Brain tumor detection and segmentation using deep learning.

Journal: Magma (New York, N.Y.)
Published Date:

Abstract

OBJECTIVES: Brain tumor detection, classification and segmentation are challenging due to the heterogeneous nature of brain tumors. Different deep learning-based algorithms are available for object detection; however, the performance of detection algorithms on brain tumor data has not been widely explored. Therefore, we aim to compare different object detection algorithms (Faster R-CNN, YOLO & SSD) for brain tumor detection on MRI data. Furthermore, the best-performing detection network is paired with a 2D U-Net for pixel-wise segmentation of abnormal tumor cells.

Authors

  • Rafia Ahsan
    Department of Electrical and Computer Engineering, Medical Image Processing Research Group (MIPRG), COMSATS University Islamabad, Islamabad, Pakistan.
  • Iram Shahzadi
    Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Bochum, Germany; Siemens Healthineers GmbH, Erlangen, Germany.
  • Faisal Najeeb
    Department of Electrical and Computer Engineering, Medical Image Processing Research Group (MIPRG), COMSATS University Islamabad, Islamabad, Pakistan. faisal.najeeb@comsats.edu.pk.
  • Hammad Omer
    Medical Image Processing Research Group (MIPRG), Department of Electrical and Computer Engineering, COMSATS University Islamabad, Pakistan. Electronic address: hammad.omer@comsats.edu.pk.