Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2511.18425 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917099980455936 |
|---|---|
| author | Yerzhanuly, Mansur |
| author_facet | Yerzhanuly, Mansur |
| contents | Pneumonia remains a leading global cause of mortality where timely diagnosis is critical. We introduce LungX, a novel hybrid architecture combining EfficientNet's multi-scale features, CBAM attention mechanisms, and Vision Transformer's global context modeling for enhanced pneumonia detection. Evaluated on 20,000 curated chest X-rays from RSNA and CheXpert, LungX achieves state-of-the-art performance (86.5 percent accuracy, 0.943 AUC), representing a 6.7 percent AUC improvement over EfficientNet-B0 baselines. Visual analysis demonstrates superior lesion localization through interpretable attention maps. Future directions include multi-center validation and architectural optimizations targeting 88 percent accuracy for clinical deployment as an AI diagnostic aid. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18425 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LungX: A Hybrid EfficientNet-Vision Transformer Architecture with Multi-Scale Attention for Accurate Pneumonia Detection Yerzhanuly, Mansur Computer Vision and Pattern Recognition Pneumonia remains a leading global cause of mortality where timely diagnosis is critical. We introduce LungX, a novel hybrid architecture combining EfficientNet's multi-scale features, CBAM attention mechanisms, and Vision Transformer's global context modeling for enhanced pneumonia detection. Evaluated on 20,000 curated chest X-rays from RSNA and CheXpert, LungX achieves state-of-the-art performance (86.5 percent accuracy, 0.943 AUC), representing a 6.7 percent AUC improvement over EfficientNet-B0 baselines. Visual analysis demonstrates superior lesion localization through interpretable attention maps. Future directions include multi-center validation and architectural optimizations targeting 88 percent accuracy for clinical deployment as an AI diagnostic aid. |
| title | LungX: A Hybrid EfficientNet-Vision Transformer Architecture with Multi-Scale Attention for Accurate Pneumonia Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.18425 |