Generalizing Common Tasks in Automated Skin Lesion Diagnosis

We present a general model using supervised learning and MAP estimation that is capable of performing many common tasks in automated skin lesion diagnosis. We apply our model to segment skin lesions, detect occluding hair, and identify the dermoscopic structure pigment network. Quantitative results...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on information technology in biomedicine 2011-07, Vol.15 (4), p.622-629
Main Authors: Wighton, P., Lee, T. K., Lui, H., McLean, D. I., Atkins, M. S.
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Automated skin lesion diagnosis (ASLD)
computer-aided diagnosis (CAD)
dermoscopy
Dermoscopy - methods
Diagnosis, Computer-Assisted - methods
Diagnosis, Differential
Hair
hair detection
Humans
Image Processing, Computer-Assisted - methods
Image segmentation
Lesions
melanoma
pigment network
Pigments
Pixel
segmentation
Skin Neoplasms - diagnosis
Skin Neoplasms - pathology
Supervised learning
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a general model using supervised learning and MAP estimation that is capable of performing many common tasks in automated skin lesion diagnosis. We apply our model to segment skin lesions, detect occluding hair, and identify the dermoscopic structure pigment network. Quantitative results are presented for segmentation and hair detection and are competitive when compared to other specialized methods. Additionally, we leverage the probabilistic nature of the model to produce receiver operating characteristic curves, show compelling visualizations of pigment networks, and provide confidence intervals on segmentations.
ISSN:1089-7771
1558-0032
DOI:10.1109/TITB.2011.2150758