利用超分辨率卷积神经网络实现胸片六十四倍数据缩减
研究训练超分辨率卷积神经网络,从64倍缩减数据生成胸片,用112张胸片(含气胸、结节、实变、磨玻璃影)验证。SR图像较线性插值更接近原图(MSE 9269±1015 vs 9429±1057,P=0.02),噪声更低,三位胸科放射科医生判读气胸、结节、实变、磨玻璃影的合并敏感度与原图无显著差异。
要点
- SR重建胸片噪声低于原图和线性插值图,三位放射科医生噪声评分更优(Ps<.01)。
- SR重建图检测气胸、结节、实变、磨玻璃影的合并敏感度与原图无显著差异。
- SR图像与原图相似度优于线性插值重建(MSE 9269±1015 vs 9429±1057,P=0.02)。
核心结论
- 使用64倍缩减数据经SR重建的胸片噪声水平低于原图,检测主要异常的敏感度与原图相当。
研究设计与样本
- 研究论文;训练SR卷积神经网络用128×128 patches(n=127030)从64倍缩减图像生成原分辨率图像;验证集112张胸片,含气胸17张、结节20张、实变18张、磨玻璃影16张;三位胸科放射科医生评估。
关键影像表现/征象
- SR重建图像较线性插值重建图像更接近原图(MSE 9269±1015 vs 9429±1057,P=0.02)。
- SR图像测量噪声低于原图和线性插值重建图,三位放射科医生对其噪声水平评分更优(Ps<.01)。
诊断标准与关键数值
- SR重建图检测气胸合并敏感度90.2%(46/51) vs 原图96.1%(49/51),P=0.19。
- SR重建图检测结节合并敏感度90.0%(54/60) vs 原图85.0%(51/60),P=0.26。
- SR重建图检测实变合并敏感度100%(54/54) vs 原图96.3%(52/54),P=0.50。
- SR重建图检测磨玻璃影合并敏感度91.7%(44/48) vs 原图95.8%(46/48),P=0.69。
临床应用与阅片要点
- SR重建胸片在检测气胸、结节、实变和磨玻璃影时合并敏感度与原图无显著差异,噪声评分更优。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: To develop and validate a super-resolution (SR) algorithm generating clinically feasible chest radiographs from 64-fold reduced data.
METHODS: An SR convolutional neural network was trained to produce original-resolution images (output) from 64-fold reduced images (input) using 128 × 128 patches (n = 127 030). For validation, 112 radiographs-including those with pneumothorax (n = 17), nodules (n = 20), consolidations (n = 18), and ground-glass opacity (GGO; n = 16)-were collected. Three image sets were prepared: the original images and those reconstructed using SR and conventional linear interpolation (LI) using 64-fold reduced data. The mean-squared error (MSE) was calculated to measure similarity between the reconstructed and original images, and image noise was quantified. Three thoracic radiologists evaluated the quality of each image and decided whether any abnormalities were present.
RESULTS: The SR-images were more similar to the original images than the LI-reconstructed images (MSE: 9269 ± 1015 vs. 9429 ± 1057; P = .02). The SR-images showed lower measured noise and scored better noise level by three radiologists than both original and LI-reconstructed images (Ps < .01). The radiologists' pooled sensitivity with the SR-reconstructed images was not significantly different compared with the original images for detecting pneumothorax (SR vs. original, 90.2% [46/51] vs. 96.1% [49/51]; P = .19), nodule (90.0% [54/60] vs. 85.0% [51/60]; P = .26), consolidation (100% [54/54] vs. 96.3% [52/54]; P = .50), and GGO (91.7% [44/48] vs. 95.8% [46/48]; P = .69).
CONCLUSIONS: SR-reconstructed chest radiographs using 64-fold reduced data showed a lower noise level than the original images, with equivalent sensitivity for detecting major abnormalities.
ADVANCES IN KNOWLEDGE: This is the first study applying super-resolution in data reduction of chest radiographs.
引用
- Nam JG, Kang SK, Choi H, et al. Sixty-four-fold data reduction of chest radiographs using a super-resolution convolutional neural network. Br J Radiol. 2024. PMID: 38265235. doi:10.1093/bjr/tqae006
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。