Rohit Bose
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rohit Bose has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
- Lee E. Fisher
Rehab Neural Engineering Labs, University of Pittsburgh
8 shared publications - Ashley N. Dalrymple
University of Utah
7 shared publications - Soumya Chatterjee
National Institute of Technology
7 shared publications - Andrei Dragomir
The N.1 Institute for Health, National University of Singapore 28 Medical Drive, #05-COR 17456 Singapore
6 shared publications - Douglas J. Weber
Carnegie Mellon University
5 shared publications - Nitish Vyomesh Thakor
Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
5 shared publications
Latest Publications
- Open Access
- 4 May 2026
- Published by SAGE Publications in Journal of Rehabilitation and Assistive Technologies Engineering
- Vol. 13
3D printing and prostheses: The current state-of-the-art and future directions
Limb difference affects millions worldwide, with prevalence expected to rise due to increasing rates of diabetes and vascular disease. Despite the need for high-quality, functional prostheses, many individuals, particularly in low- and middle-income countries, lack access to affordable, customized prostheses. 3D printing offers a promising approach to address these gaps by enabling lower-cost, highly personalized prosthetic fabrication. This narrative review examines the current state of 3D printing in prosthetics, with a focus on upper limb prostheses, socket design, and terminal attachments. Although 3D printing has been used to produce functional prostheses, particularly in non-regulated settings, clinical adoption remains limited due to concerns regarding safety, durability, and a lack of high-quality evidence. This review highlights the advantages of 3D printing, including cost-effectiveness, customization, and accessibility, while also addressing key limitations such as material performance, regulatory challenges, and insufficient clinical validation. Future research priorities include rigorous clinical trials and performance testing to establish non-inferiority compared with conventional prostheses and to support broader clinical integration.
- 4 May 2026
- Published by SAGE Publications in Journal of Rehabilitation and Assistive Technologies Engineering
- Vol. 13
Open Access3D printing and prostheses: The current state-of-the-art and future directions
Limb difference affects millions worldwide, with prevalence expected to rise due to increasing rates of diabetes and vascular disease. Despite the need for high-quality, functional prostheses, many individuals, particularly in low- and middle-income countries, lack access to affordable, customized prostheses. 3D printing offers a promising approach to address these gaps by enabling lower-cost, highly personalized prosthetic fabrication. This narrative review examines the current state of 3D printing in prosthetics, with a focus on upper limb prostheses, socket design, and terminal attachments. Although 3D printing has been used to produce functional prostheses, particularly in non-regulated settings, clinical adoption remains limited due to concerns regarding safety, durability, and a lack of high-quality evidence. This review highlights the advantages of 3D printing, including cost-effectiveness, customization, and accessibility, while also addressing key limitations such as material performance, regulatory challenges, and insufficient clinical validation. Future research priorities include rigorous clinical trials and performance testing to establish non-inferiority compared with conventional prostheses and to support broader clinical integration.
- Open Access
- 11 November 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (6) , 066003
Changes in muscle activation and joint motion during walking after transtibial amputation with sensory feedback from spinal cord stimulation: a case study
Objective . The goal of this study was to examine the effects of spinal cord stimulation (SCS) on muscle activity during walking after lower-limb amputation. Amputation results in a loss of sensory feedback and alterations in gait biomechanics, including co-contractions of antagonist muscles about the knee and ankle, and reduced pelvic obliquity range-of-motion and pelvic drop. SCS can restore sensation in the missing limb, but its effects on muscle activation and gait biomechanics have not been studied in people with lower-limb amputation. Approach . This case study included a participant with transtibial amputation who was implanted percutaneously with SCS electrodes over the lumbosacral enlargement for 84 d. SCS was used during in-lab experiments to provide somatosensory feedback from the missing limb, relaying a sense of plantar pressure when the prosthesis was in the stance phase of the gait cycle. We used electromyography (EMG) to record muscle activity from the residual and intact limbs, and 3D motion capture to measure pelvic obliquity and knee and ankle joint angles. EMG signals were recorded during walking with and without SCS at early (Day 30) and late (Day 63) time points across the implant duration. Main results . During walking, co-contraction of knee antagonist muscles was reduced following multiple sessions of SCS-mediated sensory restoration. Additionally, the activation of the hip abductor (tensor fasciae latae) muscle increased activity during gait with SCS-mediated sensory restoration, which corresponded to an increase in pelvic obliquity range-of-motion and pelvic drop, towards normal. Significance . Restoring sensation in the missing limb using SCS altered muscle activity during walking led to improved coordination and pelvic motion in an individual with lower-limb amputation.
