Estimation of Bladder Pressure and Volume from the Neural Activity of Lumbosacral Dorsal Horn Using a Long-Short-Term-Memory-based Deep Neural Network

Abstract

In this paper, we propose a deep recurrent neural network (DRNN) for the estimation of bladder pressure and volume from neural activity recorded directly from spinal cord gray matter neurons. The model was based on the Long Short-Term Memory (LSTM) architecture, which has emerged as a general and effective model for capturing long-term temporal dependencies with good generalization performance. In this way, training the network with the data recorded from one rat could lead to estimating the bladder status of different rats. We combined modeling of spiking and local field potential (LFP) activity into a unified framework to estimate the pressure and volume of the bladder. Moreover, we investigated the effect of two-electrode recording on decoding performance. The results show that the two-electrode recordings significantly improve the decoding performance compared to single-electrode recordings. The proposed framework could estimate bladder pressure and volume with an average normalized root-mean-squared (NRMS) error of 14.9 ± 4.8% and 19.7 ± 4.7% and a correlation coefficient (CC) of 83.2 ± 3.2% and 74.2 ± 6.2%, respectively. This work represents a promising approach to the real-time estimation of bladder pressure/volume in the closed-loop control of bladder function using functional electrical stimulation.

Decoding hindlimb kinematics from descending and ascending neural signals during cat locomotion

“…The central branch of the sensory axon enters the dorsal horn of the spinal cord [31]. The dorsal horn recordings in rats have been already used for detecting the sensory events generated by electrical stimulation [32] or to decode the bladder pressure [33,34]. In a previous work, we introduced decoding the hindlimb kinematics using neural recordings from the dorsal horn cells during passive hindlimb movements of anesthetized cats [35,36].…”

A general framework for automatic closed-loop control of bladder voiding induced by intraspinal microstimulation in rats

“…To cope with the limitation of the implantable artificial bladder sensors, several methods have been proposed to estimate either the IVP or volume using electroneurography of the pudendal nerve [43][44][45] , electroneurography of the pelvic nerve 46 and sacral nerve roots 46,47 , and neural activity recorded from the dorsal horn of the spinal cord 48,49 . In previous work 49 , we developed a method based on deep neural network for simultaneous estimating both pressure and volume from the neural activity recorded directly from the spinal cord gray matter neurons. Figure 12.…”

Low Frequency Tibial Neuromodulation Increases Voiding Activity - A Computational Model

“…The sample rate of the vector was 50Hz, with each step ( t ) representing a 20ms increment. The bladder data used to do so was obtained from previously published work 16 (see Animal Model Surgery and Preparation). Given the nature of the model organ, the simulation of urine-flow sensitive urethral afferents was not required.…”

“…To run the simulated model, we utilised real bladder pressure and neural data from a previously published work 16 . During the constant infusion of the bladder, simultaneous recording of neural signals from the spinal cord was conducted.…”

“…15 (methods). To ensure that the model accurately captured the system level effects of real bladder activity, the parameters and synaptic weights of the simulation were fitted using previously generated experimental rodent data 16 , as shown in fig. 1A-B.…”