DSSCC net enhanced skin cancer classification using SMOTE Tomek and optimized convolutional neural network
8.5
来源：
Nature
关键字：
AI brain science
发布时间：
2025-11-24 23:35
摘要：
DSSCC-Net is a novel deep learning framework designed for skin cancer classification, achieving an impressive accuracy of 97.82% and an AUC of 99.43%. By integrating the SMOTE-Tomek technique, the model effectively addresses class imbalance, enhancing its reliability and interpretability. Validated across multiple datasets, DSSCC-Net shows promise for real-world clinical applications, providing dermatologists with a powerful tool for early and accurate diagnosis of skin cancer.
原文：
查看原文
价值分投票
评分标准
新闻价值分采用0-10分制，综合考虑新闻的真实性、重要性、时效性、影响力等多个维度。
评分越高，表示该新闻的价值越大，越值得关注。
价值维度分析
domain_focus
1.0分+1.0分+0.9分
business_impact
1.0分+0.8分
scientific_rigor
1.5分+1.5分
timeliness_innovation
1.5分+1.5分
investment_perspective
2.5分+2.5分
market_value_relevance
1.0分+1.0分
team_institution_background
0.5分+0.5分
technical_barrier_competition
1.0分+1.0分
关键证据
DSSCC-Net achieved an average accuracy of 97.82% ± 0.37%.
Integration of SMOTE-Tomek significantly improves minority-class detection.
The model demonstrates state-of-the-art performance and readiness for real-world clinical integration.
真实性检查
否
AI评分总结
DSSCC-Net is a novel deep learning framework designed for skin cancer classification, achieving an impressive accuracy of 97.82% and an AUC of 99.43%. By integrating the SMOTE-Tomek technique, the model effectively addresses class imbalance, enhancing its reliability and interpretability. Validated across multiple datasets, DSSCC-Net shows promise for real-world clinical applications, providing dermatologists with a powerful tool for early and accurate diagnosis of skin cancer.