CoChat
Sign Up
Cited by 415Cutaneous Melanoma Detection and ManagementAI in cancer detectionAdvanced Neural Network Applications

An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models

Open access
Ali, Md Shahin, Miah, Md Sipon, Haque, Jahurul, Rahman, Md Mahbubur, Islam, Md Khairul·2021·Machine Learning with Applications
DOI 10.1016/j.mlwa.2021.100036
Open this paper in CoChat — free accountOpen PDF

Abstract

Skin cancer is one of the top three perilous types of cancer caused by damaged DNA that can cause death. This damaged DNA begins cells to grow uncontrollably and nowadays it is getting increased speedily. There exist some researches for the computerized analysis of malignancy in skin lesion images. However, analysis of these images is very challenging having some troublesome factors like light reflections from the skin surface, variations in color illumination, different shapes, and sizes of the lesions. As a result, evidential automatic recognition of skin cancer is valuable to build up the accuracy and proficiency of pathologists in the early stages. In this paper, we propose a deep convolutional neural network (DCNN) model based on deep learning approach for the accurate classification between benign and malignant skin lesions. In preprocessing we firstly, apply filter or kernel to remove noise and artifacts; secondly, normalize the input images and extract features that help for accurate classification; and finally, data augmentation increases the number of images that improves the accuracy of classification rate. To evaluate the performance of our proposed, DCNN model is compared with some transfer learning models such as AlexNet, ResNet, VGG-16, DenseNet, MobileNet, etc. The model is evaluated on the HAM10000 dataset and ultimately we obtained the highest 93.16% of training and 91.93% of testing accuracy respectively. The final outcomes of our proposed DCNN model define it as more reliable and robust when compared with existing transfer learning models.

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 · 10.1016/j.mlwa.2021.100036

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

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?

  • Class imbalance remains a central challenge in seven-class skin lesion classification using HAM10000.

    “Class imbalance remains a central challenge in seven-class skin lesion classification using HAM10000.”

    From Interpretable multimodal fusion for skin lesion classification using dermoscopic images and patient metadata (2026) · cites this paper as [15]

    The Conclusion and future work section says imbalance in the HAM10000 data hindered accuracy. But it describes the study as binary classification of benign versus malignant lesions, not seven-class classification; §4.8 likewise specifies two labels. No page numbers are available in our copy. (LLM, conf=0.89)

    Experimental — accuracy not yet measured

  • Later, CNN-based automatic feature extraction and transfer learning with pretrained models improved representation learning.

    “Later, CNN-based automatic feature extraction (14) and transfer learning with pretrained models (15, 18) improved representation learning.”

    From Interpretable multimodal fusion for skin lesion classification using dermoscopic images and patient metadata (2026) · cites this paper as [15]

    Section 5 describes transfer learning as reusing pretrained models for related problems, and Section 4.7 discusses extracting features from skin-lesion images. The paper does not establish that transfer learning improved representation learning; its reported comparison concerns classification performance, with the proposed DCNN outperforming the transfer-learning models. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Most prior studies primarily focused on improving classification accuracy through increasingly complex architectures without sufficient attention to explaining model decisions.

    “However, most prior studies primarily focused on improving classification accuracy through increasingly complex architectures without sufficient attention to explaining model decisions (14–22).”

    From Interpretable multimodal fusion for skin lesion classification using dermoscopic images and patient metadata (2026) · cites this paper as [15]

    The Literature review (page unavailable) describes prior skin-cancer models and repeatedly evaluates their classification accuracy, supporting the claim that accuracy was a focus. It does not say that most prior studies used increasingly complex architectures or gave insufficient attention to explaining model decisions; searches for interpretability and model explanations found no such discussion. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

  • Most prior studies address class imbalance through conventional image-level augmentation, which increases data volume but does not introduce genuine semantic diversity.

    “Most prior studies address this issue through conventional image-level augmentation (7, 14, 15, 17, 18, 20, 21, 23), which increases data volume but does not introduce genuine semantic diversity.”

    From Interpretable multimodal fusion for skin lesion classification using dermoscopic images and patient metadata (2026) · cites this paper as [15]

    Section 4.9 describes conventional image-level augmentation as adding slightly modified copies to increase the amount of data, and lists transformations used in this study. The conclusion says the authors balanced their dataset, but the paper does not establish that most prior studies use this approach or explicitly assess whether it introduces genuine semantic diversity. Page numbers are unavailable in our copy. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

Self-check

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

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

Cites

1 retracted

Flagged first, then by citations

Research works printed but not linked: 1

  1. Namey, E., Guest, G., Thairu, L., & Johnson, L. (2008). Data reduction techniques for large qualitative data sets. Handbook for Team-Based Qualitative Research, 2(1), 137-161.

Cited by

Sorted by citations

Related

Authors
Ali, M. S., Miah, M. S., Haque, J., Rahman, M. M., & Islam, M. K.
Affiliations
  • Islamic University (BD)
  • Ollscoil na Gaillimhe – University of Galway (IE)
Corresponding author
Islam, Md Khairul
ORCID
Venue
Machine Learning with Applications
Publisher
Elsevier BV
Published
2021-09
Volume
5
Pages
100036
ISSN
2666-8270 (ISSN-L)
DOI
10.1016/j.mlwa.2021.100036
OpenAlex
W3159690776
Cited by
415
References
43
Citations by year
2026: 27 · 2025: 85 · 2024: 110 · 2023: 106 · 2022: 77 · 2021: 10
FWCI
27.76
Type
journal article
Language
en
Open access
Licence
Locations
  • Machine Learning with Applications (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Greater South Information System
Funders
  • Budapesti Műszaki és Gazdaságtudományi Egyetem
  • FP7 Information and Communication Technologies
  • Department of Information Technology, Ministry of Communications and Information Technology
Topics
  • Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
skin cancer classification, skin lesion images, benign versus malignant differentiation, deep convolutional neural networks, transfer learning, HAM10000 dataset, data augmentation, image preprocessing, early cancer detection

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