Automated post-operative brain tumour segmentation: a deep learning model based on transfer learning from pre-operative images

Mina Ghaffari*, Gihan Samarasinghe, Michael Jameson, Farhannah Aly, Lois Holloway, Phillip Chlap, Eng-Siew Koh, Arcot Sowmya, Ruth Oliver

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

23 Citations (Scopus)

Abstract

Automated brain tumour segmentation from post-operative images is a clinically relevant yet challenging problem. In this study, an automated method for segmenting brain tumour into its subregions has been developed. The dataset consists of multimodal post-operative brain scans (T1 MRI, post-Gadolinium T1 MRI, and T2-FLAIR images) of 15 patients who were treated with post-operative radiation therapy, along with manual annotations of their tumour subregions. A 3D densely-connected U-net was developed for segmentation of brain tumour regions and extensive experiments were conducted to enhance model accuracy. A model was initially developed using the publicly available BraTS dataset consisting of pre-operative brain scans. This model achieved Dice Scores of 0.90, 0.83 and 0.78 for predicting whole tumour, tumour core, and enhancing tumour subregions when tested on BraTS20 blind validation dataset. The acquired knowledge from BraTS was then transferred to the local dataset. For augmentation purpose, the local dataset was registered to a dataset of MRI brain scans of healthy subjects. To improve the robustness of the model and enhance its accuracy, ensemble learning was used to combine the outputs of all the trained models. Even though the size of the dataset is very small, the final model can segment brain tumours with a high Dice Score of 0.83, 0.77 and 0.60 for whole tumour, tumour core and enhancing core respectively.

Original languageEnglish
Pages (from-to)28-36
Number of pages9
JournalMagnetic Resonance Imaging
Volume86
DOIs
Publication statusPublished - Feb 2022

Keywords

  • Brain tumour segmentation
  • Multimodal MRI
  • Deep learning
  • Densely connected CNN

Fingerprint

Dive into the research topics of 'Automated post-operative brain tumour segmentation: a deep learning model based on transfer learning from pre-operative images'. Together they form a unique fingerprint.

Cite this