Negligible effect of brain MRI data preprocessing for tumor segmentation

Abstract

Magnetic resonance imaging (MRI) data is heterogeneous due to differences in device manufacturers, scanning protocols, and inter-subject variability. A conventional way to mitigate MR image heterogeneity is to apply preprocessing transformations such as anatomy alignment, voxel resampling, signal intensity equalization, image denoising, and localization of regions of interest. Although a preprocessing pipeline standardizes image appearance, its influence on the quality of image segmentation and on other downstream tasks in deep neural networks has never been rigorously studied.

Experiments on three publicly available datasets evaluate the effect of different preprocessing steps in intra- and inter-dataset training scenarios. Results demonstrate that most popular standardization steps add no value to network performance; moreover, preprocessing can hamper performance. Our results suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization. Additionally, the contribution of skull-stripping in data preprocessing is almost negligible if measured in terms of estimated tumor volume.

The only essential transformation for accurate deep learning analysis is the unification of voxel spacing across the dataset. In contrast, inter-subjects anatomy alignment in the form of atlas registration is not necessary and intensity equalization steps (denoising, bias-field correction and histogram matching) do not improve performance.

The study code is accessible online.
2