FPicker improves tracing of tiny filaments in noisy microscopy images
FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Tracing tiny thread-like structures in noisy microscope images is very hard because the images are cluttered and the threads cross over each other. The authors propose FPicker, a new method that traces these filaments by focusing on their shape and connections rather than just pixel brightness. This approach works much better than earlier methods, especially when the images are extremely noisy. It also performs well on real microscope data, showing its potential for helping scientists study complex 3D biological structures.
Cryo-Electron Microscopyfilament tracingsignal-to-noise ratiotopologyspatio-angular precisionactive contourssim-to-real gapopen-curve evolutioncenter-endpoint representation
Authors
Tingyin Zhao, Mingtao Huang, Yuan Shen
Abstract
Automating filament tracing in Cryo-Electron Microscopy (Cryo-EM) is essential for 3D helical reconstruction but challenged by intersecting topologies and extremely low Signal-to-Noise Ratios ($\text{SNR} = σ_s^2/σ_n^2$ < 0.1 or -10 dB). Existing paradigms fail: pixel-wise segmenters suffer from severe topological fracturing, box-based detectors face ghost center drift, sequential trackers derail due to error accumulation, and traditional active contours collapse under artificial closed-curve constraints. To resolve these bottlenecks, we present FPicker, the first topology-guided framework reconciling these incompatibilities. It unifies perception via a center-endpoint representation and an open-curve evolution module to explicitly model non-cyclic connectivity. On simulated benchmarks, FPicker outperforms top baselines by over $40\%$ relative gain in mean spatio-angular precision (mSAP) and reduces topological gap rates by over $60\%$ under extreme noise ($-20\text{ dB}$). By learning intrinsic physical geometry rather than local texture, FPicker demonstrates strong potential as a resilient geometric backbone. Its zero-shot performance on the real-world EMPIAR dataset exhibits robust topological resistance, achieving a state-of-the-art 82.9\% mSAP upon fine-tuning. Our results also suggest modeling physical priors is a highly robust path toward bridging the sim-to-real gap in signal-starved scientific imaging. The code is publicly available at: https://github.com/tomzhaosky/FPicker.