病灶感知卷积神经网络用于胸部X线片分类
本研究回顾性收集3526例患者的10738张胸部X线片,构建病灶感知卷积神经网络(LACNN)识别14种胸部疾病,并与放射科医师比较。模型在肺不张、肿块和结节上的AUC显著高于放射科医师,其余11种病变无显著差异,单张分类时间约0.197秒。
要点
- LACNN在肺不张、肿块、结节三类病变的AUC显著高于放射科医师。
- 其余11种胸部病变上,模型与放射科医师的鉴别表现无统计学显著差异。
- 模型单张胸片分类耗时约0.197秒,放射科医师约35秒。
核心结论
- LACNN在胸片胸部疾病识别上达到放射科医师级表现,并可能扩大患者获得胸片诊断的机会。
研究设计与样本
- 回顾性收集3526例患者的10738张胸片,其中598例患者的1937张胸片用于训练和优化LACNN的病灶检测网络(LDN)。
- 其余2928例患者的8801张胸片用于训练和测试LACNN的分类网络。
- 模型在独立公开数据集ChestX-ray14上验证泛化能力,并通过遮挡测试可视化决策过程。
- 评估指标包括F1分数、敏感度、特异度和受试者工作特征曲线下面积(AUC)。
关键影像表现/征象
- 原文未报告具体影像征象描述,仅报告模型对14种胸部疾病的分类表现。
诊断标准与关键数值
- 模型对肺不张的AUC为0.831(95%CI:0.807-0.855),高于放射科医师且差异有统计学意义。
- 模型对肿块的AUC为0.959(95%CI:0.944-0.974),高于放射科医师且差异有统计学意义。
- 模型对结节的AUC为0.928(95%CI:0.906-0.950),高于放射科医师且差异有统计学意义。
- 其余11种病变的AUC与放射科医师相比无统计学显著差异。
- 在ChestX-ray14数据集上,该模型与其他先进深度学习方法相比表现出有竞争力的性能。
临床应用与阅片要点
- 引入非图像数据后模型性能略有改善。
- 原文未据此给出针对日常阅片或报告流程的具体推荐。
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
AIM: To investigate the performance of a deep-learning approach termed lesion-aware convolutional neural network (LACNN) to identify 14 different thoracic diseases on chest X-rays (CXRs).
MATERIALS AND METHODS: In total, 10,738 CXRs of 3,526 patients were collected retrospectively. Of these, 1,937 CXRs of 598 patients were selected for training and optimising the lesion-detection network (LDN) of LACNN. The remaining 8,801 CXRs from 2,928 patients were used to train and test the classification network of LACNN. The discriminative performance of the deep-learning approach was compared with that obtained by the radiologists. In addition, its generalisation was validated on the independent public dataset, ChestX-ray14. The decision-making process of the model was visualised by occlusion testing, and the effect of the integration of CXRs and non-image data on model performance was also investigated. In a systematic evaluation, F1 score, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) metrics were calculated.
RESULTS: The model generated statistically significantly higher AUC performance compared with radiologists on atelectasis, mass, and nodule, with AUC values of 0.831 (95% confidence interval [CI]: 0.807-0.855), 0.959 (95% CI: 0.944-0.974), and 0.928 (95% CI: 0.906-0.950), respectively. For the other 11 pathologies, there were no statistically significant differences. The average time to complete each CXR classification in the testing dataset was substantially longer for the radiologists (∼35 seconds) than for the LACNN (∼0.197 seconds). In the ChestX-ray14 dataset, the present model also showed competitive performance in comparison with other state-of-the-art deep-learning approaches. Model performance was slightly improved when introducing non-image data.
CONCLUSION: The proposed LACNN achieved radiologist-level performance in identifying thoracic diseases on CXRs, and could potentially expand patient access to CXR diagnostics.
引用
- Li F, Shi JX, Yan L, et al. Lesion-aware convolutional neural network for chest radiograph classification. Clin Radiol. 2020. PMID: 33077154. doi:10.1016/j.crad.2020.08.027
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。