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

被引:0
|
作者
Tanveer, Md Sayed [1 ]
Wiedeman, Christopher [2 ]
Li, Mengzhou [1 ]
Shi, Yongyi [1 ]
De Man, Bruno [3 ]
Maltz, Jonathan S. [4 ]
Wang, Ge [1 ]
机构
[1] Rensselaer Polytech Inst, Dept Biomed Engn, Troy, NY USA
[2] Rensselaer Polytech Inst, Dept Elect Comp & Syst Engn, Troy, NY USA
[3] GE HealthCare, 1 Res Circle, Niskayuna, NY USA
[4] GE HealthCare, Waukesha, WI USA
基金
美国国家卫生研究院;
关键词
Photon-counting CT; deep-silicon detector; projection denoising; artificial intelligence; neural network; deep reinforcement learning; multi-agent learning; RECONSTRUCTION; NETWORK;
D O I
10.3233/XST-230278
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
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.
引用
收藏
页码:173 / 205
页数:33
相关论文
共 50 条
  • [21] Characterization of spectrometric photon-counting X-ray detectors at different pitches
    Jurdit, M.
    Brambilla, A.
    Moulin, V.
    Ouvrier-Buffet, P.
    Radisson, P.
    Verger, L.
    JOURNAL OF INSTRUMENTATION, 2017, 12
  • [22] NOISE DUE TO PHOTON-COUNTING STATISTICS IN COMPUTED X-RAY TOMOGRAPHY
    CHESLER, DA
    RIEDERER, SJ
    PELC, NJ
    JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1977, 1 (01) : 64 - 74
  • [23] PHOTON-COUNTING SPECTROMETER FOR ATTENUATION MEASUREMENTS IN SOFT X-RAY REGION
    BEDO, DE
    TOMBOULIAN, DH
    REVIEW OF SCIENTIFIC INSTRUMENTS, 1961, 32 (02): : 184 - &
  • [24] Spectral computed tomography in the age of photon-counting X-ray detectors
    Rotkopf, Lukas T.
    Wehrse, Eckhard
    Froelich, Matthias F.
    RADIOLOGIE, 2022, 62 (06): : 504 - 510
  • [25] Guidelines for the Selection of Scintillators for Indirect Photon-Counting X-ray Detectors
    van Blaaderen, J. Jasper
    van Aarle, Casper
    Leibold, David
    Dorenbos, Pieter
    Schaart, Dennis R.
    CHEMISTRY OF MATERIALS, 2025, 37 (05) : 1716 - 1740
  • [26] Indirect photon-counting x-ray imaging using CMOS Photon Detector (CPD)
    Nishihara, Toshiyuki
    Baba, Hiroyasu
    Matsumura, Masao
    Kumagai, Oichi
    Izawa, Takashi
    MEDICAL IMAGING 2019: PHYSICS OF MEDICAL IMAGING, 2019, 10948
  • [27] Photon-counting imaging camera for high-resolution X-ray and γ-ray applications
    Hall, D. J.
    Holland, A.
    JOURNAL OF INSTRUMENTATION, 2011, 6
  • [28] A Deep Learning Approach for Rapid and Generalizable Denoising of Photon-Counting Micro-CT Images
    Nadkarni, Rohan
    Clark, Darin P.
    Allphin, Alex J.
    Badea, Cristian T.
    TOMOGRAPHY, 2023, 9 (04) : 1286 - 1302
  • [29] Photon counting silicon X-ray pixel detector modules
    Seller, P
    Derbyshire, G
    Hall, G
    Iles, GM
    Jorden, A
    Murray, P
    Prydderch, ML
    Passmore, SM
    Smith, K
    Thomas, SL
    NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2001, 466 (01): : 174 - 177
  • [30] Methods for energy dispersive x-ray spectroscopy with photon-counting and deconvolution techniques
    Forte, Alessandro
    Gawne, Thomas
    Humphries, Oliver S.
    Campbell, Thomas
    Shi, Yuanfeng
    Vinko, Sam M.
    JOURNAL OF APPLIED PHYSICS, 2025, 137 (13)