- 11 November 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (6) , 066003
Open AccessChanges in muscle activation and joint motion during walking after transtibial amputation with sensory feedback from spinal cord stimulation: a case study
Objective . The goal of this study was to examine the effects of spinal cord stimulation (SCS) on muscle activity during walking after lower-limb amputation. Amputation results in a loss of sensory feedback and alterations in gait biomechanics, including co-contractions of antagonist muscles about the knee and ankle, and reduced pelvic obliquity range-of-motion and pelvic drop. SCS can restore sensation in the missing limb, but its effects on muscle activation and gait biomechanics have not been studied in people with lower-limb amputation. Approach . This case study included a participant with transtibial amputation who was implanted percutaneously with SCS electrodes over the lumbosacral enlargement for 84 d. SCS was used during in-lab experiments to provide somatosensory feedback from the missing limb, relaying a sense of plantar pressure when the prosthesis was in the stance phase of the gait cycle. We used electromyography (EMG) to record muscle activity from the residual and intact limbs, and 3D motion capture to measure pelvic obliquity and knee and ankle joint angles. EMG signals were recorded during walking with and without SCS at early (Day 30) and late (Day 63) time points across the implant duration. Main results . During walking, co-contraction of knee antagonist muscles was reduced following multiple sessions of SCS-mediated sensory restoration. Additionally, the activation of the hip abductor (tensor fasciae latae) muscle increased activity during gait with SCS-mediated sensory restoration, which corresponded to an increase in pelvic obliquity range-of-motion and pelvic drop, towards normal. Significance . Restoring sensation in the missing limb using SCS altered muscle activity during walking led to improved coordination and pelvic motion in an individual with lower-limb amputation.
- Open Access
Perceptual Differences between Cortical and Peripheral Stimulation Strategies for Sensory Restoration
Both intracortical microstimulation (ICMS) and peripheral nerve stimulation (PNS) can restore tactile sensation to people living with physical disabilities, such as spinal cord injury (SCI) or amputation. While both techniques have demonstrated success in evoking meaningful sensations in the upper limb, they have only been investigated in separate studies with different patient populations, and thus their perceptual characteristics have never been systematically compared to determine the relative advantages and limitations of each approach. In this study, we directly compared the perceived sensations evoked by ICMS and PNS to those evoked by mechanical touch in a participant with sensory incomplete spinal cord injury. We observed that ICMS evoked more localized percepts and felt more qualitatively similar to natural touch than PNS, whereas PNS evoked higher intensity and more reliable percepts than ICMS. We also found that, across stimulation approaches, the perceived naturalness ratings of sensations were more strongly related to the other perceptual variables than to stimulation variables, suggesting that naturalness is a higher order perceptual dimension that is cognitively constructed by the participant. Our results indicate that ICMS may be the better sensory stimulation approach for conveying naturalistic touch experiences during haptic exploration, due to its similarity to mechanical touch in perceptual quality. In contrast, PNS may be the better stimulation modality to deliver consistent and effective sensory feedback during closed-loop functional tasks, due to its higher reliability. These insights provide a framework for future development of patient-specific sensory neuroprostheses based on the needs and goals of the user.
