TD-BPQBC: A 1.8{\mu}W 5.5mm3 ADC-less Neural Implant SoC utilizing 13.2pJ/Sample Time-domain Bi-phasic Quasi-static Brain Communication

TL;DR

This paper introduces TD-BPQBC, a highly energy-efficient neural implant SoC that transmits data using time-domain PWM signals, significantly reducing power consumption and enabling fully-electrical, energy-harvested brain sensors.

Contribution

The paper presents a novel time-domain bi-phasic quasi-static brain communication method and an ultra-low power neural implant SoC that offloads ADC and DSP to the receiver.

Findings

Consumes only 1.8μW power during operation

Achieves transmitter energy efficiency of 1.1pJ/b, over 30 times better than previous methods

Supports 800kSps data rate for neural sensing

Abstract

Untethered miniaturized wireless neural sensor nodes with data transmission and energy harvesting capabilities call for circuit and system-level innovations to enable ultra-low energy deep implants for brain-machine interfaces. Realizing that the energy and size constraints of a neural implant motivate highly asymmetric system design (a small, low-power sensor and transmitter at the implant, with a relatively higher power receiver at a body-worn hub), we present Time-Domain Bi-Phasic Quasi-static Brain Communication (TD- BPQBC), offloading the burden of analog to digital conversion (ADC) and digital signal processing (DSP) to the receiver. The input analog signal is converted to time-domain pulse-width modulated (PWM) waveforms, and transmitted using the recently developed BPQBC method for reducing communication power in implants. The overall SoC consumes only 1.8{\mu}W power while sensing and communicating at 800kSps. The transmitter energy efficiency is only 1.1pJ/b, which is >30X better than the state-of-the-art, enabling a fully-electrical, energy-harvested, and connected in-brain sensor/stimulator node.