Robust pulmonary segmentation for chest radiography, combining enhancement, adaptive morphology and innovative active contours

Abstract Introduction Statistical data reveal that approximately 140 million radiological exams are performed annually in Brazil. These exams are designed to detect and to analyze fractures, caused by different types of trauma; as well as, to diagnose pathologies such as pulmonary diseases. For better visualization of those lesions or abnormalities, methods of image segmentation can be implemented. Such methods lead to the separation of the region of interest, which allows extracting the characteristics and anomalies of the desired tissue. However, the methods developed by researchers in this area still have restrictions. Consequently, we present an automatic pulmonary segmentation approach that overcomes these constraints. Methods This method is composed of a combination of Discrete Wavelet Packet Frame (DWPF), morphological operations and Gradient Vector Flow (GVF). The methodology is divided into four steps: Pre-processing - the original image is enhanced by discrete wavelet; Processing - where occurs a combination of the Otsu threshold with a series of morphological operations in order to identify the pulmonary object; Post-processing - an innovative form of using GVF improves the binary information of pulmonary tissue, and; Evaluation - the segmented images were evaluated for accuracy of detection the pulmonary region and border. Results The evaluation was carried out by segmenting 247 digital X-ray challenging images of the thorax human. The results show high for values of Overlap (97,63% ± 3.34%), and Average Contour Distance (0.69mm ± 0.95mm). Conclusion The results allow verifying that the proposed technique is robust and more accurate than other methods of lung segmentation, besides being a fully automatic method of lung segmentation.

Automatic Initialization Active Contour Model for the Segmentation of the Chest Wall on Chest CT / 대한의료정보학회지

OBJECTIVES: Snake or active contours are extensively used in computer vision and medical image processing applications, and particularly to locate object boundaries. Yet problems associated with initialization and the poor convergence to boundary concavities have limited their utility. The new method of external force for active contours, which is called gradient vector flow (GVF), was recently introduced to address the problems. METHODS: This paper presents an automatic initialization value of the snake algorithm for the segmentation of the chest wall. Snake algorithms are required to have manually drawn initial contours, so this needs automatic initialization. In this paper, our proposed algorithm is the mean shape for automatic initialization in the GVF. RESULTS: The GVF is calculated as a diffusion of the gradient vectors of a gray-level or binary edge map derived from the medical images. Finally, the mean shape coordinates are used to automatic initialize thepoint of the snake. The proposed algorithm is composed of three phases: the landmark phase, the procrustes shape distance metric phase and aligning a set of shapes phase. The experiments showed the good performance of our algorithm in segmenting the chest wall by chest computed tomography. CONCLUSIONS: An error analysis for the active contours results on simulated test medical images is also presented. We showed that GVF has a large capture range and it is able to move a snake into boundary concavities. Therefore, the suggested algorithm is better than the traditional potential forces of image segmentation.

Multimodal Medical Image Registration Based on Gradient Vector Flow and Particle Swarm Optimization / 航天医学与医学工程

Objective To study the method based on gradient vector flow (GVF) and particle swarm optimization (PSO) for realizing multimodal medical image registration and improving its accuracy. Methods In view of three major components of image registration, i.e. the feature space, the similarity metric and the search strategy, a novel method was proposed with three improvements. Firstly, the GVF field was employed as the feature space. Then three similarity metrics were proposed based on GVF field. Finally, an improved PSO combined with crossover mechanism of genetic algorithm was utilized to search for the optimal transformation of two images. Results With 54 times of experiments on both simulated and real medical images, it was demonstrated that this method accurately registered the multimodal medical images to be superior to the method based on PSO of pixels, and the Walsh transform method. Conclusion The method based on GVF and PSO is effective for multimodal medical image registration.