Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset

Cemal Yılmaz; Çağrı Suiçmez; Alihan Suiçmez; Mehmet Fatih Işık

doi:10.29002/asujse.1950042

TR EN

Figshare-Br35H-SARTAJ Veri Kümesinin Birleştirilmesiyle MS-GHOST-RAAE Kullanılarak Çok Sınıflı Beyin Tümörü MR Sınıflandırması

Abstract

Bu çalışma, Figshare, Br35H ve SARTAJ kaynaklarından oluşturulan birleşik bir MRI veri kümesi kullanılarak çok sınıflı beyin tümörü sınıflandırması için hibrit bir derin öğrenme çerçevesi önermektedir. Veri kümesi, klinik olarak önemli dört sınıfa ait 7023 MRI görüntüsünü içermektedir: gliom, menenjiom, tümörsüz ve hipofiz tümörü. Önerilen yaklaşımda, öncelikle tümörle ilgili görüntü bölgelerini iyileştirmek ve ilgisiz arka plan bilgilerini azaltmak için özel bir ön işleme hattı uygulanmaktadır. Daha sonra, derin özellik çıkarımı için Çok Ölçekli GHOST Artık Dikkat Otomatik Kodlayıcı (MS-GHOST-RAAE) kullanılmaktadır. Bu mimari, kompakt, kararlı ve ayırt edici özellik temsilleri elde etmek için çok ölçekli GHOST modüllerini, artık bağlantıları ve dikkat mekanizmalarını entegre eder. Çıkarılan özellikler daha sonra geleneksel makine öğrenmesi sınıflandırıcıları kullanılarak sınıflandırılır. Deneysel sonuçlar, önerilen hibrit çerçevenin birleşik veri kümesinde %98,75 doğruluk oranına ulaştığını ve toplam işlem süresinin 543 + 269,4571 s olduğunu göstermektedir. Bu bulgular, MS-GHOST-RAAE'nin heterojen MRI görüntülerinde güçlü sınıflandırma performansı sağladığını ve beyin tümörü sınıflandırması için etkili bir bilgisayar destekli karar verme yaklaşımı sunduğunu göstermektedir.

Keywords

Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset

Abstract

This study proposes a hybrid deep learning framework for multi-class brain tumor classification using a combined MRI dataset constructed from Figshare, Br35H, and SARTAJ sources. The dataset includes 7023 MRI images belonging to four clinically important classes: glioma, meningioma, no-tumor, and pituitary tumor. In the proposed approach, a dedicated preprocessing pipeline is first applied to enhance tumor-related image regions and reduce irrelevant background information. Then, the Multi-scale GHOST Residual Attention Autoencoder (MS-GHOST-RAAE) is used for deep feature extraction. This architecture integrates multi-scale GHOST modules, residual connections, and attention mechanisms to obtain compact, stable, and discriminative feature representations. The extracted features are subsequently classified using conventional machine learning classifiers. Experimental results show that the proposed hybrid framework achieves 98.75% accuracy on the combined dataset, with a total processing time of 543 + 269.4571 s. These findings indicate that MS-GHOST-RAAE provides strong classification performance on heterogeneous MRI images and offers an effective computer-aided decision-support approach for brain tumor classification.

Keywords

References

Abirami, S., & Prasanna Venkatesan, D. G. K. D. (2022). Deep learning and spark architecture based intelligent brain tumor MRI image severity classification. Biomedical Signal Processing and Control, 76, 103644. https://doi.org/10.1016/j.bspc.2022.103644
Arı, A., & Hanbay, D. (2018). Deep learning based brain tumor classification and detection system. Turkish Journal of Electrical Engineering and Computer Sciences, 26(5), 2275–2286. https://doi.org/10.3906/elk-1801-8
Operto, F. F., Pastorino, G. M. G., Stellato, M., Morcaldi, L., Vetri, L., Carotenuto, M., Viggiano, A., & Coppola, G. (2020). Facial emotion recognition in children and adolescents with specific learning disorder. Brain Sciences, 10(8), 473. https://doi.org/10.3390/brainsci10080473
Sajid, S., Hussain, S., & Sarwar, A. (2019). Brain tumor detection and segmentation in MR images using deep learning. Arabian Journal for Science and Engineering, 44(11), 9249–9261. https://doi.org/10.1007/s13369-019-03967-8
Cheng, J., Huang, W., Cao, S., Yang, R., Yang, W., Yun, Z., Wang, Z., & Feng, Q. (2015). Enhanced performance of brain tumor classification via tumor region augmentation and partition. PLOS ONE, 10(10), e0140381. https://doi.org/10.1371/journal.pone.0140381
Michael Mahesh, K., & Arokia Renjit, J. (2020). Multiclassifier for severity‐level categorization of glioma tumors using multimodal magnetic resonance imaging brain images. International Journal of Imaging Systems and Technology, 30(1), 234–251. https://doi.org/10.1002/ima.22357
Zhou, Y., Li, Z., Zhu, H., Chen, C., Gao, M., Xu, K., & Xu, J. (2019). Holistic brain tumor screening and classification based on denseNet and recurrent neural network. In A. Crimi, S. Bakas, H. Kuijf, F. Keyvan, M. Reyes, & T. van Walsum (Eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2018 (pp. 208–217). https://doi.org/10.1007/978-3-030-11723-8_21
El-Dahshan, E.-S. A., Mohsen, H. M., Revett, K., & Salem, A.-B. M. (2014). Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. Expert Systems with Applications, 41(11), 5526–5545. https://doi.org/10.1016/j.eswa.2014.01.021

