Multi-instance learning for skin biopsy image features recognition

In this paper, a multi-instance learning framework is introduced to solve the problem of skin biopsy image features recognition. Previously reported methods for skin surface images were mostly based on color features extraction. They are incapable to be directly applied to skin biopsy image features recognition because biopsy images are often dyed and have obvious inner structures with different textures. Therefore, we regard skin biopsy images as multi-instance samples, whose instances are regions or structures captured by applying Normalized Cut. Texture feature extraction methods are used to express each region as a vectorial expression. Then two multi-instance learning algorithms reported successful in various image retrieval tasks were applied. Nine features were manually selected as target features to evaluate the proposed method on a skin disease diagnosis datasets of 6579 biopsy images from 2010 to 2011. The result showed that the proposed method is effective and medically acceptable.

[1]  Craig D Neitzel,et al.  Biopsy techniques for skin disease and skin cancer. , 2005, Oral and maxillofacial surgery clinics of North America.

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

[3]  Anneli Fogelberg,et al.  The Utility of Digital Clinical Photographs in Dermatopathology , 2004, Journal of cutaneous medicine and surgery.

[4]  Cesare Massone,et al.  The Influence of Clinical Information in the Histopathologic Diagnosis of Melanocytic Skin Neoplasms , 2009, PloS one.

[5]  Ashwin Srinivasan,et al.  Multi-instance tree learning , 2005, ICML.

[6]  J. Naeyaert,et al.  The melanoma burden in Belgium; premature morbidity and mortality make melanoma a considerable health problem. , 1999, Melanoma research.

[7]  Muhammad Shahrukh,et al.  Burden of skin diseases , 2009, Expert review of pharmacoeconomics & outcomes research.

[8]  Marcel F. Jonkman,et al.  Learning effective color features for content based image retrieval in dermatology , 2011, Pattern Recognit..

[9]  James R. Foulds,et al.  A review of multi-instance learning assumptions , 2010, The Knowledge Engineering Review.

[10]  Thomas Gärtner,et al.  Multi-Instance Kernels , 2002, ICML.

[11]  M. Llamas-Velasco,et al.  Basic concepts in skin biopsy. Part I. , 2012, Actas dermo-sifiliograficas.

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

[13]  Gene H. Golub,et al.  Matrix computations , 1983 .

[14]  Harald Kittler,et al.  Influence of evaluation of clinical pictures on the histopathologic diagnosis of inflammatory skin disorders. , 2010, Journal of the American Academy of Dermatology.

[15]  Johanne Sundby,et al.  Self-reported skin morbidity among adults: associations with quality of life and general health in a Norwegian survey. , 2004, The journal of investigative dermatology. Symposium proceedings.

[16]  Zhi-Hua Zhou,et al.  Multi-instance learning by treating instances as non-I.I.D. samples , 2008, ICML '09.

[17]  S. Aral,et al.  Psychosocial aspects of genital herpes virus infection. , 1987, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[18]  W. Grayson,et al.  Recognition of Dual or Multiple Pathology in Skin Biopsies from Patients with HIV/AIDS , 2011, Pathology research international.

[19]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[20]  Sunil Kalia,et al.  The burden of skin disease in the United States and Canada. , 2012, Dermatologic clinics.

[21]  Alan B. Fleischer,et al.  THE MAGNITUDE OF SKIN DISEASE IN THE UNITED STATES , 2000 .

[22]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[23]  Allen Gersho,et al.  Asymptotically optimal block quantization , 1979, IEEE Trans. Inf. Theory.

[24]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  A B Fleischer,et al.  Introduction. The magnitude of skin disease in the United States. , 2000, Dermatologic clinics.

[26]  Jun Zhou,et al.  MILIS: Multiple Instance Learning with Instance Selection , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  W. Bergfeld,et al.  A retrospective biopsy study of the clinical diagnostic accuracy of common skin diseases by different specialties compared with dermatology. , 2005, Journal of the American Academy of Dermatology.

[28]  M Llamas-Velasco,et al.  [Basic concepts in skin biopsy. Part I]. , 2012, Actas dermo-sifiliograficas.