Magnetic Resonance Imaging (MRI) is a cornerstone in diagnosing brain tumors. However, the complex nature of these tumors makes accurate segmentation in MRI images a demanding task.
Objective
Accurate brain tumor segmentation remains a critical challenge in medical image analysis, with early detection crucial for improving patient outcomes.
Methods
To develop and evaluate a novel UNet-based architecture for improved brain tumor segmentation in MRI images. This paper presents a novel UNet-based architecture for improved brain tumor segmentation. The UNet model architecture incorporates Leaky ReLU activation, batch normalization, and regularization to enhance training and performance. The model consists of varying numbers of layers and kernel sizes to capture different levels of detail. To address the issue of class imbalance in medical image segmentation, we employ focused loss and generalized Dice (GDL) loss functions.
Results
The proposed model was evaluated on the BraTS’2020 dataset, achieving an accuracy of 99.64% and Dice coefficients of 0.8984, 0.8431, and 0.8824 for necrotic core, edema, and enhancing tumor regions, respectively.
Conclusion
These findings demonstrate the efficacy of our approach in accurately predicting tumors, which has the potential to enhance diagnostic systems and improve patient outcomes.
GordilloNMontsenyESobrevillaP. State of the art survey on MRI brain tumor segmentation. Magn Reson Imaging2013; 31: 1426–1438.
2.
LiuZTongLChenL, et al.Deep learning based brain tumor segmentation: a survey. Complex Intell Syst2023; 9: 1001–1026.
3.
BaidUGhodasaraSMohanS, et al.The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification, http://arxiv.org/abs/2107.02314 (2021 Jul 5).
4.
PrastawaM. A brain tumor segmentation framework based on outlier detection*1. Med Image Anal2004; 8: 275–283.
5.
JalabHAHasanAM. Magnetic resonance imaging segmentation techniques of brain tumors: a review. Arch Neurosci2019; 6: 5812.
6.
WadhwaABhardwajASingh VermaV. A review on brain tumor segmentation of MRI images. Magn Reson Imaging2019; 61: 247–259.
7.
RanjbarzadehRCaputoATirkolaeeEB, et al.Brain tumor segmentation of MRI images: a comprehensive review on the application of artificial intelligence tools. Comput Biol Med2023; 152: 106405.
8.
AbdusalomovABMukhiddinovMWhangboTK. Brain tumor detection based on deep learning approaches and magnetic resonance imaging. Cancers (Basel)2023; 15: 4172.
9.
MehrotraRAnsariMAAgrawalR,et al.A transfer learning approach for AI-based classification of brain tumors. Mach Learn Appl2020; 2: 100003.
10.
HabibHAminRAhmedB,et al.Hybrid algorithms for brain tumor segmentation, classification and feature extraction. J Ambient Intell Humaniz Comput2022; 13: 2763–2784.
11.
Abd El KaderIXuGShuaiZ, et al.Brain tumor detection and classification on MR images by a deep wavelet auto-encoder model. Diagnostics2021; 11: 1589.
12.
Abd El KaderIXuGShuaiZ, et al.Differential deep convolutional neural network model for brain tumor classification. Brain Sci2021; 11: 352.
13.
SoomroTAZhengLAfifiAJ, et al.Image segmentation for MR brain tumor detection using machine learning: a review. IEEE Rev Biomed Eng2023; 16: 70–90.
14.
SaouliRAkilMKachouriR. Fully automatic brain tumor segmentation using End-to-End incremental deep neural networks in MRI images. Comput Methods Programs Biomed2018; 166: 39–49.
15.
LiuXSongLLiuS,et al.A review of deep-learning-based medical image segmentation methods. Sustainability2021; 13: 1224.
16.
KumarRKumbharkarPVanamS,et al.Medical images classification using deep learning: a survey. Multimed Tools Appl2023; 83: 19683–19728.
17.
PunnNSAgarwalS. Modality specific U-Net variants for biomedical image segmentation: a survey. Artif Intell Rev2022; 55: 5845–5889.
18.
ArulananthTSKuppusamyPGAyyasamyRK, et al.Semantic segmentation of urban environments: leveraging U-net deep learning model for cityscape image analysis. PLoS One2024; 19: e0300767.
19.
ChenYQuanLLongC, et al.Brain tumor segmentation based on the U-NET++ network with efficientnet encoder. Technol Heal Care2024; 32: 183–195.
20.
SiddiqueNPahedingSElkinCP,et al.U-Net and its variants for medical image segmentation: a review of theory and applications. IEEE Access2021; 9: 82031–82057.
21.