Kanmani, P., & Marikkannu, P. (2018). MRI brain images classification: A multi-level threshold based region optimization technique. Journal of Medical Systems, 42(4), 62. https://doi.org/10.1007/s10916-018-0915-8
Oliva, J. B., Dubey, A., Zaheer, M., Póczos, B., Salakhutdinov, R., Xing, E. P., & Schneider, J. (2018). Transformation autoregressive networks. Proceedings of the 35th International Conference on Machine Learning, 3898–3907. https://proceedings.mlr.press/v80/oliva18a.html
Talo, M., Baloglu, U. B., Yıldırım, Ö., & Rajendra Acharya, U. (2019). Application of deep transfer learning for automated brain abnormality classification using MR images. Cognitive Systems Research, 54, 176–188. https://doi.org/10.1016/j.cogsys.2018.12.007
van den Oord, A., Kalchbrenner, N., Espeholt, L., kavukcuoglu, koray, Vinyals, O., & Graves, A. (2016). Conditional image generation with pixelCNN decoders. In D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, & R. Garnett (Eds.), Advances in Neural Information Processing Systems (Vol. 29). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2016/file/b1301141feffabac455e1f90a7de2054-Paper.pdf
Tiwari, A., Srivastava, S., & Pant, M. (2020). Brain tumor segmentation and classification from magnetic resonance images: Review of selected methods from 2014 to 2019. Pattern Recognition Letters, 131, 244–260. https://doi.org/10.1016/j.patrec.2019.11.020
Kuzman, B., Petković, B., Denić, N., Petković, D., Ćirković, B., Stojanović, J., & Milić, M. (2021). Estimation of optimal fertilizers for optimal crop yield by adaptive neuro fuzzy logic. Rhizosphere, 18, 100358. https://doi.org/10.1016/j.rhisph.2021.100358
Milić, M., Petković, B., Selmi, A., Petković, D., Jermsittiparsert, K., Radivojević, A., Milovancevic, M., Khan, A., Vidosavljević, S. T., Denić, N., & Kuzman, B. (2023). Computational evaluation of microalgae biomass conversion to biodiesel. Biomass Conversion and Biorefinery, 13(4), 3179–3186. https://doi.org/10.1007/s13399-021-01314-2
Milićević, V., Denić, N., Milićević, Z., Arsić, L., Spasić-Stojković, M., Petković, D., Stojanović, J., Krkic, M., Milovančević, N. S., & Jovanović, A. (2021). E-learning perspectives in higher education institutions. Technological Forecasting and Social Change, 166, 120618. https://doi.org/10.1016/j.techfore.2021.120618
Petković, D., Barjaktarovic, M., Milošević, S., Denić, N., Spasić, B., Stojanović, J., & Milovancevic, M. (2021). Neuro fuzzy estimation of the most influential parameters for Kusum biodiesel performance. Energy, 229, 120621. https://doi.org/10.1016/j.energy.2021.120621
Stojanović, J., Petkovic, D., Alarifi, I. M., Cao, Y., Denic, N., Ilic, J., Assilzadeh, H., Resic, S., Petkovic, B., Khan, A., & Milickovic, M. (2021). Application of distance learning in mathematics through adaptive neuro-fuzzy learning method. Computers & Electrical Engineering, 93, 107270. https://doi.org/10.1016/j.compeleceng.2021.107270
Alqazzaz, S., Sun, X., Yang, X., & Nokes, L. (2019). Automated brain tumor segmentation on multi-modal MR image using SegNet. Computational Visual Media, 5(2), 209–219. https://doi.org/10.1007/s41095-019-0139-y
Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017). Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Medical Image Analysis, 36, 61–78. https://doi.org/10.1016/j.media.2016.10.004
Srinivas, V., & Santhirani, C. (2020). Hybrid particle swarm optimization-deep neural network model for speaker recognition. Multimedia Research, 3(1), 1. https://doi.org/10.46253/j.mr.v3i1.a1
Kaldera, H. N. T. K., Gunasekara, S. R., & Dissanayake, M. B. (2019). Brain tumor classification and segmentation using faster R-CNN. 2019 Advances in Science and Engineering Technology International Conferences (ASET), 1–6. https://doi.org/10.1109/ICASET.2019.8714263
Bernal, J., Kushibar, K., Asfaw, D. S., Valverde, S., Oliver, A., Martí, R., & Lladó, X. (2019). Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: A review. Artificial Intelligence in Medicine, 95, 64–81. https://doi.org/10.1016/j.artmed.2018.08.008
Seetha, J., & Raja, S. S. (2018). Brain tumor classification using convolutional neural networks. Biomedical and Pharmacology Journal, 11(3), 1457–1461. https://doi.org/10.13005/bpj/1511
Ismail, M., Soliman, A., Ghazal, M., Switala, A. E., Gimel’farb, G., Barnes, G. N., Khalil, A., & El-Baz, A. (2017). A fast stochastic framework for automatic MR brain images segmentation. PLOS ONE, 12(11), e0187391. https://doi.org/10.1371/journal.pone.0187391
