Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

This research investigates the impact of pruning on reducing the computational complexity of a five-layered Convolutional Neural Network (CNN) designed for classifying MRI brain tumors. The study focuses on enhancing the efficiency of the model by removing less important weights and neurons through pruning.

Objective

This research aims to analyze the impact of pruning on the computational complexity of a CNN for MRI brain tumor classification, identifying optimal pruning percentages to balance reduced complexity with acceptable classification performance.

Methods

The proposed CNN model is implemented for the classification of MRI brain tumors. To reduce time complexity, weights and neurons of the trained model are pruned systematically, ranging from 0 to 99 percent. The corresponding accuracies for each pruning percentage are recorded to assess the trade-off between model complexity and classification performance.

Results

The analysis reveals that the model's weights can be pruned up to 70 percent while maintaining acceptable accuracy. Similarly, neurons in the model can be pruned up to 10 percent without significantly compromising accuracy.

Conclusion

This research highlights the successful application of pruning techniques to reduce the computational complexity of a CNN model for MRI brain tumor classification. The findings suggest that judicious pruning of weights and neurons can lead to a significant improvement in inference time without compromising accuracy.

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056303076240614113525
2024-01-01
2025-06-18

  • From This Site

    /content/journals/cmir/10.2174/0115734056303076240614113525
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. BlalockD. OrtizJ.J.G. FrankleJ. GuttagJ. What is the state of neural network pruning?arXiv preprint:2003.03033, 2020.
     [Google Scholar]
  2. HanS. PoolJ. TranJ. DallyW.J. Learning both weights and connections for efficient neural networksarXiv preprint:1506.02626, 2015.
     [Google Scholar]
  3. MolchanovP. TyreeS. KarrasT. AilaT. KautzJ. Pruning convolutional neural networks for resource efficient inferencearXiv preprint:1611.06440, 2016.
     [Google Scholar]
  4. BabaeizadehM. SmaragdisP. CampbellR.H. 2016Noiseout: A simple way to prune neural networksarXiv preprint:1611.06211, 2016.
     [Google Scholar]
  5. ZhuW. FangL. YeX. MedaniM. Escorcia-GutierrezJ. IDRM: Brain tumor image segmentation with boosted RIME optimization.Comput. Biol. Med.202316610755110.1016/j.compbiomed.2023.10755137832284
     [Google Scholar]
  6. QuG. LuB. ShiJ. WangZ. YuanY. XiaY. PanZ. LinY. Motion-artifact-augmented pseudo-label network for semi-supervised brain tumor segmentation.Phys. Med. Biol.202469505502310.1088/1361‑6560/ad263438406849
     [Google Scholar]
  7. ChenG. RuJ. ZhouY. RekikI. PanZ. LiuX. LinY. LuB. ShiJ. MTANS: multi-scale mean teacher combined adversarial network with shape-aware embedding for semi-supervised brain lesion segmentation.Neuroimage202124411856810.1016/j.neuroimage.2021.11856834508895
     [Google Scholar]
  8. ChenG. LiQ. ShiF. RekikI. PanZ. RFDCR: Automated brain lesion segmentation using cascaded random forests with dense conditional random fields.Neuroimage202021111662010.1016/j.neuroimage.2020.11662032057997
     [Google Scholar]
  9. XuY. HuangH. HeidariA.A. GuiW. YeX. ChenY. ChenH. PanZ. MFeature: Towards high performance evolutionary tools for feature selection.Expert Syst. Appl.202118611565510.1016/j.eswa.2021.115655
     [Google Scholar]
  10. KhanY.F. KaushikB. ChowdharyC.L. SrivastavaG. Ensemble model for diagnostic classification of alzheimer’s disease based on brain anatomical magnetic resonance imaging.Diagnostics20221212319310.3390/diagnostics1212319336553199
     [Google Scholar]
  11. DasT.K. ChowdharyC.L. GaoX.Z. Chest X-ray investigation: a convolutional neural network approach.J. Biomim. Biomater. Biomed. Eng.202045577010.4028/www.scientific.net/JBBBE.45.57
     [Google Scholar]
