Medical image denoising uses deep learning (DnCNN, U-Net) or statistical methods (BM3D, NLM) trained on massive datasets. Patented: specific architectures, loss functions, preprocessing pipelines, hardware-specific optimizations. CRT approach: medical image pixels encoded in Z/214,414,200. 7 CRT channels = 7 independent noise dimensions. mod-11 = corruption detector (free from algebra). Per-channel neighborhood averaging = denoising. No training data. No neural network. No GPU. Demonstrated on synthetic phantom images.
Noise level (1-10):
Side-by-side: original phantom, noisy + mod-11 corruption (red pixels), CRT denoised. 7-channel CRT in Z/214,414,200. Rendered in one cvs_blit call.
Noise level (1-10):
Synthetic medical phantom (chest cross-section: lungs, heart, spine, tissue). Add noise at specified level. mod-11 detects corrupted pixels. Per-channel 3x3 averaging denoises. SNR improvement across 7 channels measured.
6 noise levels on the same phantom. Measures: noisy SNR, denoised SNR, mod-11 detection count, recovery ratio. CRT denoising improves quality at every noise level.
Source code · Public domain (CC0)
.ax source compiled to WASM via self-hosting compiler. Zero HTML authored.