Skip to content
2000
Volume 19, Issue 1
  • ISSN: 2666-2558
  • E-ISSN: 2666-2566

Abstract

Introduction/Objective

Basal Cell Carcinoma (BCC) is the most prevalent type of skin cancer, accounting for three-quarters of all cancer cases. It is often confused with other benign lesions, such as Acne Vulgaris (AV). In this paper, we propose a classification approach to discriminate BCC from AV in dermoscopic images, using an algorithm based on deep learning techniques.

Methods

A two-branch Convolutional Neural Network (CNN) is employed to construct the model. The first branch consists of CNN structures that process an RGB dermoscopic image, while the second branch leverages the pre-trained ResNet18 network with an HSV dermoscopic image input. Both branches use Principal Component Analysis (PCA), normalization, and image resizing. This concatenated architecture enables the system to exploit features extracted from both color spaces as well as CNN networks, enhancing the overall performance of the model.

Results and Discussion

The proposed architecture is assessed using two public datasets. The first one is dedicated to the binary classification of Basal Cell Carcinoma (BCC) Acne Vulgaris (AV), achieving an accuracy of 99.06%, a sensitivity of 98.73%, and a specificity of 99.37%. The second dataset addresses multiclass classification along melanoma, BCC, and AV, and achieves an accuracy of 97.17%, a sensitivity of 97.13%, and a specificity of 98.57%. The results highlight the effectiveness of the proposed model.

Conclusion

The dual-input hybrid algorithm, based on convolutional neural networks and incorporating principal component analysis, demonstrates promising results in distinguishing BCC from AV.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/rascs/10.2174/0126662558378193250308034314
2025-03-20
2025-12-09

