Document Detail


Four-class classification of skin lesions with task decomposition strategy.
MedLine Citation:
PMID:  25137721     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
This paper proposes a new computer-aided method for skin lesion classification applicable to both melanocytic skin lesions (MSLs) and non-melanocytic skin lesions (NoMSLs). Computer-aided skin lesion classification has drawn attention as an aid for detection of skin cancers. Several researchers have developed methods to distinguish between melanoma and nevus, which are both categorized as MSL. However, most of these studies did not focus on NoMSLs such as basal cell carcinoma (BCC) the most common skin cancer and seborrheic keratosis (SK) despite their high incidence rates. It is preferable to deal with these NoMSLs as well as MSLs especially for the potential users who are not enough capable of diagnosing pigmented skin lesions on their own such as dermatologists in training and physicians with different expertise. We developed a new method to distinguish among melanomas, nevi, BCCs, and SKs. Our method calculates 828 candidate features grouped into three categories: color, subregion, and texture. We introduced two types of classification models: a layered model that uses a task decomposition strategy and flat models to serve as performance baselines. We tested our methods on 964 dermoscopy images: 105 melanomas, 692 nevi, 69 BCCs, and 98 SKs. The layered model outperformed the flat models, achieving detection rates of 90.48%, 82.51%, 82.61%, and 80.61% for melanomas, nevi, BCCs, and SKs, respectively. We also identified specific features effective for the classification task including irregularity of color distribution. The results show promise for enhancing the capability of computer-aided skin lesion classification.
Authors:
Kohei Shimizu; Hitoshi Iyatomi; M Emre Celebi; Kerri-Ann Norton; Masaru Tanaka
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2014-8-15
Journal Detail:
Title:  IEEE transactions on bio-medical engineering     Volume:  -     ISSN:  1558-2531     ISO Abbreviation:  IEEE Trans Biomed Eng     Publication Date:  2014 Aug 
Date Detail:
Created Date:  2014-8-19     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0012737     Medline TA:  IEEE Trans Biomed Eng     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Motion Artifacts in Capacitive ECG Measurements: Reducing the Combined Effect of DC Voltages and Cap...
Next Document:  Identifying 3D Geometric Shapes with a Vibrotactile Glove.