Open AccessPerceptual Differences between Cortical and Peripheral Stimulation Strategies for Sensory Restoration
Both intracortical microstimulation (ICMS) and peripheral nerve stimulation (PNS) can restore tactile sensation to people living with physical disabilities, such as spinal cord injury (SCI) or amputation. While both techniques have demonstrated success in evoking meaningful sensations in the upper limb, they have only been investigated in separate studies with different patient populations, and thus their perceptual characteristics have never been systematically compared to determine the relative advantages and limitations of each approach. In this study, we directly compared the perceived sensations evoked by ICMS and PNS to those evoked by mechanical touch in a participant with sensory incomplete spinal cord injury. We observed that ICMS evoked more localized percepts and felt more qualitatively similar to natural touch than PNS, whereas PNS evoked higher intensity and more reliable percepts than ICMS. We also found that, across stimulation approaches, the perceived naturalness ratings of sensations were more strongly related to the other perceptual variables than to stimulation variables, suggesting that naturalness is a higher order perceptual dimension that is cognitively constructed by the participant. Our results indicate that ICMS may be the better sensory stimulation approach for conveying naturalistic touch experiences during haptic exploration, due to its similarity to mechanical touch in perceptual quality. In contrast, PNS may be the better stimulation modality to deliver consistent and effective sensory feedback during closed-loop functional tasks, due to its higher reliability. These insights provide a framework for future development of patient-specific sensory neuroprostheses based on the needs and goals of the user.
- Open Access
Changes in Muscle Activation and Joint Motion During Walking After Transtibial Amputation with Sensory Feedback from Spinal Cord Stimulation: A Case Study
Background: The goal of this study was to examine the effects of spinal cord stimulation (SCS) on muscle activity during walking after lower-limb amputation. Amputation results in a loss of sensory feedback and alterations in gait biomechanics, including co-contractions of antagonist muscles about the knee and ankle, and reduced pelvic obliquity range-of-motion and pelvic drop. SCS can restore sensation in the missing limb, but its effects on muscle activation and gait biomechanics have not been studied in people with lower-limb amputation. Methods: This case study included a participant with transtibial amputation who was implanted percutaneously with SCS electrodes over the lumbosacral enlargement for 84 days. SCS was used during in-lab experiments to provide somatosensory feedback from the missing limb, relaying a sense of plantar pressure when the prosthesis was in the stance phase of the gait cycle. We used electromyography (EMG) to record muscle activity from the residual and intact limbs, and 3D motion capture to measure pelvic obliquity. EMG signals were recorded during walking with and without SCS at early and late time points across the implant duration. Results: During walking, co-contraction of knee antagonist muscles was reduced following multiple sessions of SCS-mediated sensory restoration. Additionally, the activation of the hip abductor (tensor fasciae latae) muscle increased activity during gait with SCS-mediated sensory restoration, which corresponded to an increase in pelvic obliquity range-of-motion and pelvic drop, towards normal. Conclusions: Restoring sensation in the missing limb using SCS modulated muscle activity during walking leading to improved coordination and pelvic motion in an individual with lower-limb amputation.
Open AccessChanges in Muscle Activation and Joint Motion During Walking After Transtibial Amputation with Sensory Feedback from Spinal Cord Stimulation: A Case Study
Background: The goal of this study was to examine the effects of spinal cord stimulation (SCS) on muscle activity during walking after lower-limb amputation. Amputation results in a loss of sensory feedback and alterations in gait biomechanics, including co-contractions of antagonist muscles about the knee and ankle, and reduced pelvic obliquity range-of-motion and pelvic drop. SCS can restore sensation in the missing limb, but its effects on muscle activation and gait biomechanics have not been studied in people with lower-limb amputation. Methods: This case study included a participant with transtibial amputation who was implanted percutaneously with SCS electrodes over the lumbosacral enlargement for 84 days. SCS was used during in-lab experiments to provide somatosensory feedback from the missing limb, relaying a sense of plantar pressure when the prosthesis was in the stance phase of the gait cycle. We used electromyography (EMG) to record muscle activity from the residual and intact limbs, and 3D motion capture to measure pelvic obliquity. EMG signals were recorded during walking with and without SCS at early and late time points across the implant duration. Results: During walking, co-contraction of knee antagonist muscles was reduced following multiple sessions of SCS-mediated sensory restoration. Additionally, the activation of the hip abductor (tensor fasciae latae) muscle increased activity during gait with SCS-mediated sensory restoration, which corresponded to an increase in pelvic obliquity range-of-motion and pelvic drop, towards normal. Conclusions: Restoring sensation in the missing limb using SCS modulated muscle activity during walking leading to improved coordination and pelvic motion in an individual with lower-limb amputation.
