Skip to content
2000
Volume 21, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format text download EPUB
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background:

The skin, being the largest organ in the human body, plays a vital protective role. Skin lesions are changes in the appearance of the skin, such as bumps, sores, lumps, patches, and discoloration. If not identified and treated promptly, skin lesion diseases would become a serious and worrisome problem for society due to their detrimental effects. However, visually inspecting skin lesions during medical examinations can be challenging due to their similarities.

Objective:

The proposed research aimed at leveraging technological advancements, particularly deep learning methods, to analyze dermoscopic images of skin lesions and make accurate predictions, thereby aiding in diagnosis.

Methods:

The proposed study utilized four pre-trained CNN architectures, RegNetX, EfficientNetB3, VGG19, and ResNet-152, for the multi-class classification of seven types of skin diseases based on dermoscopic images. The significant finding of this study was the integration of attention mechanisms, specifically channel-wise and spatial attention, into these CNN variants. These mechanisms allowed the models to focus on the most relevant regions of the dermoscopic images, enhancing feature extraction and improving classification accuracy. Hyperparameters of the models were optimized using Bayesian optimization, a probabilistic model-based technique that efficiently uses the hyperparameter space to find the optimal configuration for the developed models.

Results:

The performance of these models was evaluated, and it was found that RegNetX outperformed the other models with an accuracy of 98.61%. RegNetX showed robust performance when integrated with both channel-wise and spatial attention mechanisms, indicating its effectiveness in focusing on significant features within the dermoscopic images.

Conclusion:

The results demonstrated the effectiveness of attention-aware deep learning models in accurately classifying various skin diseases from dermoscopic images. By integrating attention mechanisms, these models can focus on the most relevant features within the images, thereby improving their classification accuracy. The results confirmed that RegNetX, integrated with optimized attention mechanisms, can provide robust, accurate diagnoses, which is critical for early detection and treatment of skin diseases.

© 2025 The Author(s). Published by Bentham Science Publishers.
This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056332443241129113146
2025-01-01
2026-01-02

  • From This Site

    /content/journals/cmir/10.2174/0115734056332443241129113146
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056332443.html?itemId=/content/journals/cmir/10.2174/0115734056332443241129113146&mimeType=html&fmt=ahah