Tandel, G. S., Biswas, M., Kakde, O. G., Tiwari, A., Suri, H. S., Turk, M., Laird, J., Asare, C., Ankrah, A. A., Khanna, N. N., Madhusudhan, B. K., Saba, L., & Suri, J. S. (2019). A review on a deep learning perspective in brain cancer classification. Cancers, 11(1), 111. https://doi.org/10.3390/cancers11010111
Celik, M., & Inik, O. (2024). Development of hybrid models based on deep learning and optimized machine learning algorithms for brain tumor multi-classification. Expert Systems with Applications, 238, 122159. https://doi.org/10.1016/j.eswa.2023.122159
Abbas, Q., Fondón, I., & Rashid, M. (2011). Unsupervised skin lesions border detection via two-dimensional image analysis. Computer Methods and Programs in Biomedicine, 104(3), e1–e15. https://doi.org/10.1016/j.cmpb.2010.06.016
Abbas, Q., Garcia, I. F., Emre Celebi, M., & Ahmad, W. (2013). A feature‐preserving hair removal algorithm for dermoscopy images. Skin Research and Technology, 19(1), e27–e36. https://doi.org/10.1111/j.1600-0846.2011.00603.x
Bansal, P., Garg, R., & Soni, P. (2022). Detection of melanoma in dermoscopic images by integrating features extracted using handcrafted and deep learning models. Computers & Industrial Engineering, 168, 108060. https://doi.org/10.1016/j.cie.2022.108060
Chung, D. H., & Sapiro, G. (2000). Segmenting skin lesions with partial-differential-equations-based image processing algorithms. IEEE Transactions on Medical Imaging, 19(7), 763–767. https://doi.org/10.1109/42.875204
Ganster, H., Pinz, P., Rohrer, R., Wildling, E., Binder, M., & Kittler, H. (2001). Automated melanoma recognition. IEEE Transactions on Medical Imaging, 20(3), 233–239. https://doi.org/10.1109/42.918473
Lee, T., Ng, V., Gallagher, R., Coldman, A., & McLean, D. (1997). Dullrazor®: A software approach to hair removal from images. Computers in Biology and Medicine, 27(6), 533–543. https://doi.org/10.1016/S0010-4825(97)00020-6
Nguyen, N. H., Lee, T. K., & Atkins, M. S. (2010). Segmentation of light and dark hair in dermoscopic images: A hybrid approach using a universal kernel (B. M. Dawant & D. R. Haynor, Eds.; p. 76234N). https://doi.org/10.1117/12.844572
Xie, F., Li, Y., Meng, R., & Jiang, Z. (2015). No-reference hair occlusion assessment for dermoscopy images based on distribution feature. Computers in Biology and Medicine, 59, 106–115. https://doi.org/10.1016/j.compbiomed.2015.01.023
Awad, M., & Khanna, R. (2015). Efficient learning machines. Apress. https://doi.org/10.1007/978-1-4302-5990-9
Singhal, Y., Jain, A., Batra, S., Varshney, Y., & Rathi, M. (2018). Review of bagging and boosting classification performance on unbalanced binary classification. 2018 IEEE 8th International Advance Computing Conference (IACC), 338–343. https://doi.org/10.1109/IADCC.2018.8692138
Liu, H., Tian, H., Li, Y., & Zhang, L. (2015). Comparison of four Adaboost algorithm based artificial neural networks in wind speed predictions. Energy Conversion and Management, 92, 67–81. https://doi.org/10.1016/j.enconman.2014.12.053
Bhavsar, H., & Panchal, M. H. (2012). A review on support vector machine for data classification. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), 1(10), 185–189.
Dreiseitl, S., & Ohno-Machado, L. (2002). Logistic regression and artificial neural network classification models: A methodology review. Journal of Biomedical Informatics, 35(5–6), 352–359. https://doi.org/10.1016/S1532-0464(03)00034-0
Jiang, L., Wang, D., Cai, Z., & Yan, X. (2007). Survey of improving naive bayes for classification. In R. Alhajj, H. Gao, J. Li, X. Li, & O. R. Zaïane (Eds.), Advanced Data Mining and Applications (pp. 134–145). https://doi.org/10.1007/978-3-540-73871-8_14
Safavian, S. R., & Landgrebe, D. (1991). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3), 660–674. https://doi.org/10.1109/21.97458
Shafiul Azam, M., Habibullah, M., & Kabir Rana, H. (2020). Performance analysis of various machine learning approaches in stroke prediction. International Journal of Computer Applications, 175(21), 11–15. https://doi.org/10.5120/ijca2020920740
Jiang, L., Cai, Z., Wang, D., & Jiang, S. (2007). Survey of improving K-nearest-neighbor for classification. Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007), 679–683. https://doi.org/10.1109/FSKD.2007.552
Nickparvar, M. (n.d.). Brain Tumor MRI Dataset. https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset/versions/1(Accessed on 3rd March), 2021.

