Skip to main content
SpringerLink
Log in

An explainable brain tumor detection and classification model using deep learning and layer-wise relevance propagation

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The Brain tumor is the most common and devastating problem nowadays. Many people die every day as a result of a tumor’s late detection, and these lives could have been saved if the tumor had been detected at an earlier stage. The early diagnosis of the tumor is very challenging due to its complex structure and uncontrollable growth. With the advent of Convolution Neural Network (CNN) and pre-trained models, researchers have put forth many tumor detection models over the past few decades. We have observed most of the solutions only focus on accuracy, and there is a significant lack of explanation and interpretability of the model. This work proposed an explainable brain tumor detection and classification model by using pre-trained models. The suggested model consists of four phases. In the first phase, a conditional generative adversarial network (cGAN) is used to generate the synthesis MRI images of distinct classes to cope with the data unbalancing and overfitting. In the second phase brain tumor is detected by using different pre-trained models like MobileNet, InceptionResNet, EfficientNet and VGGNet, and if the tumor is detected, it is classified in the third phase by using different pre-trained models. In the last phase, layer-wise relevance propagation (LRP) is used to Interpret the model outcome. The training, validation, and testing accuracy for the tumor detection model are 99.6%, 99.2%, and 99.0%, respectively, experiment findings show that InceptionResNetV2 pre-trained model performs better as compared to another pre-trained model. However, When it came to tumor classification, EfficientNet-B0 performed significantly better than the other models. With accuracy rates of 99.3%, 99.2%, and 99.0% during training, validation, and testing, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Algorithm 1
Algorithm 2
Fig. 9
Fig. 10
Fig. 11
Algorithm 3
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Similar content being viewed by others

Data availability

Data used in this work is publicly available.

References

  1. Abu-Srhan A et al (2022) The effect of loss function on conditional generative adversarial network. J King Saud Univ Comput Inf Sci 34(9):6977–6988. https://doi.org/10.1016/j.jksuci.2022.02.018

  2. Díaz-Pernas FJ et al (2021) A deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network. Healthcare 153(9):1–14

    Google Scholar 

  3. Muhammad K et al (2021) Deep learning for multigrade brain tumor classification in smart healthcare systems: a prospective survey. IEEE Trans Neural Netw Learn Syst 32(2):507–522

    Article  PubMed  Google Scholar 

  4. Gupta RK et al (2022) Brain tumor detection and classification using cycle generative adversarial networks. Interdiscip Sci Comput Life Sci 17(01):1–17

    Google Scholar 

  5. Rudresh D et al (2021) A survey on brain tumor detection using machine learning. In: Proceeding of international conference on forensics, analytics, big data, security (FABS), pp 1–6. https://doi.org/10.1109/FABS52071.2021.9702583

  6. https://doi.org/10.1109/FABS52071.2021.9702583

  7. Nikhlesh Pathik a et al (2022) AI enabled accident detection and alert system using IoT and deep learning for smart cities. Sustain 14:1–24

  8. Banerjee S et al (2017) Brain tumor detection and classification from Multi-Channel MRIs using deep learning and transfer learning. CIS- IEEE report, pp 1–9. https://cis.ieee.org/images/files/Documents/research-grants/Report_SubhashisBanerjee.pdf

  9. Gupta RK et al (2022) COVID-19 Lesion segmentation and classification of lung CTs using GMM-based hidden markov random field and resnet 18. Int J Fuzzy Syst Appl 11(2):1–21

    MathSciNet  CAS  Google Scholar 

  10. Sun L et al (2021) Review and potential for artificial intelligence in healthcare. Int J Syst Assur Eng Manag 13(1):54–62. https://doi.org/10.1007/s13198-021-01221-9

  11. Gupta RK et al (2022) A deep neural network for detecting coronavirus disease using chest X-ray images. Int J Healthcare Inf Syst Inf 17(2):1–27. https://doi.org/10.4018/IJHISI.20220401.oa1

  12. Yang G et al (2022) Unbox the black-box for the medical explainable AI via multi-modal and multi-Centre data fusion: a mini-review, two showcases and beyond. Inf Fus 77:29–52

    Article  Google Scholar 

  13. Bas HM et al (2022) Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal 79. https://doi.org/10.1016/j.media.2022.102470

