Skip to content
2000
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background:

Deep learning models have recently been preferred to perform certain image-processing tasks. Recently, with the increasing radiation, heat, and poor lighting conditions, the raw image samples may contain noisy and ambiguous information.

Objective:

To process these images, the deep learning model requires a large number of data samples to learn the missing information from other clear data samples. This necessitates training the neural network with a huge dataset.

Methods:

The researchers are now attempting to filter and improve such noisy images via preprocessing in order to provide valid and accurate feature information to the neural network layers. However, certain research studies claim that some useful information may be lost when the image is not preprocessed with an appropriate filter or enhancement technique. The MSA (meta-synthesis and analysis) approach is utilized in this work to present the impact of the image processing applications done with and without preprocessing steps. Also, this work summarizes the existing deep learning-based image processing models utilizing or not preprocessing steps in their implementation.

Results:

This work has also found that 85% of the existing techniques involve a preprocessing step while developing a deep learning model. However, a maximum accuracy of 96.89% is observed on Sine-Net when it is implemented without a preprocessing and the same model gave 96.85% when implemented with preprocessing.

Conclusion:

This research provides various research insights on the requirement and non-requirement of preprocessing steps in a deep learning-based implementation.

© 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/10.2174/1573405620666230829150157
2024-01-01
2025-09-07

  • From This Site

    /content/journals/cmir/10.2174/1573405620666230829150157
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/20/1/CMIR-20-E290823220482.html?itemId=/content/journals/cmir/10.2174/1573405620666230829150157&mimeType=html&fmt=ahah

