Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May 24;13(11):1824.
doi: 10.3390/diagnostics13111824.

SCDet: A Robust Approach for the Detection of Skin Lesions

Shahbaz Sikandar  1 , Rabbia Mahum  1 , Adham E Ragab  2 , Sule Yildirim Yayilgan  3 , Sarang Shaikh  3
Affiliations

SCDet: A Robust Approach for the Detection of Skin Lesions

Shahbaz Sikandar et al. Diagnostics (Basel). .

Abstract

Red, blue, white, pink, or black spots with irregular borders and small lesions on the skin are known as skin cancer that is categorized into two types: benign and malignant. Skin cancer can lead to death in advanced stages, however, early detection can increase the chances of survival of skin cancer patients. There exist several approaches developed by researchers to identify skin cancer at an early stage, however, they may fail to detect the tiniest tumours. Therefore, we propose a robust method for the diagnosis of skin cancer, namely SCDet, based on a convolutional neural network (CNN) having 32 layers for the detection of skin lesions. The images, having a size of 227 × 227, are fed to the image input layer, and then pair of convolution layers is utilized to withdraw the hidden patterns of the skin lesions for training. After that, batch normalization and ReLU layers are used. The performance of our proposed SCDet is computed using the evaluation matrices: precision 99.2%; recall 100%; sensitivity 100%; specificity 99.20%; and accuracy 99.6%. Moreover, the proposed technique is compared with the pre-trained models, i.e., VGG16, AlexNet, and SqueezeNet and it is observed that SCDet provides higher accuracy than these pre-trained models and identifies the tiniest skin tumours with maximum precision. Furthermore, our proposed model is faster than the pre-trained model as the depth of its architecture is not too high as compared to pre-trained models such as ResNet50. Additionally, our proposed model consumes fewer resources during training; therefore, it is better in terms of computational cost than the pre-trained models for the detection of skin lesions.

Keywords: batch normalization; benign; convolution neural network; dermoscopic images; malignant; max pooling; skin cancer; skin lesion; softmax.

PubMed Disclaimer

Conflict of interest statement

The authors state that they have no conflict of interest.

Figures

Figure 1
Figure 1
The Proposed CBIR.
Figure 2
Figure 2
Expanded Layers of proposed model.
Figure 3
Figure 3
Convolution Filter feature map on image.
Figure 4
Figure 4
Max Pooling Process.
Figure 5
Figure 5
Skin Lesion Detection Process.
Figure 6
Figure 6
Samples of Images used in Dataset. (a) Benign, (b) Malignant.
Figure 7
Figure 7
Accuracy and Loss of proposed CNN.
Figure 8
Figure 8
Confusion Matrix.
Figure 9
Figure 9
Accuracy of proposed CNN on HAM1000 Dataset.
Figure 10
Figure 10
Accuracy of AlexNet on Dermis Dataset.
Figure 11
Figure 11
Accuracy of SqueezeNet on Dermis Dataset.
Figure 12
Figure 12
Comparison with Machine Learning Techniques [15,52,53].
Figure 13
Figure 13
Comparison with Segmentation Techniques [18,54,55].
Figure 14
Figure 14
Comparison with Deep Learning Techniques [26,27,56,57].
See this image and copyright information in PMC

References

    1. Latif J., Xiao C., Imran A., Tu S. Medical Imaging using Machine Learning and Deep Learning Algorithms: A Review; Proceedings of the 2019 IEEE International Conference on Big Data (Big Data); Sukkur, Pakistan. 30–31 January 2019; pp. 1–5. - DOI
    1. Zemouri R., Zerhouni N., Racoceanu D. Deep Learning in the Biomedical Applications: Recent and Future Status. Appl. Sci. 2019;9:1526. doi: 10.3390/app9081526. - DOI
    1. Ravishankar S., Ye J.C., Fessler J.A. Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning. Proc. IEEE. 2019;108:86–109. doi: 10.1109/JPROC.2019.2936204. - DOI - PMC - PubMed
    1. Qiu L., Kantekure K., Vitkin E., Itzkan I., Perelman L.T., Zhang L., Turzhitsky V., Khan U., Zakharov Y., Pleskow D.K., et al. Multispectral Endoscopy With Light Gating for Early Cancer Detection. IEEE J. Sel. Top. Quantum Electron. 2018;25:1–9. doi: 10.1109/JSTQE.2018.2854608. - DOI - PMC - PubMed
    1. Pardo A., Streeter S.S., Maloney B.W., Gutierrez-Gutierrez J.A., McClatchy D.M., Wells W.A., Paulsen K.D., Lopez-Higuera J.M., Pogue B.W., Conde O.M. Modeling and Synthesis of Breast Cancer Optical Property Signatures With Generative Models. IEEE Trans. Med. Imaging. 2021;40:1687–1701. doi: 10.1109/TMI.2021.3064464. - DOI - PMC - PubMed

LinkOut - more resources