Cost-Effective Active Learning for Melanoma Segmentation

2017/11/24 by Gorriz, Marc, Axel Carlier, Emmanuel Faure +3 · 4 citations
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.1711.09168

openalex publication_date 2017/11/24 · openalex created_date 2017/12/04 · openalex updated_date 2026/07/28

Abstract

We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a practical Cost-Effective Active Learning approach using dropout at test time as Monte Carlo sampling to model the pixel-wise uncertainty and to analyze the image information to improve the training performance. The source code of this project is available at https://marc-gorriz.github.io/CEAL-Medical-Image-Segmentation/ .

Citations

• Learning Deconvolution Network for Semantic Segmentation

Cited by

• Minimax Active Learning
• Boosting Active Learning with Knowledge Transfer
• Mask-guided sample selection for Semi-Supervised Instance Segmentation
• Deep Active Learning for Efficient Training of a LiDAR 3D Object Detector

Related

• Breaking the Barrier: Selective Uncertainty-based Active Learning for Medical Image Segmentation
• A Study of Acquisition Functions for Medical Imaging Deep Active Learning
• TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation
• Efficient Active Learning for Image Classification and Segmentation\n using a Sample Selection and Conditional Generative Adversarial Network
• Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation