3D convolutional neural networks for tumor segmentation using long-range 2D context. (April 2019)

• Record Type: Journal Article
• Authors: Mlynarski, Pawel; Delingette, Hervé; Criminisi, Antonio; Ayache, Nicholas
• Is Part Of: Computerized medical imaging and graphics. Volume 73(2019)
• Page Start: 60
• Page End: 72
• Publication Date: 2019-04
• Subjects: 3D Convolutional Neural Networks -- Brain tumor -- Multisequence MRI -- Segmentation -- Ensembles of models; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2019.02.001
• Languages: English
• ISSNs: 0895-6111

Abstract

Graphical abstract: Abstract: We present an efficient deep learning approach for the challenging task of tumor segmentation in multisequence MR images. In recent years, Convolutional Neural Networks (CNN) have achieved state-of-the-art performances in a large variety of recognition tasks in medical imaging. Because of the considerable computational cost of CNNs, large volumes such as MRI are typically processed by subvolumes, for instance slices (axial, coronal, sagittal) or small 3D patches. In this paper we introduce a CNN-based model which efficiently combines the advantages of the short-range 3D context and the long-range 2D context. Furthermore, we propose a network architecture with modality-specific subnetworks in order to be more robust to the problem of missing MR sequences during the training phase. To overcome the limitations of specific choices of neural network architectures, we describe a hierarchical decision process to combine outputs of several segmentation models. Finally, a simple and efficient algorithm for training large CNN models is introduced. We evaluate our method on the public benchmark of the BRATS 2017 challenge on the task of multiclass segmentation of malignant brain tumors. Our method achieves good performances and produces accurate segmentations with median Dice scores of 0.918 (whole tumor), 0.883 (tumor core) and 0.854 (enhancing core).