- Open Access
- 28 December 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (11) , 1502
Publisher Correction: Restoration of sensory feedback from the foot and reduction of phantom limb pain via closed-loop spinal cord stimulation
- 28 December 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (11) , 1502
Open AccessPublisher Correction: Restoration of sensory feedback from the foot and reduction of phantom limb pain via closed-loop spinal cord stimulation
- 14 December 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (8) , 992-1003
Restoration of sensory feedback from the foot and reduction of phantom limb pain via closed-loop spinal cord stimulation
Restoring somatosensory feedback in individuals with lower-limb amputations would reduce the risk of falls and alleviate phantom limb pain. Here we show, in three individuals with transtibial amputation (one traumatic and two owing to diabetic peripheral neuropathy), that sensations from the missing foot, with control over their location and intensity, can be evoked via lateral lumbosacral spinal cord stimulation with commercially available electrodes and by modulating the intensity of stimulation in real time on the basis of signals from a wireless pressure-sensitive shoe insole. The restored somatosensation via closed-loop stimulation improved balance control (with a 19-point improvement in the composite score of the Sensory Organization Test in one individual) and gait stability (with a 5-point improvement in the Functional Gait Assessment in one individual). And over the implantation period of the stimulation leads, the three individuals experienced a clinically meaningful decrease in phantom limb pain (with an average reduction of nearly 70% on a visual analogue scale). Our findings support the further clinical assessment of lower-limb neuroprostheses providing somatosensory feedback.
- 14 December 2023
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 8 (8) , 992-1003
Restoration of sensory feedback from the foot and reduction of phantom limb pain via closed-loop spinal cord stimulation
Restoring somatosensory feedback in individuals with lower-limb amputations would reduce the risk of falls and alleviate phantom limb pain. Here we show, in three individuals with transtibial amputation (one traumatic and two owing to diabetic peripheral neuropathy), that sensations from the missing foot, with control over their location and intensity, can be evoked via lateral lumbosacral spinal cord stimulation with commercially available electrodes and by modulating the intensity of stimulation in real time on the basis of signals from a wireless pressure-sensitive shoe insole. The restored somatosensation via closed-loop stimulation improved balance control (with a 19-point improvement in the composite score of the Sensory Organization Test in one individual) and gait stability (with a 5-point improvement in the Functional Gait Assessment in one individual). And over the implantation period of the stimulation leads, the three individuals experienced a clinically meaningful decrease in phantom limb pain (with an average reduction of nearly 70% on a visual analogue scale). Our findings support the further clinical assessment of lower-limb neuroprostheses providing somatosensory feedback.
