Deep learning based neural network application for automatic ultrasonic computed tomographic bone image segmentation

Deep-learning techniques have led to technological progress in the area of medical imaging segmentation especially in the ultrasound domain. In this paper, the main goal of this study is to optimize a deep-learning-based neural network architecture for automatic segmentation in Ultrasonic Computed Tomography (USCT) bone images in a short time process. The proposed method is based on an end to end neural network architecture. First, the novelty is shown by the improvement of Variable Structure Model of Neuron (VSMN), which is trained for both USCT noise removal and dataset augmentation. Second, a VGG-SegNet neural network architecture is trained and tested on new USCT images not seen before for automatic bone segmentation. Therefore, we offer a free USCT dataset. In addition, the proposed model is implemented on both the CPU and the GPU, hence overcoming previous works by a value of 97.38% and 96% for training and validation and achieving high segmentation accuracy for testing with a small error of 0.006, in a short time process. The suggested method demonstrates its ability to augment USCT data and then to automatically segment USCT bone structures achieving excellent accuracy outperforming the state of the art.

     

On the improvement of combined fuzzy topological and directional relations information

Concept of combined extraction of topological and directional relations information developed by Zahzah et al. [1] by employing the Allen's temporal relations in 1D spatial domain was improved by Matsakis and Nikitenko [2]. This latter algorithm has high computational complexity due to its limitations of object approximation and segment fuzzification.In this paper, fuzzy Allen relations are used to define the fuzzy topological and directional relations information between different objects. Some extended results of Salamat and Zahzah [3] are discussed. Polygonal object approximation allows us to use fuzzy operators and this approach reduces computational complexity of the method for computing the combined topological and directional relations. To validate the method, some experiments are tested giving satisfactory and promising results. Affine transformation are depicted, these properties will be helpful for using the method in other areas of image analysis such as object tracking.