EUVIMEDEUVIMED entdecken
Crossref

Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity

Jingyu Zhong iD, Yangfan Hu, Yue Xing, Lingyun Wang iD, Jianying Li, Wei Lu, Xiaomeng Shi, Defang Ding, Xiang Ge, Huan Zhang, Weiwu Yao

Acta Radiologica · 2024

DOI: 10.1177/02841851241262765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Radiologica, 2024. Verfasst von Jingyu Zhong und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, PR China. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Radiographic Image Interpretation, Computer-Assisted, Radiography, Abdominal. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Yangfan Project of Science and Technology Commission of Shanghai Municipality, National Natural Science Foundation of China, Laboratory Open Fund of Key Technology and Materials in Minimally Invasive Spine Surgery.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The best settings of deep learning image reconstruction (DLIR) algorithm for abdominal low-kiloelectron volt (keV) virtual monoenergetic imaging (VMI) have not been determined.

Purpose

To determine the optimal settings of the DLIR algorithm for abdominal low-keV VMI. Material and Methods The portal-venous phase computed tomography (CT) scans of 109 participants with 152 lesions were reconstructed into four image series: VMI at 50 keV using adaptive statistical iterative reconstruction (Asir-V) at 50% blending (AV-50); and VMI at 40 keV using AV-50 and DLIR at medium (DLIR-M) and high strength (DLIR-H). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of nine anatomical sites were calculated. Noise power spectrum (NPS) using homogenous region of liver, and edge rise slope (ERS) at five edges were measured. Five radiologists rated image quality and diagnostic acceptability, and evaluated the lesion conspicuity.

Results

The SNR and CNR values, and noise and noise peak in NPS measurements, were significantly lower in DLIR images than AV-50 images in all anatomical sites (all P < 0.001). The ERS values were significantly higher in 40-keV images than 50-keV images at all edges (all P < 0.001). The differences of the peak and average spatial frequency among the four reconstruction algorithms were significant but relatively small. The 40-keV images were rated higher with DLIR-M than DLIR-H for diagnostic acceptance ( P < 0.001) and lesion conspicuity ( P = 0.010).

Conclusion

DLIR provides lower noise, higher sharpness, and more natural texture to allow 40 keV to be a new standard for routine VMI reconstruction for the abdomen and DLIR-M gains higher diagnostic acceptance and lesion conspicuity rating than DLIR-H.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningTomography, X-Ray ComputedRadiographic Image Interpretation, Computer-AssistedRadiography, AbdominalSignal-To-Noise RatioRadiography, Dual-Energy Scanned ProjectionHumansFemaleMaleMiddle AgedAgedAdultAlgorithmsAged, 80 and overImage Processing, Computer-AssistedRetrospective Studies

Stichwörter der Autor:innen

Multidetector computed tomographycontrast enhancementdeep learningimage reconstruction

Autor:innen und Institutionen

  • Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, PR China.
  • Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, PR China.
  • Computed Tomography Research Center, GE Healthcare, Beijing, PR China.
  • Computed Tomography Research Center, GE Healthcare, Shanghai, PR China.
  • Department of Materials, Imperial College London, London, UK.

ORCID-Profile: Jingyu Zhong, Lingyun Wang

Förderung

  • Yangfan Project of Science and Technology Commission of Shanghai Municipality
  • National Natural Science Foundation of China
  • Laboratory Open Fund of Key Technology and Materials in Minimally Invasive Spine Surgery
  • Research Fund of Tongren Hospital, Shanghai Jiao Tong University School of Medicine
  • Research Found of Health Commission of Changing District, Shanghai Municipality

Zitieren

APA

Zhong, J., Hu, Y., Xing, Y., Wang, L., Li, J., Lu, W., Shi, X., Ding, D., Ge, X., Zhang, H., & Yao, W. (2024). Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity. Acta Radiologica. https://doi.org/10.1177/02841851241262765

Vancouver

Zhong J, Hu Y, Xing Y, Wang L, Li J, Lu W, et al. Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity. Acta Radiologica. 2024. doi:10.1177/02841851241262765

BibTeX
@article{Zhong2024,
  author = {Zhong, Jingyu and Hu, Yangfan and Xing, Yue and Wang, Lingyun and Li, Jianying and Lu, Wei and Shi, Xiaomeng and Ding, Defang and Ge, Xiang and Zhang, Huan and Yao, Weiwu},
  title = {Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity},
  journal = {Acta Radiologica},
  year = {2024},
  doi = {10.1177/02841851241262765}
}
Kostenlos starten →