Multivariate generalized Gaussian function mixture for volume modeling of parathyroid glands

Listewnik, Maria H.; Piwowarska-Bilska, Hanna; Safranow, Krzysztof; Iwanowski, Jacek; Chosia, Maria; Ostrowski, Marek; Birkenfeld, Bożena; Mazurek, P.

doi:10.1109/mmar.2017.8046974

Cited by 1 publication

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach, proposed in [31], assumes modeling of parathyroid glands using multivariate generalized Gaussian function mixture. Standard Gaussian function is not feasible for the modeling because shape control is not available.…”

Section: Related Workmentioning

confidence: 99%

“…Standard Gaussian function is not feasible for the modeling because shape control is not available. Generalized Gaussian function (GGD-Generalized Gaussian Distribution with sharpness control parameter, known also as a version 1 [35]-there is also version 2 with skew control parameter) and an optimization process using random walk were tested [31].…”

Section: Related Workmentioning

confidence: 99%

“…It could lead to human operator induced error, therefore automated volume analysis is very important for achieving reliability. Synthetic volumes that are generated from the model are used in this work for the evaluation of the estimation algorithm and allow testing and validation of estimated properties for different algorithms [31]. The assumed volume is 32 × 32 × 32 voxels (cells) in size and was selected based on observation of real SPECT volumes.…”

Section: Datamentioning

confidence: 99%

“…This method was chosen because of previous experiments related to true volumes of parathyroid glands [31]. It was found that the estimation of 3D position, amplitude, orientation, and scale is not sufficient.…”

Section: Model For Analysis By Synthesis Using Gaussian Mixture Modelmentioning

confidence: 99%

“…In this paper, SPECT patient data was deliberately not used, because the quality of estimation cannot be calculated this way. An alternative approach that was proposed in [31], which is based on a comparison of synthetic volume, and achieved from an estimation algorithm (synthesized) is the only possible method for the proper evaluation of the optimization algorithm. Such an approach with the use of Monte Carlo sampling allows the determination of estimation quality parameters.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Estimation of Parameters of Parathyroid Glands Using Particle Swarm Optimization and Multivariate Generalized Gaussian Function Mixture

et al. 2019

Self Cite

View full text Add to dashboard Cite

Featured Application: The analyzed technique allows the estimation of parameters of small objects from SPECT volumes. Data analysis was based on Particle Swarm Optimization that reduces error between assumed model and measurements. Analysis by Synthesis was used for the estimation of parameters. Abstract: The paper introduces a fitting method for Single-Photon Emission Computed Tomography (SPECT) images of parathyroid glands using generalized Gaussian function for quantitative assessment of preoperative parathyroid SPECT/CT scintigraphy results in a large patient cohort. Parathyroid glands are very small for SPECT acquisition and the overlapping of 3D distributions was observed. The application of multivariate generalized Gaussian function mixture allows modeling, but results depend on the optimization algorithm. Particle Swarm Optimization (PSO) with global best, ring, and random neighborhood topologies were compared. The obtained results show benefits of random neighborhood topology that gives a smaller error for 3D position and the position estimation was improved by about 3% voxel size, but the most important is the reduction of processing time to a few minutes, compared to a few hours in relation to the random walk algorithm. Moreover, the frequency of obtaining low MSE values was more than two times higher for this topology. The presented method based on random neighborhood topology allows quantifying activity in a specific voxel in a short time and could be applied it in clinical practice.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Datamentioning

confidence: 99%

Section: Model For Analysis By Synthesis Using Gaussian Mixture Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations