Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Computer - Aided Drug Design
  4. Volume 21, Issue 1
  5. Article
Volume 21, Issue 1
  • ISSN: 1573-4099
  • E-ISSN: 1875-6697

Abstract

Background

Diagnosis and treatment planning play a very vital role in improving the survival of oncological patients. However, there is high variability in the shape, size, and structure of the tumor, making automatic segmentation difficult. The automatic and accurate detection and segmentation methods for brain tumors are proposed in this paper.

Methods

A modified ResNet50 model was used for tumor detection, and a ResUNetmodel-based convolutional neural network for segmentation is proposed in this paper. The detection and segmentation were performed on the same dataset consisting of pre-contrast, FLAIR, and post-contrast MRI images of 110 patients collected from the cancer imaging archive. Due to the use of residual networks, the authors observed improvement in evaluation parameters, such as accuracy for tumor detection and dice similarity coefficient for tumor segmentation.

Results

The accuracy of tumor detection and dice similarity coefficient achieved by the segmentation model were 96.77% and 0.893, respectively, for the TCIA dataset. The results were compared based on manual segmentation and existing segmentation techniques. The tumor mask was also individually compared to the ground truth using the SSIM value. The proposed detection and segmentation models were validated on BraTS2015 and BraTS2017 datasets, and the results were consensus.

Conclusion

The use of residual networks in both the detection and the segmentation model resulted in improved accuracy and DSC score. DSC score was increased by 5.9% compared to the UNet model, and the accuracy of the model was increased from 92% to 96.77% for the test set.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cad/10.2174/1573409920666230816090626
2024-08-06
2025-01-18

