# Classification of MRI data using Deep Learning and Gaussian Process-based Model Selection

## TL;DR

This paper presents a method combining deep learning with Gaussian Process-based model selection to improve MRI image classification accuracy, addressing hyper-parameter tuning challenges for clinical applicability.

## Contribution

It introduces an adaptive hyper-parameter optimization approach using Gaussian Processes to enhance deep learning models for MRI classification.

## Key findings

- Up to 20% accuracy improvement on difficult classes
- Effective hyper-parameter optimization with Gaussian Processes
- Enhanced model performance over baseline architectures

## Abstract

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).