A Hierarchical K-Nearest Neighbor Approach for Volume of Tissue Activated Estimation

Pava, Iván De La; Mejia, Jenniffer Bustamante; Álvarez-Meza, Andrés Marino; Álvarez, Mauricio A.; Orozco, Álvaro A.; Henao, Oscar

doi:10.1007/978-3-319-52277-7_16

Cited by 2 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 10 shows the final reconstruction error for the isotropic and anisotropic cases, respectively. The error distributions, involving information of both monopolar and bipolar configurations, are in ranges of values similar to those reported in the literature for machine learning based VTA estimation strategies that solve only the traditional VTA estimation problem [33,34]. Also, in congruence with SVM performance a slight downward trend is observed in the median error as the impedance value increases, and higher errors appear when the conductivity of the tissue is assumed to be anisotropic (with respect to the isotropic condition) due to the greater complexity in the form of these activation volumes; however, these errors stayed below those obtained with common techniques for the solution of the direct problem, such as the use of activation functions [33].…”

Section: Testing the Proposed Machine Learning Approachsupporting

confidence: 71%

“…On the whole, the proposed methodology generates errors with respect to the gold standard (once the VTA is re-calculated from the estimated parameters) in ranges comparable to those reported in the literature for other machine learning strategies that seek to solve only the traditional or direct problem of VTA estimation [33,34].…”

Section: Discussionmentioning

confidence: 66%

“…The parameters of these algorithms were selected through nested cross-validation. Then, the returned DBS parameters were used to estimate new VTAs, through the methodology described in [34]. Lastly, the new VTAs were directly compared with the corresponding reference VTAs in the datasets through the error metric (Equation 12) introduced in [33]:…”

Section: Experiments and Validation Schemementioning

confidence: 99%

“…In order to evaluate the proposed methodology in terms of its ability to generate a set of parameters that result in a VTA close to the target one, the error between the VTAs computed from the estimated parameters and the reference VTAs was obtained through equation (12). The estimation of the VTAs from the parameters was made using a hierarchical K-nearest neighbor (HKNN) approach that consists of a data-driven approximation of an expected squared error functional to obtain a local weighted VTA averaging [34]. Figure 10 shows the final reconstruction error for the isotropic and anisotropic cases, respectively.…”

Section: Testing the Proposed Machine Learning Approachmentioning

confidence: 99%

“…After training the system with DBS parameters as inputs and elliptic profiles representing the VTA as outputs, it achieved a lower computational time than that of standard models [16]. Likewise, our group developed a hierarchical K-nearest neighbor-based approach that accomplishes the same goal without simplifying the shape of the VTA [34]. Nonetheless, in spite of the considerable benefits offered by the previously described VTA computation and visualization systems, they still depend on a heuristic search (trial and error) of the stimulation parameters necessary to generate a target (desired) VTA.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A machine learning approach to support deep brain stimulation programming

Gómez-Orozco

Panche

Álvarez-Meza

et al. 2019

redin

View full text Add to dashboard Cite

Adjusting the stimulation parameters is a challenge in deep brain stimulation (DBS) therapy due to the vast number of different configurations available. As a result, systems based on the visualization of the volume of tissue activated (VTA) produced by a particular stimulation setting have been developed. However, the medical specialist still has to search, by trial and error, for a DBS set-up that generates the desired VTA. Therefore, our goal is developing a DBS parameter tuning strategy for current clinical devices that allows defining a target VTA under biophysically viable constraints. We propose a machine learning approach that allows estimating the DBS parameter values for a given VTA, which comprises two main stages: i) A K-nearest neighbors-based deformation to define a target VTA preserving biophysically viable constraints. ii) A parameter estimation stage that consists of a data projection using metric learning to highlight relevant VTA properties, and a regression/classification algorithm to estimate the DBS parameters that generate the target VTA. Our methodology allows setting a biophysically compliant target VTA and accurately predicts the required configuration of stimulation parameters. Also, the performance of our approach is stable for both isotropic and anisotropic tissue conductivities. Furthermore, the computational cost of the trained system is acceptable for real-world implementations.

show abstract

Section: Testing the Proposed Machine Learning Approachsupporting

confidence: 71%

Section: Discussionmentioning

confidence: 66%

Section: Experiments and Validation Schemementioning

confidence: 99%

Section: Testing the Proposed Machine Learning Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A machine learning approach to support deep brain stimulation programming

Gómez-Orozco

Panche

Álvarez-Meza

et al. 2019

redin

View full text Add to dashboard Cite

show abstract

Machine Learning’s Application in Deep Brain Stimulation for Parkinson’s Disease: A Review

et al. 2020

View full text Add to dashboard Cite

Deep brain stimulation (DBS) is a surgical treatment for advanced Parkinson’s disease (PD) that has undergone technological evolution that parallels an expansion in clinical phenotyping, neurophysiology, and neuroimaging of the disease state. Machine learning (ML) has been successfully used in a wide range of healthcare problems, including DBS. As computational power increases and more data become available, the application of ML in DBS is expected to grow. We review the literature of ML in DBS and discuss future opportunities for such applications. Specifically, we perform a comprehensive review of the literature from PubMed, the Institute for Scientific Information’s Web of Science, Cochrane Database of Systematic Reviews, and Institute of Electrical and Electronics Engineers’ (IEEE) Xplore Digital Library for ML applications in DBS. These studies are broadly placed in the following categories: (1) DBS candidate selection; (2) programming optimization; (3) surgical targeting; and (4) insights into DBS mechanisms. For each category, we provide and contextualize the current body of research and discuss potential future directions for the application of ML in DBS.

show abstract

A Hierarchical K-Nearest Neighbor Approach for Volume of Tissue Activated Estimation

Cited by 2 publications

References 9 publications

A machine learning approach to support deep brain stimulation programming

A machine learning approach to support deep brain stimulation programming

Machine Learning’s Application in Deep Brain Stimulation for Parkinson’s Disease: A Review

Contact Info

Product

Resources

About