Konrad Ciecierski

Foundations of automatic system for intrasurgical localization of subthalamic nucleus in Parkinson patients

During deep brain stimulation DBS treatment of Parkinson disease, the target of the surgery is the subthalamic nucleus STN. This anatomical structure is small 9×7×4 mm and poorly visible using Computer Tomography CT or Magnetic Resonance Imaging MRI scans.Because of that, a multi-electrode micro recording system is used intra surgically for better localization of the target nucleus. This paper presents five different analytical methods, that can be used to construct an autonomic system which can aid neurosurgeons in precise localization of the

Foundations of recommender system for STN localization during DBS surgery in parkinson's patients

Subthalamic\;Nucleus

Discrimination of the Micro Electrode Recordings for STN Localization during DBS Surgery in Parkinson's Patients

STN. Such system could be used during surgery in the environment of the operation theater. Described methods take as input signals recorded from the micro electrodes. Their result in turn allows one to tell which from the recorded signals comes from the STN. First method bases on the recorded action potentials, i.e. on electrical activity of neurons that are near electrodes recording tip. Second utilizes root mean square of recorded signals. Third takes into account amplitude of the background noise present in the recorded signal. The last two methods examine Low Frequency Background LFB and High Frequency Background HFB.

Selection of the optimal microelectrode during DBS surgery in Parkinson's patients

During deep brain stimulation (DBS) treatment of Parkinson disease, the target of the surgery is the subthalamic nucleus (STN). As STN is small (9 x 7 x 4 mm) and poorly visible in CT or MRI, multi-electrode micro recording systems are used during DBS surgery for its better localization. This paper presents five different analytical methods, that can be used to construct an autonomic system assisting neurosurgeons in precise localization of the STN nucleus. Such system could be used during surgery in the environment of the operation theater. Signals recorded from the micro electrodes are taken as input in all five described methods. Their result in turn allows to tell which one from the recorded signals comes from the STN. First method utilizes root mean square of recorded signals. Second takes into account amplitude of the background noise present in the recorded signal. 3rd and 4th methods examine Low Frequency Background (LFB) and High Frequency Background (HFB). Finally, last one looks at correlation between recordings taken by different electrodes.

Intraoperative Decision Making with Rough Set Rules for STN DBS in Parkinson Disease

During deep brain stimulation DBS treatment of Parkinson disease, the target of the surgery is a small 9 x 7 x 4 mm deep within brain placed structure called Subthalamic Nucleus STN. It is similar morphologically to the surrounding tissue and as such poorly visible in CT or MRI. The goal of the surgery is the permanent precise placement of the stimulating electrode within target nucleus. Precision is extremely important as wrong placement of the stimulating electrode may lead to serious mood disturbances. To obtain exact location of the STN nucleus an intraoperative stereotactic supportive navigation is being used. A set of 3 to 5 parallel micro electrodes is inserted into brain and in measured steps advanced towards expected location of the nucleus. At each step electrodes record activity of the surrounding neural tissue. Because STN has a distinct physiology, the signals recorded within it also display specific features. It is therefore possible to provide analytical methods targeted for detection of those STN specific characteristics. Basing on such methods this paper presents clustering and classification approaches for discrimination of the micro electrode recordings coming from the STN nucleus. Application of those methods during the neurosurgical procedure might lessen the risks of medical complications and might also shorten the --- out of necessity awake --- part of the surgery.

Applications of decision support systems in functional neurosurgery

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) is effective treatment of Parkinson disease. Because the STN is small (9×7×4mm) and it is not well visible using conventional imaging techniques, multi-microelectrode recordings are used to ensure accurate detection of the STN borders. Commonly used discriminations which microelectrodes signal relates to the activity of the STN are signal quality and neurologists experience dependent. The purpose of this paper is to determine the STN coordinates in a more objective way. We present analysis of the neurological signals acquired during DBS surgeries. The purpose of our method is to discover which one of the scanning microelectrodes reaches the target area guaranteeing a most successful surgery. Signals acquired from microelectrodes are first filtered. Subsequently the spikes are detected and classified. After that, new signal is reconstructed from spikes. This signals power is then calculated by means of FFT. Finally cumulative sum of the signals power is used to choose a proper electrode. The ultimate goal of our research is to build a decision support system for the DBS surgery. A successful strategy showing which of the recording microelectrodes should be replaced by the DBS electrode is probably the most difficult and challenging.

