用EfficientNet-B4+U-Net自动分割胸部X光片气胸区域，提升诊断准确率。
Chest X-ray Pneumothorax Segmentation Using EfficientNet-B4 Transfer Learning in a U-Net Architecture
- 采用EfficientNet-B4作为编码器的U-Net结构，实现高效特征提取
- 在PTX-498数据集上达到0.7008的IoU和0.8241的Dice分数
- 适合临床辅助诊断，尤其帮助识别微小气胸病变
气胸是胸膜腔内异常积气，若未及时发现可能危及生命。胸部X光片是首选诊断工具，但小病灶常不明显。本文提出一种基于U-Net与EfficientNet-B4编码器的自动化深度学习分割流程，使用SIIM-ACR数据集进行训练，结合数据增强和二元交叉熵加Dice损失函数，在独立的PTX-498数据集上取得0.7008的交并比（IoU）和0.8241的Dice评分。结果表明该模型能精准定位气胸区域，有效辅助放射科医生诊断。
原文摘要 · Abstract (English)
Pneumothorax, the abnormal accumulation of air in the pleural space, can be life-threatening if undetected. Chest X-rays are the first-line diagnostic tool, but small cases may be subtle. We propose an automated deep-learning pipeline using a U-Net with an EfficientNet-B4 encoder to segment pneumothorax regions. Trained on the SIIM-ACR dataset with data augmentation and a combined binary cross-entropy plus Dice loss, the model achieved an IoU of 0.7008 and Dice score of 0.8241 on the independent PTX-498 dataset. These results demonstrate that the model can accurately localize pneumothoraces and support radiologists.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。