http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Novel Breast mass segmentation method based on patch merging and GHFCM
Shenghua Gu,Yunjie Chen,Jin Wang,Jeong-Uk Kim 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.10
Breast cancer is regarded as one of the most frequent mortality causes among women. It is very important to create a system to diagnose suspicious masses in mammograms for early breast cancer detection. In this paper, we propose an automatic breast mass segmentation method based on patch merging method and generalized hierarchical Fuzzy C Means (GHFCM). The patch merging method is used to obtain the adaptive region of interest (ROI), while the GHFCM method which is able to overcome the drawbacks of effect of image noise and Euclidean distance FCM which is sensitive to outliers is used to obtain the precisely mass segmentation results. The new method is evaluated over MiniMIAS dataset. The segmentation performance from experimentations demonstrates that our method outperforms the other compared methods.
A Novel Brain Tumor Segmentation Method for Multi-Modality Human Brain MRIs
Tianming Zhan,Shenghua Gu,Lei Jiang,Yongzhao Zhan 보안공학연구지원센터 2015 International Journal of Multimedia and Ubiquitous Vol.10 No.11
Delineating brain tumor boundaries from multi-modality magnetic resonance images (MRIs) is a crucial step in brain cancer surgical and treatment planning. In this paper, we propose a fully automatic technique for brain tumor segmentation from multi-modality human brain MRIs. We first use the intensities of different modalities in MRIs to represent the features of both normal and abnormal tissues. Then, the multiple classifier system (MCS) is applied to calculate the probabilities of brain tumor and normal brain tissue in the whole image. At last, the spatial-contextual information is proposed by constraining the classified neighbors to improve the classification accuracy. Our method was evaluated on 20 multi-modality patient datasets with competitive segmentation results.
Tianming Zhan,Shenghua Gu,Can Feng,Yongzhao Zhan,Jin Wang 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.9
Automatic brain tumor segmentation from multispectral magnetic resonance imaging (MRI) data is an important but a challenging task because of the high diversity in the appearance of tumor tissues among different patients and in many cases similarity with the normal tissues. In this paper, we propose a fully automatic technique for brain tumor segmentation from multispectral human brain MRIs. We first use the intensities of different patches in multispectral MRIs to represent the features of both normal and abnormal tissues and generate a dictionary for following tissue classification. Then, the sparse representation classification (SRC) is applied to classify the brain tumor and normal brain tissue in the whole image. At last, the Markov random field (MRF) regularization introduces spatial constraints to the SRC to take into account the pair-wise homogeneity in terms of classification labels and multispectral voxel intensities. Our method was evaluated on 20 multi-modality patient datasets with competitive segmentation results.