In-pixel AI for lossy data compression at source for X-ray detectors

Manuel B. Valentin, Giuseppe Di Guglielmo*, Danny Noonan, Priyanka Dilip, Panpan Huang, Adam Quinn, Thomas Zimmerman, Davide Braga, Seda Ogrenci, Chris Jacobsen, Nhan Tran, Farah Fahim

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Integrating neural networks for data compression directly in the Read-Out Integrated Circuits (ROICs), i.e. the pixelated front-end, would result in a significant reduction in off-chip data transfer, overcoming the I/O bottleneck. Our ROIC test chip (AI-In-Pixel-65) is designed in a 65 nm Low Power CMOS process for the readout of pixelated X-ray detectors. Each pixel consists of an analog front-end for signal processing and a 10b analog-to-digital converter operating at 100KSPS. We compare two non-reconfigurable techniques, Principal Component Analysis (PCA) and an AutoEncoder (AE) as lossy data compression engines implemented within the pixelated area. The PCA algorithm achieves 50× compression, adds one clock cycle latency, and results in a 21% increase in the pixel area. The AE achieves 70× compression, adds 30 clock cycle latency, and results in a similar area increase.

Keywords

  • Data-compression at source
  • Machine-learning in pixel sensors
  • Microscopy
  • Ptychography
  • Read-out integrated circuits
  • X-ray detectors

ASJC Scopus subject areas

  • Nuclear and High Energy Physics
  • Instrumentation

Fingerprint

Dive into the research topics of 'In-pixel AI for lossy data compression at source for X-ray detectors'. Together they form a unique fingerprint.

Cite this