  14. Amin J et al (2021) Brain tumor detection and classification using machine learning: a comprehensive survey. Complex Intell Syst. https://doi.org/10.1007/s40747-021-00563-y

  15. Lather M, Singh P (2020) Investigating brain tumor segmentation and detection techniques. Proced Comput Sci 167:121–130

    Article  Google Scholar 

  16. Saba T et al (2020) Brain tumor detection using fusion of hand crafted and deep learning features. Cogn Syst Res 59:221–230

    Article  Google Scholar 

  17. Anand Kumar KS, Prasad AY, Metan J (2022) A hybrid deep CNN-Cov-19-res-net transfer learning architype for an enhanced brain tumor detection and classification scheme in medical image processing. Biomed Signal Process Control 76. https://doi.org/10.1016/j.bspc.2022.103631

  18. Devkota B et al (2018) Image segmentation for early-stage brain tumor detection using mathematical morphological reconstruction. Proced Comput Sci 125:115–123

    Article  Google Scholar 

  19. Dvorak P et al (2015) Automated multi-contrast brain pathological area extraction from 2D MR images. J Appl Res Technol 13(1):58–69

    Article  Google Scholar 

  20. Wessam M (2022) Salama and Ahmed Shokry, “a novel framework for brain tumor detection based on convolutional variational generative models”. Multimed Tools Appl 81:16441–16454

    Article  Google Scholar 

  21. Hossain T et al (2019) Brain tumor detection using convolutional neural network, In: the proc. of 1st IEEE International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), pp 1–7. https://doi.org/10.1109/ICASERT.2019.8934561

  22. More SS et al (2021) Convolutional neural network based brain tumor detection. 5th IEEE international conference on intelligent computing and control systems (ICICCS) pp 1532–1538. https://doi.org/10.1109/ICICCS51141.2021.9432164

  23. Gaur L et al (2022) Explanation-driven deep learning model for prediction of brain tumor status using MRI image data. Front Genet. https://doi.org/10.3389/fgene.2022.822666

  24. Ma Y et al (2021) ML-CGAN: conditional generative adversarial network with a Meta-learner structure for high-quality image generation with few training data. Cogn Comput 13:418–430

    Article  Google Scholar 

  25. Bach S et al (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One pp 1–46. https://doi.org/10.1371/journal.pone.0130140

  26. Available at http://heatmapping.org/. Access: 10/05/2022

  27. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceeding in the International Conference on Learning Representations (ICLR). https://www.researchgate.net/publication/265385906_Very_Deep_Convolutional_Networks_for_Large-Scale_Image_Recognition

  28. Howard AG et al (2017) MobileNets: efficient convolutional neural networks for Mobile vision applications, arXiv, pp 1–9.  https://doi.org/10.48550/arXiv.1704.04861

  29. Phiphiphatphaisit S, Surinta O (2020) Food image classification with improved MobileNet architecture and data augmentation. In: Proc. the 3rd international conference on information science and systems, pp 51–56. https://www.researchgate.net/publication/340470168_Food_Image_Classification_with_Improved_MobileNet_Architecture_and_Data_Augmentation

  30. Szegedy C et al (2017) Inception-v4, inception-ResNet and the impact of residual connections on learning (vol 31, issue 1). In: proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp 4278–4284. https://doi.org/10.1609/aaai.v31i1.11231

  31. Tan M, Le QV (2019) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks arxiv, pp 1–11. https://doi.org/10.48550/arXiv.1905.11946

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science & Engineering, Madhyanchal Professional University, Bhopal, 462044, India

    Saurabh Mandloi & Mohd Zuber

  2. Department of Computer Science & Engineering, Pandit Deendayal Energy University, Gandhinagar, 382007, India

    Rajeev Kumar Gupta

Authors
  1. Saurabh Mandloi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohd Zuber
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rajeev Kumar Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rajeev Kumar Gupta.

Ethics declarations

Conflict of interest

No conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mandloi, S., Zuber, M. & Gupta, R.K. An explainable brain tumor detection and classification model using deep learning and layer-wise relevance propagation. Multimed Tools Appl 83, 33753–33783 (2024). https://doi.org/10.1007/s11042-023-16708-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16708-9

Keywords

Search

Navigation