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

arXiv: https://arxiv.org/abs/1909.02344 · HTML: https://mlsanity.com/paper/1909.02344/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 11 of 11)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Self-supervised Assisted Active Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2205.07021/) (2022)
- [Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network](https://mlsanity.com/paper/2411.13873/) (2024)
- [A Survey on Active Deep Learning: From Model-driven to Data-driven](https://mlsanity.com/paper/2101.09933/) (2021)
- [Task-Aware Active Learning for Endoscopic Image Analysis](https://mlsanity.com/paper/2204.03440/) (2022)
- [Information Gain Sampling for Active Learning in Medical Image Classification](https://mlsanity.com/paper/2208.00974/) (2022)
- [Visual In-Context Learning for Few-Shot Eczema Segmentation](https://mlsanity.com/paper/2309.16656/) (2023)
- [Active Learning for Imbalanced Civil Infrastructure Data](https://mlsanity.com/paper/2210.10586/) (2022)
- [Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification](https://mlsanity.com/paper/2307.15987/) (2023)
- [OneSeg: Self-learning and One-shot Learning based Single-slice Annotation for 3D Medical Image Segmentation](https://mlsanity.com/paper/2309.13671/) (2023)
- [Automated Measurement of Eczema Severity with Self-Supervised Learning](https://mlsanity.com/paper/2504.15193/) (2025)

## Abstract (arXiv)

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% of samples, our approach can achieve state-of-the-art 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.