  12. KalaiselviT. PadmapriyaS.T. SriramakrishnanP. SomasundaramK. Deriving tumor detection models using convolutional neural networks from MRI of human brain scans.Int. J. Inf. Technol.202012240340810.1007/s41870‑020‑00438‑4
     [Google Scholar]
  13. ChaudharyA. BhattacharjeeV. An efficient method for brain tumor detection and categorization using MRI images by K-means clustering and DWT.Int. J. Inf. Technol.202012114114810.1007/s41870‑018‑0255‑4
     [Google Scholar]
  14. SaraswatA. SharmaN. Salvaging tumor from T1-weighted CE-MR images using automatic segmentation techniques.Int. J. Inf. Technol.20221441869187410.1007/s41870‑022‑00953‑6
     [Google Scholar]
  15. MohsenH. El-DahshanE.S.A. El-HorbatyE.S.M. SalemA.B.M. Classification using deep learning neural networks for brain tumors.Future Comput. Inform. J.201831687110.1016/j.fcij.2017.12.001
     [Google Scholar]
  16. KalaiselviT. SriramakrishnanP. SomasundaramK. Brain abnormality detection from MRI of human head scans using the bilateral symmetry property and histogram similarity measures.2016 International Computer Science and Engineering Conference (ICSEC)14-17 December 2016, Chiang Mai, Thailand, pp. 1-6.201610.1109/ICSEC.2016.7859867
     [Google Scholar]
  17. KamnitsasK. LedigC. NewcombeV.F.J. SimpsonJ.P. KaneA.D. MenonD.K. RueckertD. GlockerB. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation.Med. Image Anal.201736617810.1016/j.media.2016.10.00427865153
     [Google Scholar]
  18. RazzakM. I. NazS. ZaibA. Deep Learning for Medical Image Processing: Overview, Challenges and the Future.Classification in BioApps.Springer2018
     [Google Scholar]
  19. KleesiekJ. UrbanG. HubertA. SchwarzD. Maier-HeinK. BendszusM. BillerA. Deep MRI brain extraction: A 3D convolutional neural network for skull stripping.Neuroimage201612946046910.1016/j.neuroimage.2016.01.02426808333
     [Google Scholar]
  20. PereiraS. PintoA. AlvesV. SilvaC.A. Brain tumor segmentation using convolutional neural networks in MRI images.IEEE Trans. Med. Imaging20163551240125110.1109/TMI.2016.253846526960222
     [Google Scholar]
  21. ZhaoL. JiaK. Multiscale CNNs for brain tumor segmentation and diagnosis.Comput. Math. Methods Med.201620161710.1155/2016/835629427069501
     [Google Scholar]
  22. GespergerJ. LichteneggerA. RoetzerT. SalasM. EuguiP. HarperD.J. MerkleC.W. AugustinM. KieselB. MerceaP.A. WidhalmG. BaumannB. WoehrerA. Improved diagnostic imaging of brain tumors by multimodal microscopy and deep learning.Cancers2020127180610.3390/cancers1207180632640583
     [Google Scholar]
  23. LatifG. IskandarD.N.F.A. AlghazoJ. ButtM.M. Brain MR image classification for glioma tumor detection using deep convolutional neural network features.Curr. Med. Imaging2021171566310.2174/157340561666620031112242932160848
     [Google Scholar]
  24. LatifG. Ben BrahimG. IskandarD.N.F.A. BasharA. AlghazoJ. Glioma Tumors’ classification using deep-neural-network-based features with SVM classifier.Diagnostics2022124101810.3390/diagnostics1204101835454066
     [Google Scholar]
  25. AhujaS. PanigrahiB.K. GandhiT.K. Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques.Mach. Learn. Appl.2022710021210.1016/j.mlwa.2021.100212
     [Google Scholar]
  26. RendaA. FrankleJ. CarbinM. Comparing rewinding and fine-tuning in neural network pruning.arXiv preprint:2003.02389, 2020.
     [Google Scholar]
  27. WangC. ZhangG. GrosseR. Picking winning tickets before training by preserving gradient flow.arXiv preprint arXiv:2002.07376, 2020.
     [Google Scholar]
  28. TanakaH. KuninD. YaminsD.L. GanguliS. Pruning neural networks without any data by iteratively conserving synaptic flow.arXiv preprint arXiv:2006.05467, 2020.
     [Google Scholar]
  29. GaleT. ElsenE. HookerS. The state of sparsity in deep neural networks.arXiv preprint:1902.09574, 2019.
     [Google Scholar]
  30. MolchanovP. MallyaA. TyreeS. FrosioI. KautzJ. Importance estimation for neural network pruning. arXiv:1906.10771, 201910.48550/arXiv.1906.10771
     [Google Scholar]
  31. LeeN. AjanthanT. GouldS. TorrP.H. A signal propagation perspective for pruning neural networks at initialization.arXiv preprint:1906.06307, 2019.
