A survey on computer-assisted Parkinson's Disease diagnosis

During the last few decades, substantial scientific and technological efforts have been focused on the development of neuroprostheses. The major emphasis has been on techniques for connecting the human nervous system with a robotic prosthesis via natural-feeling interfaces. The peripheral nerves provide access to highly processed and segregated neural command signals from the brain that can in principle be used to determine user intent and control muscles. If these signals could be used, they might allow near-natural and intuitive control of prosthetic limbs with multiple degrees of freedom. This review summarizes the history of neuroprosthetic interfaces and their ability to record from and stimulate peripheral nerves. We also discuss the types of interfaces available and their applications, the kinds of peripheral nerve signals that are used, and the algorithms used to decode them. Finally, we explore the prospects for future development in this area.

https://iopscience.iop.org/article/10.1088/1741-2552/aab383/pdf

Motor-commands decoding using peripheral nerve signals: a review

Spike sorting is one of the most important data analysis problems in neurophysiology. The precision in all steps of the spike-sorting procedure critically affects the accuracy of all subsequent analyses. After data preprocessing and spike detection have been carried out properly, both feature extraction and spike clustering are the most critical subsequent steps of the spike-sorting procedure. The proposed spike sorting approach comprised a new feature extraction method based on shape, phase, and distribution features of each spike (hereinafter SS-SPDF method), which reveal significant information of the neural events under study. In addition, we applied an efficient clustering algorithm based on K-means and template optimization in phase space (hereinafter K-TOPS) that included two integrative clustering measures (validity and error indices) to verify the cohesion-dispersion among spike events during classification and the misclassification of clustering, respectively. The proposed method/algorithm was tested on both simulated data and real neural recordings. The results obtained for these datasets suggest that our spike sorting approach provides an efficient way for sorting both single-unit spikes and overlapping waveforms. By analyzing raw extracellular recordings collected from the rostral-medial prefrontal cortex (rmPFC) of behaving rabbits during classical eyeblink conditioning, we have demonstrated that the present method/algorithm performs better at classifying spikes and neurons and at assessing their modulating properties than other methods currently used in neurophysiology.

/pdf/spike-sorting-based-on-shape-phase-and-distribution-features-2n9w8gsj3o.pdf

Spike sorting based on shape, phase, and distribution features, and K -TOPS clustering with validity and error indices

Next-generation brain machine interfaces demand a high-channel-count neural recording system to wirelessly monitor activities of thousands of neurons A hardware efficient neural signal processor (NSP) is greatly desirable to ease the data bandwidth bottleneck for a fully implantable wireless neural recording system This paper demonstrates a complete multichannel spike sorting NSP module that incorporates all of the necessary spike detector, feature extractor, and spike classifier blocks To meet high-channel-count and implantability demands, each block was designed to be highly hardware efficient and scalable while sharing resources efficiently among multiple channels To process multiple channels in parallel, scalability analysis was performed, and the utilization of each block was optimized according to its input data statistics and the power, area and/or speed of each block Based on this analysis, a prototype 32-channel spike sorting NSP scalable module was designed and tested on an FPGA using synthesized datasets over a wide range of signal to noise ratios The design was mapped to 130 nm CMOS to achieve 075 μW power and 0023 mm2 area consumptions per channel based on post synthesis simulation results, which permits scalability of digital processing to 690 channels on a 4×4 mm2 electrode array

A Hardware-Efficient Scalable Spike Sorting Neural Signal Processor Module for Implantable High-Channel-Count Brain Machine Interfaces

There is a need for integrated spike sorting processors in implantable devices with low power consumption that have improved accuracy. Learning the characteristics of the variable input neural signals and adapting the functionality of the sorting process can improve the accuracy. An adaptive spike sorting processor is presented accounting for the variation in the input signal noise characteristics and the variable difficulty in the selection of the spike characteristics, which significantly improves the accuracy. The adaptive spike processor was fabricated in 180-nm CMOS technology for proof of concept. It performs conditional detection, alignment, adaptive feature extraction, and online clustering with sorting threshold self-tuning capability. The chip was tested under different input signal conditions to demonstrate its adaptation capability providing a median classification accuracy of 84.5% and consuming 148 μW from a 1.8 V supply voltage.

