深度学习计算机辅助检测肺结节或肿块的胸片最佳矩阵尺寸研究
该回顾性研究从两家机构收集2088张异常(结节/肿块)和352张正常胸片,由三位胸部放射科医师标注2758个异常区域,用1736张异常胸片训练卷积神经网络(CNN),剩余352张异常和352张正常胸片作为测试集,比较不同矩阵尺寸(256、448、896、1344、1792)对Mask R-CNN和RetinaNet检测性能的影响。结果显示矩阵尺寸896在两种CNN中均表现出最高或显著较高的检测性能(FOM和敏感度),且无需额外训练数据即可提升CAD性能。
要点
- 矩阵尺寸896在Mask R-CNN和RetinaNet中均获得最高FOM(分别为0.869和0.906)。
- 输入矩阵尺寸显著影响深度学习CAD检测胸片结节或肿块的性能。
诊断标准与关键数值
- Mask R-CNN中矩阵尺寸896和1344的FOM分别为0.869和0.856,显著高于256、448和1792的FOM(0.667-0.820)(p < 0.05)。
- RetinaNet中矩阵尺寸896的FOM为0.906,显著高于其他尺寸(0.329-0.832)(p < 0.05)。
- 小 nodules(<10 mm)敏感度分别为0.418和0.409,肿块敏感度分别为0.937和0.956。
- Mask R-CNN中矩阵尺寸896和1344以及RetinaNet中矩阵尺寸896的敏感度显著高于其他尺寸(p < 0.05)。
临床应用与阅片要点
- 作者结论认为矩阵尺寸896在不同CNN模型中对各种大小异常检测性能最高。
- 作者结论认为最佳矩阵尺寸可在不增加训练数据的情况下提升CAD性能。
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 investigate the optimal input matrix size for deep learning-based computer-aided detection (CAD) of nodules and masses on chest radiographs.
METHODS: We retrospectively collected 2088 abnormal (nodule/mass) and 352 normal chest radiographs from two institutions. Three thoracic radiologists drew 2758 abnormalities regions. A total of 1736 abnormal chest radiographs were used for training and tuning convolutional neural networks (CNNs). The remaining 352 abnormal and 352 normal chest radiographs were used as a test set. Two CNNs (Mask R-CNN and RetinaNet) were selected to validate the effects of the squared different matrix size of chest radiograph (256, 448, 896, 1344, and 1792). For comparison, figure of merit (FOM) of jackknife free-response receiver operating curve and sensitivity were obtained.
RESULTS: In Mask R-CNN, matrix size 896 and 1344 achieved significantly higher FOM (0.869 and 0.856, respectively) for detecting abnormalities than 256, 448, and 1792 (0.667-0.820) (p < 0.05). In RetinaNet, matrix size 896 was significantly higher FOM (0.906) than others (0.329-0.832) (p < 0.05). For sensitivity of abnormalities, there was a tendency to increase sensitivity when lesion size increases. For small nodules (< 10 mm), the sensitivities were 0.418 and 0.409, whereas the sensitivities were 0.937 and 0.956 for masses. Matrix size 896 and 1344 in Mask R-CNN and matrix size 896 in RetinaNet showed significantly higher sensitivity than others (p < 0.05).
CONCLUSIONS: Matrix size 896 had the highest performance for various sizes of abnormalities using different CNNs. The optimal matrix size of chest radiograph could improve CAD performance without additional training data.
KEY POINTS: • Input matrix size significantly affected the performance of a deep learning-based CAD for detection of nodules or masses on chest radiographs. • The matrix size 896 showed the best performance in two different CNN detection models. • The optimal matrix size of chest radiographs could enhance CAD performance without additional training data.
引用
- Kim YG, Lee SM, Lee KH, et al. Optimal matrix size of chest radiographs for computer-aided detection on lung nodule or mass with deep learning. Eur Radiol. 2020. PMID: 32350657. doi:10.1007/s00330-020-06892-9
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。