A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data
This addresses the challenge of training set selection for medical image analysis, offering a more efficient method that reduces processing costs and improves prediction accuracy, though it is incremental as it applies an existing bandit method to a specific domain problem.
The paper tackles the problem of efficiently selecting a training set from big medical image data to address dataset heterogeneity, using a multi-armed bandit approach with Thompson sampling based on meta information, resulting in higher accuracy with only a fraction of the training data on a brain MRI age estimation task with 7,250 subjects from 10 datasets.
With the availability of big medical image data, the selection of an adequate training set is becoming more important to address the heterogeneity of different datasets. Simply including all the data does not only incur high processing costs but can even harm the prediction. We formulate the smart and efficient selection of a training dataset from big medical image data as a multi-armed bandit problem, solved by Thompson sampling. Our method assumes that image features are not available at the time of the selection of the samples, and therefore relies only on meta information associated with the images. Our strategy simultaneously exploits data sources with high chances of yielding useful samples and explores new data regions. For our evaluation, we focus on the application of estimating the age from a brain MRI. Our results on 7,250 subjects from 10 datasets show that our approach leads to higher accuracy while only requiring a fraction of the training data.