Scan Camera X-Ray Imaging With ML Noise Removal for Better S/N
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radiographic image acquisition devices suffer from insufficient signal-to-noise (S/N) ratio due to the addition of detection data from multiple columns, leading to increased noise values.
Innovation Solution
A radiographic image acquiring device with a detection element comprising pixel lines arranged in columns, where detection signals from at least two pixels are combined and output sequentially, followed by a noise removal process using a trained model constructed through machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If detection data from multiple columns is added to improve signal value, then signal value improves, but noise value increases and S/N ratio does not improve sufficiently
Solution Approach 1:
The detection element is divided into multiple pixel lines with M pixels each, arranged in N columns. By segmenting the detection area into multiple regions and processing them separately before combining, the system achieves better noise characteristics compared to simple addition of all detection data.
Solution Approach 2:
Different pixel lines are assigned different functions based on their position. The first pixel line detects radiation in a specific area while the second pixel line detects radiation in a different area, allowing local optimization of detection quality and noise characteristics for each region.
2Reliability
If multiple pixels are combined to improve signal, then signal components increase, but noise components also increase
Solution Approach 1:
The system dynamically selects which pixel lines to combine based on the specific detection requirements and radiation conditions. The readout circuit can flexibly configure the combination of pixel lines, allowing adaptive optimization of signal-to-noise ratio for different imaging scenarios.
Solution Approach 2:
The patent introduces an intermediate processing stage where detection signals from multiple pixel lines are combined in a controlled manner before final image reconstruction. This intermediary processing allows for noise reduction while preserving signal integrity, acting as a mediator between raw detection data and final image output.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach effectively improves the S/N ratio in radiographic images by removing noise components while enhancing signal components.
Implementation Method 1
a scintillator configured to be provided on the imaging device to convert the radiation into light
Data Source
AI summary
A image acquiring device includes a camera configured to scan radiation passing through a target object in one direction and acquire an X-ray image, a scintillator configured to convert the X-rays into light, and a control device configured to input the X-ray image to a trained model constructed through machine learning in advance and execute a noise removal process. The camera includes a scan camera in which pixel lines each having M pixels arranged in one direction are configured to be arranged in N columns in a direction orthogonal to one direction and which is configured to output a detection signal for each of the pixels, and a readout circuit configured to output the X-ray image by adding the detection signals output from at least two pixels for each of the pixel lines of N columns in the scan camera and sequentially outputting the added N detection signals.