عرض بسيط للتسجيلة

المؤلفUllah, Faizad
المؤلفAnsari, Shahab U.
المؤلفHanif, Muhammad
المؤلفAyari, Mohamed A.
المؤلفChowdhury, Muhammad E.
المؤلفKhandakar, Amith A.
المؤلفKhan, Muhammad S.
تاريخ الإتاحة2023-04-17T06:57:45Z
تاريخ النشر2021
اسم المنشورSensors
المصدرScopus
معرّف المصادر الموحدhttp://dx.doi.org/10.3390/s21227528
معرّف المصادر الموحدhttp://hdl.handle.net/10576/41977
الملخصMRI 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. 2021 by the authors. Licensee MDPI, Basel, Switzerland.
راعي المشروعFunding: The authors also thank the Higher Education Commission (HEC), Pakistan, for funding this research under the Artificial Intelligence in Healthcare, IIPL, National Center of Artificial Intelligence (NCAI) and partial funding by HEC-SRGP research grant.
اللغةen
الناشرMDPI
الموضوعBrain tumor segmentation
Deep learning
Gibbs ringing artifact
Image enhancement
Medical image processing
العنوانBrain mr image enhancement for tumor segmentation using 3d u-net
النوعArticle
رقم العدد22
رقم المجلد21
dc.accessType Open Access


الملفات في هذه التسجيلة

Thumbnail

هذه التسجيلة تظهر في المجموعات التالية

عرض بسيط للتسجيلة