Abstract
MRI images are visually inspected by domain experts for the analysis and quantification of the tumorous tissues. Due to the large volumetric data, manual reporting on the images is subjective, cumbersome, and error prone. To address these problems, automatic image analysis tools are employed for tumor segmentation and other subsequent statistical analysis. However, prior to the tumor analysis and quantification, an important challenge lies in the pre-processing. In the present study, permutations of different pre-processing methods are comprehensively investigated. In particular, the study focused on Gibbs ringing artifact removal, bias field correction, intensity normalization, and adaptive histogram equalization (AHE). The pre-processed MRI data is then passed onto 3D U-Net for automatic segmentation of brain tumors. The segmentation results demonstrated the best performance with the combination of two techniques, i.e., Gibbs ringing artifact removal and bias-field correction. The proposed technique achieved mean dice score metrics of 0.91, 0.86, and 0.70 for the whole tumor, tumor core, and enhancing tumor, respectively. The testing mean dice scores achieved by the system are 0.90, 0.83, and 0.71 for the whole tumor, core tumor, and enhancing tumor, respectively. The novelty of this work concerns a robust pre-processing sequence for improving the segmentation accuracy of MR images. The proposed method overcame the testing dice scores of the state-of-the-art methods. The results are benchmarked with the existing techniques used in the Brain Tumor Segmentation Challenge (BraTS) 2018 challenge.
Highlights
IntroductionMedical imaging plays an important role in disease identification and treatment planning
Different preprocessing techniques, i.e., bias field correction, intensity normalization, histogram equalization, and Gibbs ringing artifact removal were employed to analyze the effect of preprocessing techniques and find out the optimal pre-processing technique to train the deep network, i.e., 3D U-Net
We investigated whether bias field correction followed by Gibbs ringing artifact removal gives us improved segmentation results
Summary
Medical imaging plays an important role in disease identification and treatment planning. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are used to monitor the disease progression and diagnosis. Segmentation of affected regions and identification of disease is sometimes affected by the degraded image quality. Automatic segmentation of cancerous regions in brain MRI is a challenging task [1] due to the presence of noise in MRI generated at the time of acquisition and transmission [2,3], intensity inhomogeneity of MRI [4], variability of intensity ranges due to different vendor scanners, and capturing of non-brain tissues (eyes, spinal cord, and skull) in the brain MRI [5]. The skull stripping is considered as an important pre-processing step and, MRI datasets, such as the Multimodal Brain
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
