Browsing by Author "Costa, D. C."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Assessment of the potential of convolutional neuronal networks in the differential diagnosis of Parkinson’s disease based on brain imaging [123I]FP-CIT SPECTPublication . Valador, N.; Oliveira, F. P.; Ferreira, P. M.; Vieira, Lina Oliveira; Costa, D. C.Aim/Introduction: To evaluate the potential of convolutional neural networks (CNN) in the differential diagnosis of Parkinson’s disease (PD) based on [123I]FP-CIT single-photon emission computed tomography (SPECT) images, compared to other machine learning-based classifiers. Materials and Methods: This work included 806 [123I]FP-CIT SPECT brain images (208 health controls and 598 with PD). Data were obtained from the Parkinson’s Progression Markers Initiative (PPMI) database (www.ppmi-info.org/data). For each subject, only the first scan was considered (baseline or screening). The protocol of image acquisition and pre-processing is available at http://www.ppmi-info.org/study-design/research-documentsand-sops/. CNN was compared against k-nearest neighbor (kNN), logistic regression (LG), decision trees (DT), support vector machines (SVM), and artificial neural networks (ANN) classifiers. The CNN classifier was trained with 2-dimensional image patches (dimensions: 88 mm x 82 mm) containing the striatal region, extracted from the head superior-inferior maximum intensity projection. The remaining classifiers were trained with five features extracted from the 3-dimensional striatal region: caudate binding potential, putamen binding potential, putamen to caudate ratio, the volume of the striatal region with “normal uptake”, and the major axis of that region. The minimum values extracted from each cerebral hemisphere were used. The split ratio of the dataset was 75:25 (75% for training and 25% for testing). Each of the five features was also considered individually to assess its potential for classification in terms of performance (accuracy, sensitivity, and specificity). Results: In the test dataset, the accuracy, sensitivity, and specificity of the CNN were 96%, 98%, and 91%, respectively. This finding was very similar to what we obtained with the other classifiers (kNN: 95%, 99%, 85%; LG: 94%, 97%, 86%, DT: 94%, 97%, 84%, SVM: 94%, 98%, 88%, and ANN: 94%, 97%, 86%). The accuracy differences are not statistically significant (Cochran Q test, p = 0.592). Individually, the feature that best differentiates PD from normal scans was the putamen binding potential with 93% accuracy, 93% sensitivity, and 94% specificity in the test dataset, based on the optimal cutoff (1.716) that maximizes Younden’s coefficient in the training dataset. Conclusion: CNN classifier proved to be as robust and accurate as the other classifiers frequently used in the type of problems as in this work, with the great advantage of using images as direct input. All machine learning-based classifiers tested are robust and very accurate in the classification of brain [123I]FP-CIT SPECT scans. Standard visual clinical evaluation should be complemented with quantification classification used also as a training tool.
- Comparison between 3D laser scanning and computed tomography on the modelling of head surfacePublication . Sousa, E.; Vieira, L.; Costa, D. M. S.; Costa, D. C.; Parafita, R.; Loja, AméliaThe measurement of people physical parameters and proportions constitutes an importante field of science, the anthropometry, since it is related to the characterization of the human size and constitution; it allows improving the design and sizing of systems and devices to human use. To enable these measurements, different direct and indirect methodologies may be used depending on the particular aim of a specific study and on the eventual availability of data sources that can be used also for this purpose. Because of this relevance, the present work intends to assess the influence of diferente acquisition and reconstruction methods in the modelling of a 3D head surface. In order to assess the significance of the differences between acquisition and reconstruction methods a set of measurements between several anatomic references of a physical phantom were carried out. Statistical evaluation using the Friedman test for non-parametrical pared samples was considered. We found, so far, no statistically significant differences between the several methods considered for acquisition and reconstruction.
- Using 3D anthropometric data for the modelling of customised head immobilisation masksPublication . Loja, MAR; Sousa, Eva; Vieira, Lina Oliveira; Costa, D. M.; Craveiro, D. S.; Parafita, R.; Costa, D. C.Head immobilization thermoplastic masks for radiotherapy purposes involve a distressful modeling procedure for the patient. To assess the possibility of using different acquisition and reconstruction methods to obtain a 3D skin surface model of PIXY-phantom-head and to present a proposal of an alternative head immobilization mask prototype. Phantom head geometry acquisitions using: computed tomography (reconstructed with ImageJ and Osirix); and 3D Laser Scanner (reconstructed with SolidWorks). From these reconstructed surface models, a set of landmarks was measured and subsequently compared with physical measurements obtained with a Rosscraft-Calliper. For statistical evaluation, relative deviations graphics and Friedman-test for non-parametrical paired samples were used, with a significance level of 5%. For a first assessment of the proposed mask performance, a radiotransparent material was considered, the strength and stiffness evaluation is performed using the finite element method. There are small differences between all the acquisitions and reconstructions methods and the physical measurements, statistically significant differences (X2F(6)) = 6.863, p=0.334) were not found. The proposed mask performed well from the strength and stiffness perspectives, leading to the desired immobilization aim. The immobilization mask design proposal may be an effective alternative to the present completely hand-made situation, which presents a high degree of discomfort and stress to the patients.