Accurate brain tumour segmentation is critical for diagnosis and treatment planning, yet challenging due to tumour complexity. Manual segmentation is time-consuming and variable, necessitating automated methods. Deep learning, particularly 3D U-Net architectures, has revolutionised medical image analysis by leveraging volumetric data to capture spatial context, enhancing segmentation accuracy. This paper reviews brain tumour segmentation methods, emphasising 3D U-Net advancements. We analyse contributions from the Brain Tumour Segmentation (BraTS) challenges (2014-2023), highlighting key improvements and persistent challenges, including tumour heterogeneity, limited annotated data, varied imaging protocols, computational constraints, and model generalisation. Unlike previous reviews, we synthesise these challenges, proposing targeted research directions: enhancing model robustness through domain adaptation and multi-institutional data sharing, developing lightweight architectures for clinical deployment, integrating multi-modal and clinical data, and incorporating explainability techniques to build clinician trust. By addressing these challenges, we aim to guide future research toward developing more robust, generalisable, and clinically applicable segmentation models, ultimately improving patient outcomes in neuro-oncology.
References
[1]
J.H. Medicine. Brain Tumors and Brain Cancer. https://www.hopkinsmedicine.org/health/conditions-and-diseases/brain-tumor
[2]
Tie, J., Peng, H. and Zhou, J. (2021) MRI Brain Tumor Segmentation Using 3D U-Net with Dense Encoder Blocks and Residual Decoder Blocks. ComputerModelinginEngineering&Sciences, 128, 427-445. https://doi.org/10.32604/cmes.2021.014107
[3]
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J.S., et al. (2017) Advancing the Cancer Genome Atlas Glioma MRI Collections with Expert Segmentation Labels and Radiomic Features. ScientificData, 4, Article ID: 170117. https://doi.org/10.1038/sdata.2017.117
[4]
M. B. & Spine. Brain Tumor Diagnosis and Treatment Options. Cincinnati, OH Mayfield Brain & Spine. https://mayfieldclinic.com/pe-braintumor.htm
[5]
A. A. of N. Surgeons. Brain Tumors. AANS. https://www.aans.org/patients/conditions-treatments/brain-tumors/
[6]
Kaifi, R. (2023) A Review of Recent Advances in Brain Tumor Diagnosis Based on Ai-Based Classification. Diagnostics, 13, Article No. 3007. https://doi.org/10.3390/diagnostics13183007
[7]
Martucci, M., Russo, R., Schimperna, F., D’Apolito, G., Panfili, M., Grimaldi, A., et al. (2023) Magnetic Resonance Imaging of Primary Adult Brain Tumors: State of the Art and Future Perspectives. Biomedicines, 11, Article No. 364. https://doi.org/10.3390/biomedicines11020364
[8]
Sabeghi, P., Zarand, P., Zargham, S., Golestany, B., Shariat, A., Chang, M., et al. (2024) Advances in Neuro-Oncological Imaging: An Update on Diagnostic Approach to Brain Tumors. Cancers, 16, Article No. 576. https://doi.org/10.3390/cancers16030576
[9]
Bakas, S., Zeng, K., Sotiras, A., Rathore, S., Akbari, H., Gaonkar, B., et al. (2016) GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation. In: Crimi, A., et al., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 144-155. https://doi.org/10.1007/978-3-319-30858-6_13
[10]
Ahamed, M.F., Hossain, M.M., Nahiduzzaman, M., Islam, M.R., Islam, M.R., Ahsan, M., et al. (2023) A Review on Brain Tumor Segmentation Based on Deep Learning Methods with Federated Learning Techniques. ComputerizedMedicalImagingandGraphics, 110, Article ID: 102313. https://doi.org/10.1016/j.compmedimag.2023.102313
[11]
Kaur, D. and Kaur, Y. (2014) Various Image Segmentation Techniques: A Review.
