Automated brain extraction of multi-sequence MRI using artificial neural networks
This addresses the need for robust brain extraction in clinical and research MRI analysis, particularly for pathological cases, though it is incremental as it builds on existing neural network approaches.
The paper tackles the problem of brain extraction in MRI neuroimaging, which often fails with pathological or heterogeneous data, by introducing HD-BET, a neural network-based algorithm that outperforms six existing methods with median improvements of +1.16 to +2.11 points in DICE coefficient and -0.66 to -2.51 mm in Hausdorff distance.
Brain extraction is a critical preprocessing step in the analysis of MRI neuroimaging studies and influences the accuracy of downstream analyses. The majority of brain extraction algorithms are, however, optimized for processing healthy brains and thus frequently fail in the presence of pathologically altered brain or when applied to heterogeneous MRI datasets. Here we introduce a new, rigorously validated algorithm (termed HD-BET) relying on artificial neural networks that aims to overcome these limitations. We demonstrate that HD-BET outperforms six popular, publicly available brain extraction algorithms in several large-scale neuroimaging datasets, including one from a prospective multicentric trial in neuro-oncology, yielding state-of-the-art performance with median improvements of +1.16 to +2.11 points for the DICE coefficient and -0.66 to -2.51 mm for the Hausdorff distance. Importantly, the HD-BET algorithm shows robust performance in the presence of pathology or treatment-induced tissue alterations, is applicable to a broad range of MRI sequence types and is not influenced by variations in MRI hardware and acquisition parameters encountered in both research and clinical practice. For broader accessibility our HD-BET prediction algorithm is made freely available (http://www.neuroAI-HD.org) and may become an essential component for robust, automated, high-throughput processing of MRI neuroimaging data.