Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 471 - Contemporary Statistical Methods for Imaging Data Analysis
Type: Contributed
Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistics in Imaging
Abstract #312443
Title: Extracting Dermoscopic Features with Neural Style Transfer for Skin Lesion Classification
Author(s): Yutong Li* and Ruoqing Zhu and Annie Qu
Companies: University of Illinois at Urbana-Champaign and University of Illinois at Urbana-Champaign and University of Illinois at Urbana-Champaign
Keywords: Cancer Detection; Neural Style Transfer ; Image Recognition; Machine Learning; Deep Learning
Abstract:

Skin cancer, the most commonly found human malignancy, is primarily diagnosed visually via dermoscopic analysis, biopsy and histopathological examination. However, unlike other types of cancer, automated image classification of skin lesions is deemed more challenging due to the irregularity and variability in the lesions’ appearances. We propose an adaptation of the Neural Style Transfer (NST) as a novel feature extraction and image pre-processing step to construct image covariates. This takes advantage of the second-moment information of deep image features for more accurate melanoma image classification. We represent each dermoscopic image as the style image and transfer the style of the lesion onto a homogeneous content image. This transfers the main variability of each lesion onto the same localized region, which normalizes the main pattern of each lesion and aligns the position of the pixels across all considered lesions. We then integrate the generated images together and extract latent, low-rank style features using tensor decomposition. We train and cross-validate our model on a balanced dermoscopic data set collected from the International Skin Imaging Collaboration (ISI


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program