Back

A Hybrid Framework for Accurate Melanoma Diagnosis: Leveraging Generative AI with Enhanced CNN+ Architectures

Wu, Y.; Zhang, B.; Yan, Y.; Li, J.; Wu, Y.; Kim, S. S.; Huang, K.; Ye, Q.; Yu, Y.; Tong, G.

2026-04-28 dermatology
10.64898/2026.04.27.26351813 medRxiv
Show abstract

Melanocytes become cancerous, forming tumors that may invade and destroy the surrounding tissues. When melanocytes acquire invasive characteristics, the anchored melanoma begins to damage the normal cells. Therefore, early intervention and diagnosis are essential to avoid high morbidity and mortality in malignant melanoma. However, It is challenging to distinguish the difference between malignant melanoma and benign clump of melanocytes. Based on a data set of 10,000 melanocyte tumors, this paper develops a new model system to improve the accuracy of distinguishing between benign and malignant melanocytes. In the first stage, the original CNN architectures are used, such as ResNet18, ResNet50, VGG11, and VGG16. Synthetic medical images, generated via a Diffusion Model to extract informative features from the original dataset, are used to train the CNN architectures. This approach improves classification accuracy from 91.1% to 92.9%. In the second stage, the fully connected layer of each neural network is replaced with a high-level classifier, XGBoost, to perform secondary classification. This hybrid strategy further enhances performance, achieving up to 93.3% accuracy by using the synthetic images.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

1
PLOS ONE
4510 papers in training set
Top 17%
10.4%
2
Scientific Reports
3102 papers in training set
Top 5%
10.4%
3
Informatics in Medicine Unlocked
21 papers in training set
Top 0.1%
7.0%
4
Frontiers in Medicine
113 papers in training set
Top 0.7%
5.0%
5
Bulletin of Mathematical Biology
84 papers in training set
Top 0.4%
4.4%
6
Frontiers in Computational Neuroscience
53 papers in training set
Top 0.6%
3.8%
7
Frontiers in Public Health
140 papers in training set
Top 2%
3.2%
8
Bioengineering
24 papers in training set
Top 0.1%
3.2%
9
Computers in Biology and Medicine
120 papers in training set
Top 1%
2.7%
10
IEEE Access
31 papers in training set
Top 0.2%
2.4%
50% of probability mass above
11
European Journal of Cancer
10 papers in training set
Top 0.1%
2.1%
12
IEEE Journal of Biomedical and Health Informatics
34 papers in training set
Top 0.7%
2.1%
13
Frontiers in Immunology
586 papers in training set
Top 3%
2.1%
14
Medical Image Analysis
33 papers in training set
Top 0.6%
1.8%
15
Neurocomputing
13 papers in training set
Top 0.2%
1.7%
16
Biology Methods and Protocols
53 papers in training set
Top 0.9%
1.7%
17
Journal of Pathology Informatics
13 papers in training set
Top 0.2%
1.5%
18
BMC Cancer
52 papers in training set
Top 2%
1.4%
19
Nature Machine Intelligence
61 papers in training set
Top 2%
1.4%
20
Nature Communications
4913 papers in training set
Top 55%
1.4%
21
npj Digital Medicine
97 papers in training set
Top 3%
1.3%
22
PLOS Digital Health
91 papers in training set
Top 2%
1.0%
23
Cells
232 papers in training set
Top 4%
1.0%
24
iScience
1063 papers in training set
Top 24%
1.0%
25
Biomedical Signal Processing and Control
18 papers in training set
Top 0.4%
0.9%
26
Journal of Medical Imaging
11 papers in training set
Top 0.2%
0.9%
27
npj Precision Oncology
48 papers in training set
Top 1%
0.9%
28
Expert Systems with Applications
11 papers in training set
Top 0.3%
0.8%
29
Cureus
67 papers in training set
Top 4%
0.8%
30
PLOS Computational Biology
1633 papers in training set
Top 24%
0.8%