Details

Primary Language

English

Subjects

Biomedical Engineering (Other)

Journal Section

Research Article

Authors

Cemal Yılmaz
0000-0003-2053-052X
Türkiye

Çağrı Suiçmez ^*
0000-0002-9709-2276
Türkiye

Alihan Suiçmez
0000-0002-0502-6547
Türkiye

Mehmet Fatih Işık
0000-0003-3064-7131
Türkiye

Early Pub Date

June 4, 2026

Publication Date

-

Submission Date

May 12, 2026

Acceptance Date

May 20, 2026

Published in Issue

Year 2026 Number: Advanced Online Publication

DOI

https://doi.org/10.29002/asujse.1950042

IZ

https://izlik.org/JA85GU54YW

Cite

RIS / Bibtex

APA

Yılmaz, C., Suiçmez, Ç., Suiçmez, A., & Işık, M. F. (2026). Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset. Aksaray University Journal of Science and Engineering, Advanced Online Publication, 32-58. https://doi.org/10.29002/asujse.1950042

AMA

1.Yılmaz C, Suiçmez Ç, Suiçmez A, Işık MF. Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset. Aksaray J. Sci. Eng. 2026;(Advanced Online Publication):32-58. doi:10.29002/asujse.1950042

Chicago

Yılmaz, Cemal, Çağrı Suiçmez, Alihan Suiçmez, and Mehmet Fatih Işık. 2026. “Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset”. Aksaray University Journal of Science and Engineering, no. Advanced Online Publication: 32-58. https://doi.org/10.29002/asujse.1950042.

EndNote

Yılmaz C, Suiçmez Ç, Suiçmez A, Işık MF (June 1, 2026) Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset. Aksaray University Journal of Science and Engineering Advanced Online Publication 32–58.

IEEE

[1]C. Yılmaz, Ç. Suiçmez, A. Suiçmez, and M. F. Işık, “Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset”, Aksaray J. Sci. Eng., no. Advanced Online Publication, pp. 32–58, June 2026, doi: 10.29002/asujse.1950042.

ISNAD

Yılmaz, Cemal - Suiçmez, Çağrı - Suiçmez, Alihan - Işık, Mehmet Fatih. “Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset”. Aksaray University Journal of Science and Engineering. Advanced Online Publication (June 1, 2026): 32-58. https://doi.org/10.29002/asujse.1950042.

JAMA

1.Yılmaz C, Suiçmez Ç, Suiçmez A, Işık MF. Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset. Aksaray J. Sci. Eng. 2026;:32–58.

MLA

Yılmaz, Cemal, et al. “Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset”. Aksaray University Journal of Science and Engineering, no. Advanced Online Publication, June 2026, pp. 32-58, doi:10.29002/asujse.1950042.

Vancouver

1.Cemal Yılmaz, Çağrı Suiçmez, Alihan Suiçmez, Mehmet Fatih Işık. Multi-Class Brain Tumor MRI Classification Using MS-GHOST-RAAE on a Combined Figshare-Br35H-SARTAJ Dataset. Aksaray J. Sci. Eng. 2026 Jun. 1;(Advanced Online Publication):32-58. doi:10.29002/asujse.1950042