article · Cluster Computing
Skin cancer is a dangerous malignancy that can spread rapidly throughout the body, making early identification vital to prevent critical complications and avoid aggressive interventions. Convolutional neural networks assist medical professionals by extracting complex visual features from clinical images to identify abnormalities at nascent stages. A deep convolutional neural network architecture was developed to classify multiple categories of skin cancer lesions. When tested against standard benchmark transfer learning models, including VGG16, VGG19, DenseNet121, DenseNet201, and MobileNetV2, the architecture demonstrated superior performance on unbalanced datasets. It achieved an accuracy of 98.5 percent on the HAM10000 dataset and 97.1 percent on the ISIC-2019 dataset. The framework effectively addresses problems arising from class imbalance, offering high precision, recall, and specificity in distinguishing different types of lesions.
Early diagnosis of skin cancer significantly reduces the risk of complications and the necessity for aggressive medical treatment. Developing artificial intelligence models that can reliably identify lesions despite uneven and unbalanced clinical data gives dermatologists a more robust diagnostic aid, potentially improving clinical decision-making and patient outcomes during early stages of disease.
The framework is designed as a diagnostic support tool for dermatologists and medical practitioners to classify skin lesions from digital images. Tested on established benchmark datasets rather than in clinical trials, the technology is at an applied research stage. Further validation in real-world clinical workflows and integration into medical imaging software would be required before commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Skin cancer is one of the most dangerous types of cancer due to its immediate appearance and the possibility of rapid spread. It arises from uncontrollably growing cells, rapidly dividing cells in one area of the body, invading other bodily tissues, and spreading throughout the body. Early detection helps prevent cancer progress from reaching critical levels, reducing the risk of complications and the need for more aggressive treatment options. Convolutional neural networks (CNNs) revolutionize skin cancer diagnosis by extracting intricate features from images, enabling an accurate classification of lesions. Their role extends to early detection, providing a powerful tool for dermatologists to identify abnormalities in their nascent stages, ultimately improving patient outcomes. This study proposes a novel deep convolutional neural network (DCNN) approach to classifying skin cancer lesions. The proposed DCNN model is evaluated using two unbalanced datasets, namely HAM10000 and ISIC-2019. The DCNN model is compared with other transfer learning models, including VGG16, VGG19, DenseNet121, DenseNet201, and MobileNetV2. Its performance is assessed using four widely used evaluation metrics: accuracy, recall, precision, F1-score, specificity, and AUC. The experimental results demonstrate that the proposed DCNN model outperforms other deep learning (DL) models that utilized these datasets. The proposed DCNN model achieved the highest accuracy with the HAM10000 and ISIC-2019 datasets, reaching $$98.5\%$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>98.5</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> and $$97.1\%$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mn>97.1</mml:mn> <mml:mo>%</mml:mo> </mml:mrow> </mml:math> , respectively. These experimental results show how competitive and successful the DCNN model is in overcoming the problems caused by class imbalance and raising skin cancer classification accuracy. Furthermore, the proposed model demonstrates superior performance, particularly excelling in terms of accuracy, compared to other recent studies that utilize the same datasets, which highlights the robustness and effectiveness of the proposed DCNN.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s10586-024-04540-1
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