- Open Access
Characterizing spinal reflexes evoked by spinal cord stimulation to restore sensation in people with lower-limb amputation
Background: People with lower-limb amputations lack sensory inputs from their missing limb, which increases their risk of falling. We recently demonstrated that spinal cord stimulation (SCS) can restore sensation in the missing lower limb. Previous studies have shown that SCS can affect motor control by exciting spinal reflex pathways after stroke or spinal cord injury. The effects of SCS on spinal reflex activation have not been studied in people with lower-limb amputation. Furthermore, it is unknown if SCS-evoked spinal reflex activation would perturb walking. Therefore, the goal of this study was to characterize SCS-evoked spinal reflexes in people with lower-limb amputation and quantify effects on gait parameters, including step cycle duration and limb alternation symmetry. Methods: We implanted percutaneous SCS electrodes over the lumbosacral enlargement in 3 people with trans-tibial amputation (2 diabetic neuropathy; 1 traumatic) for 28 or 84 days. SCS was delivered to restore sensation in the missing limb during walking based on signals from a pressure-sensing insole in the shoe under the prosthesis. We used electromyography (EMG) to record posterior root-muscle (PRM) reflexes in the residual limb while participants were seated, standing, or walking. We characterized rate-dependent depression and recruitment properties of the PRM reflexes. We used pressure data from instrumented insoles to measure the step cycle duration and limb alternation symmetry with and without SCS. Results: SCS evoked PRM reflexes in the residual limb muscles in all participants, which was confirmed by the presence of rate-dependent depression at stimulation frequencies ≥2Hz. Overall, there was broad activation of residual limb muscles with SCS that varied with the position of the stimulating electrode relative to the lumbar spinal cord. PRM reflexes were also activated during walking, as confirmed by the presence of rate-dependent depression. However, SCS-evoked PRM reflexes did not disrupt gait, with similar step cycle duration or limb alternation symmetry with and without SCS. Conclusions: Restoring sensation in the missing limb using SCS excites spinal reflexes according to the expected rostral-caudal myotomes but does not disrupt the step cycle duration or limb alternation symmetry in people with trans-tibial amputation.
Open AccessCharacterizing spinal reflexes evoked by spinal cord stimulation to restore sensation in people with lower-limb amputation
Background: People with lower-limb amputations lack sensory inputs from their missing limb, which increases their risk of falling. We recently demonstrated that spinal cord stimulation (SCS) can restore sensation in the missing lower limb. Previous studies have shown that SCS can affect motor control by exciting spinal reflex pathways after stroke or spinal cord injury. The effects of SCS on spinal reflex activation have not been studied in people with lower-limb amputation. Furthermore, it is unknown if SCS-evoked spinal reflex activation would perturb walking. Therefore, the goal of this study was to characterize SCS-evoked spinal reflexes in people with lower-limb amputation and quantify effects on gait parameters, including step cycle duration and limb alternation symmetry. Methods: We implanted percutaneous SCS electrodes over the lumbosacral enlargement in 3 people with trans-tibial amputation (2 diabetic neuropathy; 1 traumatic) for 28 or 84 days. SCS was delivered to restore sensation in the missing limb during walking based on signals from a pressure-sensing insole in the shoe under the prosthesis. We used electromyography (EMG) to record posterior root-muscle (PRM) reflexes in the residual limb while participants were seated, standing, or walking. We characterized rate-dependent depression and recruitment properties of the PRM reflexes. We used pressure data from instrumented insoles to measure the step cycle duration and limb alternation symmetry with and without SCS. Results: SCS evoked PRM reflexes in the residual limb muscles in all participants, which was confirmed by the presence of rate-dependent depression at stimulation frequencies ≥2Hz. Overall, there was broad activation of residual limb muscles with SCS that varied with the position of the stimulating electrode relative to the lumbar spinal cord. PRM reflexes were also activated during walking, as confirmed by the presence of rate-dependent depression. However, SCS-evoked PRM reflexes did not disrupt gait, with similar step cycle duration or limb alternation symmetry with and without SCS. Conclusions: Restoring sensation in the missing limb using SCS excites spinal reflexes according to the expected rostral-caudal myotomes but does not disrupt the step cycle duration or limb alternation symmetry in people with trans-tibial amputation.
- Open Access
- 25 January 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (4) , 1251-1262
Neuromuscular disease detection based on feature extraction from time–frequency images of EMG signals employing robust hyperbolic Stockwell transform
In this paper, a novel technique for detection of healthy (H), myopathy, (M) and amyotrophic lateral sclerosis (ALS) electromyography (EMG) signals is proposed employing robust hyperbolic Stockwell transform (HST). HST is an efficient signal processing technique to analyze any nonstationary signal in joint time–frequency (T–F) plane. However, a major issue with HST is the optimum selection of Gaussian window parameters since the resolution in the T–F plane depends on the shape of the window. Considering the aforesaid fact, in this article, a genetic algorithm (GA) based optimized HST is proposed for improved EMG signal analysis in T–F plane. Several novel features were extracted from HST spectrum and features with high statistical significance were selected for classification using several benchmark classifiers. It was observed that optimized HST resulted in better classification accuracy of EMG signals which indicates its potential for clinical applications.
