Oriented pattern analysis for streak detection in dermoscopy images

Authors:
Maryam Sadeghi;Tim K. Lee;David McLean;Harvey Lui;M. Stella Atkins
Affiliations:
School of Computing Science, Simon Fraser University, Canada, Department of Dermatology and Skin Science, University of British Columbia, Canada, Cancer Control Research Program, BC Cancer Researc ...;School of Computing Science, Simon Fraser University, Canada, Department of Dermatology and Skin Science, University of British Columbia, Canada, Cancer Control Research Program, BC Cancer Researc ...;Department of Dermatology and Skin Science, University of British Columbia, Canada;Department of Dermatology and Skin Science, University of British Columbia, Canada;School of Computing Science, Simon Fraser University, Canada, Department of Dermatology and Skin Science, University of British Columbia, Canada
Venue:
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2012

Citing 4
Cited 1

Analyzing oriented patterns

Computer Vision, Graphics, and Image Processing
Fingerprint Image Enhancement: Algorithm and Performance Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fully Automatic Random Walker Segmentation for Skin Lesions in a Supervised Setting

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Modeling the dermoscopic structure pigment network using a clinically inspired feature set

MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality

Detection of pigment network in dermoscopy images using supervised machine learning and structural analysis

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

There is an increasing demand for automated detection and analysis of dermoscopy structures and malignancy clues such as streaks in dermoscopy images, for computer-aided early diagnosis of deadly melanoma. This paper presents a novel approach for streak detection and visualization on dermoscopic images. We tackle the detection of streaks by means of ridge and valley estimation. Orientation estimation and correction is applied to detect low contrast and fuzzy streaks lines, and candidate streaks are used to classify dermoscopy images into streaks Absent or Present with the AUC of 90.5% on 300 dermoscopy images. Our approach can also detect starburst pattern of regular streaks using detected linear structures with accuracy of 81.5% and AUC of 87.7%.