Isfahan University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Automatic Segmentation of Glioma Tumors From Brats 2018 Challenge Dataset Using a 2D U-Net Network



Papi Z1 ; Abedi I1 ; Dalvand F2 ; Amouheidari A3
Authors
Show Affiliations
Authors Affiliations
  1. 1. Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
  2. 2. Department of Radiation Engineering, School of Medicine, Shahid Beheshti University, Tehran, Iran
  3. 3. Department of Radiotherapy, Isfahan Milad Hospital, Isfahan, Iran

Source: Tehran University Medical Journal Published:2022

Abstract

Background: Glioma is the most common primary brain tumor, and early detection of tumors is important in the treatment planning for the patient. The precise segmentation of the tumor and intratumoral areas on the MRI by a radiologist is the first step in the diagnosis, which, in addition to the consuming time, can also receive different diagnoses from different physicians. The aim of this study was to provide an automated method for segmenting the tumor and intratumoral areas. Methods: This is a fundamental-applied study that was conducted from May 2020 to September 2021 using multimodal MRI images of 285 patients with glioma tumors from the BraTS 2018 Database. This database was collected from 19 different MRI imaging centers, including multimodal MRI images of 210 HGG patients, and 75 LGG patients. In this study, a 2D U-Net architecture was designed with a patch-based method for training, which comprises an encoding path for feature extraction and a symmetrical decoding path. The training of this network was performed in three separate stages, using data from high-grade gliomas (HGG), and low-grade gliomas (LGG), and combining two groups of 210, 75, and 220 patients, respectively. Results: The proposed model estimated the Dice Similarity Coefficient (DSC) results in HGG datasets 0.85, 0.85, 0.77, LGG datasets 0.80, 0.66, 0.51, and the combination of the two groups 0.88, 0.79, 0.77 for regions the whole tumor, tumor core, and enhancing region in the training dataset, respectively. The results related to Hussdorf Distance (HD) for HGG datasets were 8.24, 9.92, 4.43, LGG datasets 11.5, 11.31, 2.23, and the combination of the two groups 7.20, 8.82, 4.43 for regions the whole tumor, tumor core, and enhancing region in the training dataset, respectively. Conclusion: Using the U-Net network can help physicians in the accurate segmentation of the tumor and its various areas, as well as increase the survival rate of these patients and improve their quality of life through accurate diagnosis and early treatment. © 2022 Tehran University of Medical Sciences. All rights reserved.
Related Docs
View other Related Docs
1. Auto-Segmentation and Classification of Glioma Tumors With the Goals of Treatment Response Assessment Using Deep Learning Based on Magnetic Resonance Imaging, Neuroinformatics (2023)
2. Glioma Segmentation With Dwi Weighted Images, Conventional Anatomical Images, and Post-Contrast Enhancement Magnetic Resonance Imaging Images by U-Net, Physical and Engineering Sciences in Medicine (2022)
3. Classification and Staging of Brain Glioma Tumors Using Magnetic Resonance Imaging and Machine Learning Algorithms, Journal of Isfahan Medical School (2022)
4. The Segmentation of Therapeutic Target Area in Glioma Cancer Patients by Transfer Learning, Journal of Isfahan Medical School (2023)
5. Deep Learning Approaches for Automated Classification and Segmentation of Head and Neck Cancers and Brain Tumors in Magnetic Resonance Images: A Meta-Analysis Study, International Journal of Computer Assisted Radiology and Surgery (2021)
6. Using of Laplacian Re-Decomposition Image Fusion Algorithm for Glioma Grading With Swi, Adc, and Flair Images, Polish Journal of Medical Physics and Engineering (2021)
7. Performance Comparison of Different Medical Image Fusion Algorithms for Clinical Glioma Grade Classification With Advanced Magnetic Resonance Imaging (Mri), Scientific Reports (2023)
8. A Review of Glioblastoma Tumors With Primitive Neuronal Component and a Case Report of a Patient With This Uncommon Tumor at a Rare Location, Clinical Case Reports (2020)
Experts (# of related papers)
View all Related Experts
Amir Khorasani (5)
Mohammad Bagher Tavakoli (5)
Other Related Docs
9. Optimization of Ct Slice Thickness in 3D-Crt and Imrt Planning of Low Grade Glioma, International Journal of Radiation Research (2021)
10. Segmentation of Pancreatic Ductal Adenocarcinoma (Pdac) and Surrounding Vessels in Ct Images Using Deep Convolutional Neural Networks and Texture Descriptors, Scientific Reports (2022)
11. Convolutional Neural Networks in Auto-Segmentation of Nasopharyngeal Carcinoma Tumor — a Systematic Review and Meta-Analysis, Oncology in Clinical Practice (2024)
12. Exploring the Efficacy of Multi-Flavored Feature Extraction With Radiomics and Deep Features for Prostate Cancer Grading on Mpmri, BMC Medical Imaging (2023)
13. Imaging Role in Diagnosis, Prognosis, and Treatment Response Prediction Associated With High-Grade Glioma, Journal of Medical Signals and Sensors (2024)
14. Improvement Grading Brain Glioma Using T2 Relaxation Times and Susceptibility-Weighted Images in Mri, Informatics in Medicine Unlocked (2023)
15. Investigating the Feasibility of Differentiating Ms Active Lesions From Inactive Ones Using Texture Analysis and Machine Learning Methods in Dwi Images, Multiple Sclerosis and Related Disorders (2024)
16. Deep-Neural Network Approaches for Predicting 3D Dose Distribution in Intensity-Modulated Radiotherapy of the Brain Tumors, Journal of Applied Clinical Medical Physics (2024)
17. Radiomic Feature Reproducibility: The Impact of Inter-Scanner and Inter-Modality Variations, Iranian Journal of Medical Physics (2021)
18. Breast Cancer Diagnosis in Dce-Mri Using Mixture Ensemble of Convolutional Neural Networks, Pattern Recognition (2017)
19. A Pipeline to Quantify Spinal Cord Atrophy With Deep Learning: Application to Differentiation of Ms and Nmosd Patients, Physica Medica (2021)
20. Isfahan Artificial Intelligence Event 2023: Lesion Segmentation and Localization in Magnetic Resonance Images of Patients With Multiple Sclerosis, Journal of Medical Signals and Sensors (2025)
21. Preliminary Study of Multiple B-Value Diffusion-Weighted Images and T1 Post Enhancement Magnetic Resonance Imaging Images Fusion With Laplacian Re-Decomposition (Lrd) Medical Fusion Algorithm for Glioma Grading, European Journal of Radiology Open (2021)