期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

Adaptive segmentation based on multi-classification model for dermoscopy images 被引量：2

Adaptive segmentation based on multi-classification model for dermoscopy images
原文传递
导出
摘要 Segmentation accuracy of dermoscopy images is important in the computer-aided diagnosis of skin cancer and a wide variety of segmentation methods for dermoscopy images have been developed. Considering that each method has its strengths and weaknesses, a novel adaptive segmentation framework based on multi-classification model is proposed for dermoscopy images. Firstly, five patterns of images are summarized according to the factors influencing segmentation. Then the matching relation is established between each image pattern and its optimal segmentationmethod. Next, the given image is classified into one of the five patterns by the multi-classification model based on BP neural network. Finaily, the optimal segmentation method for this image is selected according to the matching relation, and then the image is effectively segmented. Experiments show that the proposed method delivers better accuracy and more robust segmentation results compared with the other seven state-of-the-art methods. Segmentation accuracy of dermoscopy images is important in the computer-aided diagnosis of skin cancer and a wide variety of segmentation methods for dermoscopy images have been developed. Considering that each method has its strengths and weaknesses, a novel adaptive segmentation framework based on multi-classification model is proposed for dermoscopy images. Firstly, five patterns of images are summarized according to the factors influencing segmentation. Then the matching relation is established between each image pattern and its optimal segmentationmethod. Next, the given image is classified into one of the five patterns by the multi-classification model based on BP neural network. Finaily, the optimal segmentation method for this image is selected according to the matching relation, and then the image is effectively segmented. Experiments show that the proposed method delivers better accuracy and more robust segmentation results compared with the other seven state-of-the-art methods.
作者 Fengying XIE Yefen WU Yang LI Zhiguo JIANG Rusong MENG
机构地区 Image Processing Center General Hospital of the Air Force
出处 《Frontiers of Computer Science》 SCIE EI CSCD 2015年第5期720-728,共9页 中国计算机科学前沿（英文版）
基金 Acknowledgements This work was supported by the National Natural Science Foundation of China （Grant Nos. 61471016, 61371134 and 61271436）.
关键词 adaptive segmentation feature extraction pattern classification dermoscopy image adaptive segmentation, feature extraction, pattern classification, dermoscopy image
分类号 TP391.41 [自动化与计算机技术—计算机应用技术] TN919.81 [电子电信—通信与信息系统]
  • 相关文献

参考文献29

  • 1Siegel R, Ma J, Zou Z, Jemal A. Cancer statistics, 2014. CA: a Cancer Journal for Clinicians, 2014, 64(1): 9-29.
  • 2Di Leo G, Liguofi C, Paolillo A, Sommella P. An improved proce- dure for the automatic detection of dermoscopy structures in digital ELMimages of skin lesions. In: Proceedings of the IEEE International Conference on V'Lrtual Environment, Human-Computer Interfaces, and Measurement Systems. 2008, 190-194.
  • 3Soyer H P, Smolle J, Kerl H, Stettnre H. Early diagnosis of malignant melanoma by surface microscopy. The Lancet, 1987, 330(8562): 803.
  • 4Korotkov K, Garcia R. Computerized analysis of pigmented skin le- sions: a review. Artificial Intelligence In Medicine, 2012, 56(2): 69-90.
  • 5Celebi M E, Iyatomi H, Schaefer G, Stoecker W V. Lesion border detection in dermoscopy images. Computerized Medical Imaging and Graphics, 2009, 33(2): 148-153.
  • 6Grana C, PeUacani G, Cucehiara R, Seidenari S. A new algorithm for border description of polarized fight surface microscopic images of pigmented skin lesions. IEEE Transactions on Medical Imaging, 2003, 22(8): 959-964.
  • 7Silveira M, Nasdmento J C, Marques J S, Marcal A R S, Mendonca T, Yarauchi S, Maeda J, Rozeira J. Comparison of segmentation meth- ods for melanoma diagnosis in dermoscopy images. IEEE Journal of Selected Topics in Signal Processing, 2009, 3(1): 35-45.
  • 8Xu C, Prince J. Snakes, shapes, and gradient vector flow. IEEE Trans- actions on Image Process, 1998, 7(3): 359-369.
  • 9Nascimento J, Marques J S. Adaptive snakes using the EM algorithm. IEEE Transactions on Image Process, 2005, 14:1678-1686.
  • 10Chan T, Sandberg B, Vese L. Active contours without edges for vec- torvalued images. Journal of Visual Communication and Image Repre- sentation, 2000, 11(2): 130-141.

同被引文献22

  • 1孟如松,蔡瑞康,赵广,成晓湘,姜志国,周付根,杨泽生,陈进.偏振光皮肤镜数字图像分析技术的研究及在色素性皮损诊断中的探讨[J].中国体视学与图像分析,2006,11(2):122-126. 被引量：27
  • 2WHO I Skin cancers, World Health Organization [ On- line]. Available: hltp ://www. who. int/uv/faq/skincan- cer/en/index1, html.
  • 3Sober , Burstein JM. Computerized digital image analy- sis:an aid for melanoma diagnosis [J ]. The Journal of Dermatology, 1994,21 ( 11 ) :885 - 890.
  • 4Xie FY, Li YN, Meng RS, et al. No-reference hair occlusion assessment for dermoscopy images based on distribu- tion feature [ J]. Computers in Biology and Medicine, 2015,59 : 106 - 115.
  • 5Lu YN,Xie FY,Wu YF,et al. No reference uneven illumina- tion assessment for dermoscopy images[J I. Signal Pro- cessing Leflers, IEEE,2015,22(5 ) :534 - 538.
  • 6Xie FY, Lu YN, Bovik AC, et al. Application-Driven No-ref- erence quality assessment for dermoscopy images with multiple distortions [ J ]. IEEE Trans. Biomedical Engineer- ing, DOI: 10.1109/TBME. 20]5. 2493580,201.5.
  • 7Taouil K, Ben Romdhane N, Bouhlel MS. A new automat- ic approach for edge detection of skin lesion images [ C]//Information and Communication Technologies, 2006. ICTTA'06.2nd. IEEE ,2006, 1:212 - 220.
  • 8Tanaka T, Yamada R, Tanaka AA, et al. A study on the image diagnosis of melanoma [ C ] //Engineering in Medicine and Biology Sociely, 2004. IEAABS'04.26th An- nual International Conference of the IEEE. IEEE, 2004,1 : 1597 - 1600.
  • 9Lee T,Ng V,Gallagher R,et al. Dullrazor :A software approach to hair removal from images [ J ]. Computers in Biology and Medicine, 1997,27 (6) :533 - 543.
  • 10Xie FY, Qin SY, Jiang ZG, et al. PDE-based unsupervised repair of hair-occluded information in dermoscopy ima- ges of melanoma [ J ]. Computerized Medical Imaging and Graphics,2009,33 (4) :275 - 282.

引证文献2

二级引证文献8

Frontiers of Computer Science
2015年 第5期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部