A novel deep recurrent convolutional neural network for subthalamic nucleus localization using local field potential signals

• Autorzy: Hosny Mohamed , Zhu Minwei , Su Yixian , Gao Wenpeng , Fu Yili

Identyfikatory

DOI

10.1016/j.bbe.2021.09.005

• Języki publikacji: EN

Abstrakty

EN

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is a well-established interventional treatment for improving motor symptoms of patients suffering from Parkinson’s disease (PD). While STN is originally localized using imaging modalities, additional intraoperative guidance such as microelectrode recording (MER) is crucial to refine the final electrode trajectory. Analysis of MER by an experienced neurophysiologist maintains good clinical outcomes, although the procedure requires long duration and jeopardizes the safety of the surgery. Lately, local field potentials (LFP) investigation has inspired the emergence of adaptive DBS and revealed beneficial perception of PD mechanisms. Several studies confronting LFP analysis to detect the anatomical borders of STN, have focused on handcrafted feature engineering, which does not certainly capture delicate differences in LFP. This study gauges the ability of deep learning to exhibit valuable insight into the electrophysiological neural rhythms of STN using LFP. A recurrent convolutional neural network (CNN) strategy is presented, where local features are extracted from LFP signals via CNN, followed by recurrent layers to aggregate the best features for classification. The proposed model outperformed the state-of-the-art techniques, yielding highest average accuracy of 96.79%. This is the first study on the analysis of LFP signals to localize STN using deep recurrent CNN. The developed model has the potential to extract high level biomarkers regarding STN region, which would boost the neurosurgeon’s confidence in adjusting the trajectory intraoperatively for optimal lead implantation. LFP is a robust guidance tool and could be an alternative solution to the current scenario using MER.

Słowa kluczowe

EN

recurrent convolutional neural network; deep learning; subthalamic nucleus detection; Parkinson’s disease; deep brain stimulation; local field potential

PL

sieć neuronowa konwolucyjna; uczenie głębokie; choroba Parkinsona; stymulacja mózgu; potencjał pola lokalnego

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 4
• Strony: 1561--1574
• Opis fizyczny: Bibliogr. 46 poz., rys., tab., wykr.

Twórcy

autor

Hosny Mohamed

• School of Life Science and Technology, Harbin Institute of Technology, Nangang District, Harbin, China; Department of Electrical Engineering, Benha Faculty of Engineering, Benha University, Benha, Egypt

autor

Zhu Minwei

• Department of Neurosurgery, First Affiliated Hospital of Harbin Medical University, Nangang District, Harbin, China

autor

Su Yixian

• School of Life Science and Technology, Harbin Institute of Technology, Nangang District, Harbin, China

autor

Gao Wenpeng

• School of Life Science and Technology, Harbin Institute of Technology, Nangang District, Harbin, China

autor

Fu Yili

• School of Life Science and Technology, Harbin Institute of Technology, Nangang District, Harbin, China

