18152856. PCCT ENERGY CALIBRATION FROM X-RAY TUBE SPECTRA USING A NEURAL NETWORK simplified abstract (CANON MEDICAL SYSTEMS CORPORATION)
Contents
PCCT ENERGY CALIBRATION FROM X-RAY TUBE SPECTRA USING A NEURAL NETWORK
Organization Name
CANON MEDICAL SYSTEMS CORPORATION
Inventor(s)
Kent C. Burr of Vernon Hills IL (US)
Nikolay Markov of Vernon Hills IL (US)
Yi Qiang of Vernon Hills IL (US)
PCCT ENERGY CALIBRATION FROM X-RAY TUBE SPECTRA USING A NEURAL NETWORK - A simplified explanation of the abstract
This abstract first appeared for US patent application 18152856 titled 'PCCT ENERGY CALIBRATION FROM X-RAY TUBE SPECTRA USING A NEURAL NETWORK
The patent application describes an apparatus for calibrating a detector using an X-ray tube as a radiation source and a trained neural network to estimate calibration parameters for each channel of the detector.
- Acquires an energy spectrum from a scan using an X-ray tube.
- Estimates calibration parameters such as gain and offset for each detector channel using a trained neural network.
- Calibrates each channel using the estimated parameters.
- Neural network trained using measurements from isotope peak positions, K-edge absorption features, or K-edge emission peaks.
Potential Applications: - Medical imaging equipment calibration - Industrial quality control for X-ray inspection systems - Scientific research involving X-ray analysis
Problems Solved: - Ensures accurate calibration of detector channels - Streamlines the calibration process using neural networks
Benefits: - Improved accuracy in detecting and measuring radiation levels - Time and cost savings in calibration procedures
Commercial Applications: Title: "Advanced Detector Calibration System for X-ray Equipment" This technology can be used in medical imaging devices, security scanners, and industrial inspection systems to ensure precise and reliable results.
Questions about the technology: 1. How does the use of a trained neural network improve detector calibration compared to traditional methods? - The neural network can quickly and accurately estimate calibration parameters based on complex energy spectra, reducing the need for manual adjustments.
2. What are the key advantages of using isotope peak positions, K-edge absorption features, and K-edge emission peaks in training the neural network? - These measurements provide distinct and reliable data points for the neural network to learn from, resulting in more accurate calibration outcomes.
Original Abstract Submitted
An apparatus for calibrating a detector, including acquiring an energy spectrum obtained from a scan using an X-ray tube as a source of radiation, estimating calibration parameters, such as a gain and an offset, for each of several channels of the detector by applying the acquired first energy spectrum to inputs of a trained neural network that outputs the calibration parameters, and calibrating each of the plurality of channels using the estimation parameters. The neural network is trained to produce target output calibration parameters, using two or more measurements selected from isotope peak positions, K-edge absorption features, or K-edge emission peaks.
