Histo-pathological image analysis using OS-FCM and level sets

Malignant melanomas are the most serious form of skin cancer accounting for the majority of skin cancer related deaths. Histo-pathological images of skin tissues are analyzed for detecting various types of melanomas. The automatic analysis of these images can greatly facilitate the diagnosis task for dermato-pathologists. The first and foremost step in automatic histo-pathological image analysis is to accurately segment the images into dermal and epidermal layers along with segmenting other tissues structures such as nests and melanocytic cells which indicate the presence of cancer. In this paper, we present a novel technique for segmenting the dermal-epidermal junction based on color features which are initially clustered using the Orientation Sensitive Fuzzy C-means algorithm (OS-FCM) and later refined with level set based algorithms. A few novel parameters which define the architecture of the dermis are then extracted. Experimental results on a small database of skin tissue images show the efficacy of the proposed methodology in differentiating between melanomas and naevi.

[1]  Mihai Datcu,et al.  Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation , 2010, IEEE Geoscience and Remote Sensing Letters.

[2]  Kim L. Boyer,et al.  Classifying land development in high-resolution panchromatic satellite images using straight-line statistics , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[3]  P. Schmid.  Segmentation of digitized dermatoscopic images by two-dimensional color clustering , 1999, IEEE Transactions on Medical Imaging.

[4]  Jun Zhang,et al.  Segmentation of dermatoscopic images by stabilized inverse diffusion equations , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[5]  David M. Blei,et al.  Supervised Topic Models , 2007, NIPS.

[6]  Riccardo Bono,et al.  Early diagnosis of malignant melanoma: Proposal of a working formulation for the management of cutaneous pigmented lesions from the Melanoma Cooperative Group. , 2003, International journal of oncology.

[7]  Allen R. Hanson,et al.  Extracting Straight Lines , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[9]  Anil M. Cheriyadat,et al.  Unsupervised Semantic Labeling Framework for Identification of Complex Facilities in High-Resolution Remote Sensing Images , 2010, 2010 IEEE International Conference on Data Mining Workshops.

[10]  Mehmet Celenk,et al.  A color clustering technique for image segmentation , 1990, Comput. Vis. Graph. Image Process..

[11]  Shu-Yuan Chen,et al.  Retrieval of translated, rotated and scaled color textures , 2003, Pattern Recognit..

[12]  Mark Steyvers,et al.  Finding scientific topics , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Sang Uk Lee,et al.  On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques , 1990, Pattern Recognit..

[15]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Chong Wang,et al.  Simultaneous image classification and annotation , 2009, CVPR.

[17]  Thierry Donadey,et al.  Boundary detection of black skin tumors using an adaptive radial-based approach , 2000, Medical Imaging: Image Processing.

[18]  R. Braun,et al.  Dermoscopy of pigmented lesions: a valuable tool in the diagnosis of melanoma. , 2004, Swiss medical weekly.

[19]  Shashi Shekhar,et al.  An efficient spatial semi-supervised learning algorithm , 2007, Int. J. Parallel Emergent Distributed Syst..

[20]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[21]  A. Kundu,et al.  Rotation and Gray Scale Transform Invariant Texture Identification using Wavelet Decomposition and Hidden Markov Model , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Anil M. Cheriyadat,et al.  Large-Scale Geospatial Indexing for Image-Based Retrieval and Analysis , 2005, ISVC.