Improved Brain Tumor Segmentation in MR Images with a Modified U-Net
Source abstract
Abstract
Detecting brain tumors is crucial in medical diagnostics due to the serious health risks these abnormalities present to patients. Deep learning approaches can significantly improve localization in various medical issues, particularly brain tumors. This paper emphasizes the use of deep learning models to segment brain tumors using a large dataset. The study involves comparing modifications to U-Net structures, including kernel size, number of channels, dropout ratio, and changing the activation function from ReLU to Leaky ReLU. Optimizing these parameters has notably enhanced brain tumor segmentation in MR images, achieving a Global Accuracy of 99.4% and a dice similarity coefficient of 90.2%. The model was trained, validated, and tested on many magnetic resonance images, with a training time not exceeding 19 min on a powerful GPU. This approach can be extended in medical care and hospitals to assist radiologists in identifying tumor locations and suspicious regions, thereby improving diagnosis and treatment effectiveness. The software could also be integrated into MR equipment protocols.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Brain Tumor Detection and Classification · Advanced Neural Network Applications · Medical Image Segmentation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Biomedical Systems and Informatics Engineering, Yarmouk University, Irbid 21163, Jordan
King Hussein Medical Center, The Jordanian Royal Medical Services, Amman 11855, Jordan
The Institute of Biomedical Technology, Al-Balqa Applied University, Al-Salt 19117, Jordan
Faculty of Electrical Engineering & Technology, Pauh Putra Campus, Universiti Malaysia Perlis (UniMAP), Arau 02600, Perlis, Malaysia
Centre of Excellence for Advanced Computing, Pauh Putra Campus, Universiti Malaysia Perlis (UniMAP), Arau 02600, Perlis, Malaysia
References (44)
Show source-provided references
1. Introduction to Machine Learning for Brain Imaging10.1016/j.neuroimage.2010.11.004 ↗
2. Human Brain Mapping10.1038/s41592-023-02106-4 ↗
3. Brain Tumors10.1016/j.amjmed.2017.12.039 ↗
4. Pediatric Brain Tumors10.1016/j.ncl.2018.04.009 ↗
5. Headache and Brain Tumor10.1016/j.nic.2019.01.008 ↗
6. CT and MRI of Brain Tumors
7. Analysis of Deep Learning Techniques for Brain Tumour Classification from CT & MRI Images10.17762/ijritcc.v10i12.5944 ↗
8. Automated Brain Tumor Detection Using Machine Learning: A Bibliometric Review10.1016/j.wneu.2023.03.115 ↗
9. Brain Tumour Classification Using Machine Learning Algorithm10.1088/1742-6596/2318/1/012042 ↗
10. A Review of Brain Tumor Segmentation of MRI Image Using Machine Learning Algorithm
11. Brain Tumor Classification Based on Enhanced CNN Model
12. Deep CNN for Brain Tumor Classification10.1007/s11063-020-10398-2 ↗
13. Machine Learning for Brain Signal Analysis10.26577/ijbch.2021.v14.i2.01 ↗
14. Brain Tumor Detection and Classification Using Machine Learning: A Comprehensive Survey10.1007/s40747-021-00563-y ↗
15. Baecker, L., Garcia-Dias, R., Vieira, S., Scarpazza, C., and Mechelli, A. (2021). Machine Learning for Brain Age Prediction: Introduction to Methods and Clinical Applications. EBioMedicine, 72.10.1016/j.ebiom.2021.103600 ↗
16. Comparative Evaluation for Detection of Brain Tumor Using Machine Learning Algorithms
17. Using Human Brain Activity to Guide Machine Learning10.1038/s41598-018-23618-6 ↗
18. Automated Brain Tumor Detection and Segmentation Using Modified UNet and ResNet Model10.1007/s00500-023-08420-5 ↗
19. Fang, L., and Wang, X. (2023). Multi-input Unet Model Based on the Integrated Block and the Aggregation Connection for MRI Brain Tumor Segmentation. Biomed. Signal Process. Control, 79.10.1016/j.bspc.2022.104027 ↗
20. Efficient Brain Tumour Detection System by Cascaded Fully Convolutional Improved DenseNet with Attention-based Adaptive Swin Unet-derived Segmentation Strategy10.1007/s00530-024-01319-7 ↗
21. FPGA-based Implementation of a Resource-Efficient UNET Model for Brain Tumour Segmentation
22. Deep Transfer Learning Model for Brain Tumor Segmentation and Classification Using UNet and Chopped VGGNet
23. BTSwin-Unet: 3D U-shaped Symmetrical Swin Transformer-based Network for Brain Tumor Segmentation with Self-supervised Pre-training10.1007/s11063-022-10919-1 ↗
24. YOLO-UNet Architecture for Detecting and Segmenting the Localized MRI Brain Tumor Image
25. UNet and Transformer-Based Model for Multi-Modality Brain Tumor Segmentation10.14445/23488549/IJECE-V10I8P103 ↗
26. Yaru3DFPN: A Lightweight Modified 3D UNet with Feature Pyramid Network and Combine Thresholding for Brain Tumor Segmentation10.1007/s00521-024-09475-7 ↗
27. Meta-heuristic-based FCM-UNet Segmentation with Multi-objective Function and Deep Learning for Brain Tumour Classification10.1080/21681163.2022.2092034 ↗
28. Improved Brain Tumor Segmentation Using UNet-LSTM Architecture10.1007/s42979-024-02799-0 ↗
29. A Hybrid Attention-Based Residual Unet for Semantic Segmentation of Brain Tumor
30. Zheng, P., Zhu, X., and Guo, W. (2022). Brain Tumour Segmentation Based on an Improved U-Net. BMC Med. Imaging, 22.10.1186/s12880-022-00931-1 ↗
31. Efficient Simultaneous Segmentation and Classification of Brain Tumors from MRI Scans Using Deep Learning10.1016/j.bbe.2023.08.003 ↗
32. Deep Residual Network Based Brain Tumor Segmentation and Detection with MRI Using Improved Invasive Bat Algorithm10.1007/s11042-022-13769-0 ↗
33. Zoghbi, A., Benleulmi, M., Cheriguene, S., Azizi, N., Lagrini, S., and Layeb, S.N. (2022). Improved Cerebral Images Semantic Segmentation Using Advanced Approaches of Deep Learning. Communications in Computer and Information Science, Springer.10.1007/978-3-031-08277-1_6 ↗
34. Brain Tumor Detection Based on MRI Image Segmentation Using U-Net
35. nnU-Net: A Self-configuring Method for Deep Learning-based Biomedical Image Segmentation10.1038/s41592-020-01008-z ↗
36. Efficient NNU-Net for brain tumor segmentation10.1109/ACCESS.2023.3329517 ↗
37. Huang, L., Miron, A., Hone, K., and Li, Y. (2024). Segmenting Medical Images: From UNet to Res-UNet and nnUNet. arXiv.10.1109/CBMS61543.2024.00086 ↗
38. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.
39. U-Net: Convolutional Networks for Biomedical Image Segmentation10.1007/978-3-319-24574-4_28 ↗
40. Measures of the Amount of Ecologic Association Between Species10.2307/1932409 ↗
41. Image Segmentation Using Deep Learning: A Survey
42. Cho, Y. (2021). Weighted Intersection over Union (wIoU): A New Evaluation Metric for Image Segmentation. arXiv.
43. Salvaraju, R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.74 ↗
44. Cheng, J. (2017). Brain Magnetic Resonance Imaging Tumor Dataset, Figshare LLP. Figshare MRI Dataset Version 5.