Brain Extraction from Normal and Pathological Images: A Joint PCA/Image-Reconstruction Approach

TL;DR

This paper introduces a novel joint PCA/image-reconstruction method for brain extraction that effectively handles images with strong pathologies, outperforming existing approaches across multiple datasets.

Contribution

It proposes a new model combining PCA, total variation, and sparse terms to explicitly account for pathologies during brain extraction, enabling better accuracy and pathology identification.

Findings

Achieves the highest median Dice score of 97.11 across datasets.

Outperforms popular methods like ROBEX, BEaST, MASS, BET, BSE, and deep learning approaches.

Effectively extracts brains from images with tumors and traumatic injuries.

Abstract

Brain extraction from images is a common pre-processing step. Many approaches exist, but they are frequently only designed to perform brain extraction from images without strong pathologies. Extracting the brain from images with strong pathologies, for example, the presence of a tumor or of a traumatic brain injury, is challenging. In such cases, tissue appearance may deviate from normal tissue and violates algorithmic assumptions for these approaches; hence, the brain may not be correctly extracted. This paper proposes a brain extraction approach which can explicitly account for pathologies by jointly modeling normal tissue and pathologies. Specifically, our model uses a three-part image decomposition: (1) normal tissue appearance is captured by principal component analysis, (2) pathologies are captured via a total variation term, and (3) non-brain tissue is captured by a sparse term. Decomposition and image registration steps are alternated to allow statistical modeling in a fixed atlas space. As a beneficial side effect, the model allows for the identification of potential pathologies and the reconstruction of a quasi-normal image in atlas space. We demonstrate the effectiveness of our method on four datasets: the IBSR and LPBA40 datasets which show normal images, the BRATS dataset containing images with brain tumors and a dataset containing clinical TBI images. We compare the performance with other popular models: ROBEX, BEaST, MASS, BET, BSE and a recently proposed deep learning approach. Our model performs better than these competing methods on all four datasets. Specifically, our model achieves the best median (97.11) and mean (96.88) Dice scores over all datasets. The two best performing competitors, ROBEX and MASS, achieve scores of 96.23/95.62 and 96.67/94.25 respectively. Hence, our approach is an effective method for high quality brain extraction on a wide variety of images.