Skip to Main content Skip to Navigation
Journal articles

3D Convolutional Neural Networks for Tumor Segmentation using Long-range 2D Context

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).
Complete list of metadata

Cited literature [44 references]  Display  Hide  Download
Contributor : Pawel Mlynarski Connect in order to contact the contributor
Submitted on : Tuesday, February 12, 2019 - 10:04:57 AM
Last modification on : Friday, July 8, 2022 - 10:09:00 AM
Long-term archiving on: : Monday, May 13, 2019 - 1:41:28 PM


Files produced by the author(s)




Pawel Mlynarski, Hervé Delingette, Antonio Criminisi, Nicholas Ayache. 3D Convolutional Neural Networks for Tumor Segmentation using Long-range 2D Context. Computerized Medical Imaging and Graphics, Elsevier, In press, 73, pp.60-72. ⟨10.1016/j.compmedimag.2019.02.001⟩. ⟨hal-01883716v2⟩



Record views


Files downloads