Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks

Magnetic resonance imaging (MRI) is an indispensable tool in diagnosing brain-tumor patients. Automated tumor segmentation is being widely researched to accelerate the MRI analysis and allow clinicians to precisely plan treatment-accurate delineation of brain tumors is a critical step in assessing their volume, shape, boundaries, and other characteristics. However, it is still a very challenging task due to inherent MR data characteristics and high variability, e.g., in tumor sizes or shapes. We present a new deep learning approach for accurate brain tumor segmentation which can be trained from small and heterogeneous datasets annotated by a human reader (providing high-quality ground-truth segmentation is very costly in practice).

In this paper, we present a new deep learning technique for segmenting brain tumors from fluid attenuation inversion recovery MRI. Our technique exploits fully convolutional neural networks, and it is equipped with a battery of augmentation techniques that make the algorithm robust against low data quality, and heterogeneity of small training sets. We train our models using only positive (tumorous) examples, due to the limited amount of available data.

Our algorithm was tested on a set of stage II-IV brain-tumor patients (image data collected using MAGNETOM Prisma 3T, Siemens). Rigorous experiments, backed up with statistical tests, revealed that our approach outperforms the state-of-the-art approach (utilizing hand-crafted features) in terms of segmentation accuracy, offers very fast training and instant segmentation (analysis of an image takes less than a second). Building our deep model is 1.3 times faster compared with extracting features for extremely randomized trees, and this training time can be controlled. Finally, we showed that too aggressive data augmentation may lead to deteriorated performance of the model, especially in the fixed-budget training (with maximum numbers of training epochs).

Our method yields the better performance when compared with the state of the art method which utilizes hand-crafted features. In addition, our deep network can be effectively applied to difficult (small, imbalanced, and heterogeneous) datasets, offers controllable training time, and infers in real-time.