Segmentation of Brain Tumors from MRI Images Using Convolutional Autoencoder
Source abstract
Abstract
The use of machine learning algorithms and modern technologies for automatic segmentation of brain tissue increases in everyday clinical diagnostics. One of the most commonly used machine learning algorithms for image processing is convolutional neural networks. We present a new convolutional neural autoencoder for brain tumor segmentation based on semantic segmentation. The developed architecture is small, and it is tested on the largest online image database. The dataset consists of 3064 T1-weighted contrast-enhanced magnetic resonance images. The proposed architecture’s performance is tested using a combination of two different data division methods, and two different evaluation methods, and by training the network with the original and augmented dataset. Using one of these data division methods, the network’s generalization ability in medical diagnostics was also tested. The best results were obtained for record-wise data division, training the network with the augmented dataset. The average accuracy classification of pixels is 99.23% and 99.28% for 5-fold cross-validation and one test, respectively, and the average dice coefficient is 71.68% and 72.87%. Considering the achieved performance results, execution speed, and subject generalization ability, the developed network has great potential for being a decision support system in everyday clinical practice.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Brain Tumor Detection and Classification · Advanced Neural Network Applications · Medical Imaging and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Innovation Center, School of Electrical Engineering, University of Belgrade, 11120 Belgrade, Serbia
School of Electrical Engineering, University of Belgrade, 11120 Belgrade, Serbia
References (37)
Show source-provided references
1. Fr-Mrinet: A Deep Convolutional Encoder-Decoder for Brain Tumor Segmentation with Relu-RGB and Sliding-Window
2. Cheng, J., Huang, W., Cao, S., Yang, R., Yang, W., Yun, Z., Wang, Z., and Feng, Q. (2015). Enhanced Performance of Brain Tumor Classification via Tumor Region Augmentation and Partition. PLoS ONE, 10.10.1371/journal.pone.0140381 ↗
3. Badža, M.M., and Barjaktarović, M.Č. (2020). Classification of Brain Tumors from MRI Images Using a Convolutional Neural Network. Appl. Sci., 10.10.3390/app10061999 ↗
4. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.10.1007/978-3-319-24574-4_28 ↗
5. (2021, March 11). Multimodal Brain Tumor Segmentation Challenge BRATS. Available online: http://braintumorsegmentation.org/.
6. Jiang, Z., Ding, C., Liu, M., and Tao, D. (2019). Two-Stage Cascaded u-Net: 1st Place Solution to Brats Challenge 2019 Segmentation Task. International MICCAI Brainlesion Workshop, Springer.10.1007/978-3-030-46640-4_22 ↗
7. Fully Automatic Brain Tumor Segmentation Using End-to-End Incremental Deep Neural Networks in MRI Images10.1016/j.cmpb.2018.09.007 ↗
8. Deep Learning with Mixed Supervision for Brain Tumor Segmentation10.1117/1.JMI.6.3.034002 ↗
9. Big Data Analysis for Brain Tumor Detection: Deep Convolutional Neural Networks10.1016/j.future.2018.04.065 ↗
10. Amin, J., Sharif, M., Raza, M., and Yasmin, M. (2018). Detection of Brain Tumor Based on Features Fusion and Machine Learning. J. Ambient. Intell. Humaniz. Comput., 1–17.10.1007/s12652-018-1092-9 ↗
11. Chen, X., Nguyen, B.P., Chui, C.-K., and Ong, S.-H. (2016, January 9–12). Automated Brain Tumor Segmentation Using Kernel Dictionary Learning and Superpixel-Level Features. Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary.