- 25 January 2022
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 32 (4) , 1251-1262
Open AccessNeuromuscular disease detection based on feature extraction from time–frequency images of EMG signals employing robust hyperbolic Stockwell transform
In this paper, a novel technique for detection of healthy (H), myopathy, (M) and amyotrophic lateral sclerosis (ALS) electromyography (EMG) signals is proposed employing robust hyperbolic Stockwell transform (HST). HST is an efficient signal processing technique to analyze any nonstationary signal in joint time–frequency (T–F) plane. However, a major issue with HST is the optimum selection of Gaussian window parameters since the resolution in the T–F plane depends on the shape of the window. Considering the aforesaid fact, in this article, a genetic algorithm (GA) based optimized HST is proposed for improved EMG signal analysis in T–F plane. Several novel features were extracted from HST spectrum and features with high statistical significance were selected for classification using several benchmark classifiers. It was observed that optimized HST resulted in better classification accuracy of EMG signals which indicates its potential for clinical applications.
- Open Access
- 4 November 2021
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 18 (5) , 056068
Stimulation of the dorsal root ganglion using an Injectrode®
Objective. The goal of this work was to compare afferent fiber recruitment by dorsal root ganglion (DRG) stimulation using an injectable polymer electrode (Injectrode®) and a more traditional cylindrical metal electrode. Approach. We exposed the L6 and L7 DRG in four cats via a partial laminectomy or burr hole. We stimulated the DRG using an Injectrode or a stainless steel (SS) electrode using biphasic pulses at three different pulse widths (80, 150, 300 μs) and pulse amplitudes spanning the range used for clinical DRG stimulation. We recorded antidromic evoked compound action potentials (ECAPs) in the sciatic, tibial, and common peroneal nerves using nerve cuffs. We calculated the conduction velocity of the ECAPs and determined the charge-thresholds and recruitment rates for ECAPs from Aα, Aβ, and Aδ fibers. We also performed electrochemical impedance spectroscopy measurements for both electrode types. Main results. The ECAP thresholds for the Injectrode did not differ from the SS electrode across all primary afferents (Aα, Aβ, Aδ) and pulse widths; charge-thresholds increased with wider pulse widths. Thresholds for generating ECAPs from Aβ fibers were 100.0 ± 32.3 nC using the SS electrode, and 90.9 ± 42.9 nC using the Injectrode. The ECAP thresholds from the Injectrode were consistent over several hours of stimulation. The rate of recruitment was similar between the Injectrodes and SS electrode and decreased with wider pulse widths. Significance. The Injectrode can effectively excite primary afferents when used for DRG stimulation within the range of parameters used for clinical DRG stimulation. The Injectrode can be implanted through minimally invasive techniques while achieving similar neural activation to conventional electrodes, making it an excellent candidate for future DRG stimulation and neuroprosthetic applications.
