Boosting instance prototypes to detect local dermoscopic features

Local dermoscopic features are useful in many dermoscopic criteria for skin cancer detection. We address the problem of detecting local dermoscopic features from epiluminescence (ELM) microscopy skin lesion images. We formulate the recognition of local dermoscopic features as a multi-instance learning (MIL) problem. We employ the method of diverse density (DD) and evidence confidence (EC) function to convert MIL to a single-instance learning (SIL) problem. We apply Adaboost to improve the classification performance with support vector machines (SVMs) as the base classifier. We also propose to boost the selection of instance prototypes through changing the data weights in the DD function. We validate the methods on detecting ten local dermoscopic features from a dataset with 360 images. We compare the performance of the MIL approach, its boosting version, and a baseline method without using MIL. Our results show that boosting can provide performance improvement compared to the other two methods.

[1]  Masaru Tanaka,et al.  Pattern Classification of Nevus with Texture Analysis , 2008 .

[2]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Wu-Jun Li,et al.  Localized content-based image retrieval through evidence region identification , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Tomás Lozano-Pérez,et al.  A Framework for Multiple-Instance Learning , 1997, NIPS.

[5]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[6]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[7]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Yixin Chen,et al.  Image Categorization by Learning and Reasoning with Regions , 2004, J. Mach. Learn. Res..

[9]  Begoña Acha,et al.  Pattern analysis of dermoscopic images based on Markov random fields , 2009, Pattern Recognit..

[10]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[13]  S. Menzies,et al.  Automated epiluminescence microscopy: human vs machine in the diagnosis of melanoma. , 1999, Archives of dermatology.

[14]  R. Johr.  Dermoscopy: alternative melanocytic algorithms-the ABCD rule of dermatoscopy, Menzies scoring method, and 7-point checklist. , 2002, Clinics in dermatology.

[15]  Thomas G. Dietterich,et al.  Learning non-redundant codebooks for classifying complex objects , 2009, ICML '09.

[16]  G. Argenziano,et al.  Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions. Comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis. , 1998, Archives of dermatology.