DeepAI AI Chat
Log In Sign Up

An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis

by   Xueying Shi, et al.
The Chinese University of Hong Kong

Automated skin lesion analysis is very crucial in clinical practice, as skin cancer is among the most common human malignancy. Existing approaches with deep learning have achieved remarkable performance on this challenging task, however, heavily relying on large-scale labelled datasets. In this paper, we present a novel active learning framework for cost-effective skin lesion analysis. The goal is to effectively select and utilize much fewer labelled samples, while the network can still achieve state-of-the-art performance. Our sample selection criteria complementarily consider both informativeness and representativeness, derived from decoupled aspects of measuring model certainty and covering sample diversity. To make wise use of the selected samples, we further design a simple yet effective strategy to aggregate intra-class images in pixel space, as a new form of data augmentation. We validate our proposed method on data of ISIC 2017 Skin Lesion Classification Challenge for two tasks. Using only up to 50 performances on both tasks, which are comparable or exceeding the accuracies with full-data training, and outperform other well-known active learning methods by a large margin.


page 1

page 2

page 3

page 4


A Two-Stage Method for Skin Lesion Analysis

This report summarises our method and validation results for the ISIC Ch...

CS-AF: A Cost-sensitive Multi-classifier Active Fusion Framework for Skin Lesion Classification

Convolutional neural networks (CNNs) have achieved the state-of-the-art ...

Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning

In this report, we introduce the outline of our system in Task 3: Diseas...

Active Learning for Interactive Audio-Animatronic Performance Design

We present a practical neural computational approach for interactive des...

Self-supervised Assisted Active Learning for Skin Lesion Segmentation

Label scarcity has been a long-standing issue for biomedical image segme...

Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification

Although deep convolutional neural networks (DCNNs) have achieved signif...

Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning

Recent advances in deep learning have led to breakthroughs in the develo...