ZhangCAchuthanAHimelGMS. State-of-the-Art and challenges in pancreatic CT segmentation: a systematic review of U-net and its variants. IEEE Access2024; 12: 78726–78742.
22.
SubasiA. Medical image segmentation using artificial intelligence. In: Applications of artificial intelligence in healthcare and biomedicine. Elsevier; 2024, pp.377–400.
23.
SunGPanYKongW, et al.DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation. Front Bioeng Biotechnol2024; 12: 1398237.
24.
FarhadpourSWarnerTAMaxwellAE. Selecting and interpreting multiclass loss and accuracy assessment metrics for classifications with class imbalance: guidance and best practices. Remote Sens2024; 16: 533.
25.
IantsenA. Occidentale LUDEB. Automated tumor segmentation in multimodal PET/CT/MR imaging To cite this version: HAL Id: tel-04573020 Andrei IANTSEN, 2024.
26.
BokhovkinABurnaevE. Boundary loss for remote sensing imagery semantic segmentation, 2019, pp.388–401.
27.
FidonLLiWGarcia-Peraza-HerreraLC, et al.Generalised Wasserstein dice score for imbalanced multi-class segmentation using holistic convolutional networks, 2018, pp.64–76.
28.
MaJHeYLiF, et al.Segment anything in medical images. Nat Commun2024; 15: 654.
29.
JaffariRHashmaniMAReyes-AldasoroCC. A novel focal phi loss for power line segmentation with auxiliary classifier U-net. Sensors2021; 21: 2803.
SoltaninejadMZhangLLambrouT, et al.MRI brain tumor segmentation and patient survival prediction using random forests and fully convolutional networks, 2018, pp.204–15. http://link.springer.com/10.1007/978-3-319-75238-9_18.
32.
SailunazKBestepeDAlhajjS, et al.Brain tumor detection and segmentation: interactive framework with a visual interface and feedback facility for dynamically improved accuracy and trust. PLoS One2023; 18: e0284418.
33.
CoupetMUrrutyTLeelanupabT, et al.A multi-sequences MRI deep framework study applied to glioma classfication. Multimed Tools Appl2022; 81: 13563–13591.
34.
WenYChenLDengY, et al.Pixel-wise triplet learning for enhancing boundary discrimination in medical image segmentation. Knowledge-Based Syst2022; 243: 108424.
35.
TongGLiYChenH, et al.Improved U-NET network for pulmonary nodules segmentation. Optik (Stuttg)2018; 174: 460–469.
36.
EelbodeTBertelsJBermanM, et al.Optimization for medical image segmentation: theory and practice when evaluating with dice score or jaccard Index. IEEE Trans Med Imaging2020; 39: 3679–3690.
37.
YangFZamzmiGAngaraS, et al.Assessing inter-annotator agreement for medical image segmentation. IEEE Access2023; 11: 21300–21312.
38.
Gab AllahAMSarhanAMElshennawyNM. Edge U-net: brain tumor segmentation using MRI based on deep U-net model with boundary information. Expert Syst Appl2023; 213: 118833.
39.
RazaRIjaz BajwaUMehmoodY, et al.dResU-Net: 3D deep residual U-net based brain tumor segmentation from multimodal MRI. Biomed Signal Process Control2023; 79: 103861.
40.
AboussalehIRiffiJEl FazazyK, et al.Efficient U-net architecture with multiple encoders and attention mechanism decoders for brain tumor segmentation. Diagnostics2023; 13: 872.
41.
Abd-EllahMKAwadAIKhalafAAM,et al.Automatic brain-tumor diagnosis using cascaded deep convolutional neural networks with symmetric U-net and asymmetric residual-blocks. Sci Rep2024; 14: 9501.
42.
AboeleneinNMSonghaoPKoubaaA, et al.HTTU-Net: hybrid two track U-net for automatic brain tumor segmentation. IEEE Access2020; 8: 101406–15.
43.
ChenYQuanLLongC, et al.Brain tumor segmentation based on the U-NET++ network with efficientnet encoder. Technol Heal Care2024; 32: 183–195.
44.
BhattANigamVS. Highly accurate brain tumor detection with high sensitivity using transform-based functions and machine learning algorithms. Technol Heal Care2024; 32: 4239–4256.
45.
GaiXCaiHWangJ, et al.Construction of multi-scale feature fusion segmentation model of MRI knee images based on dual attention mechanism weighted aggregation. Technol Heal Care2024; 32: 277–286.
46.
WangJYinL. CNN-based glioma detection in MRI: a deep learning approach. Technol Heal Care2024; 32: 4965–4982.