Bibliografia

• [1] Xiao Y, Lau JC, Hemachandra D, Gilmore G, Khan AR, Peters TM. Image Guidance in Deep Brain Stimulation Surgery to Treat Parkinson’s Disease: A Comprehensive Review. IEEE Trans Biomed Eng 2021;68(3):1024–33.
• [2] Martin T, Peralta M, Gilmore G, Sauleau P, Haegelen C, Jannin P, et al. Extending convolutional neural networks for localizing the subthalamic nucleus from micro-electrode recordings in Parkinson’s disease. Biomed Signal Process Control September 2020;2021(67) 102529.
• [3] Valsky D, Blackwell KT, Tamir I, Eitan R, Bergman H, Israel Z. Real-time machine learning classification of pallidal borders during deep brain stimulation surgery. J Neural Eng 2020;17(1).
• [4] Zhang Y, Xu S, Xiao G, Song Y, Gao F, Wang M, et al. High frequency stimulation of subthalamic nucleus synchronously modulates primary motor cortex and caudate putamen based on dopamine concentration and electrophysiology activities using microelectrode arrays in Parkinson’s disease rats. Sensors Actuators B: Chem 2019;301(June) 127126.
• [5] Velisar A, Syrkin-Nikolau J, Blumenfeld Z, Trager M, Afzal M, Prabhakar V, et al. Dual threshold neural closed loop deep brain stimulation in Parkinson disease patients. Brain Stimul 2019;12(4):868–76.
• [6] Alper MA, Goudreau J, Daniel M. Pose and optical flow fusion (poff) for accurate tremor detection and quantification. Biocybernetics Biomed Eng 2020;40(1):468–81.
• [7] Chen KHS, Chen R. Invasive and Noninvasive Brain Stimulation in Parkinson’s Disease: Clinical Effects and Future Perspectives. Clin Pharmacol Ther 2019;106(4):763–75.
• [8] Boller JK, Barbe MT, Pauls KAM, Reck C, Brand M, Maier F, et al. Decision-making under risk is improved by both dopaminergic medication and subthalamic stimulation in Parkinson’s disease. Exp Neurol 2014;254:70–7.
• [9] Barbe MT, Tonder L, Krack P, Debû B, Schüpbach M, Paschen S, et al. Deep Brain Stimulation for Freezing of Gait in Parkinson’s Disease With Early Motor Complications. Movement Disorders 2020;35(1):82–90.
• [10] Khawaldeh S, Tinkhauser G, Shah SA, Peterman K, Debove I, Nguyen TAK, et al. Subthalamic nucleus activity dynamics and limb movement prediction in Parkinson’s disease. Brain: J Neurol 2020;143(2):582–96.
• [11] Mao Z, Ling Z, Pan L, Xu X, Cui Z, Liang S, et al. Comparison of Efficacy of Deep Brain Stimulation of Different Targets in Parkinson’s Disease: A Network Meta-Analysis. Frontiers in Aging Neuroscience 2019;11(FEB):1–8.
• [12] Rui K, Maszczyk T, An A, See Q, Dauwels J, Kon N, et al. A review on microelectrode recording selection of features for machine learning in deep brain stimulation surgery for Parkinson ’ s disease. Clin Neurophysiol 2019;130(1):145–54.
• [13] Farrokhi F, Buchlak QD, Sikora M, Esmaili N, Marsans M, McLeod P, et al. Investigating Risk Factors and Predicting Complications in Deep Brain Stimulation Surgery with Machine Learning Algorithms. World Neurosurgery 2020;134:468–81.
• [14] Rolston JD, Englot DJ, Starr PA, Larson PS. An unexpectedly high rate of revisions and removals in deep brain stimulation surgery: analysis of multiple databases. Parkinsonism Related Disorders 2016;33:72–7.
• [15] Peralta M, Bui QA, Ackaouy A, Martin T, Gilmore G, Haegelen C, et al. SepaConvNet for Localizing the Subthalamic Nucleus Using One Second Micro-electrode Recordings. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2020;2020-July:888–893.
• [16] Lozano CS, Ranjan M, Boutet A, Xu DS, KucharczykW, Fasano A, et al. Imaging alone versus microelectrode recording-guided targeting of the STN in patients with Parkinson’s disease. J Neurosurg 2019;1306(6):1847–52.
• [17] Mehanna R, Machado AG, Connett JE, Alsaloum F, Cooper SE. Intraoperative Microstimulation Predicts Outcome of Postoperative Macrostimulation in Subthalamic Nucleus Deep Brain Stimulation for Parkinson’s Disease. Neuromodulation 2017;20(5):456–63.
• [18] Hartmann CJ, Fliegen S, Groiss SJ,Wojtecki L, Schnitzler A. An update on best practice of deep brain stimulation in parkinson’s disease. Therapeutic Adv Neurol Disorders 2019;12:1–20.
• [19] Liu X, Zhang J, Fu K, Gong R, Chen J, Zhang J. Microelectrode Recording-Guided Versus Intraoperative Magnetic Resonance Imaging-Guided Subthalamic Nucleus Deep Brain Stimulation Surgery for Parkinson Disease: A 1-Year Follow-Up Study. World Neurosurgery 2017;107:900–5.
• [20] Lee PS, Weiner GM, Corson D, Kappel J, Chang YF, Suski VR, et al. Outcomes of interventional-MRI versus microelectrode recording-guided subthalamic deep brain stimulation. Frontiers in Neurology 2018;9(APR):1–8.
• [21] Hosny M, Zhu M, GaoW, Fu Y. A novel deep LSTM network for artifacts detection in microelectrode recordings. Biocybern Biomed Eng 2020;40(3):1052–63.
• [22] Telkes I, Ince NF, Onaran I, Abosch A. Localization of subthalamic nucleus borders using macroelectrode local field potential recordings. In: 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC. p. 2621–4.
• [23] Telkes I, Ince NF, Onaran I, Abosch A. Spatio-spectral characterization of local field potentials in the subthalamic nucleus via multitrack microelectrode recordings. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2015:5561–5564.
