MedAL: Deep Active Learning Sampling Method for Medical Image Analysis
This addresses the costly need for large labeled datasets in medical imaging, offering a domain-specific improvement for more efficient model training.
The paper tackles the problem of reducing labeled data requirements for deep learning in medical image analysis by proposing MedAL, a novel active learning sampling method that selects unlabeled examples to maximize distance in feature space, achieving 80% accuracy on Diabetic Retinopathy detection with only 425 labeled images, a 32% reduction compared to standard uncertainty sampling.
Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance.Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance. However, such large labeled datasets are costly to acquire. Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance.In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space. We then extend our sampling method to define a better initial training set, without the need for a trained model, by using ORB feature descriptors. We validate MedAL on 3 medical image datasets and show that our method is robust to different dataset properties. MedAL is also efficient, achieving 80% accuracy on the task of Diabetic Retinopathy detection using only 425 labeled images, corresponding to a 32% reduction in the number of required labeled examples compared to the standard uncertainty sampling technique, and a 40% reduction compared to random sampling.