A Resource-Optimized VLSI Implementation of a Patient-Specific Seizure Detection Algorithm on a Custom-Made 2.2 cm ^2 Wireless Device for Ambulatory Epilepsy Diagnostics

• Published in: IEEE transactions on biomedical circuits and systems Vol. 13; no. 6; pp. 1175 - 1185
• Main Authors: Zhan, Tianyu, Fatmi, Syyeda Zainab, Guraya, Sam, Kassiri, Hossein
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2019
• Subjects: Algorithms; Biomedical monitoring; Electrodes; Electroencephalography; Electroencephalography - instrumentation; Electroencephalography - methods; Energy-efficient VLSI implementation; Epilepsy; Epilepsy - diagnosis; Humans; machine learning; Monitoring; patient specific; point-of-care diagnostics; Point-of-Care Systems; seizure detection; Seizures - diagnosis; Support Vector Machine; SVM; Very large scale integration; wearable devices; Wearable Electronic Devices; Wireless communication; Wireless Technology; wireless wearable sensors
• ISSN: 1932-4545; 1940-9990; 1940-9990
• DOI: 10.1109/TBCAS.2019.2948301

A patient-specific epilepsy diagnostic solution in the form of a wireless wearable ambulatory device is presented. First, the design, VLSI implementation, and experimental validation of a resource-optimized machine learning algorithm for epilepsy seizure detection are described. Next, the development of a mini-PCB that integrates a low-power wireless data transceiver and a programmable processor for hosting the seizure detection algorithm is discussed. The algorithm uses only EEG signals from the frontal lobe electrodes while yielding a seizure detection sensitivity and specificity competitive to the standard full EEG systems. The experimental validation of the algorithm VLSI implementation proves the possibility of conducting accurate seizure detection using quickly-mountable dry-electrode headsets without the need for uncomfortable/painful through-hair electrodes or adhesive gels. Details of design and optimization of the algorithm, the VLSI implementation, and the mini-PCB development are presented and resource optimization techniques are discussed. The optimized implementation is uploaded on a low-power Microsemi Igloo FPGA, requires 1237 logic elements, consumes 110 μW dynamic power, and yields a minimum detection latency of 10.2 μs. The measurement results from the FPGA implementation on data from 23 patients (198 seizures in total) shows a seizure detection sensitivity and specificity of 92.5% and 80.1%, respectively. Comparison to the state of the art is presented from system integration, the VLSI implementation, and the wireless communication perspectives.