- 4 November 2021
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 18 (5) , 056068
Open AccessStimulation of the dorsal root ganglion using an Injectrode®
Objective. The goal of this work was to compare afferent fiber recruitment by dorsal root ganglion (DRG) stimulation using an injectable polymer electrode (Injectrode®) and a more traditional cylindrical metal electrode. Approach. We exposed the L6 and L7 DRG in four cats via a partial laminectomy or burr hole. We stimulated the DRG using an Injectrode or a stainless steel (SS) electrode using biphasic pulses at three different pulse widths (80, 150, 300 μs) and pulse amplitudes spanning the range used for clinical DRG stimulation. We recorded antidromic evoked compound action potentials (ECAPs) in the sciatic, tibial, and common peroneal nerves using nerve cuffs. We calculated the conduction velocity of the ECAPs and determined the charge-thresholds and recruitment rates for ECAPs from Aα, Aβ, and Aδ fibers. We also performed electrochemical impedance spectroscopy measurements for both electrode types. Main results. The ECAP thresholds for the Injectrode did not differ from the SS electrode across all primary afferents (Aα, Aβ, Aδ) and pulse widths; charge-thresholds increased with wider pulse widths. Thresholds for generating ECAPs from Aβ fibers were 100.0 ± 32.3 nC using the SS electrode, and 90.9 ± 42.9 nC using the Injectrode. The ECAP thresholds from the Injectrode were consistent over several hours of stimulation. The rate of recruitment was similar between the Injectrodes and SS electrode and decreased with wider pulse widths. Significance. The Injectrode can effectively excite primary afferents when used for DRG stimulation within the range of parameters used for clinical DRG stimulation. The Injectrode can be implanted through minimally invasive techniques while achieving similar neural activation to conventional electrodes, making it an excellent candidate for future DRG stimulation and neuroprosthetic applications.
- 10 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (20) , 23335-23343
Focal Epileptic Area Recognition Employing Cross EEG Rhythm Spectrum Images and Convolutional Neural Network
Accurate detection of focal seizure area through EEG screening is important to remove the affected regions of human brain, prior to surgery. Considering the aforesaid fact, in this paper, we propose a novel approach for automated detection and classification of focal electroencephalography (EEG) signals. In this contribution, we procured the focal and non focal EEG signals recorded from the temporal lobe epileptic patients and decomposed the recorded EEG data into several brain rhythms to obtain their time variation of different neural oscillations. Then, we selected a random EEG signal from each rhythm as a reference and performed cross wavelet transform (XWT) of the rest of the EEG rhythms with their respective chosen reference rhythms to examine their nature of correlation in both time scale and time-frequency frame. Finally, the obtained cross-rhythm spectrum time-frequency image plots were fed to a customized CNN model for the purpose of automated feature extraction and classification of EEG signals. The performance of the proposed CNN model was also compared with two pre-trained benchmark CNN models namely AlexNet and VGGNet16, respectively. We observed that the proposed EEG signal classification framework has delivered 100% accuracy for the delta (δ) rhythm and that too at a significantly reduced training time compared to the existing state-of-the-art CNN models. Interestingly, the detection accuracy was also found to be the highest for a particular EEG rhythm, which can be proven useful in real time analysis for accurate diagnosis of focal epilepsy.
- 10 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (20) , 23335-23343
Focal Epileptic Area Recognition Employing Cross EEG Rhythm Spectrum Images and Convolutional Neural Network
Accurate detection of focal seizure area through EEG screening is important to remove the affected regions of human brain, prior to surgery. Considering the aforesaid fact, in this paper, we propose a novel approach for automated detection and classification of focal electroencephalography (EEG) signals. In this contribution, we procured the focal and non focal EEG signals recorded from the temporal lobe epileptic patients and decomposed the recorded EEG data into several brain rhythms to obtain their time variation of different neural oscillations. Then, we selected a random EEG signal from each rhythm as a reference and performed cross wavelet transform (XWT) of the rest of the EEG rhythms with their respective chosen reference rhythms to examine their nature of correlation in both time scale and time-frequency frame. Finally, the obtained cross-rhythm spectrum time-frequency image plots were fed to a customized CNN model for the purpose of automated feature extraction and classification of EEG signals. The performance of the proposed CNN model was also compared with two pre-trained benchmark CNN models namely AlexNet and VGGNet16, respectively. We observed that the proposed EEG signal classification framework has delivered 100% accuracy for the delta (δ) rhythm and that too at a significantly reduced training time compared to the existing state-of-the-art CNN models. Interestingly, the detection accuracy was also found to be the highest for a particular EEG rhythm, which can be proven useful in real time analysis for accurate diagnosis of focal epilepsy.