Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Runhao, Zha, Fengyi, Ding, Fei, Yao, Guangzhen, Zhang, Peng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916062645190656
author Liu, Runhao
Zha, Fengyi
Ding, Fei
Yao, Guangzhen
Zhang, Peng
author_facet Liu, Runhao
Zha, Fengyi
Ding, Fei
Yao, Guangzhen
Zhang, Peng
contents Skin cancer classification is challenging due to high inter-class similarity, intra-class variability, and artifacts in dermoscopic images. To address these issues, we propose an improved ResNet-50 with Adaptive Spatial Feature Fusion (ASFF), which adaptively integrates multi-scale semantic and surface features to refine representations and reduce overfitting. The ResNet-50 model is enhanced with an adaptive feature fusion mechanism to achieve more effective multi-scale feature extraction and improve overall performance. Specifically, a dual-branch design fuses high-level semantic and mid-level detail features which use global average pooling and fully connected layers to produce spatial weights, and emphasizes lesion-relevant regions. Evaluated on a balanced subset of ISIC 2020 (3,297 images, randomly selected from the original dataset), the ASFF-based ResNet-50 outperforms multiple CNN baselines, achieving 93.182% accuracy with superior precision, recall, specificity, and F1. It also reaches 0.9670 AUC (P-R) and 0.9717 AUC (ROC). Grad-CAM visualizations show more accurate focus on lesion areas.The proposed model also generalizes well to ISIC 2019 external validation, outperforming the ResNet-50 baseline. These findings demonstrate that the proposed approach provides a more effective and efficient solution for computer-aided skin cancer diagnosis. The generation codes, weights and confusion matrices are open sourced in https://github.com/Grapesea/ASFF-ResNet50-enhanced.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion
Liu, Runhao
Zha, Fengyi
Ding, Fei
Yao, Guangzhen
Zhang, Peng
Computer Vision and Pattern Recognition
Skin cancer classification is challenging due to high inter-class similarity, intra-class variability, and artifacts in dermoscopic images. To address these issues, we propose an improved ResNet-50 with Adaptive Spatial Feature Fusion (ASFF), which adaptively integrates multi-scale semantic and surface features to refine representations and reduce overfitting. The ResNet-50 model is enhanced with an adaptive feature fusion mechanism to achieve more effective multi-scale feature extraction and improve overall performance. Specifically, a dual-branch design fuses high-level semantic and mid-level detail features which use global average pooling and fully connected layers to produce spatial weights, and emphasizes lesion-relevant regions. Evaluated on a balanced subset of ISIC 2020 (3,297 images, randomly selected from the original dataset), the ASFF-based ResNet-50 outperforms multiple CNN baselines, achieving 93.182% accuracy with superior precision, recall, specificity, and F1. It also reaches 0.9670 AUC (P-R) and 0.9717 AUC (ROC). Grad-CAM visualizations show more accurate focus on lesion areas.The proposed model also generalizes well to ISIC 2019 external validation, outperforming the ResNet-50 baseline. These findings demonstrate that the proposed approach provides a more effective and efficient solution for computer-aided skin cancer diagnosis. The generation codes, weights and confusion matrices are open sourced in https://github.com/Grapesea/ASFF-ResNet50-enhanced.
title Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.03876