Real-Time Pixel-Level Scatter Correction Using FPGA-Based Convolutional Neural Network for Time-of-Flight X-Ray Imaging
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Time-of-flight measurement shows great potential for enhancing X-ray imaging while reducing radiation dose, but also challenges systems' data handling and thermal limits. To reduce this data generation with minimal hardware resources, we propose to use an FPGA-based convolutional neural network to perform real-time scatter correction. The convolutional neural network performs pixel-wise estimation of primary photon counts from Time-of-flight distributions, enabling a practical and ultra-fast scatter correction method physically close to the detector. In simulations, the convolutional neural network achieves a mean absolute percentage error over the full image of 1.0 % compare to 23.6 % for the threshold-based scatter rejection method, significantly outperforming it. This suggests that the model captures the underlying scattering effect with great precision.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.010 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it