In this study, a novel incremental supervised neural network (ISNN) is proposed for the segmentation of medical images. Performance of the ISNN is investigated for tissue segmentation in medical images obtained from various imaging modalities. Two feature extraction methods based on transform and moments are comparatively investigated to segment the tissues in medical images. Two-dimensional (2D) continuous wavelet transform (CWT) and the moments of the gray-level histogram (MGH) are computed in order to form the feature vectors of ultrasound (US) bladder and phantom images, X-ray computerized tomography (CT) and magnetic resonance (MR) head images. In the 2D-CWT method, feature vectors are formed by the intensity of one pixel of each wavelet-plane of different energy bands. The MGH represents the tissues within the sub-windows by using the spatial variation of image intensities. In this study, the ISNN and Grow and Learn (GAL) network are employed for the segmentation task. It is observed that the ISNN has significantly eliminated the disadvantages of the GAL network in the segmentation of the medical images.
In the internal medicine wide spectrum the gastroenterology is one of the chapters, less enlightened by the scientific evidence. It does not mean that the practice of the grasntroenterology may ot be improved by the systematic use of the approaches of the evidence based medicine
This paper presents an improved incremental self-organizing map (I2SOM) network that uses automatic threshold (AT) value for the segmentation of ultrasound (US) images. In order to show the validity of proposed scheme, it has been compared with Kohonen’s SOM. Two-dimensional (2D) fast Fourier transform (FFT) and 2D continuous wavelet transform (CWT) were computed in order to form the feature vectors of US bladder and phantom images. In this study, it is observed that the proposed automatic threshold scheme for ISOM network has significantly eliminated the former ISOM network’s threshold problem for US images. This improvement enhances the robustness of ISOM algorithm. Obtained results show that ISOM with AT value has similar segmentation performance with Kohonen’s network.
This prototype development explains the challenges encountered during the ISO/IEEE 11073 standard implementation process. The complexity of the standard and the consequent heavy requirements, which have not encouraged software engineers to adopt the standard. The developing complexity evaluation drives us to propose two possible implementation strategies that cover almost all possible use cases and eases handling the standard by non-expert users. The first one is focused on medical devices (MD) and proposes a low-memory and low-processor usage technique. It is based on message patterns that allow simple functions to generate ISO/IEEE 11073 messages and to process them easily. MD act as X73 agent. Second one is focused on more powerful device X73 manager, which do not have the MDs' memory and processor usage constraints. The protocol between Agent and Manager is point-to-point and we can distribute the functionality between devices.
Developed both implementation X73 Agent and Manager will cut developing time for applications based on ISO/EEE 11073.