  • From This Site

    /content/journals/cad/10.2174/1573409920666230816090626
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. DograJ. JainS. SoodM. Gradient‐based kernel selection technique for tumour detection and extraction of medical images using graph cut.IET Image Process.2020141849310.1049/iet‑ipr.2018.6615
     [Google Scholar]
  2. RouseC. GittlemanH. OstromQ.T. KruchkoC. Barnholtz-SloanJ.S. Years of potential life lost for brain and CNS tumors relative to other cancers in adults in the United States, 2010.Neuro-oncol.2016181707710.1093/neuonc/nov249 26459813
     [Google Scholar]
  3. Brain tumor facts.Available from: https://braintumor.org/brain-tumors/about-brain-tumors/brain-tumo r-facts/ 2022
  4. DograJ. JainS. SharmaA. KumarR. SoodM. Brain tumor detection from MR images employing fuzzy graph cut technique.Recent Advances in Computer Science and Communications202013336236910.2174/2213275912666181207152633
     [Google Scholar]
  5. VijanA. DubeyP. JainS. Comparative analysis of various image fusion techniques for Brain Magnetic Resonance Images.Procedia Computer Science202016741342210.1016/j.procs.2020.03.250
     [Google Scholar]
  6. Jin Liu Min Li Jianxin Wang Fangxiang Wu Tianming Liu Yi Pan, A survey of MRI-based brain tumor segmentation methods.Tsinghua Sci. Technol.201419657859510.1109/TST.2014.6961028
     [Google Scholar]
  7. LiangZ-P. LauterburP.C. Principles of magnetic resonance imaging: A signal processing perspectiveThe institute of electrical and electronics engineers press2000
     [Google Scholar]
  8. DrevelegasA. PapanikolaouN. Imaging modalities in brain tumors.Imaging of Brain Tumors with Histological Correlations.Springer2011133310.1007/978‑3‑540‑87650‑2_2
     [Google Scholar]
  9. DograJ. JainS. SoodM. Glioma classification of MRI brain tumor employing machine learning.Int. J. Innov. Technol. Explor. Eng.20198826762682[IJITEE].
     [Google Scholar]
  10. MenzeB.H. JakabA. BauerS. Kalpathy-CramerJ. FarahaniK. KirbyJ. BurrenY. PorzN. SlotboomJ. WiestR.; et al. The multimodal brain tumor image segmentation benchmark (brats).IEEE Transactions on Medical Imaging201534101993202410.1109/tmi.2014.2377694
     [Google Scholar]
  11. BauerS. WiestR. NolteL.P. ReyesM. A survey of MRI-based medical image analysis for brain tumor studies.Phys. Med. Biol.20135813R97R12910.1088/0031‑9155/58/13/R97 23743802
     [Google Scholar]
  12. AngeliniE. ClatzO. MandonnetE. KonukogluE. CapelleL. DuffauH. Glioma dynamics and computational models: A review of segmentation, registration, and in silico growth algorithms and their clinical applications.Curr. Med. Imaging Rev.20073426227610.2174/157340507782446241
     [Google Scholar]
  13. PrastawaM. BullittE. HoS. GerigG. Robust estimation for brain tumor segmentation.Lect. Notes Comput. Sci.2003287953053710.1007/978‑3‑540‑39903‑2_65
     [Google Scholar]
  14. BauerS. NolteL-P. ReyesM. Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization.Lecture Notes in Computer Science201135436110.1007/978‑3‑642‑23626‑6_44
     [Google Scholar]
  15. ZikicD. GlockerB. KonukogluE. CriminisiA. DemiralpC. ShottonJ. ThomasO.M. DasT. JenaR. PriceS.J. Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR.Medical Image Computing and Computer-Assisted Intervention - MICCAI 2012201236937610.1007/978‑3‑642‑33454‑2_46
     [Google Scholar]
  16. McBeeM.P. AwanO.A. ColucciA.T. GhobadiC.W. KadomN. KansagraA.P. TridandapaniS. AuffermannW.F. deep learning in radiology.Acad. Radiol.201825111472148010.1016/j.acra.2018.02.018 29606338
     [Google Scholar]
  17. MazurowskiM.A. BudaM. SahaA. BashirM.R. Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI.J. Magn. Reson. Imaging201949493995410.1002/jmri.26534 30575178
     [Google Scholar]
  18. BudaM. SahaA. MazurowskiM.A. Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm.Comput. Biol. Med.201910921822510.1016/j.compbiomed.2019.05.002 31078126
     [Google Scholar]
  19. HavaeiM. DavyA. Warde-FarleyD. BiardA. CourvilleA. BengioY. PalC. JodoinP.M. LarochelleH. Brain tumor segmentation with deep neural networks.Med. Image Anal.201735183110.1016/j.media.2016.05.004 27310171
     [Google Scholar]
  20. HavaeiM. GuizardN. LarochelleH. JodoinP-M. Deep learning trends for focal brain pathology segmentation in MRI.Lecture Notes in Computer Science201612514810.1007/978‑3‑319‑50478‑0_6
     [Google Scholar]
  21. NaserM.A. DeenM.J. Brain tumor segmentation and grading of lower-grade glioma using deep learning in MRI images.Comput. Biol. Med.202012110375810.1016/j.compbiomed.2020.103758 32568668
     [Google Scholar]
  22. DograJ. ShrutiJ.M.S. Glioma extraction from MRI images employing GBKS graph cut technique.Visual Computer, Springer20203687589110.1007/s00371‑019‑01698‑3