[12]
Aslam, A., Khan, E. and Beg, M.M.S. (2015) Improved Edge Detection Algorithm for Brain Tumor Segmentation. ProcediaComputerScience, 58, 430-437. https://doi.org/10.1016/j.procs.2015.08.057
[13]
Archana, R. and Jeevaraj, P.S.E. (2024) Deep Learning Models for Digital Image Processing: A Review. ArtificialIntelligenceReview, 57, Article No. 11. https://doi.org/10.1007/s10462-023-10631-z
[14]
Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25. http://code.google.com/p/cuda-convnet/
[15]
Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. 3rd International Conference on Learning Representations, ICLR 2015, San Diego, 7-9 May 2015. https://arxiv.org/abs/1409.1556v6
[16]
Szegedy, C., Liu, W., Jia, Y.Q., Sermanet, P., Reed, S., Anguelov, D., et al. (2015) Going Deeper with Convolutions. 2015 IEEEConferenceonComputerVisionandPatternRecognition (CVPR), Boston, 7-12 June 2015, 1-9. https://doi.org/10.1109/cvpr.2015.7298594
[17]
Chollet, F. (2017) Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEEConferenceonComputerVisionandPatternRecognition (CVPR), Honolulu, 21-26 July 2017, 1800-1807. https://doi.org/10.1109/cvpr.2017.195
[18]
Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI 2015, Munich, 5-9 October 2015, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
[19]
He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEEConferenceonComputerVisionandPatternRecognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. https://doi.org/10.1109/cvpr.2016.90
[20]
Huang, G., Liu, Z., Van Der Maaten, L. and Weinberger, K.Q. (2017) Densely Connected Convolutional Networks. 2017 IEEEConferenceonComputerVisionandPatternRecognition (CVPR), Honolulu, 21-26 July 2017, 2261-2269. https://doi.org/10.1109/cvpr.2017.243
[21]
Nguyen, T.T., Nguyen, H., Bui, T., Nguyen-Tat, T.B. and Ngo, V.M. (2024) Brain Tumor Segmentation in MRI Images with 3D U-Net and Contextual Transformer. 2024 InternationalConferenceonMultimediaAnalysisandPatternRecognition (MAPR), Da Nang, 15-16 August 2024, 1-6. https://doi.org/10.1109/mapr63514.2024.10660920
[22]
Khaliki, M.Z. and Başarslan, M.S. (2024) Brain Tumor Detection from Images and Comparison with Transfer Learning Methods and 3-Layer CNN. ScientificReports, 14, Article No. 2664. https://doi.org/10.1038/s41598-024-52823-9
[23]
Ahmed, S.F., Alam, M.S.B., Hassan, M., Rozbu, M.R., Ishtiak, T., Rafa, N., et al. (2023) Deep Learning Modelling Techniques: Current Progress, Applications, Advantages, and Challenges. Artificial Intelligence Review, 56, 13521-13617. https://doi.org/10.1007/s10462-023-10466-8
[24]
Menze, B.H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., et al. (2015) The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEETransactionsonMedicalImaging, 34, 1993-2024. https://doi.org/10.1109/tmi.2014.2377694
[25]
Pohle, R. and Toennies, K.D. (2001) Segmentation of Medical Images Using Adaptive Region Growing. SPIEProceedings, 4322, 1337-1346. https://doi.org/10.1117/12.431013
[26]
Shanthi, K.J. and Kumar, M.S. (2007) Skull Stripping and Automatic Segmentation of Brain MRI Using Seed Growth and Threshold Techniques. 2007 InternationalConferenceonIntelligentandAdvancedSystems, Kuala Lumpur, 25-28 November 2007, 422-426. https://doi.org/10.1109/icias.2007.4658421
[27]
Manikandan, R., Monolisa, G.S. and Saranya, K. (2013) A Cluster Based Segmentation of Magnetic Resonance Images for Brain Tumor Detection. Middle-East Journal of Scientific Research, 14, 669-672.