References

  1. FujiyoshiH. HirakawaT. YamashitaT. Deep learning-based image recognition for autonomous driving.IATSS Res.201943424425210.1016/j.iatssr.2019.11.008
     [Google Scholar]
  2. MaQ. Improving SAR target recognition performance using multiple preprocessing techniques.Comput. Intell. Neurosci.202120211810.1155/2021/657236234394337
     [Google Scholar]
  3. GoceriE. Intensity normalization in brain mr images using spatially varying distribution matching.Conference: Conferences Computer Graphics, Visualization, Computer Vision and Image ProcessingLisbon, Portugal2017300304
     [Google Scholar]
  4. GoceriE. Fully automated and adaptive intensity normalization using statistical features for brain MR images.Celal Bayar Üniv. Fen Bilim. Derg201814112513410.18466/cbayarfbe.384729
     [Google Scholar]
  5. Göçeri̇E. ÜnlüM.Z. Di̇cleO. A comparative performance evaluation of various approaches for liver segmentation from SPIR images.Turk. J. Electr. Eng. Comput. Sci.201523374176810.3906/elk‑1304‑36
     [Google Scholar]
  6. GoceriN. GoceriE. A neural network based kidney segmentation from MR images.2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)09-11 December 2015Miami, FL, USA20151195119810.1109/ICMLA.2015.229
     [Google Scholar]
  7. GoceriE. UnluM.Z. GuzelisC. DicleO. An automatic level set based liver segmentation from MRI data sets.3rd International Conference on Image Processing Theory, Tools and Applications, IPTA15 October 2012Istanbul; Turkey201210.1109/IPTA.2012.6469551
     [Google Scholar]
  8. GoceriE. Automatic kidney segmentation using gaussian mixture model on MRI sequences.Electrical Power Systems and Computers. WanX. SpringerBerlin, Heidelberg20119910.1007/978‑3‑642‑21747‑0_4
     [Google Scholar]
  9. GoceriE. Automated skin cancer detection: Where we are and the way to the future.2021 44th International Conference on Telecommunications and Signal Processing (TSP)26-28 July 2021Brno, Czech Republic202110.1109/TSP52935.2021.9522605
     [Google Scholar]
  10. GoceriE. Evaluation of denoising techniques to remove speckle and Gaussian noise from dermoscopy images.Comput. Biol. Med.202315210647410.1016/j.compbiomed.2022.10647436563540
     [Google Scholar]
  11. GöçeriE. Impact of deep learning and smartphone technologies in dermatology: Automated diagnosis.2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA)09-12 November 2020Paris, France202010.1109/IPTA50016.2020.9286706
     [Google Scholar]
  12. DuraE. DomingoJ. GöçeriE. Martí-BonmatíL. A method for liver segmentation in perfusion MR images using probabilistic atlases and viscous reconstruction.Pattern Anal. Appl.20182141083109510.1007/s10044‑017‑0666‑z
     [Google Scholar]
  13. SultanaF. SufianA. DuttaP. Evolution of image segmentation using deep convolutional neural network: A survey.Knowl. Base. Syst.2020201-20210606210.1016/j.knosys.2020.106062
     [Google Scholar]
  14. GuR. WangG. SongT. HuangR. AertsenM. DeprestJ. OurselinS. VercauterenT. ZhangS. CA-Net: Comprehensive attention convolutional neural networks for explainable medical image segmentation.IEEE Trans. Med. Imaging202140269971110.1109/TMI.2020.303525333136540
     [Google Scholar]
  15. GöçeriE. Convolutional neural network based desktop applications to classify dermatological diseases.2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS)09-11 December 2020Genova, Italy202010.1109/IPAS50080.2020.9334956
     [Google Scholar]
  16. GoceriE. KarakasA.A. Comparative evaluations of cnn based networks for skin lesion classification.14th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing (CGVCVIP 2020)Zagreb, Croatia2020
     [Google Scholar]
  17. GoceriE. Classification of skin cancer using adjustable and fully convolutional capsule layers.Biomed. Signal Process. Control20238510494910.1016/j.bspc.2023.104949
     [Google Scholar]
  18. LinZ. WangY. ZhengZ. JiaJ. GaoW. IOP-CapsNet with ISEMRA: Fetching part-to-whole topology for improving detection performance of articulated instances.Expert Syst. Appl.202322612024710.1016/j.eswa.2023.120247
     [Google Scholar]
  19. Asgari TaghanakiS. AbhishekK. CohenJ.P. Cohen-AdadJ. HamarnehG. Deep semantic segmentation of natural and medical images: a review.Artif. Intell. Rev.202154113717810.1007/s10462‑020‑09854‑1
     [Google Scholar]
  20. TarekegnA.N. GiacobiniM. MichalakK. A review of methods for imbalanced multi-label classification.Pattern Recognit.202111810796510.1016/j.patcog.2021.107965
     [Google Scholar]
  21. SunZ. WangC. ZhaoY. YanC. Multi-label ECG signal classification based on ensemble classifier.IEEE Access2020811798611799610.1109/ACCESS.2020.3004908
     [Google Scholar]
  22. GoceriE. Medical image data augmentation: Techniques, comparisons and interpretations.Artif. Intell. Rev.2023145Epub ahead of print10.1007/s10462‑023‑10453‑z37362888
     [Google Scholar]
  23. GoceriEvgin Comparison of the impacts of dermoscopy image augmentation methods on skin cancer classification and a new augmentation method with wavelet packets.Int. J. Imaging Syst. Technol.202333410.1002/ima.22890
