Automated Breast Tumor Segmentation in DCE-MRI Using Deep Learning

Mohammed Benjelloun, Mohammed El Adoui, Mohamed Amine Larhmam, Sidi Ahmed Mahmoudi

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

Abstract

Segmentation of breast tumor is an important step for breast cancer follow-up and treatment. Automating this challenging task can help radiologists to reduce the high workload of breast cancer analysis. In this paper, we propose a deep learning approach to automate the segmentation of breast tumors in DCE-MRI data. We build an architecture based on U-net fully convolutional neural network. The trained model can handle both detection and segmentation on each single breast slice. In this study, we used a dataset of 86 DCE-MRI, acquired before and after chemotherapy, of 43 patients with local breast cancer, a total of 5452 slices. The data have been annotated manually by an experienced radiologist. The model was trained and validated on 85% and 15% of the data and achieved a mean IoU of 76,14%.

Original languageEnglish
Title of host publication2018 4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728116372
DOIs
Publication statusPublished - 2 Jul 2018
Externally publishedYes
Event4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018 - Brussels, Belgium
Duration: 26 Nov 201828 Nov 2018

Publication series

Name2018 4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018

Conference

Conference4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018
Country/TerritoryBelgium
CityBrussels
Period26/11/1828/11/18

Keywords

  • Breast cancer
  • DCE-MRI
  • Deep Learning
  • Tumor segmentation

Fingerprint

Dive into the research topics of 'Automated Breast Tumor Segmentation in DCE-MRI Using Deep Learning'. Together they form a unique fingerprint.

Cite this