12. A Package-SFERCB-“Segmentation, Feature Extraction, Reduction and Classification Analysis by Both SVM and ANN for Brain Tumors”10.1016/j.asoc.2016.05.020 ↗
13. MRI Brain Classification Using Texture Features, Fuzzy Weighting and Support Vector Machine10.2528/PIERB13052805 ↗
14. Sundararaj, G.K., and Balamurugan, V. (2014, January 27–29). An Expert System Based on Texture Features and Decision Tree Classifier for Diagnosis of Tumor in Brain MR Images. Proceedings of the 2014 International Conference on Contemporary Computing and Informatics (IC3I), Mysore, India.10.1109/IC3I.2014.7019690 ↗
15. Tripathi, P.C., and Bag, S. (2020). Non-Invasively Grading of Brain Tumor Through Noise Robust Textural and Intensity Based Features. Advances in Intelligent Systems and Computing, Springer.10.1007/978-981-13-9042-5_45 ↗
16. Chouksey, M., Jha, R.K., and Sharma, R. (2020). A Fast Technique for Image Segmentation Based on Two Meta-Heuristic Algorithms. Multimed. Tools Appl., 1–53.10.1007/s11042-019-08138-3 ↗
17. Feature Selection Based on Hybrid Optimization for Magnetic Resonance Imaging Brain Tumor Classification and Segmentation
18. Phaye, S.S.R., Sikka, A., Dhall, A., and Bathula, D. (2018). Dense and Diverse Capsule Networks: Making the Capsules Learn Better. arXiv.
19. Pashaei, A., Sajedi, H., and Jazayeri, N. (2018, January 25–26). Brain Tumor Classification via Convolutional Neural Network and Extreme Learning Machines. Proceedings of the 2018 8th International Conference on Computer and Knowledge Engineering, ICCKE 2018, Mashhad, Iran.10.1109/ICCKE.2018.8566571 ↗
20. Multi-Classification of Brain Tumor Images Using Deep Neural Network10.1109/ACCESS.2019.2919122 ↗
21. Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas10.3174/ajnr.A5667 ↗
22. ScienceDirect Classification Using Deep Learning Neural Networks for Brain Tumors10.1016/j.fcij.2017.12.001 ↗
23. Deep Autoencoder-Decoder Framework for Semantic Segmentation of Brain Tumor
24. Pereira, S., Meier, R., Alves, V., Reyes, M., and Silva, C.A. (2018). Automatic Brain Tumor Grading from MRI Data Using Convolutional Neural Networks and Quality Assessment. Understanding and Interpreting Machine Learning in Medical Image Computing Applications, Springer.10.1007/978-3-030-02628-8_12 ↗
25. Cheng, J. (2021, March 11). Brain Tumor Dataset. Available online: https://figshare.com/articles/brain_tumor_dataset/1512427.
26. Performance Evaluation of Classification Algorithms by K-Fold and Leave-One-out Cross Validation10.1016/j.patcog.2015.03.009 ↗
27. The Need to Approximate the Use-Case in Clinical Machine Learning10.1093/gigascience/gix019 ↗
28. Using and Understanding Cross-Validation Strategies. Perspectives on Saeb et al10.1093/gigascience/gix020 ↗
29. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the Difficulty of Training Deep Feedforward Neural Networks. Proceedings of the thirteenth international conference on artificial intelligence and statistics, Sardinia, Italy.
30. Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis10.1038/s41598-020-64803-w ↗
31. He, H., and Ma, Y. (2013). Imbalanced Learning, Wiley.10.1002/9781118646106 ↗
32. A. Learning from Imbalanced Data10.1109/TKDE.2008.239 ↗
33. Kaldera, H.N.T.K., Gunasekara, S.R., and Dissanayake, M.B. (April, January 26). Brain Tumor Classification and Segmentation Using Faster R-CNN. Proceedings of the 2019 Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates.10.1109/ICASET.2019.8714263 ↗
34. Toward Improving Safety in Neurosurgery with an Active Handheld Instrument10.1007/s10439-018-2091-x ↗
35. Robust Biometric Recognition from Palm Depth Images for Gloved Hands10.1109/THMS.2015.2453203 ↗
36. LIBSVM: A Library for Support Vector Machines10.1145/1961189.1961199 ↗
37. Bagging Predictors10.1007/BF00058655 ↗