/pdf/an-adaptive-neural-spike-processor-with-embedded-active-2wynz8ctr4.pdf

An Adaptive Neural Spike Processor With Embedded Active Learning for Improved Unsupervised Sorting Accuracy

Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.

Feature Extraction Using Extrema Sampling of Discrete Derivatives for Spike Sorting in Implantable Upper-Limb Neural Prostheses

In Parkinson’s disease (PD), on-demand deep brain stimulation is required so that stimulation is regulated to reduce side effects resulting from continuous stimulation and PD exacerbation due to untimely stimulation. Also, the progressive nature of PD necessitates the use of dynamic detection schemes that can track the nonlinearities in PD. This paper proposes the use of dynamic feature extraction and dynamic pattern classification to achieve dynamic PD detection taking into account the demand for high accuracy, low computation, and real-time detection. The dynamic feature extraction and dynamic pattern classification are selected by evaluating a subset of feature extraction, dimensionality reduction, and classification algorithms that have been used in brain–machine interfaces. A novel dimensionality reduction technique, the maximum ratio method (MRM) is proposed, which provides the most efficient performance. In terms of accuracy and complexity for hardware implementation, a combination having discrete wavelet transform for feature extraction, MRM for dimensionality reduction, and dynamic k-nearest neighbor for classification was chosen as the most efficient. It achieves a classification accuracy of 99.29%, an F1-score of 97.90%, and a choice probability of 99.86%.

/pdf/toward-on-demand-deep-brain-stimulation-using-online-46kvie7ixp.pdf

Toward On-Demand Deep Brain Stimulation Using Online Parkinson’s Disease Prediction Driven by Dynamic Detection

This paper presents an adaptable dictionary-based feature extraction approach for spike sorting offering high accuracy and low computational complexity for implantable applications. It extracts and learns identifiable features from evolving subspaces through matched unsupervised subspace filtering. To provide compatibility with the strict constraints in implantable devices such as the chip area and power budget, the dictionary contains arrays of {–1, 0 and 1} and the algorithm need only process addition and subtraction operations. Three types of such dictionary were considered. To quantify and compare the performance of the resulting three feature extractors with existing systems, a neural signal simulator based on several different libraries was developed. For noise levels σN between 0.05 and 0.3 and groups of 3 to 6 clusters, all three feature extractors provide robust high performance with average classification errors of less than 8% over five iterations, each consisting of 100 generated data segments. To our knowledge, the proposed adaptive feature extractors are the first able to classify reliably 6 clusters for implantable applications. An ASIC implementation of the best performing dictionary-based feature extractor was synthesized in a 65-nm CMOS process. It occupies an area of 0.09 mm2 and dissipates up to about 10.48 μW from a 1 V supply voltage, when operating with 8-bit resolution at 30 kHz operating frequency.

/pdf/accurate-very-low-computational-complexity-spike-sorting-19z19pahng.pdf

Accurate, Very Low Computational Complexity Spike Sorting Using Unsupervised Matched Subspace Learning

Continuous deep brain stimulation for Parkinson's disease (PD) patients results in side effects and shortening of the pacemaker battery life. This can be remedied using adaptive stimulation. To achieve adaptive DBS, patient customized PD detection is required due to the inconsistency associated with biomarkers across patients and time. This paper proposes the use of patient specific feature extraction together with adaptive support vector machine (SVM) classifiers to create a patient customized detector for PD. The patient specific feature extraction is obtained using the extrema of the ratio between the PD and non-PD spectra bands of each patient as features, while the adaptive SVM classifier adjusts its decision boundary until a suitable model is obtained. This yields individualised features and classifier pairs for each patient. Datasets containing local field potentials of PD patients were used to validate the method. Six of the nine patient datasets tested achieved a classification accuracy greater than 98%. The adaptive detector is suitable for realization on chip.

Majid Zamani

Papers

Feature Extraction Using Extrema Sampling of Discrete Derivatives for Spike Sorting in Implantable Upper-Limb Neural Prostheses

An Adaptive Neural Spike Processor With Embedded Active Learning for Improved Unsupervised Sorting Accuracy

Toward On-Demand Deep Brain Stimulation Using Online Parkinson’s Disease Prediction Driven by Dynamic Detection

Accurate, Very Low Computational Complexity Spike Sorting Using Unsupervised Matched Subspace Learning

Patient specific Parkinson's disease detection for adaptive deep brain stimulation