No abstract

The gradient vector flow (GVF) algorithm has been used extensively as an efficient method for medical image segmentation. This algorithm suffers from poor robustness against noise as well as lack of convergence in small scale details and concavities. As a cure to this problem, in this paper the idea of multi scale is applied to the traditional GVF algorithm for segmentation of brain tumors in MRI images. Using this idea, the active contour is evolved with respect to scaled edge maps in a multi scale manner. The edge detection performance of the modified GVF algorithm is further enhanced by applying a threshold-based edge detector to improve the edge map. The Bspline snake is selected for representation of the active contour, due to its ability to capture corners and its local control. The results showed an improvement of 30% in the accuracy of tumor segmentation against traditional GVF and 10 % as compared to Bspline GVF in the presence of noise, besides the repeatability of the algorithm in contrast to traditional GVF. The clinical evaluation also proved the accuracy and sensitivity of the proposed method as 92.8% and 95.4%, respectively.

This paper presents a fast algorithm for sequence alignment in Biocomputing using Bloom filters. The idea behind this proposed method is comparing subsequence of incoming sequences with Bloom filter and discovering the matched subsequence. The sequence alignment problem has a large number of comparisons. According to the last successful experiences of useing Bloom filter in similar issues such as web search, it seems that using Bloom filter to solving this problem can be an appropriate solution. To evaluate the proposed algorithm, it has been implemented and compared to the NeedlemanWunsch method. Results show that in average, outpout quality is improved by 41%, memory usage by 84%, and response time by 52% compared to Needleman-Wunsch method are improved. In addition, for real samples, output quality is almost equivalent, memory usage is improved by 95% and response time by 40% compared to the Needleman-Wunsch method.

No abstract

No abstract