RESUMO
Background: The Periaqueductal gray (PAG) and the periventricular gray (PVG) are the anatomical targets for deep brain stimulation (DBS) to treat severe, refractory neuropathic pain. Methods: Seven (four female and three male) patients were qualified for PAG/PVG DBS because of neuropathic facial pain. Frame-based unilateral implantations of DBS were conducted according to indirect planning of the PAG/PVG, contralateral to reported pain (3389, Activa SC 37603, Medtronic). The efficacy of PAG/PVG DBS on pain was measured with Numeric Pain Rating Scale (NRS) and Neuropathic Pain Symptom Inventory (NPSI) before surgery and 3, 12, and 24 months after surgery. Results: The mean age of the group at the implantation was 43.7 years (range: 28-62; SD: 12.13). The mean duration of pain varied from 2 to 12 years (mean: 7.3; SD: 4.11). Five patients suffered from left-sided facial pain and two suffered right-sided facial pain. The etiology of pain among four patients was connected to ischemic brain stroke and in one patient to cerebral hemorrhagic stroke. Patients did not suffer from any other chronic medical condition The beginnings of ailments among two patients were related to craniofacial injury. NRS decreased by 54% at the 3 months follow-up. The efficacy of the treatment measured with mean NRS decreased at one-year follow-up to 48% and to 45% at 24 months follow-up. The efficacy of the treatment measured with NPSI decreased from 0.27 to 0.17 at 2 years follow-up (mean reduction by 38%). The most significant improvement was recorded in the first section of NPSI (Q1: burning- reduced by 53%). The records of the last section (number five) of the NPSI (paresthesia/dysesthesia- Q11/Q12) have shown aggravation of those symptoms by 10% at the two-years follow-up. No surgery- or hardware-related complications were reported in the group. Transient adverse effects related to the stimulation were eliminated during the programming sessions. Conclusion: PAG/PVG DBS is an effective and safe method of treatment of medically refractory neuropathic facial pain. The effectiveness of the treatment tends to decrease at 2 years follow-up. The clinical symptoms which tend to respond the best is burning pain. Symptoms like paresthesia and dysesthesia might increase after DBS treatment, even without active stimulation.
RESUMO
Data classification is one of the most commonly used applications of machine learning. The are many developed algorithms that can work in various environments and for different data distributions that perform this task with excellence. Classification algorithms, just like other machine learning algorithms have one thing in common: in order to operate on data, they must see the data. In the present world, where concerns about privacy, GDPR (General Data Protection Regulation), business confidentiality and security are growing bigger and bigger; this requirement to work directly on the original data might become, in some situations, a burden. In this paper, an approach to the classification of images that cannot be directly accessed during training has been made. It has been shown that one can train a deep neural network to create such a representation of the original data that i) without additional information, the original data cannot be restored, and ii) that this representation-called a masked form-can still be used for classification purposes. Moreover, it has been shown that classification of the masked data can be done using both classical and neural network-based classifiers.