     [Google Scholar]
  24. GoceriE. Image augmentation for deep learning based lesion classification from skin images.2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS)09-11 December 2020Genova, Italy202010.1109/IPAS50080.2020.9334937
     [Google Scholar]
  25. MewadaH. 2D-wavelet encoded deep CNN for image-based ECG classification.Multimedia Tools Appl.20238213205532056910.1007/s11042‑022‑14302‑z
     [Google Scholar]
  26. ArsalanM. HaiderA. ChoiJ. ParkK.R. Diabetic and hypertensive retinopathy screening in fundus images using artificially intelligent shallow architectures.J. Pers. Med.2021121710.3390/jpm1201000735055322
     [Google Scholar]
  27. GaoZ. LuZ. WangJ. YingS. ShiJ. A convolutional neural network and graph convolutional network based framework for classification of breast histopathological images.IEEE J. Biomed. Health Inform.20222673163317310.1109/JBHI.2022.315367135196251
     [Google Scholar]
  28. AslanZ. AkinM. A deep learning approach in automated detection of schizophrenia using scalogram images of EEG signals.Phys. Eng. Sci. Med.2022451839610.1007/s13246‑021‑01083‑234822131
     [Google Scholar]
  29. AkbarimajdA. HoertelN. HussainM.A. NeshatA.A. MarhamatiM. BakhtoorM. MomenyM. Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images.J. Comput. Sci.20226310176310.1016/j.jocs.2022.10176335818367
     [Google Scholar]
  30. FraiwanM. FaouriE. On the automatic detection and classification of skin cancer using deep transfer learning.Sensors.20222213496310.3390/s2213496335808463
     [Google Scholar]
  31. JiangH. JiangX. RuY. ChenQ. LiX. XuL. ZhouH. ShiM. Rapid and non-destructive detection of natural mildew degree of postharvest Camellia oleifera fruit based on hyperspectral imaging.Infrared Phys. Technol.202212310416910.1016/j.infrared.2022.104169
     [Google Scholar]
  32. JosephS. OlugbaraO.O. Preprocessing effects on performance of skin lesion saliency segmentation.Diagnostics.202212234410.3390/diagnostics1202034435204435
     [Google Scholar]
  33. Shamila EbenezerA. Deepa KanmaniS. SivakumarM. Jeba PriyaS. Effect of image transformation on EfficientNet model for COVID-19 CT image classification.Mater. Today Proc.2022512512251910.1016/j.matpr.2021.12.12134926175
     [Google Scholar]
  34. InanM.S.K. AlamF.I. HasanR. Deep integrated pipeline of segmentation guided classification of breast cancer from ultrasound images.Biomed. Signal Process. Control20227510355310.1016/j.bspc.2022.103553
     [Google Scholar]
  35. AladhadhS. AlsaneaM. AlorainiM. KhanT. HabibS. IslamM. An effective skin cancer classification mechanism via medical vision transformer.Sensors20222211400810.3390/s2211400835684627
     [Google Scholar]
  36. ZhangZ. YangS. LiuS. CaoX. DurraniT.S. Ground-based remote sensing cloud detection using dual pyramid network and encoder–decoder constraint.IEEE Trans. Geosci. Remote Sens.20226011010.1109/TGRS.2022.3163917
     [Google Scholar]
  37. PirhonenJ. OjalaR. KivekäsK. VepsäläinenJ. TammiK. Brake light detection algorithm for predictive braking.Appl. Sci.2022126280410.3390/app12062804
     [Google Scholar]
  38. AljabriM. AljameelS.S. Min-AllahN. AlhuthayfiJ. AlghamdiL. AlduhailanN. AlfehaidR. AlqarawiR. AlharekyM. ShahinS.Y. Al TurkiW. Canine impaction classification from panoramic dental radiographic images using deep learning models.Inform. Med. Unlocked.20223010091810.1016/j.imu.2022.100918
     [Google Scholar]
  39. MomenyM. LatifA.M. Agha SarramM. SheikhpourR. ZhangY.D. A noise robust convolutional neural network for image classification.Results Eng.20211010022510.1016/j.rineng.2021.100225
     [Google Scholar]
  40. MujahidA. AwanM.J. YasinA. MohammedM.A. DamaševičiusR. MaskeliūnasR. AbdulkareemK.H. Real-time hand gesture recognition based on deep learning YOLOv3 model.Appl. Sci.2021119416410.3390/app11094164
     [Google Scholar]
  41. KimH.J. LeeD.H. NiazA. KimC.Y. MemonA.A. ChoiK.N. Multiple-clothing detection and fashion landmark estimation using a single-stage detector.IEEE Access20219116941170410.1109/ACCESS.2021.3051424
     [Google Scholar]
  42. AtliI. GedikO.S. Sine-Net: A fully convolutional deep learning architecture for retinal blood vessel segmentation.Eng Sci Technol Int J202124227128310.1016/j.jestch.2020.07.008
     [Google Scholar]
  43. GautamA. RamanB. Towards effective classification of brain hemorrhagic and ischemic stroke using CNN.Biomed. Signal Process. Control20216310217810.1016/j.bspc.2020.102178
     [Google Scholar]
  44. KrajncD. PappL. NakuzT.S. MagometschniggH.F. GrahovacM. SpielvogelC.P. EcsediB. Bago-HorvathZ. HaugA. KaranikasG. BeyerT. HackerM. HelbichT.H. PinkerK. Breast tumor characterization using [18F] FDG-PET/CT imaging combined with data preprocessing and radiomics.Cancers2021136124910.3390/cancers1306124933809057
     [Google Scholar]
  45. AhamedK.U. IslamM. UddinA. AkhterA. PaulB.K. YousufM.A. UddinS. QuinnJ.M.W. MoniM.A. A deep learning approach using effective preprocessing techniques to detect COVID-19 from chest CT-scan and X-ray images.Comput. Biol. Med.202113910501410.1016/j.compbiomed.2021.10501434781234