References

  1. MazharT. HaqI. DittaA. MohsanS.A.H. RehmanF. ZafarI. GansauJ.A. GohL.P.W. The role of machine learning and deep learning approaches for the detection of skin cancer.Healthcare (Basel)202311341510.3390/healthcare1103041536766989
     [Google Scholar]
  2. CaiG. ZhuY. WuY. JiangX. YeJ. YangD. A multimodal transformer to fuse images and metadata for skin disease classification.Vis. Comput.202239711335540957
     [Google Scholar]
  3. PachecoA.G.C. KrohlingR.A. An attention-based mechanism to combine images and metadata in deep learning models applied to skin cancer classification.IEEE J. Biomed. Health Inform.20212593554356310.1109/JBHI.2021.306200233635800
     [Google Scholar]
  4. SinghJ. SandhuJ.K. KumarY. An analysis of detection and diagnosis of different classes of skin diseases using artificial intelligence-based learning approaches with hyper parameters.Arch. Comput. Methods Eng.20243121051107810.1007/s11831‑023‑10005‑2
     [Google Scholar]
  5. TembhurneJ.V. HebbarN. PatilH.Y. DiwanT. Skin cancer detection using ensemble of machine learning and deep learning techniques.Multimedia Tools Appl.20238218275012752410.1007/s11042‑023‑14697‑3
     [Google Scholar]
  6. InthiyazS. AltahanB.R. AhammadS.H. RajeshV. KalangiR.R. SmiraniL.K. HossainM.A. RashedA.N.Z. Skin disease detection using deep learning.Adv. Eng. Softw.202317510336110.1016/j.advengsoft.2022.103361
     [Google Scholar]
  7. GulzarY. KhanS.A. Skin lesion segmentation based on vision transformers and convolutional neural networks - A comparative study.Appl. Sci. (Basel)20221212599010.3390/app12125990
     [Google Scholar]
  8. GururajH.L. ManjuN. NagarjunA. AradhyaV.N.M. FlamminiF. DeepSkin: A deep learning approach for skin cancer classification.IEEE Access202311502055021410.1109/ACCESS.2023.3274848
     [Google Scholar]
  9. OmerogluA.N. MohammedH.M.A. OralE.A. AydinS. A novel soft attention-based multi-modal deep learning framework for multi-label skin lesion classification.Eng. Appl. Artif. Intell.202312010589710.1016/j.engappai.2023.105897
     [Google Scholar]
  10. AlhudhaifA. AlmaslukhB. AseeriA.O. GulerO. PolatK. A novel nonlinear automated multi-class skin lesion detection system using soft-attention based convolutional neural networks.Chaos Solitons Fractals202317011340910.1016/j.chaos.2023.113409
     [Google Scholar]
  11. XiangS. LiN. WangY. ZhouS. WeiJ. LiS. Automatic delineation of the 3D left atrium from LGE-MRI: Actor-critic based detection and semi-supervised segmentation.IEEE J. Biomed. Health Inform.20242863545355610.1109/JBHI.2024.337312738442054
     [Google Scholar]
  12. YaoW. BaiJ. LiaoW. From cnn to transformer: A review of medical image segmentation models.J. Imaging Inform. Med.37420241529154710.1007/s10278‑024‑00981‑7
     [Google Scholar]
  13. KumarR. KumbharkarP. VanamS. SharmaS. Medical images classification using deep learning: A survey.Multimedia Tools Appl.2023837196831972810.1007/s11042‑023‑15576‑7
     [Google Scholar]
  14. GongY. QiuH. LiuX. YangY. ZhuM. Research and application of deep learning in medical image reconstruction and enhancement.Front. Comput. Intell. Sys.202473727610.54097/8w12d064
     [Google Scholar]
  15. OliveiraR.B. FilhoM.E. MaZ. PapaJ.P. PereiraA.S. TavaresJ.M.R.S. Computational methods for the image segmentation of pigmented skin lesions: A review.Comput. Methods Programs Biomed.201613112714110.1016/j.cmpb.2016.03.03227265054
     [Google Scholar]
  16. RasoolS. A systematic analysis for the detection of skin disease using deep learning methodologies.J. Comput. Biomed. Informat.20234026675
     [Google Scholar]
  17. LiH. PanY. ZhaoJ. ZhangL. Skin disease diagnosis with deep learning: A review.Neurocomputing202146436439310.1016/j.neucom.2021.08.096
     [Google Scholar]
  18. VayadandeK. BhosleA.A. PawarR.G. JoshiD.J. BailkeP.A. LohadeO. Innovative approaches for skin disease identification in machine learning: A comprehensive study.Oral Oncology Reports20241010036510.1016/j.oor.2024.100365
     [Google Scholar]
  19. StrzeleckiM. KociołekM. StrąkowskaM. KozłowskiM. GrzybowskiA. SzczypińskiP.M. Artificial intelligence in the detection of skin cancer: State of the art.Clin. Dermatol.202442328029510.1016/j.clindermatol.2023.12.02238181888
     [Google Scholar]
  20. NasirM. Attique KhanM. SharifM. LaliI.U. SabaT. IqbalT. An improved strategy for skin lesion detection and classification using uniform segmentation and feature selection based approach.Microsc. Res. Tech.201881652854310.1002/jemt.2300929464868
     [Google Scholar]
  21. BordoloiD. SinghV. KaliyaperumalK. Classification and detection of skin disease based on machine learning and image processing evolutionary models.Comput. Assist. Methods Eng. Sci.20233224725610.24423/cames.479
     [Google Scholar]
  22. BhardwajA. RegeP.P. Skin lesion classification using deep learning.In: SpringerSingapore202157558910.1007/978‑981‑15‑8391‑9_42
     [Google Scholar]
  23. AlDeraS.A. OthmanM.T.B. A model for classification and diagnosis of skin disease using machine learning and image processing techniques.Int. J. Adv. Comput. Sci. Appl.202213510.14569/IJACSA.2022.0130531
     [Google Scholar]
  24. AhammedM. MamunM.A. UddinM.S. A machine learning approach for skin disease detection and classification using image segmentation.Healthcare Analytics2022210012210.1016/j.health.2022.100122
