CNNs, Transformers, Hybrid, and Vision Language Models for Skin Cancer Detection

2026-05-25

AI Summary

This study addresses the lack of unified evaluation of diverse deep learning models for skin cancer detection, which has hindered informed model selection for clinical deployment. We present the first systematic comparison of twelve state-of-the-art architectures—including CNNs, Vision Transformers, hybrid models (e.g., MaxViT Tiny, CoAtNet0), and vision-language models (e.g., SigLIP, CLIP)—within a consistent framework on the PAD-UFES-20 dataset, focusing on binary classification for screening. Performance is assessed using clinically relevant metrics such as AUC and sensitivity at 80% specificity. Results demonstrate that hybrid models and SigLIP achieve the best overall performance, while CLIP exhibits notably high precision. This work establishes a reproducible benchmark to guide practical model selection, with all code publicly released.

Abstract

Skin cancer is a common and fast rising malignancy worldwide. Early detection is critical for improving outcomes. Deep learning models trained on dermoscopic and clinical images can support automated and fast triage. However, many studies evaluate only a limited set of architectures. Experimental setups also vary across studies. In this paper, we present a unified evaluation of twelve deep learning models for binary skin cancer detection on the PAD-UFES-20 dataset. The models span four families: convolutional neural networks (CNN), vision transformers (ViT), hybrid convolution transformer backbones, and vision language models (VLM). Performance is assessed using AUC, the maximum F1 score with its precision and recall, and sensitivity at 80% specificity, reflecting screening oriented requirements. Our results show that well tuned CNNs already provide strong baselines, but transformer based families consistently improve discrimination. Hybrid models (MaxViT Tiny, CoAtNet0) and a SigLIP based VLM achieve the best overall trade off between ranking performance and clinically relevant operating points, while CLIP based model offers high precision. The full codebase for all experiments is publicly released. Together, these findings offer practical guidance on which model families are most suitable for real world deployment in skin cancer screening and establish a reproducible reference point for future work on PAD-UFES-20.

Problem

• skin cancer detection
• deep learning models
• model evaluation
• unified benchmark
• PAD-UFES-20

Innovation

• vision transformers
• hybrid architectures
• vision language models
• skin cancer detection
• unified evaluation