     [Google Scholar]
  32. MostafaH. WangX. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization.Proceedings of the 36 th International Conference on Machine Learning2019, Long Beach, California, pp.1-10.
     [Google Scholar]
  33. DettmersT. ZettlemoyerL. Sparse networks from scratch: Faster training without losing performance.arXiv preprint arXiv:1907.04840, 2019.
     [Google Scholar]
  34. EvciU. GaleT. MenickJ. CastroP.S. ElsenE. Rigging the lottery: Making all tickets winners.Proceedings of the 37 th International Conference on Machine Learning.2020, Vienna, Austria, pp. 1-11.
     [Google Scholar]
  35. HeY. KangG. DongX. FuY. YangY. Soft filter pruning for accelerating deep convolutional neural networksProceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18).201810.24963/ijcai.2018/309
     [Google Scholar]
  36. LeeN. AjanthanT. TorrP.H. Snip: Single-shot network pruning based on connection sensitivity.arXiv preprint:1810.02340, 2018.
     [Google Scholar]
  37. FrankleJ. CarbinM. The lottery ticket hypothesis: Finding sparse, trainable neural networks.arXiv preprint arXiv:1803.03635, 2018.
     [Google Scholar]
  38. MocanuD.C. MocanuE. StoneP. NguyenP.H. GibescuM. LiottaA. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.Nat. Commun.201891238310.1038/s41467‑018‑04316‑329921910
     [Google Scholar]
  39. LiuZ. LiJ. ShenZ. HuangG. YanS. ZhangC. 2017Learning efficient convolutional networks through network slimming.Proceedings of the IEEE international conference on computer vision.2736274410.1109/ICCV.2017.298
     [Google Scholar]
  40. LiH. KadavA. DurdanovicI. SametH. GrafH.P. Pruning filters for efficient convnets.arXiv preprint arXiv:1608.08710, 2016.
     [Google Scholar]
  41. ChoudharyT. MishraV. GoswamiA. SarangapaniJ. Heuristic-based automatic pruning of deep neural networks.Neural Comput. Appl.20223464889490310.1007/s00521‑021‑06679‑z
     [Google Scholar]
  42. VaderaS. AmeenS. Methods for pruning deep neural networks.IEEE Access202210632806330010.1109/ACCESS.2022.3182659
     [Google Scholar]
  43. BraTS2013 Challenge, MRI brain tumor database.Available from:https://www.smir.ch/BRATS/Start2013
    [Google Scholar]
  44. MenzeB.H. JakabA. BauerS. Kalpathy-CramerJ. FarahaniK. KirbyJ. BurrenY. PorzN. SlotboomJ. WiestR. LancziL. GerstnerE. WeberM.A. ArbelT. AvantsB.B. AyacheN. BuendiaP. CollinsD.L. CordierN. CorsoJ.J. CriminisiA. DasT. DelingetteH. DemiralpC. DurstC.R. DojatM. DoyleS. FestaJ. ForbesF. GeremiaE. GlockerB. GollandP. GuoX. HamamciA. IftekharuddinK.M. JenaR. JohnN.M. KonukogluE. LashkariD. MarizJ.A. MeierR. PereiraS. PrecupD. PriceS.J. RavivT.R. RezaS.M.S. RyanM. SarikayaD. SchwartzL. ShinH.C. ShottonJ. SilvaC.A. SousaN. SubbannaN.K. SzekelyG. TaylorT.J. ThomasO.M. TustisonN.J. UnalG. VasseurF. WintermarkM. YeD.H. ZhaoL. ZhaoB. ZikicD. PrastawaM. ReyesM. Van LeemputK. The multimodal brain tumor image segmentation benchmark (BRATS).IEEE Trans. Med. Imaging201534101993202410.1109/TMI.2014.237769425494501
     [Google Scholar]
  45. KalaiselviT. PadmapriyaT. SriramakrishnanP. PriyadharshiniV. Development of automatic glioma brain tumor detection system using deep convolutional neural networks.Int. J. Imaging Syst. Technol.202030492693810.1002/ima.22433
     [Google Scholar]
  46. FernandesF.E. YenG.G. Automatic searching and pruning of deep neural networks for medical imaging diagnostic.IEEE Trans. Neural Netw. Learn. Syst.202132125664567410.1109/TNNLS.2020.302730833048758
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056303076240614113525
Loading
Improving Efficiency of Brain Tumor Classification Models Using Pruning Techniques
Curr. Med. Imaging 20, e15734056303076 (2024); https://doi.org/10.2174/0115734056303076240614113525
/content/journals/cmir/10.2174/0115734056303076240614113525
/content/journals/cmir/10.2174/0115734056303076240614113525
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Brain tumor; Classification; Convolutional neural networks (CNN); MRI; Neural network; Pruning

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test