  • From This Site

    /content/journals/rascs/10.2174/0126662558378193250308034314
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. SchadendorfD. AkkooiV.A.C.J. BerkingC. GriewankK.G. GutzmerR. HauschildA. StangA. RoeschA. UgurelS. Melanoma.Lancet20183921015197198410.1016/S0140‑6736(18)31559‑930238891
     [Google Scholar]
  2. ZhangW. ZengW. JiangA. HeZ. ShenX. DongX. FengJ. LuH. Global, regional and national incidence, mortality and disability‐adjusted life‐years of skin cancers and trend analysis from 1990 to 2019: An analysis of the Global Burden of Disease Study 2019.Cancer Med.202110144905492210.1002/cam4.404634105887
     [Google Scholar]
  3. DaiJ. LinK. HuangY. LuY. ChenW.Q. ZhangX.R. HeB.S. PanY.Q. WangS.K. FanW.X. Identification of critically carcinogenesis-related genes in basal cell carcinoma.OncoTargets Ther.2018116957696710.2147/OTT.S17050430410353
     [Google Scholar]
  4. RoenigkR.K. RatzL.J. BailinP.L. WheelandR.G. Trends in the presentation and treatment of basal cell carcinomas.J. Dermatol. Surg. Oncol.198612886086510.1111/j.1524‑4725.1986.tb01993.x
     [Google Scholar]
  5. AltamuraD. MenziesS.W. ArgenzianoG. ZalaudekI. SoyerH.P. SeraF. AvramidisM. DeAmbrosisK. FargnoliM.C. PerisK. Dermatoscopy of basal cell carcinoma: Morphologic variability of global and local features and accuracy of diagnosis.J. Am. Acad. Dermatol.2010621677510.1016/j.jaad.2009.05.03519828209
     [Google Scholar]
  6. MarkowitzO. UtzS. Differentiating early stage cystic keratoacanthoma, nodular basal cell carcinoma, and excoriated acne vulgaris by clinical exam, dermoscopy, and optical coherence tomography: A report of 3 cases.J. Clin. Aesthet. Dermatol.201584485026060518
     [Google Scholar]
  7. AydinD. HölmichL.R. JakobsenL.P. Metastatic basal cell carcinoma caused by carcinoma misdiagnosed as acne – Case report and literature review.Clin. Case Rep.20164660160410.1002/ccr3.57527398205
     [Google Scholar]
  8. SnowS.N. SahlW. LoJ.S. MohsF.E. WarnerT. DekkingaJ.A. FeyziJ. Metastatic basal cell carcinoma. Report of five cases.Cancer199473232833510.1002/1097‑0142(19940115)73:2<328:AID‑CNCR2820730216>3.0.CO;2‑U8293396
     [Google Scholar]
  9. MarchettiM.A. CodellaN.C.F. DuszaS.W. GutmanD.A. HelbaB. KallooA. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images.J. Am. Acad. Dermatol.201878227027710.1016/j.jaad.2017.08.016
     [Google Scholar]
  10. EstevaA. KuprelB. NovoaR.A. KoJ. Dermatologist-level classification of skin cancer with deep neural networks.Nature2017542763911511810.1038/nature21056
     [Google Scholar]
  11. KharazmiP. AlJasserM.I. LuiH. WangZ.J. LeeT.K. Automated detection and segmentation of vascular structures of skin lesions seen in dermoscopy, with an application to basal cell carcinoma classification.IEEE J. Biomed. Health Inform.20172161675168410.1109/JBHI.2016.263734227959832
     [Google Scholar]
  12. KharazmiP. ZhengJ. LuiH. WangJ.Z. LeeT.K. A computer-aided decision support system for detection and localization of cutaneous vasculature in dermoscopy images via deep feature learning.J. Med. Syst.20184223310.1007/s10916‑017‑0885‑229318397
     [Google Scholar]
  13. KefelS. GuvencP. LeAnderR. StricklinS.M. StoeckerW.V. Discrimination of basal cell carcinoma from benign lesions based on extraction of ulcer features in polarized‐light dermoscopy images.Skin Res. Technol.201218447147510.1111/j.1600‑0846.2011.00595.x22356565
     [Google Scholar]
  14. ChengB. ErdosD. StanleyR.J. StoeckerW.V. CalcaraD.A. GómezD.D. Automatic detection of basal cell carcinoma using telangiectasia analysis in dermoscopy skin lesion images.Skin Res. Technol.201117327828710.1111/j.1600‑0846.2010.00494.x23815446
     [Google Scholar]
  15. GuvencP. LeAnderR.W. KefelS. StoeckerW.V. RaderR.K. HintonK.A. StricklinS.M. RabinovitzH.S. OlivieroM. MossR.H. Sector expansion and elliptical modeling of blue‐gray ovoids for basal cell carcinoma discrimination in dermoscopy images.Skin Res. Technol.2013191e532e53610.1111/srt.1200623020816
     [Google Scholar]
  16. MauryaA. StanleyR.J. LamaN. JagannathanS. SaeedD. SwinfardS. HagertyJ.R. StoeckerW.V. A deep learning approach to detect blood vessels in basal cell carcinoma.Skin Res. Technol.202228457157610.1111/srt.1315035611797
     [Google Scholar]
  17. SerranoC. LazoM. SerranoA. Toledo-PastranaT. Barros-TornayR. AchaB. Clinically inspired skin lesion classification through the detection of dermoscopic criteria for basal cell carcinoma.J. Imaging20228719710.3390/jimaging807019735877641
     [Google Scholar]
  18. MauryaA. StanleyR.J. LamaN. NambisanA.K. PatelG. SaeedD. SwinfardS. SmithC. JagannathanS. HagertyJ.R. StoeckerW.V. Hybrid topological data analysis and deep learning for basal cell carcinoma diagnosis.J. Imag. Inform. Med.20243719210610.1007/s10278‑023‑00924‑838343238
     [Google Scholar]
  19. MauryaA. StanleyR.J. AradhyulaH.Y. LamaN. Basal cell carcinoma diagnosis with fusion of deep learning and telangiectasia features.J. Imag. Inform. Med.20243731137115010.1007/s10278‑024‑00969‑3
     [Google Scholar]
  20. Al-MasniM.A. KimD.H. KimT.S. Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification.Comput. Meth. Prog. Biomed.202019010535110.1016/j.cmpb.2020.10535132028084
     [Google Scholar]
  21. IqbalI. YounusM. WalayatK. KakarM.U. MaJ. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images.Comput. Med. Imaging Graph.20218810184310.1016/j.compmedimag.2020.10184333445062
