Classification of MRI data using Deep Learning and Gaussian Process-based Model Selection
This work addresses the need for accurate MRI classification in medical imaging, but it is incremental as it applies an existing optimization technique to a specific domain.
The paper tackles the problem of classifying MRI images by anatomical field of view using deep learning, where a Gaussian Process-based model selection method improved performance by up to 20% for difficult classes compared to a baseline network.
The classification of MRI images according to the anatomical field of view is a necessary task to solve when faced with the increasing quantity of medical images. In parallel, advances in deep learning makes it a suitable tool for computer vision problems. Using a common architecture (such as AlexNet) provides quite good results, but not sufficient for clinical use. Improving the model is not an easy task, due to the large number of hyper-parameters governing both the architecture and the training of the network, and to the limited understanding of their relevance. Since an exhaustive search is not tractable, we propose to optimize the network first by random search, and then by an adaptive search based on Gaussian Processes and Probability of Improvement. Applying this method on a large and varied MRI dataset, we show a substantial improvement between the baseline network and the final one (up to 20\% for the most difficult classes).