[28]
Abbasi, S. and Tajeripour, F. (2017) Detection of Brain Tumor in 3D MRI Images Using Local Binary Patterns and Histogram Orientation Gradient. Neurocomputing, 219, 526-535. https://doi.org/10.1016/j.neucom.2016.09.051
[29]
Abdel-Maksoud, E., Elmogy, M. and Al-Awadi, R. (2015) Brain Tumor Segmentation Based on a Hybrid Clustering Technique. EgyptianInformaticsJournal, 16, 71-81. https://doi.org/10.1016/j.eij.2015.01.003
[30]
Alzubaidi, L., Zhang, J., Humaidi, A.J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., et al. (2021) Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. JournalofBigData, 8, 1-74. https://doi.org/10.1186/s40537-021-00444-8
[31]
Mall, P.K., Singh, P.K., Srivastav, S., Narayan, V., Paprzycki, M., Jaworska, T., et al. (2023) A Comprehensive Review of Deep Neural Networks for Medical Image Processing: Recent Developments and Future Opportunities. HealthcareAnalytics, 4, Article ID: 100216. https://doi.org/10.1016/j.health.2023.100216
[32]
Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M. and Parmar, M. (2024) A Review of Convolutional Neural Networks in Computer Vision. ArtificialIntelligenceReview, 57, 1-43. https://doi.org/10.1007/s10462-024-10721-6
[33]
Pereira, S., Pinto, A., Alves, V. and Silva, C.A. (2016) Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images. IEEETransactionsonMedicalImaging, 35, 1240-1251. https://doi.org/10.1109/tmi.2016.2538465
[34]
Krichen, M. (2023) Convolutional Neural Networks: A Survey. Computers, 12, Article No. 151. https://doi.org/10.3390/computers12080151
[35]
Rosebrock, A. (2021) Convolutional Neural Networks (CNNs) and Layer Types. https://pyimagesearch.com/2021/05/14/convolutional-neural-networks-cnns-and-layer-types/
[36]
Tan, H.H. and Lim, K.H. (2019) Vanishing Gradient Mitigation with Deep Learning Neural Network Optimization. 2019 7thInternationalConferenceonSmartComputing&Communications (ICSCC), Sarawak, 28-30 June 2019, 1-4. https://doi.org/10.1109/icscc.2019.8843652
[37]
Yash (2021) The Challenge of Vanishing/Exploding Gradients in Deep Neural Networks. https://www.analyticsvidhya.com/blog/2021/06/the-challenge-of-vanishing-exploding-gradients-in-deep-neural-networks/
[38]
Fred, A. and Agarap, M. (2018) Deep Learning Using Rectified Linear Units (RELU). 1-6.
[39]
Xu, J., Li, Z., Du, B., Zhang, M. and Liu, J. (2020) Reluplex Made More Practical: Leaky ReLU. 2020 IEEESymposiumonComputersandCommunications (ISCC), Rennes, 7-10 July 2020, 1-7. https://doi.org/10.1109/iscc50000.2020.9219587
[40]
Lederer, J. (2021) Activation Functions in Artificial Neural Networks: A Systematic Overview. https://arxiv.org/abs/2101.09957v1
[41]
Ramachandran, P., Zoph, B. and Le, Q.V. (2017) Searching for Activation Functions.
[42]
Basirat, M. and Roth, P.M. (2018) The Quest for the Golden Activation Function. http://arxiv.org/abs/1808.00783v1
[43]
Pratiwi, H., Windarto, A.P., Susliansyah, S., Aria, R.R., Susilowati, S., Rahayu, L.K., et al. (2020) Sigmoid Activation Function in Selecting the Best Model of Artificial Neural Networks. JournalofPhysics: ConferenceSeries, 1471, Article ID: 012010. https://doi.org/10.1088/1742-6596/1471/1/012010
[44]
Salih, M.M., Salih, M.E. and Ahmed, M.A.A. (2019) Enhancement of U-Net Performance in MRI Brain Tumour Segmentation Using HardELiSH Activation Function. 2019 InternationalConferenceonComputer, Control, Electrical, andElectronicsEngineering (ICCCEEE), Khartoum, 21-23 September 2019, 1-5. https://doi.org/10.1109/iccceee46830.2019.9071235
[45]
Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolutional Networks for Semantic Segmentation. 2015 IEEEConferenceonComputerVisionandPatternRecognition (CVPR), Boston, 7-12 June 2015, 431-440. https://doi.org/10.1109/cvpr.2015.7298965
[46]
Rguibi, Z., Hajami, A., Zitouni, D., Elqaraoui, A. and Bedraoui, A. (2022) CXAI: Explaining Convolutional Neural Networks for Medical Imaging Diagnostic. Electronics, 11, Article No. 1775. https://doi.org/10.3390/electronics11111775