     [Google Scholar]
  22. WangS.Q. ZhangX.Y. LiuJ. TaoC. ZhuC.Y. ShuC. XuT. JinH.Z. Deep learning-based, computer-aided classifier developed with dermoscopic images shows comparable performance to 164 dermatologists in cutaneous disease diagnosis in the Chinese population.Chin. Med. J.2020133172027203610.1097/CM9.000000000000102332826613
     [Google Scholar]
  23. JasilS.P.G. UlagamuthalviV. A hybrid CNN architecture for skin lesion classification using deep learning.Soft Comput.2023202311010.1007/s00500‑023‑08035‑w
     [Google Scholar]
  24. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognitionProceedings of the IEEE conference on computer vision and pattern recognition2016770778
     [Google Scholar]
  25. CelebiM.E. KingraviH.A. UddinB. IyatomiH. AslandoganY.A. StoeckerW.V. MossR.H. A methodological approach to the classification of dermoscopy images.Comput. Med. Imaging Graph.200731636237310.1016/j.compmedimag.2007.01.00317387001
     [Google Scholar]
  26. PatilP.M. PatilY. Robust skin colour detection and tracking algorithm.Int. J. Eng. Res. Technol.20121822780181
     [Google Scholar]
  27. O’SheaK. An introduction to convolutional neural networksarXiv:1511.08458201519
     [Google Scholar]
  28. ShinH.C. RothH.R. GaoM. LuL. XuZ. NoguesI. YaoJ. MolluraD. SummersR.M. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.IEEE Trans. Med. Imaging20163551285129810.1109/TMI.2016.252816226886976
     [Google Scholar]
  29. SonkaM. HlavacV. BoyleR. Image processing, analysis and machine vision.ChamSpringer2013
     [Google Scholar]
  30. VidalR. MaY. SastryS. Generalized principal component analysis (GPCA).IEEE Trans. Pattern Anal. Mach. Intell.200527121945195910.1109/TPAMI.2005.24416355661
     [Google Scholar]
  31. DhillonA. VermaG.K. Convolutional neural network: A review of models, methodologies and applications to object detection.Prog. Artif. Intell.2020928511210.1007/s13748‑019‑00203‑0
     [Google Scholar]
  32. ZafarA. AamirM. NawiM.N. ArshadA. RiazS. AlrubanA. DuttaA.K. AlmotairiS. A comparison of pooling methods for convolutional neural networks.Appl. Sci.20221217864310.3390/app12178643
     [Google Scholar]
  33. SrivastavaN. HintonG. KrizhevskyA. SutskeverI. SalakhutdinovR. Dropout: A simple way to prevent neural networks from overfitting.J. Mach. Learn. Res.201415119291958
     [Google Scholar]
  34. IoffeS. Batch normalization: Accelerating deep network training by reducing internal covariate shiftarXiv:1502.03167201519
     [Google Scholar]
  35. RussakovskyO. DengJ. SuH. KrauseJ. SatheeshS. MaS. HuangZ. KarpathyA. KhoslaA. BernsteinM. BergA.C. Fei-FeiL. Imagenet large scale visual recognition challenge.Int. J. Comput. Vis.2015115321125210.1007/s11263‑015‑0816‑y
     [Google Scholar]
  36. KandelI. CastelliM. The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset.ICT Exp.20206431231510.1016/j.icte.2020.04.010
     [Google Scholar]
  37. RubyU. YendapalliV. Binary cross entropy with deep learning technique for image classification.Int. J. Adv. Trends Comput. Sci. Eng202091019
     [Google Scholar]
  38. KingmaD.P. Adam: A method for stochastic optimizationarXiv:1412.6980201416
     [Google Scholar]
  39. Kaggle,Kaggle Platform[Online]. Available: https://www.kaggle.com
  40. BryanJ. MaavbccKaggle, [Online]. Available: https://www.kaggle.com/datasets/johnbryangl/ma-avbcc
  41. BryanJ. OrigavbccKaggle, [Online]. Available: https://www.kaggle.com/datasets/johnbryangl/orig-avbcc
  42. TschandlP. RosendahlC. KittlerH. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions.Sci. Data20185118016110.1038/sdata.2018.16130106392
     [Google Scholar]
  43. ScarlatD. MelanomaKaggle, [Online]. Available: https://www.kaggle.com/datasets/drscarlat/melanoma
  44. NakamuraK. DerbelB. WonK.J. HongB.W. Learning-rate annealing methods for deep neural networks.Electronics (Basel)20211016202910.3390/electronics10162029
     [Google Scholar]
  45. WidaatallaY. WolswijkT. AdanF. HillenL.M. WoodruffH.C. HalilajI. IbrahimA. LambinP. MosterdK. The application of artificial intelligence in the detection of basal cell carcinoma: A systematic review.J. Eur. Acad. Dermatol. Venereol.20233761160116710.1111/jdv.1896336785993
     [Google Scholar]
  46. ISIC ArchiveInternational Skin Imaging Collaboration[Online]. Available: https://www.isic-archive.com
  47. Challenge 2017ISIC ISIC 2017: Skin Lesion Analysis Towards Melanoma Detection.2017[Online]. Available: http://challenge2017.isicarchive.com
  48. Challenge 2018ISIC ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection.2018[Online]. Available: http://challenge2018.isicarchive.com
  49. Challenge 2019ISIC ISIC 2019: Skin Lesion Analysis Towards Melanoma Detection.2019[Online]. Available: http://challenge2019.isicarchive.com
/content/journals/rascs/10.2174/0126662558378193250308034314
Loading
Basal Cell Carcinoma Detection Using Convolutional Neural Network
Recent Advances in Computer Science and Communications 19, E26662558378193 (2026); https://doi.org/10.2174/0126662558378193250308034314
/content/journals/rascs/10.2174/0126662558378193250308034314
/content/journals/rascs/10.2174/0126662558378193250308034314
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Acne vulgaris; basal cell carcinoma; binary classification; convolutional neural network; principal component analysis; ResNet18

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