A 0.064 mm² 16-Channel In-Pixel Neural Front End with Improved System Common-Mode Rejection Exploiting a Current-Mode Summing Approach

Abstract

In this work, we introduce the design of a 16-channel in-pixel neural analog front end that employs a current-based summing approach to establish a common-mode feedback loop. The primary aim of this novel structure is to enhance both the system common-mode rejection ratio (SCMRR) and the common-mode interference (CMI) range. Compared to more conventional designs, the proposed front end utilizes DC-coupled inverter-based main amplifiers, which significantly reduce the occupied on-chip area. Additionally, the current-based implementation of the CMFB loop obviates the need for voltage buffers, replacing them with simple common-gate transistors, which, in turn, decreases both area occupancy and power consumption. The proposed architecture is further examined from an analytical standpoint, providing a comprehensive evaluation through design equations of its performance in terms of gain, common-mode rejection, and noise power. A 50 μm × 65 μm compact layout of the pixel amplifiers that make up the recording channels of the front end was designed using a 180 nm CMOS process. Simulations conducted in Cadence Virtuoso reveal an SCMRR of 80.5 dB and a PSRR of 72.58 dB, with a differential gain of 44 dB and a bandwidth that fully encompasses the frequency range of the bio-signals that can be theoretically captured by the neural probe. The noise integrated in the range between 1 Hz and 7.5 kHz results in an input-referred noise (IRN) of 4.04 μVrms. Power consumption is also tested, with a measured value of 3.77 μW per channel, corresponding to an overall consumption of about 60 μW. To test its robustness with respect to PVT and mismatch variations, the front end is evaluated through extensive parametric simulations and Monte Carlo simulations, revealing favorable results.

Keywords

• front end
• neural recording
• system common-mode rejection ratio