Unsupervised Machine Learning in Classification of Neurobiological Data

In neurosurgical treatment of the Parkinson Disease (PD) the target is a small (9 x 7 x 4 mm) deep within brain placed structure called Subthalamic Nucleus (STN). The goal of the Deep Brain Stimulation (DBS) surgery is the permanent precise placement of the stimulating electrode within target nucleus. As this structure poorly discriminates in CT or MRI it is usually stereotactically located using microelectrode recording. Several microelectrodes are parallelly inserted into the brain and in measured steps they are advanced towards expected location of the nucleus. At each step, from 20 mm above the target, the neuronal activity is recorded. Because STN has a distinct physiology, the signals recorded within it also present specific features. By extracting certain features from recordings provided by the microelectrodes, it is possible to construct a classifier that provides useful discrimination. This discrimination divides the recordings into two classes, i.e. those registered within the STN and those registered outside of it. Using the decision tree based classifiers, the best results have been obtained using the Random Forest method. In this paper we compared the results obtained from the Random Forest to those provided by the classification based upon rules extracted by the rough set approach.

Detection of SNr Recordings Basing upon Spike Shape Classes and Signal’s Background

Functional neurosurgery is used for treatment of conditions in central nervous system that arise from its improper physiology. One of the possible approaches is Deep Brain Stimulation (DBS). In this procedure a stimulating electrode is placed in desired brain’s area to locally affect its activity. Among others, DBS can be used as a treatment for dystonia, depression, obsessive-compulsive disorder (OCD) and Parkinson’s Disease (PD). In this paper authors focus on application of classifiers in Deep Brain Stimulation (DBS) for Parkinson’s Disease (PD). In neurosurgical treatment of the Parkinson’s Disease the target is a small (9 x 7 x 4 mm) deeply in brain situated structure called Subthalamic Nucleus (STN). The goal of the Deep Brain Stimulation is the precise permanent placement of the stimulating electrode within target nucleus. As this structure poorly visible in CT or MRI it is usually stereotactically located using microelectrode recording. Several microelectrodes are parallelly inserted into the brain and then in measured steps advanced towards expected location of the nucleus. At each step, usually from 10 mm above expected center of the STN, the neuronal activity is recorded. Because STN has a distinct physiology, the signals recorded within it also present specific features. By extraction certain attributes from recordings provided by the microelectrodes, it is possible to construct a binary classifier that provides useful discrimination. This discrimination divides the recordings into two classes, i.e. those registered within the STN and those registered outside of it. From this it is known which microelectrodes and at which depths have passed through the STN and thus a physiological map of its surrounding is made.

Frequency Based Mapping of the STN Borders

In many cases of neurophysiological data analysis, the best results can be obtained using supervised machine learning approaches. Such very good results were obtained in detection of neurophysiological recordings recorded within Subthalamic Nucleus (\({ STN}\)) during deep brain stimulation (DBS) surgery for Parkinson disease. Supervised machine learning methods relay however on external knowledge provided by an expert. This becomes increasingly difficult if the subject’s domain is highly specialized as is the case in neurosurgery. The proper computation of features that are to be used for classification without good domain knowledge can be difficult and their proper construction heavily influences quality of the final classification. In such case one might wonder whether, how much and to what extent the unsupervised methods might become useful. Good result of unsupervised approach would indicate presence of a natural grouping within recordings and would also be a further confirmation that features selected for classification and clustering provide good basis for discrimination of recordings recorded within Subthalamic Nucleus (\({ STN}\)). For this test, the set of over 12 thousand of brain neurophysiological recordings with precalculated attributes were used. This paper shows comparison of results obtained from supervised - random forest based - method with those obtained from unsupervised approaches, namely K-Means and Hierarchical clustering approaches. It is also shown, how inclusion of certain types of attributes influences the clustering based results.

Spike Sorting Based upon PCA over DWT Frequency Band Selection

During deep brain stimulation (DBS) surgery for Parkinson disease, the target is the subthalamic nucleus (STN). STN is small, (\(9\times 7\times 4\) mm) and typically localized by a series of parallel microelectrodes. As those electrodes are in steps advanced towards and through the STN, they record the neurobiological activity of the surrounding tissues. The electrodes are advanced until they pass through the STN and/or they reach the Substantia Nigra pars reticulata (SNr). There is no necessity of going further as the SNr lies ventral to the STN. There are good classification methods for detection weather given recording comes from the STN or not, they still do sometimes falsely identify SNr recordings as STN ones. This paper focuses on method devised for SNr detection, specifically on detection if given recording bears characteristics typical for SNr. Presented method relies on spike sorting and assessing characteristics of the obtained spike shape classes together with the enhanced analysis of the signal’s background computed by the STN classification methods described in [8, 9, 10, 11, 12].