     [Google Scholar]
  46. CastiglioneA. VijayakumarP. NappiM. SadiqS. UmerM. Covid-19: automatic detection of the novel coronavirus disease from ct images using an optimized convolutional neural network.IEEE Trans. Industr. Inform.20211796480648810.1109/TII.2021.3057524
     [Google Scholar]
  47. MaX. NiuY. GuL. WangY. ZhaoY. BaileyJ. LuF. Understanding adversarial attacks on deep learning based medical image analysis systems.Pattern Recognit.202111010733210.1016/j.patcog.2020.107332
     [Google Scholar]
  48. SoriW.J. FengJ. GodanaA.W. LiuS. GelmechaD.J. DFD-Net: Lung cancer detection from denoised CT scan image using deep learning.Front. Comput. Sci.202115215270110.1007/s11704‑020‑9050‑z
     [Google Scholar]
  49. WangY. CaiJ. LouieD.C. WangZ.J. LeeT.K. Incorporating clinical knowledge with constrained classifier chain into a multimodal deep network for melanoma detection.Comput. Biol. Med.202113710481210.1016/j.compbiomed.2021.10481234507158
     [Google Scholar]
  50. ShenX. MaH. LiuR. LiH. HeJ. WuX. Lesion segmentation in breast ultrasound images using the optimized marked watershed method.Biomed. Eng. Online20212015710.1186/s12938‑021‑00891‑734098970
     [Google Scholar]
  51. ChenL. ZhengM. DuanS. LuoW. YaoL. Underwater target recognition based on improved YOLOv4 neural network.Electronics20211014163410.3390/electronics10141634
     [Google Scholar]
  52. HaE.G. JeonK.J. KimY.H. KimJ.Y. HanS.S. Automatic detection of mesiodens on panoramic radiographs using artificial intelligence.Sci. Rep.20211112306110.1038/s41598‑021‑02571‑x34845320
     [Google Scholar]
  53. RodriguesL.F. NaldiM.C. MariJ.F. Comparing convolutional neural networks and preprocessing techniques for HEp-2 cell classification in immunofluorescence images.Comput. Biol. Med.202011610354210.1016/j.compbiomed.2019.10354231790962
     [Google Scholar]
  54. MajeedT. RashidR. AliD. AsaadA. Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays.Phys. Eng. Sci. Med.20204341289130310.1007/s13246‑020‑00934‑833025386
     [Google Scholar]
  55. ZhaoH. SunY. LiH. Retinal vascular junction detection and classification via deep neural networks.Comput. Methods Programs Biomed.202018310509610.1016/j.cmpb.2019.10509631586789
     [Google Scholar]
  56. IgarashiS. SasakiY. MikamiT. SakurabaH. FukudaS. Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet.Comput. Biol. Med.202012410395010.1016/j.compbiomed.2020.10395032798923
     [Google Scholar]
  57. ChenZ. LiD. ShenH. MoH. ZengZ. WeiH. Automated segmentation of fluid regions in optical coherence tomography B-scan images of age-related macular degeneration.Opt. Laser Technol.202012210583010.1016/j.optlastec.2019.105830
     [Google Scholar]
  58. HeidariM. MirniaharikandeheiS. KhuzaniA.Z. DanalaG. QiuY. ZhengB. Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms.Int. J. Med. Inform.202014410428410.1016/j.ijmedinf.2020.10428432992136
     [Google Scholar]
  59. ShayestehS.P. AlikhassiA. FarhanF. GahletakiR. SoltanabadiM. HaddadP. Bitarafan-RajabiA. Prediction of response to neoadjuvant chemoradiotherapy by MRI-based machine learning texture analysis in rectal cancer patients.J. Gastrointest. Cancer202051260160910.1007/s12029‑019‑00291‑031456114
     [Google Scholar]
  60. Behzadi-khormoujiH. RostamiH. SalehiS. Derakhshande-RishehriT. MasoumiM. SalemiS. KeshavarzA. GholamrezanezhadA. AssadiM. BatouliA. Deep learning, reusable and problem-based architectures for detection of consolidation on chest X-ray images.Comput. Methods Programs Biomed.202018510516210.1016/j.cmpb.2019.10516231715332
     [Google Scholar]
  61. ZafarK. GilaniS.O. WarisA. AhmedA. JamilM. KhanM.N. Sohail KashifA. Skin lesion segmentation from dermoscopic images using convolutional neural network.Sensors2020206160110.3390/s2006160132183041
     [Google Scholar]
  62. BakH.Y. ParkS.B. Comparative study of movie shot classification based on semantic segmentation.Appl. Sci.20201010339010.3390/app10103390
     [Google Scholar]
  63. LinC. ZhaoG. YangZ. YinA. WangX. GuoL. ChenH. MaZ. ZhaoL. LuoH. WangT. DingB. PangX. ChenQ. Cir-net: Automatic classification of human chromosome based on inception-resnet architecture.IEEE/ACM Trans. Comput. Biol. Bioinformatics20221931285129332750868
     [Google Scholar]
  64. MzoughiH. NjehI. WaliA. SlimaM.B. BenHamidaA. MhiriC. MahfoudheK.B. Deep multi-scale 3D convolutional neural network (CNN) for MRI gliomas brain tumor classification.J. Digit. Imaging202033490391510.1007/s10278‑020‑00347‑932440926
     [Google Scholar]
/content/journals/cmir/10.2174/1573405620666230829150157
Loading
Implementation and Efficient Analysis of Preprocessing Techniques in Deep Learning for Image Classification
Curr. Med. Imaging 20, e290823220482 (2024); https://doi.org/10.2174/1573405620666230829150157
/content/journals/cmir/10.2174/1573405620666230829150157
/content/journals/cmir/10.2174/1573405620666230829150157
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Deep learning; Feature processing; Filters; Illumination variance; Image enhancement; Noise removal

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