An ensemble of 2D convolutional neural network for 3D brain tumor segmentation

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


We propose an ensemble of 2D convolutional neural networks to predict the 3D brain tumor segmentation mask using the multi-contrast brain images. A pretrained Resnet50 and Nasnet-mobile architecture were used as an encoder, which was appended with a decoder network to create an encoder-decoder neural network architecture. The encoder-decoder network was trained end to end using T1, T1 contrast-enhanced, T2 and T2-Flair images to classify each pixel in the 2D input image to either no tumor, necrosis/non-enhancing tumor (NCR/NET), enhancing tumor (ET) or edema (ED). Separate Resent50 and Nasnet-mobile architectures were trained for axial, sagittal and coronal slices. Predictions from 5 inferences including Resnet at all three orientations and Nasnet-mobile at two orientations were averaged to predict the final probabilities and subsequently the tumor mask. The mean dice scores calculated from 166 were 0.8865, 0.7372 and 0.7743 for whole tumor, tumor core and enhancing tumor respectively.

Original languageEnglish
Title of host publicationBrainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
Subtitle of host publication5th International Workshop, BrainLes 2019, Held in Conjunction with MICCAI 2019, Revised Selected Papers
EditorsAlessandro Crimi, Spyridon Bakas
Place of PublicationCham Switzerland
Number of pages9
ISBN (Electronic)9783030466404
ISBN (Print)9783030466398
Publication statusPublished - 2020
EventInternational MICCAI Brain Lesion Workshop 2019 - Shenzhen, China
Duration: 17 Oct 201917 Oct 2019
Conference number: 5th

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


WorkshopInternational MICCAI Brain Lesion Workshop 2019
Abbreviated titleBrainLes 2019
OtherHeld in conjunction with the Medical Image Computing for Computer Assisted Intervention, MICCAI 2019


  • Brain tumor segmentation
  • Convolutional neural network
  • Ensemble networks
  • Residual learning

Cite this