINE topics: Deep Learning, Iodine. Cited 26 times so far (Crossref); 32 references. The full text is freely available (open access, CC BY 4.0).

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Iterative reconstruction (IR) has increasingly replaced traditional reconstruction methods in computed tomography (CT). The next paradigm shift in image reconstruction is likely to come from artificial intelligence, with deep learning reconstruction (DLR) solutions already entering the clinic. An enduring disadvantage to IR has been a change in noise texture, which can affect diagnostic confidence. DLR has demonstrated the potential to overcome this issue and has recently become available for dual‐energy CT.

Purpose

To evaluate the spatial resolution, noise properties, and detectability index of a commercially available DLR algorithm for dual‐energy CT of the abdomen and compare it to single‐energy (SE) CT.

Methods

An oval 25 cm x 35 cm custom‐made phantom was scanned on a GE Revolution CT scanner (GE Healthcare, Waukesha, WI) at two dose levels (13 and 5 mGy) and two iodine concentrations (8 and 2 mg/mL), using three typical abdominal scan protocols: dual‐energy (DE), SE 80 kV (SE‐80 kV) and SE 120 kV (SE‐120 kV). Reconstructions were performed with three strengths of IR (ASiR‐V: AR0%, AR50%, AR100%) and three strengths of DLR (TrueFidelity: low, medium, high). The DE acquisitions were reconstructed as mono‐energetic images between 40 and 80 keV. The noise power spectrum (NPS), task transfer function (TTF), and detectability index (d’) were determined for the reconstructions following the recommendations of AAPM Task Group 233.

Results

Noise magnitude reductions (relative to AR0%) for the SE protocols were on average (−29%, −21%) for (AR50%, TF‐M), while for DE‐70 keV were (−28%, −43%). There was less reduction in mean frequency (f av ) for DLR than for IR, with similar results for SE and DE imaging. There was, however, a substantial change in the NPS shape when using DE with DLR, quantifiable by a marked reduction in the peak frequency (f peak ) that was absent in SE mode. All protocols and reconstructions (including AR0%) exhibited slight to moderate shifts towards lower spatial frequencies at the lower dose (

Subjects

MeSH terms (MEDLINE)

Deep LearningIodineArtificial IntelligenceRadiation DosageTomography, X-Ray ComputedAlgorithmsPhantoms, ImagingAbdomenRadiographic Image Interpretation, Computer-Assisted

Author keywords

DECTdeep learning image reconstructionimage quality

Substances

Iodine

Authors and institutions

  • Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Stockholm, Sweden.
  • Department of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden.
  • Department of Clinical Science, Intervention and Technology, Karolinska Institutet, Stockholm, Sweden.

Cite

APA

Thor, D., Titternes, R., & Poludniowski, G. (2023). Spatial resolution, noise properties, and detectability index of a deep learning reconstruction algorithm for dual‐energy CT of the abdomen. Medical Physics. https://doi.org/10.1002/mp.16300

Vancouver

Thor D, Titternes R, Poludniowski G. Spatial resolution, noise properties, and detectability index of a deep learning reconstruction algorithm for dual‐energy CT of the abdomen. Medical Physics. 2023. doi:10.1002/mp.16300

BibTeX
@article{Thor2023,
  author = {Thor, Daniel and Titternes, Rebecca and Poludniowski, Gavin},
  title = {Spatial resolution, noise properties, and detectability index of a deep learning reconstruction algorithm for dual‐energy CT of the abdomen},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16300}
}
Start for free →