     [Google Scholar]
  23. RanjithG. ParvathyR. VikasV. ChandrasekharanK. NairS. Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.Neuroradiol. J.201528210611110.1177/1971400915576637 25923676
     [Google Scholar]
  24. PereiraS. PintoA. AlvesV. SilvaC.A. Brain tumor segmentation using convolutional neural networks in MRI images.IEEE Transactions on Medical Imaging.20163551240125110.1109/TMI.2016.2538465
     [Google Scholar]
  25. DingY. LiC. YangQ. QinZ. QinZ. How to improve the deep residual network to segment multi-modal brain tumor images.IEEE Access2019715282115283110.1109/ACCESS.2019.2948120
     [Google Scholar]
  26. RazzakM.I. ImranM. XuG. Efficient brain tumor segmentation with multiscale two-pathway-group conventional neural networks.IEEE J. Biomed. Health Inform.20192351911191910.1109/JBHI.2018.2874033 30295634
     [Google Scholar]
  27. YeF. ZhengY. YeH. HanX. LiY. WangJ. PuJ. Parallel pathway dense neural network with weighted fusion structure for brain tumor segmentation.Neurocomputing202142511110.1016/j.neucom.2020.11.005
     [Google Scholar]
  28. LouisD.N. OhgakiH. WiestlerO.D. CaveneeW.K. BurgerP.C. JouvetA. ScheithauerB.W. KleihuesP. The 2007 WHO classification of tumours of the central nervous system.Acta Neuropathol.200711429710910.1007/s00401‑007‑0243‑4 17618441
     [Google Scholar]
  29. DograJ. JainS. SoodM. Novel seed selection techniques for MR brain image segmentation using graph cut.Comput. Methods Biomech. Biomed. Eng. Imaging Vis.20208438939910.1080/21681163.2019.1697966
     [Google Scholar]
  30. WangZ. ZouY. PeterX. Hybrid dilation and attention residual U-Net for medical image segmentation.Comput. Biol. Med.2021134104449
     [Google Scholar]
  31. JinQ. MengZ. SunC. CuiH. SuR. Ra-unet, A hybrid deep attention-awarenetwork to extract liver and tumor in ct scans.Front. Bioeng. Biotechnol.2020860513210.3389/fbioe.2020.605132
     [Google Scholar]
  32. RonnebergerO. FischerP. BroxT. U-net, Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted InterventionSpringerCham201523424110.1007/978‑3‑319‑24574‑4_28
     [Google Scholar]
  33. HintonG.E. SalakhutdinovR.R. Reducing the dimensionality of data with neural networks.Science2006313578650450710.1126/science.1127647 16873662
     [Google Scholar]
  34. LiD. DharmawanD.A. NgB.P. RahardjaS. Residual u-net for retinal vesselsegmentation2019 IEEE International Conference on Image Processing (ICIP)Taipei, Taiwan, Sept 22-25, 20191425142910.1109/ICIP.2019.8803101
     [Google Scholar]
  35. KermiA. MahmoudiI. KhadirM.T. Deep convolutional neural networks using unet for automatic brain tumor segmentation in multi-modal mri volumes.International MICCAI Brainlesion WorkshopSpringer20183748
     [Google Scholar]
  36. DevallaS.K. RenukanandP.K. SreedharB.K. SubramanianG. ZhangL. PereraS. MariJ.M. ChinK.S. TunT.A. StrouthidisN.G. AungT. ThiéryA.H. GirardM.J.A. DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images.Biomed. Opt. Express2018973244326510.1364/BOE.9.003244 29984096
     [Google Scholar]
  37. AghalariM. AghagolzadehA. EzojiM. Brain tumor image segmentation via asymmetric/symmetric UNet based on two-pathway-residual blocks.Biomed Sig Process Cont.202169102841
     [Google Scholar]
  38. ShenH. ZhangJ. ZhengW. Efficient symmetry-driven fully convolutional network for multimodal brain tumor segmentation.2017 IEEE International Conference on Image Processing (ICIP)Beijing, China, Feb 17-20, 20173864386810.1109/ICIP.2017.8297006
     [Google Scholar]
  39. DiceL.R. Measures of the amount of ecologic association between species.Ecology194526329730210.2307/1932409
     [Google Scholar]
  40. WangZ. BovikA.C. SheikhH.R. SimoncelliE.P. Image quality assessment: from error visibility to structural similarity.IEEE Trans. Image Process.200413460061210.1109/TIP.2003.819861 15376593
     [Google Scholar]
  41. BatistaJ. Vikić-TopićD. LučićB. The difference between the accuracy of real and the corresponding random model is a useful parameter for validation of two-state classification model quality.Croat. Chem. Acta201689452753410.5562/cca3117
     [Google Scholar]
/content/journals/cad/10.2174/1573409920666230816090626
Loading
Detection of Brain Tumor Employing Residual Network-based Optimized Deep Learning
Curr. Computeraided Drug Des. 21, 15 (2025); https://doi.org/10.2174/1573409920666230816090626
/content/journals/cad/10.2174/1573409920666230816090626
/content/journals/cad/10.2174/1573409920666230816090626
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Brain tumor segmentation; convolutional neural network; deep learning; MRI; ResNet50; ResUNet

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