Name
Abstract | ||
|---|---|---|
As a significant complement for skin surface images, skin biopsy image may reveal causes and severity of many skin diseases, especially in the case of skin cancer inspection. With rapid increment of skin disease patients, computational methods have been introduced for automatic classification of skin images. However, due to the complex relationship among annotation terms and features of local regions, it becomes a great challenge for skin biopsy image feature recognition and annotation. In this paper, we attempt to model the potential knowledge and experience of doctors on skin biopsy image annotation by using a recent proposed machine learning model, named multi-instance multi-label (MIML) model. We show that the relationship among annotation terms and skin biopsy images is naturally consistent with the MIML framework. We further propose a sparse Bayesian MIML algorithm which can produce a probability indicating the confidence of annotating a term. The proposed algorithm framework is evaluated on a real dataset from a large local hospital containing 12,700 skin biopsy images. The results show that the proposed algorithm is effective and prominent. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/BIBM.2013.6732500 | BIBM |
Keywords | Field | DocType |
skin disease patient,annotation term,automatic classification,miml framework,sparse bayesian multiinstance multilabel model,normalized cut,bayes methods,learning (artificial intelligence),sparse bayesian miml algorithm,gaussian process,skin biopsy image annotation,skin surface image,local region,sparse bayesian learning,skin biopsy image analysis,cancer,feature extraction,image classification,large local hospital,mulit-instance multi-label learning,real dataset,skin disease severity,machine learning model,computational method,complex relationship,skin,skin biopsy image feature recognition,medical image processing,skin cancer inspection,probability,learning artificial intelligence | Automatic image annotation,Annotation,Pattern recognition,Computer science,Skin cancer,Feature recognition,Feature extraction,Skin biopsy,Artificial intelligence,Contextual image classification,Machine learning,Bayesian probability | Conference |
Volume | Issue | ISSN |
null | null | 2156-1125 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gang Zhang | 1 | 0 | 0.34 |
| Xiangyang Shu | 2 | 0 | 0.68 |
| Yongjing Huang | 3 | 0 | 0.34 |
| Yingrong Lao | 4 | 1 | 1.07 |
| Zhaohui Liang | 5 | 26 | 15.31 |
| Shanxing Ou | 6 | 2 | 1.39 |
| Jimmy Huang | 7 | 3 | 1.74 |