Published on Fri Mar 10 2017

Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis

Adrian Galdran, Aitor Alvarez-Gila, Maria Ines Meyer, Cristina L. Saratxaga, Teresa Araújo, Estibaliz Garrote, Guilherme Aresta, Pedro Costa, A. M. Mendonça, Aurélio Campilho

Dermoscopic skin images are often obtained with different imaging devices, under varying acquisition conditions. We propose to leverage computational color constancy techniques to build an artificial data augmentation technique. We employ this technique for training two deep convolutional neural networks for the tasks of skin lesion segmentation

0
0
0
Abstract

Dermoscopic skin images are often obtained with different imaging devices, under varying acquisition conditions. In this work, instead of attempting to perform intensity and color normalization, we propose to leverage computational color constancy techniques to build an artificial data augmentation technique suitable for this kind of images. Specifically, we apply the \emph{shades of gray} color constancy technique to color-normalize the entire training set of images, while retaining the estimated illuminants. We then draw one sample from the distribution of training set illuminants and apply it on the normalized image. We employ this technique for training two deep convolutional neural networks for the tasks of skin lesion segmentation and skin lesion classification, in the context of the ISIC 2017 challenge and without using any external dermatologic image set. Our results on the validation set are promising, and will be supplemented with extended results on the hidden test set when available.

Sat Oct 31 2020
Computer Vision
Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation
Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum.
0
0
0
Tue Oct 29 2019
Machine Learning
Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
Recent advances in computer vision and deep learning have led to breakthroughs in the development of automated skin image analysis. Skin cancer classification models have achieved performance higher than trained expert dermatologists. No attempt has been made to evaluate the consistency in performance of machine learning models across populations with varying skin tones.
0
0
0
Wed Sep 05 2018
Computer Vision
Data Augmentation for Skin Lesion Analysis
Deep learning models show remarkable results in automated skin lesion analysis. These models demand considerable amounts of data, while annotated images are often limited. Data augmentation can expand the training dataset by transforming input images.
0
0
0
Mon Jan 11 2021
Machine Learning
Analysis of skin lesion images with deep learning
Skin cancer is the most common cancer worldwide, with melanoma being the deadliest form. Dermoscopy is a skin imaging modality that has shown an improvement in the diagnosis of skin cancer compared to visual examination without support.
0
0
0
Mon Mar 23 2020
Computer Vision
Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
0
0
0
Wed Aug 21 2019
Machine Learning
A CNN toolbox for skin cancer classification
We describe a software toolbox for the configuration of deep neural networks in the domain of skin cancer classification. The implemented software allows developers to quickly set up new convolutional neural network (CNN) architectures and hyper-parameter configurations.
0
0
0