     [Google Scholar]
  25. ArshadM. KhanM.A. TariqU. ArmghanA. AleneziF. Younus JavedM. AslamS.M. KadryS. A computer-aided diagnosis system using deep learning for multiclass skin lesion classification.Comput. Intell. Neurosci.202120211961907910.1155/2021/961907934912449
     [Google Scholar]
  26. TaouilK. Ben RomdhaneN. Automatic segmentation and classification of skin lesion images.The 2nd International Conference on Distributed Frameworks for Multimedia ApplicationsPenang, Malaysia, 15-17 May 2006, pp. 1-12.10.1109/DFMA.2006.296918
     [Google Scholar]
  27. ShanthiT. SabeenianR.S. AnandR. Automatic diagnosis of skin diseases using convolution neural network.Microprocess. Microsyst.20207610307410.1016/j.micpro.2020.103074
     [Google Scholar]
  28. López-LeyvaJ.A. Guerra-RosasE. Álvarez-BorregoJ. Multi-class diagnosis of skin lesions using the fourier spectral information of images on additive color model by artificial neural network.IEEE Access20219352073521610.1109/ACCESS.2021.3061873
     [Google Scholar]
  29. EstevaA. KuprelB. NovoaR.A. KoJ. SwetterS.M. BlauH.M. ThrunS. Dermatologist-level classification of skin cancer with deep neural networks.Nature2017542763911511810.1038/nature2105628117445
     [Google Scholar]
  30. AhmadB. UsamaM. HuangC-M. HwangK. HossainM.S. MuhammadG. Discriminative feature learning for skin disease classification using deep convolutional neural network.IEEE Access20208390253903310.1109/ACCESS.2020.2975198
     [Google Scholar]
  31. Al-AntariM.A. RiveraP. Al-masniM.A. An automatic recognition of multi-class skin lesions via deep learning convolutional neural networks.ISIC2018: Skin Image Analysis Workshop and Challenge2018
     [Google Scholar]
  32. MiltonM.A.A. Automated skin lesion classification using ensemble of deep neural networks in ISIC 2018: Skin lesion analysis towards melanoma detection challenge.10802arXiv201910.48550/arXiv.1901.10802
     [Google Scholar]
  33. VachmanusS. NorasetT. PiyanonpongW. RattananukromT. TuarobS. DeepMetaForge: A deep vision-transformer metadata-fusion network for automatic skin lesion classification.IEEE Access20231114546714548410.1109/ACCESS.2023.3345225
     [Google Scholar]
  34. DesaleR.P. PatilP.S. An efficient multi-class classification of skin cancer using optimized vision transformer.Med. Biol. Eng. Comput.623773-789789202410.1007/s11517‑023‑02969‑x
     [Google Scholar]
  35. RezaeeK. ZadehH.G. Self-attention transformer unit-based deep learning framework for skin lesions classification in smart healthcare.Discov. Appl. Sci.202461310.1007/s42452‑024‑05655‑1
     [Google Scholar]
  36. MauryaR. MahapatraS. DuttaM.K. SinghV.P. KarnatiM. SahuG. PandeyN.N. Skin cancer detection through attention guided dual autoencoder approach with extreme learning machine.Sci. Rep.20241411778510.1038/s41598‑024‑68749‑139090261
     [Google Scholar]
  37. FanC. ZhuZ. PengB. EAAC-Net: An efficient adaptive attention and convolution fusion network for skin lesion segmentation.J. Imaging Inform. Med.202410.1007/s10278‑024‑01223‑6
     [Google Scholar]
  38. LiuX. ZhangC. ZhangL. Vision mamba: A comprehensive survey and taxonomy.2024arXiv10.48550/arXiv.2405.04404
     [Google Scholar]
  39. SubramanianM. ShanmugavadivelK. NandhiniP.S. On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leaves.Neural Comput. Appl.20223416139511396810.1007/s00521‑022‑07246‑w
     [Google Scholar]
  40. NaeemA. AneesT. KhalilM. SNC_Net: Skin cancer detection by integrating handcrafted and deep learning-based features using dermoscopy images.Mathematics127103010.3390/math12071030
     [Google Scholar]
  41. SadikR. MajumderA. BiswasA.A. AhammadB. RahmanM.M. An in-depth analysis of Convolutional Neural Network architectures with transfer learning for skin disease diagnosis.Healthcare Analytics2023310014310.1016/j.health.2023.100143
     [Google Scholar]
  42. GhoshH. A study on the application of machine learning and deep learning techniques for skin cancer detection.Int. J. Comput. Sys. Eng.20241815159
     [Google Scholar]
  43. RashidJ. IshfaqM. AliG. SaeedM.R. HussainM. AlkhalifahT. AlturiseF. SamandN. Skin cancer disease detection using transfer learning technique.Appl. Sci. (Basel)20221211571410.3390/app12115714
     [Google Scholar]
  44. ChoudharyP. SinghaiJ. YadavJ.S. Skin lesion detection based on deep neural networks.Chemom. Intell. Lab. Syst.23010465910.1016/j.chemolab.2022.104659
     [Google Scholar]
  45. GoudaW. SamaN.U. Al-WaakidG. HumayunM. JhanjhiN.Z. Detection of skin cancer based on skin lesion images using deep learning.Healthcare (Basel)2022107118310.3390/healthcare1007118335885710
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056332443241129113146
Loading
Attention-aware Deep Learning Models for Dermoscopic Image Classification for Skin Disease Diagnosis
Curr. Med. Imaging 21, E15734056332443 (2025); https://doi.org/10.2174/0115734056332443241129113146
/content/journals/cmir/10.2174/0115734056332443241129113146
/content/journals/cmir/10.2174/0115734056332443241129113146
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Attention mechanism; Bayesian optimization; CNN; EfficientNetB3; RegNetX; ResNet-152; Skin lesion; VGG19

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