[47]
Avesta, A., Hossain, S., Lin, M., Aboian, M., Krumholz, H.M. and Aneja, S. (2023) Comparing 3D, 2.5D, and 2D Approaches to Brain Image Auto-Segmentation. Bioengineering, 10, Article No. 181. https://doi.org/10.3390/bioengineering10020181
[48]
Zhang, Y., Liao, Q., Ding, L. and Zhang, J. (2022) Bridging 2D and 3D Segmentation Networks for Computation-Efficient Volumetric Medical Image Segmentation: An Empirical Study of 2.5D Solutions. ComputerizedMedicalImagingandGraphics, 99, Article ID: 102088. https://doi.org/10.1016/j.compmedimag.2022.102088
[49]
Yu, Q., Xia, Y., Xie, L., Fishman, E.K. and Yuille, A.L. (2019) Thickened 2D Networks for Efficient 3D Medical Image Segmentation. http://arxiv.org/abs/1904.01150
[50]
Sun, Y., Hsieh, A., Fang, S., Wu, H., Kao, L., Chung, W., et al. (2021) Can 3D Artificial Intelligence Models Outshine 2D Ones in the Detection of Intracranial Metastatic Tumors on Magnetic Resonance Images? JournaloftheChineseMedicalAssociation, 84, 956-962. https://doi.org/10.1097/jcma.0000000000000614
[51]
Taha, A.A. and Hanbury, A. (2015) Metrics for Evaluating 3D Medical Image Segmentation: Analysis, Selection, and Tool. BMCMedicalImaging, 15, Article No. 29. https://doi.org/10.1186/s12880-015-0068-x
[52]
Sensitivity and Specificity—Wikipedia. https://en.wikipedia.org/wiki/Sensitivity_and_specificity
[53]
Precision and Recall—Wikipedia. https://en.wikipedia.org/wiki/Precision_and_recall
[54]
10.1 Sensitivity and Specificity—Foundations of Biomedical Science: Quantitative Literacy: Theory and Problems. https://oercollective.caul.edu.au/foundations-of-biomedical-science/chapter/10-1-sensitivity-and-specificity/
[55]
Thada, V. and Jaglan, V. (2013) Comparison of Jaccard, Dice, Cosine Similarity Coefficient to Find Best Fitness Value for Web Retrieved Documents Using Genetic Algorithm. International Journal of Innovations in Engineering and Technology, 2, 202-205.
[56]
Aydin, O.U., Taha, A.A., Hilbert, A., Khalil, A.A., Galinovic, I., Fiebach, J.B., et al. (2021) On the Usage of Average Hausdorff Distance for Segmentation Performance Assessment: Hidden Error When Used for Ranking. EuropeanRadiologyExperimental, 5, Article No. 4. https://doi.org/10.1186/s41747-020-00200-2
[57]
Fernando, K.R.M. and Tsokos, C.P. (2023) Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation. InformationFusion, 92, 450-465. https://doi.org/10.1016/j.inffus.2022.12.013
[58]
Montaha, S., Azam, S., Rakibul Haque Rafid, A.K.M., Hasan, M.Z. and Karim, A. (2023) Brain Tumor Segmentation from 3D MRI Scans Using U-Net. SNComputerScience, 4, Article No. 386. https://doi.org/10.1007/s42979-023-01854-6
[59]
Ullah, F., Ansari, S.U., Hanif, M., Ayari, M.A., Chowdhury, M.E.H., Khandakar, A.A., et al. (2021) Brain MR Image Enhancement for Tumor Segmentation Using 3D U-Net. Sensors, 21, Article No. 7528. https://doi.org/10.3390/s21227528
[60]
Feng, X., Tustison, N.J., Patel, S.H. and Meyer, C.H. (2020) Brain Tumor Segmentation Using an Ensemble of 3D U-Nets and Overall Survival Prediction Using Radiomic Features. FrontiersinComputationalNeuroscience, 14, Article ID: 488825. https://doi.org/10.3389/fncom.2020.00025
[61]
Henry, T., Carré, A., Lerousseau, M., Estienne, T., Robert, C., Paragios, N., et al. (2021) Brain Tumor Segmentation with Self-Ensembled, Deeply-Supervised 3D U-Net Neural Networks: A Brats 2020 Challenge Solution. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 327-339. https://doi.org/10.1007/978-3-030-72084-1_30
[62]
Ballestar, L.M. and Vilaplana, V. (2021) MRI Brain Tumor Segmentation and Uncertainty Estimation Using 3D-Unet Architectures. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 376-390. https://doi.org/10.1007/978-3-030-72084-1_34
[63]
Wang, F., Jiang, R., Zheng, L., Meng, C. and Biswal, B. (2020) 3D U-Net Based Brain Tumor Segmentation and Survival Days Prediction. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 131-141. https://doi.org/10.1007/978-3-030-46640-4_13
