Segmentation is crucial in medical imaging analysis to help extract regions of interest (ROI) from different imaging modalities. The aim of this study is to develop and train a 3D convolutional neural network (CNN) for skull segmentation in magnetic resonance imaging (MRI). 58 gold standard volumetric labels were created from computed tomography (CT) scans in standard tessellation language (STL) models. These STL models were converted into matrices and overlapped on the 58 corresponding MR images to create the MRI gold standards labels. The CNN was trained with these 58 MR images and a mean ± standard deviation (SD) Dice similarity coefficient (DSC) of 0.7300 ± 0.04 was achieved. A further investigation was carried out where the brain region was removed from the image with the help of a 3D CNN and manual corrections by using only MR images. This new dataset, without the brain, was presented to the previous CNN which reached a new mean ± SD DSC of 0.7826 ± 0.03. This paper aims to provide a framework for segmenting the skull using CNN and STL models, as the 3D CNN was able to segment the skull with a certain precision.
In reconstructive craniofacial surgery, the bilateral symmetry of the midplane of the facial skeleton plays an important role in surgical planning. Surgeons can take advantage of the intact side of the face as a template for the malformed side by accurately locating the midplane to assist in the preparation of the surgical procedure. However, despite its importance, the location of the midline is still a subjective procedure. The aim of this study was to present a 3D technique using a convolutional neural network and geometric moments to automatically calculate the craniofacial midline symmetry of the facial skeleton from CT scans. To perform this task, a total of 195 skull images were assessed to validate the proposed technique. In the symmetry planes, the technique was found to be reliable and provided good accuracy. However, further investigations to improve the results of asymmetric images may be carried out.
Assuming a symmetric pattern plays a fundamental role in the diagnosis and surgical treatment of facial asymmetry, for reconstructive craniofacial surgery, knowing the precise location of the facial midline is important since for most reconstructive procedures the intact side of the face serves as a template for the malformed side. However, the location of the midline is still a subjective procedure, despite its importance. This study aimed to automatically locate the bilateral symmetry midline of the facial skeleton based on an invariant moment technique using pseudo-Zernike moments. A total of 367 skull images were evaluated using the proposed technique. The technique was found to be reliable and provided good accuracy in the symmetry planes. This new technique will be utilized for subsequent studies to evaluate diverse craniofacial reconstruction techniques.
In this work, the problem of recognition of objects using images extracted from a 3D industrial sensor is discussed. We focus in 7 feature extractors based on invariant moments and 2 based on independent component analysis, as well as on 3 classifiers (k-Nearest Neighbor, Support Vector Machine and Artificial Neural Network-Multi-Layer Perceptron). To choose the best feature extractor, their performance was compared in terms of classification accuracy rate and extraction time by the k-nearest neighbors classifier using euclidean distance. For what concerns the feature extraction, descriptors based on sorted-Independent Component Analysis and on Zernike moments performed better, leading to accuracy rates over 90.00 % and requiring relatively low time feature extraction (about half-second), whereas among the different classifiers used in the experiments, the suport vector machine outperformed when the Zernike moments were adopted as feature descriptor.
7 September 2022 in Journal of Vibration Engineering & Technologies