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

arXiv: https://arxiv.org/abs/2510.03876 · HTML: https://mlsanity.com/paper/2510.03876/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [Probabilistic Method for Optimizing Submarine Search and Rescue Strategy Under Environmental Uncertainty](https://mlsanity.com/paper/2505.02186/) (2025)

## Built on by (most cited first, 1 of 1)

- [Two-Stage Fine-Tuning of ResNet50 for High-Sensitivity Melanoma Detection on Dermoscopic Images](https://mlsanity.com/paper/2606.17504/) (2026)

## Abstract (arXiv)

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.