• [24] Karthick PA, Wan KR, An Qi AS, Dauwels J, King NKK. Automated detection of subthalamic nucleus in deep brain stimulation surgery for parkinson’s disease using microelectrode recordings and wavelet packet features. J Neurosci Methods 2020;343:108826.
• [25] Valsky D, Marmor-Levin O, Deffains M, Eitan R, Blackwell KT, Bergman H, et al. Stop! border ahead: Automatic detection of subthalamic exit during deep brain stimulation surgery. Mov Disord 2017;32(1):70–9.
• [26] Telkes I, Sabourin S, Durphy J, Adam O, Sukul V, Raviv N, et al. Functional Use of Directional Local Field Potentials in the Subthalamic Nucleus Deep Brain Stimulation. Front Human Neurosci 2020;14(April):1–9.
• [27] Telkes I, Viswanathan A, Jimenez-Shahed J, Abosch A, Ozturk M, Gupte A, et al. Local field potentials of subthalamic nucleus contain electrophysiological footprints of motor subtypes of Parkinson’s disease. Proc National Acad Sci USA 2018;115(36):E8567–76.
• [28] Cao L, Jie L, Zhou Y, Liu Y, Liu H. Automatic feature group combination selection method based on GA for the functional regions clustering in DBS. Comput Methods Programs Biomed 2020;183.
• [29] Ozturk M, Telkes I, Jimenez-Shahed J, Viswanathan A, Tarakad A, Kumar S, et al. Randomized, Double-Blind Assessment of LFP Versus SUA Guidance in STN-DBS Lead Implantation: A Pilot Study. Front Neurosci 2020;14(June):1–12.
• [30] Khosravi M, Atashzar SF, Gilmore G, Jog MS, Patel RV. Intraoperative Localization of STN during DBS Surgery using a Data-driven Model. IEEE J Transl Eng Health Med 2020;8:1–9.
• [31] Hosny M, Zhu M, Gao W, Fu Y. Detection of subthalamic nucleus using novel higher-order spectra features in microelectrode recordings signals. Biocybern Biomed Eng 2021;41(2):704–16.
• [32] Telkes I, Jimenez-Shahed J, Viswanathan A, Abosch A, Ince NF. Prediction of STN-DBS electrode implantation track in Parkinson’s disease by using local field potentials. Front Neurosci 2016;10(MAY):1–16.
• [33] Cao L, Li J, Zhou Y, Liu Y, Zhao Y, Liu H. Online identification of functional regions in deep brain stimulation based on an unsupervised random forest with feature selection. J Neural Eng 2019;16(6).
• [34] Cagnan H, Dolan K, He X, Contarino MF, Schuurman R, Van Den Munckhof P, et al. Automatic subthalamic nucleus detection from microelectrode recordings based on noise level and neuronal activity. Journal of Neural Engineering 2011;8(4):046006 (9 pages).
• [35] Kostoglou K, Michmizos KP, Stathis P, Sakas D, Nikita KS, Mitsis GD. Classification and Prediction of Clinical Improvement in Deep Brain Stimulation from Intraoperative Microelectrode Recordings. IEEE Trans Biomed Eng 2017;64(5):1123–30.
• [36] Pinzon-Morales RD, Garces-Arboleda M, Orozco-Gutierrez AA. Automatic identification of various nuclei in the basal ganglia for Parkinson’s disease neurosurgery. Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 2009:3473–3476.
• [37] Hammad M, Iliyasu AM, Subasi A, Ho ESL, El-Latif AAA. A Multitier Deep Learning Model for Arrhythmia Detection. IEEE Trans Instrum Meas 2021;70:1–9.
• [38] Shamir RR, Duchin Y, Kim J, Patriat R, Marmor O, Bergman H, et al. Microelectrode Recordings Validate the Clinical Visualization of Subthalamic-Nucleus Based on 7T Magnetic Resonance Imaging and Machine Learning for Deep Brain Stimulation Surgery. Clin Neurosurg 2019;84(3):749–56.
• [39] Schlaier JR, Habermeyer C, Janzen A, Fellner C, Hochreiter A, Proescholdt M, et al. The influence of intraoperative microelectrode recordings and clinical testing on the location of final stimulation sites in deep brain stimulation for Parkinson’s disease. Acta Neurochir 2013;155(2):357–66.
• [40] Kocabicak E, Alptekin O, Aygun D, Yildiz O, Temel Y. Microelectrode recording for deep brain stimulation on the subthalamic nucleus in patients with advanced parkinson’s diesease: advantage or loss of time. Turk Neurosurg 2019;29(5):677–82.
• [41] Thompson JA, Lanctin D, Ince NF, Abosch A. Clinical implications of local field potentials for understanding and treating movement disorders. Stereotact Funct Neurosurg 2014;92(4):251–63.
• [42] Priori A, Foffani G, Rossi L, Marceglia S. Adaptive deep brain stimulation (aDBS) controlled by local field potential oscillations. Exp Neurol 2013;245:77–86.
• [43] Feldmann LK, Neumann Wj, Faust K, Schneider GH, Kühn AA. Risk of Infection after Deep Brain Stimulation Surgery with Externalization and Local-Field Potential Recordings: Twelve-Year Experience from a Single Institution. Stereotactic and Functional Neurosurgery 2021;:1–9.
• [44] Rajpurohit V, Danish SF, Hargreaves EL, Wong S. Optimizing computational feature sets for subthalamic nucleus localization in DBS surgery with feature selection. Clin Neurophysiol 2015;126(5):975–82.
• [45] Schiaffino L, Rosado Munoz A, Guerrero Martinez J, Francés Villora J, Gutiérrez A, Martinez Torres I, et al. STN area detection using K-NN classifiers for MER recordings in Parkinson patients during neurostimulator implant surgery. J Phys: Conf Ser 2016;705(1):441–4.
• [46] Vargas Cardona HD, Álvarez MA, Orozco Á A. Multi-task learning for subthalamic nucleus identification in deep brain stimulation. Int J Mach Learn Cybern 2018;9(7):1181–92.