Fast reconstruction-based ROI triggering via anomaly detection in the CYGNO optical TPC

Abstract Optical-readout time projection chambers (TPCs) produce megapixel-scale images whose fine-grained topological information is essential for rare-event searches, but whose size challenges real-time data selection. We present an unsupervised, reconstruction-based anomaly-detection strategy for fast region-of-interest (ROI) extraction that operates directly on minimally processed camera frames. A convolutional autoencoder (AE) trained exclusively on pedestal images learns the detector noise morphology without labels, simulation, or fine-grained calibration. Applied to standard data-taking frames, localized reconstruction residuals identify particle-induced structures, from which compact ROIs are extracted via thresholding and spatial clustering. Using real data from the CYGNO optical TPC prototype, we compare two pedestal-trained AE configurations that differ only in their training objective, enabling a controlled study of its impact. The best configuration retains <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo stretchy="false">(</mml:mo> <mml:mn>93.0</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.2</mml:mn> <mml:mo stretchy="false">)</mml:mo> <mml:mi mathvariant="normal">%</mml:mi> </mml:mrow> </mml:math> of reconstructed signal intensity while discarding <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:mo stretchy="false">(</mml:mo> <mml:mn>97.8</mml:mn> <mml:mo>±</mml:mo> <mml:mn>0.1</mml:mn> <mml:mo stretchy="false">)</mml:mo> <mml:mi mathvariant="normal">%</mml:mi> </mml:mrow> </mml:math> of the image area, with an inference time of ∼25 ms per frame on a consumer GPU. The results demonstrate that careful design of the training objective is critical for effective reconstruction-based anomaly detection and that pedestal-trained AEs provide a transparent and detector-agnostic baseline for online data reduction in optical TPCs.