CoChat
Sign Up
Cited by 240Cutaneous Melanoma Detection and ManagementAI in cancer detectionNonmelanoma Skin Cancer Studies

The DOI matches its Crossref record; 74 of the 76 references it cites were found in a registry or an index.

DSCC_Net: Multi-Classification Deep Learning Models for Diagnosing of Skin Cancer Using Dermoscopic Images

Open access
Tahir, Maryam, Naeem, Ahmad, Malik, Hassaan, Tanveer, Jawad, Naqvi, Rizwan Ali, Lee, Seung-Won·2023·Cancers
DOI 10.3390/cancers15072179PMC PMC10093058
Open this paper in CoChat — free accountOpen PDF

Abstract

Skin cancer is one of the most lethal kinds of human illness. In the present state of the health care system, skin cancer identification is a time-consuming procedure and if it is not diagnosed initially then it can be threatening to human life. To attain a high prospect of complete recovery, early detection of skin cancer is crucial. In the last several years, the application of deep learning (DL) algorithms for the detection of skin cancer has grown in popularity. Based on a DL model, this work intended to build a multi-classification technique for diagnosing skin cancers such as melanoma (MEL), basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanocytic nevi (MN). In this paper, we have proposed a novel model, a deep learning-based skin cancer classification network (DSCC_Net) that is based on a convolutional neural network (CNN), and evaluated it on three publicly available benchmark datasets (i.e., ISIC 2020, HAM10000, and DermIS). For the skin cancer diagnosis, the classification performance of the proposed DSCC_Net model is compared with six baseline deep networks, including ResNet-152, Vgg-16, Vgg-19, Inception-V3, EfficientNet-B0, and MobileNet. In addition, we used SMOTE Tomek to handle the minority classes issue that exists in this dataset. The proposed DSCC_Net obtained a 99.43% AUC, along with a 94.17%, accuracy, a recall of 93.76%, a precision of 94.28%, and an F1-score of 93.93% in categorizing the four distinct types of skin cancer diseases. The rates of accuracy for ResNet-152, Vgg-19, MobileNet, Vgg-16, EfficientNet-B0, and Inception-V3 are 89.32%, 91.68%, 92.51%, 91.12%, 89.46% and 91.82%, respectively. The results showed that our proposed DSCC_Net model performs better as compared to baseline models, thus offering significant support to dermatologists and health experts to diagnose skin cancer.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/cancers15072179

Cites

74 of 74 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Workflow of the proposed DSCC_Net model.
Figure 1 Workflow of the proposed DSCC_Net model.CC BY · PubMed Central
Figure 2 Original image samples of skin cancer extracted from three datasets.
Figure 2 Original image samples of skin cancer extracted from three datasets.CC BY · PubMed Central
Figure 3 SMOTE Tomek generates samples of images to solve the class imbalance issue.
Figure 3 SMOTE Tomek generates samples of images to solve the class imbalance issue.CC BY · PubMed Central
Figure 4 Architecture of proposed DSCC_Net used to classify skin cancer diseases.
Figure 4 Architecture of proposed DSCC_Net used to classify skin cancer diseases.CC BY · PubMed Central
Figure 5 The fundamental structure of the flattened layer.
Figure 5 The fundamental structure of the flattened layer.CC BY · PubMed Central
Figure 6 Remarkable accuracy improvement with or without SMOTE Tomek in the proposed model compared to other baseline deep networks; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 6 Remarkable accuracy improvement with or without SMOTE Tomek in the proposed model compared to other baseline deep networks; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 7 Results of the proposed DSCC_Net model with and without up-sampling; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 7 Results of the proposed DSCC_Net model with and without up-sampling; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 8 Precision results of the proposed model, DSCC_Net, and other baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 8 Precision results of the proposed model, DSCC_Net, and other baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 9 The recall analysis measures the proportion of true positive results correctly identified by a predictive model out of all actual positives; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 9 The recall analysis measures the proportion of true positive results correctly identified by a predictive model out of all actual positives; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 10 The value of the F1-score between the proposed model and six baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 10 The value of the F1-score between the proposed model and six baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 11 Loss value of the proposed DSCC_Net model and other baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 11 Loss value of the proposed DSCC_Net model and other baseline models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 12 ROC curve comparing the performance of baseline models with the proposed DSCC_Net model; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 12 ROC curve comparing the performance of baseline models with the proposed DSCC_Net model; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 13 AU(ROC) curve evaluation with extension for the proposed model and other models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 13 AU(ROC) curve evaluation with extension for the proposed model and other models; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 14 Using a confusion matrix to compare the proposed DSCC_Net with other deep networks; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.
Figure 14 Using a confusion matrix to compare the proposed DSCC_Net with other deep networks; (a) Vgg-16, (b) Vgg-19, (c) EfficientNet-B0, (d) ResNet-152, (e) Inception-V3, (f) MobileNet, (g) Proposed Model with SMOTE Tomek, and (h) Proposed Model without SMOTE Tomek.CC BY · PubMed Central
Figure 15 Grad-CAM evaluation of the proposed DSCC_Net model for skin cancer diseases.
Figure 15 Grad-CAM evaluation of the proposed DSCC_Net model for skin cancer diseases.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 3

  1. Le Duyen, N.T., Hieu, X.L., Lua, T.N., and Hoan, T.N. (2020). Transfer learning with class-weighted and focal loss function for automatic skin cancer classification. arXiv.
  2. Saksham, B., and Gomekar, A. (2019, January 6–8). Deep learning diagnosis of pigmented skin lesions. Proceedings of the 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India.
  3. Tomáš, M., Bajić, B., Yildirim, S., Hardeberg, J.Y., Lindblad, J., and Sladoje, N. (2018). Ensemble of convolutional neural networks for dermoscopic images classification. arXiv.

Cited by

Sorted by citations

See all 240

Related

See all

Metadata

Authors
Tahir, M., Naeem, A., Malik, H., Tanveer, J., Naqvi, R. A., & Lee, S.-W.
Affiliations
  • National College of Business Administration and Economics (PK)
  • University of Management and Technology (PK)
  • Sejong University (KR)
  • Sungkyunkwan University (KR)
Corresponding author
  • Naqvi, Rizwan Ali
  • Lee, Seung-Won
ORCID
Venue
Cancers
Publisher
MDPI AG
Published
2023-04-06
Volume
15
Issue
7
Pages
2179
ISSN
2072-6694 (ISSN-L)
DOI
10.3390/cancers15072179
PMC
PMC10093058
OpenAlex
W4362665647
Cited by
240
References
76
Citations by year
2026: 53 · 2025: 88 · 2024: 68 · 2023: 31
FWCI
29.10
Type
journal article
Language
en
Open access
Licence
Locations
  • Cancers (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Ministry of Science and ICT (MSIT) (NRF2022R1G1A1010226, NRF2021R1I1A2059735)
Topics
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Dermatology › Nonmelanoma Skin Cancer Studies
Keywords
skin cancer classification, dermoscopic images, melanoma, basal cell carcinoma, squamous cell carcinoma, melanocytic nevi, convolutional neural networks, early detection, class imbalance, SMOTE-Tomek, ISIC 2020, HAM10000, dermis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review