Visualizing CoAtNet Predictions for Aiding Melanoma Detection

TL;DR

This paper introduces a hybrid CoAtNet model for melanoma classification, combining CNN and Transformer features to improve early detection accuracy, potentially aiding clinical diagnosis and patient outcomes.

Contribution

It presents a novel multi-class melanoma classifier using CoAtNet, integrating convolutional and Transformer architectures for enhanced generalization and performance.

Findings

Achieved 0.901 precision and 0.895 recall in melanoma classification.

Attained 0.923 average precision, outperforming existing models.

Demonstrated potential for aiding early melanoma diagnosis.

Abstract

Melanoma is considered to be the most aggressive form of skin cancer. Due to the similar shape of malignant and benign cancerous lesions, doctors spend considerably more time when diagnosing these findings. At present, the evaluation of malignancy is performed primarily by invasive histological examination of the suspicious lesion. Developing an accurate classifier for early and efficient detection can minimize and monitor the harmful effects of skin cancer and increase patient survival rates. This paper proposes a multi-class classification task using the CoAtNet architecture, a hybrid model that combines the depthwise convolution matrix operation of traditional convolutional neural networks with the strengths of Transformer models and self-attention mechanics to achieve better generalization and capacity. The proposed multi-class classifier achieves an overall precision of 0.901, recall 0.895, and AP 0.923, indicating high performance compared to other state-of-the-art networks.