Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
PreprintCited by 56Cutaneous Melanoma Detection and ManagementAI in cancer detectionAdvanced Neural Network Applications

The DOI matches its Crossref record; 44 of the 49 references it cites were found in a registry or an index.

Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique

Open access
Elshahawy, Manar, Elnemr, Ahmed, Oproescu, Mihai, Schiopu, Adriana-Gabriela, Elgarayhi, Ahmed, Elmogy, Mohammed M., Sallah, Mohammed·2023·Diagnostics
DOI 10.20944/preprints202307.1970.v1PMC PMC10486497

Preprint — published as 10.3390/diagnostics13172804

Open this paper in CoChat — free accountOpen PDF

Abstract

Cancer is a condition in which the body's cells proliferate unchecked. Skin cancer is one of the deadliest diseases that impacts the skin on many levels. There are several different types of the disease, including melanoma, basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanocytic nevus. Due to its increased prevalence, skin cancer, in particular melanoma, is be-coming a serious health problem. Early identification of skin lesions is crucial for successful treatment. Due to their resemblance, many skin lesions are misclassified, which is a severe issue. Researchers seek computer-aided diagnostic tools for early malignant tumor detection. First, a new model based on the combination of "you only look once" (YOLOv5) and "ResNet50" is proposed for melanoma detection with its degree using humans against a machine with 10,000 training images (HAM10000). Second, feature maps integrate gradient change, which allows rapid inference, boosts precision, and reduces the number of hyperparameters in the model, making it smaller. Finally, to get the desired outcomes, the current YOLOv5 model is changed by adding new classes for dermatoscopic images of typical lesions with pigmented skin. The pro-posed approach improves melanoma detection with a real-time speed of 0.4 ms non-maximum suppression (NMS) per image. The performance metrics average is 99.0%, 98.6%, 98.8%, 99.5, 98.3%, and 98.7% for precision, recall, dice similarity coefficient (DSC), accuracy, mean average precision (MAP) from 0.0 to 0.5, and MAP from 0.5 to 0.95, respectively. Compared to cur-rent melanoma detection approaches, the provided approach is more efficient using deep fea-tures.

Overview

Integrity signals

Registry

Crossref · 10.20944/preprints202307.1970.v1

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Figures

Figure 1 Skin lesion classification with common types.
Figure 1 Skin lesion classification with common types.CC BY · PubMed Central
Figure 2 The ABCD lesion diagnosis criteria focus on identifying specifics. Asymmetry: (a) both sides match the other, and (b) one side does not match the other. Border: (c) regular edges and (d) irregular or blurred. Color: (e) consistent shades and (f) different shades. Diameter: (g) the lesion is smaller than 6 mm and (h) the lesion is larger than 6 mm.
Figure 2 The ABCD lesion diagnosis criteria focus on identifying specifics. Asymmetry: (a) both sides match the other, and (b) one side does not match the other. Border: (c) regular edges and (d) irregular or blurred. Color: (e) consistent shades and (f) different shades. Diameter: (g) the lesion is smaller than 6 mm and (h) the lesion is larger than 6 mm.CC BY · PubMed Central
Figure 3 The proposed framework for categorizing seven skin lesions.
Figure 3 The proposed framework for categorizing seven skin lesions.CC BY · PubMed Central
Figure 4 The components of the YOLOv5 model are used for melanoma classification.
Figure 4 The components of the YOLOv5 model are used for melanoma classification.CC BY · PubMed Central
Figure 5 The evaluation of the precision curve, recall curve, and mean average precision at two thresholds for the second run using 100 epochs. (a) precision curve, (b) recall curve, (c) mean average precision at threshold equal 0 to 0.5, and (d) mean average precision at threshold equal 0.5 to 0.95.
Figure 5 The evaluation of the precision curve, recall curve, and mean average precision at two thresholds for the second run using 100 epochs. (a) precision curve, (b) recall curve, (c) mean average precision at threshold equal 0 to 0.5, and (d) mean average precision at threshold equal 0.5 to 0.95.CC BY · PubMed Central
Figure 6 YOLOv5 precision–recall curves for each class. The average precision for each class is the area under each curve for the HAM10000 dataset.
Figure 6 YOLOv5 precision–recall curves for each class. The average precision for each class is the area under each curve for the HAM10000 dataset.CC BY · PubMed Central
Figure 7 An example batch of detection results on some test images using YOLOv5.
Figure 7 An example batch of detection results on some test images using YOLOv5.CC BY · PubMed Central
Figure 8 A comparison between the proposed model and other techniques based on the HAM10000 dataset.
Figure 8 A comparison between the proposed model and other techniques based on the HAM10000 dataset.CC BY · PubMed Central

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Show all 49 references

Cited by

See all 56

Related

See all

Metadata

Authors
Elshahawy, M., Elnemr, A., Oproescu, M., Schiopu, A.-G., Elgarayhi, A., Elmogy, M. M., & Sallah, M.
Affiliations
  • Mansoura University (EG)
  • University of Pitesti (RO)
Corresponding author
  • Oproescu, Mihai
  • Elmogy, Mohammed M.
ORCID
Venue
Diagnostics
Publisher
MDPI AG
Published
2023-07-28
Volume
13
Issue
17
Pages
2804-2804
ISSN
2075-4418 (ISSN-L)
DOI
10.20944/preprints202307.1970.v1
PMC
PMC10486497
OpenAlex
W4386283861
Cited by
51
References
49
Citations by year
2026: 9 · 2025: 29 · 2024: 11 · 2023: 2
FWCI
6.22
Type
journal article
Language
en
Open access
Licence
Locations
  • Diagnostics (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
University of Bisha
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
melanoma detection, skin lesion classification, YOLOv5, ResNet50, dermoscopic images, HAM10000 dataset, computer-aided diagnosis, skin cancer

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. https://app.cochat.ai/papers/10.20944/preprints202307.1970.v1
The paper
Elshahawy, M., Elnemr, A., Oproescu, M., Schiopu, A.-G., Elgarayhi, A., Elmogy, M. M., & Sallah, M. (2023). Early Melanoma Detection Based on a Hybrid YOLOv5 and ResNet Technique. Diagnostics. https://doi.org/10.20944/preprints202307.1970.v1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.