EUVIMEDEUVIMED entdecken
Crossref

Deep-silicon photon-counting x-ray projection denoising through reinforcement learning

Md Sayed Tanveer, Christopher Wiedeman, Mengzhou Li, Yongyi Shi, Bruno De Man, Jonathan S Maltz, Ge Wang

Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics · 2024

DOI: 10.3233/xst-230278 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, 2024. Verfasst von Md Sayed Tanveer und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA. Hauptthemen laut MEDLINE: Silicon, Algorithms. Die Arbeit nennt 42 Literaturangaben. Gefördert von: NCI NIH HHS, NHLBI NIH HHS, NIBIB NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: In recent years, deep reinforcement learning (RL) has been applied to various medical tasks and produced encouraging results. OBJECTIVE: In this paper, we demonstrate the feasibility of deep RL for denoising simulated deep-silicon photon-counting CT (PCCT) data in both full and interior scan modes. PCCT offers higher spatial and spectral resolution than conventional CT, requiring advanced denoising methods to suppress noise increase. METHODS: In this work, we apply a dueling double deep Q network (DDDQN) to denoise PCCT data for maximum contrast-to-noise ratio (CNR) and a multi-agent approach to handle data non-stationarity. RESULTS: Using our method, we obtained significant image quality improvement for single-channel scans and consistent improvement for all three channels of multichannel scans. For the single-channel interior scans, the PSNR (dB) and SSIM increased from 33.4078 and 0.9165 to 37.4167 and 0.9790 respectively. For the multichannel interior scans, the channel-wise PSNR (dB) increased from 31.2348, 30.7114, and 30.4667 to 31.6182, 30.9783, and 30.8427 respectively. Similarly, the SSIM improved from 0.9415, 0.9445, and 0.9336 to 0.9504, 0.9493, and 0.0326 respectively. CONCLUSIONS: Our results show that the RL approach improves image quality effectively, efficiently, and consistently across multiple spectral channels and has great potential in clinical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SiliconAlgorithmsX-RaysSignal-To-Noise RatioTomography, X-Ray ComputedImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Photon-counting CTartificial intelligencedeep reinforcement learningdeep-silicon detectormulti-agent learningneural networkprojection denoising

Substanzen

Silicon

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA.
  • Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA.
  • GE HealthCare, One Research Circle, Niskayuna, NY, USA.
  • GE HealthCare, Waukesha, WI, USA.

Förderung

  • NCI NIH HHS
  • NHLBI NIH HHS
  • NIBIB NIH HHS

Zitieren

APA

Tanveer, M. S., Wiedeman, C., Li, M., Shi, Y., De Man, B., Maltz, J. S., & Wang, G. (2024). Deep-silicon photon-counting x-ray projection denoising through reinforcement learning. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics. https://doi.org/10.3233/xst-230278

Vancouver

Tanveer MS, Wiedeman C, Li M, Shi Y, De Man B, Maltz JS, et al. Deep-silicon photon-counting x-ray projection denoising through reinforcement learning. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics. 2024. doi:10.3233/xst-230278

BibTeX
@article{Tanveer2024,
  author = {Tanveer, Md Sayed and Wiedeman, Christopher and Li, Mengzhou and Shi, Yongyi and De Man, Bruno and Maltz, Jonathan S and Wang, Ge},
  title = {Deep-silicon photon-counting x-ray projection denoising through reinforcement learning},
  journal = {Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics},
  year = {2024},
  doi = {10.3233/xst-230278}
}
Kostenlos starten →