[64]
Sun, L., Zhang, S., Chen, H. and Luo, L. (2019) Brain Tumor Segmentation and Survival Prediction Using Multimodal MRI Scans with Deep Learning. FrontiersinNeuroscience, 13, Article ID: 468066. https://doi.org/10.3389/fnins.2019.00810
[65]
Kamnitsas, K., Ledig, C., Newcombe, V.F.J., Simpson, J.P., Kane, A.D., Menon, D.K., et al. (2017) Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation. MedicalImageAnalysis, 36, 61-78. https://doi.org/10.1016/j.media.2016.10.004
[66]
Kamnitsas, K., et al. (2017) Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation. http://arxiv.org/abs/1711.01468
[67]
Myronenko, A. (2019) 3D MRI Brain Tumor Segmentation Using Autoencoder Regularization. In: Crimi, A., et al., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 311-320. https://doi.org/10.1007/978-3-030-11726-9_28
[68]
Jiang, Z., Ding, C., Liu, M. and Tao, D. (2020) Two-Stage Cascaded U-Net: 1st Place Solution to Brats Challenge 2019 Segmentation Task. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 231-241. https://doi.org/10.1007/978-3-030-46640-4_22
[69]
Isensee, F., Jäger, P.F., Full, P.M., Vollmuth, P. and Maier-Hein, K.H. (2021) nnU-Net for Brain Tumor Segmentation. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 118-132. https://doi.org/10.1007/978-3-030-72087-2_11
[70]
Luu, H.M. and Park, S. (2022) Extending nn-UNet for Brain Tumor Segmentation. In: Crimi, A. and Bakas, S., Eds., Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Springer International Publishing, 173-186. https://doi.org/10.1007/978-3-031-09002-8_16
[71]
Zeineldin, R.A., Karar, M.E., Coburger, J., Wirtz, C.R. and Burgert, O. (2020) Deepseg: Deep Neural Network Framework for Automatic Brain Tumor Segmentation Using Magnetic Resonance FLAIR Images. InternationalJournalofComputerAssistedRadiologyandSurgery, 15, 909-920. https://doi.org/10.1007/s11548-020-02186-z
[72]
Ferreira, A., et al. (2024) How We Won BraTS 2023 Adult Glioma Challenge? Just Faking It! Enhanced Synthetic Data Augmentation and Model Ensemble for Brain Tumour Segmentation. https://arxiv.org/abs/2402.17317v2
[73]
Biswas, A., Md Abdullah Al, N., Imran, A., Sejuty, A.T., Fairooz, F., Puppala, S., et al. (2023) Generative Adversarial Networks for Data Augmentation. In: Zheng, B., et al., Eds., DataDrivenApproachesonMedicalImaging, Springer Nature, 159-177. https://doi.org/10.1007/978-3-031-47772-0_8
[74]
Types of GANs for Medical Imaging. https://www.researchgate.net/publication/386451967_Types_of_GANs_for_Medical_Imaging
[75]
MRI Cross-Modality Image-to-Image Translation with CycleGAN|by Aditya Kakde|Medium. https://adityakakde.medium.com/mri-cross-modality-image-to-image-translation-with-cyclegan-7720a4c786b2
[76]
Hu, Q., Wei, Y., Pang, J. and Liang, M. (2024) Unsupervised Domain Adaptation for Brain Structure Segmentation via Mutual Information Maximization Alignment. BiomedicalSignalProcessingandControl, 90, Article ID: 105784. https://doi.org/10.1016/j.bspc.2023.105784
[77]
Huang, L., Zhu, E., Chen, L., Wang, Z., Chai, S. and Zhang, B. (2022) A Transformer-Based Generative Adversarial Network for Brain Tumor Segmentation. FrontiersinNeuroscience, 16, Article ID: 1054948. https://doi.org/10.3389/fnins.2022.1054948
[78]
Sille, R., Choudhury, T., Sharma, A., Chauhan, P., Tomar, R. and Sharma, D. (2023) A Novel Generative Adversarial Network-Based Approach for Automated Brain Tumour Segmentation. Medicina, 59, Article No. 119. https://doi.org/10.3390/medicina59010119
[79]
Kumar, M.P., Hasmitha, D., Usha, B., Jyothsna, B. and Sravya, D. (2024) Brain Tumor Classification Using MobileNet. 2024 InternationalConferenceonIntegratedCircuitsandCommunicationSystems (ICICACS), Raichur, 23-24 February 2024, 1-7. https://doi.org/10.1109/icicacs60521.2024.10499117
[80]
Baig, M.D., Haq, H.B.U., Akram, W. and Awan, A.M. (2024) Brain Tumor Detection Enhanced with Transfer Learning Using SqueezeNet. DecisionMakingAdvances, 2, 129-141. https://doi.org/10.31181/dma21202432
