[论文解读] Automated detection and quantification of COVID-19 airspace disease on chest radiographs: A novel approach achieving radiologist-level performance using a CNN trained on digital reconstructed radiographs (DRRs) from CT-based ground-truth
本研究提出一种深度学习方法,使用卷积神经网络(CNN)在基于CT的真值生成的数字化重建放射影像(DRRs)上进行训练,以检测和量化胸部X光片(CXR)上的COVID-19相关肺泡病变。该方法达到放射科医生水平的准确性,预测值与真值之间平均绝对误差(MAE)为9.56%–9.78%,相关系数为0.78–0.81。
Purpose: To leverage volumetric quantification of airspace disease (AD) derived from a superior modality (CT) serving as ground truth, projected onto digitally reconstructed radiographs (DRRs) to: 1) train a convolutional neural network to quantify airspace disease on paired CXRs; and 2) compare the DRR-trained CNN to expert human readers in the CXR evaluation of patients with confirmed COVID-19. Materials and Methods: We retrospectively selected a cohort of 86 COVID-19 patients (with positive RT-PCR), from March-May 2020 at a tertiary hospital in the northeastern USA, who underwent chest CT and CXR within 48 hrs. The ground truth volumetric percentage of COVID-19 related AD (POv) was established by manual AD segmentation on CT. The resulting 3D masks were projected into 2D anterior-posterior digitally reconstructed radiographs (DRR) to compute area-based AD percentage (POa). A convolutional neural network (CNN) was trained with DRR images generated from a larger-scale CT dataset of COVID-19 and non-COVID-19 patients, automatically segmenting lungs, AD and quantifying POa on CXR. CNN POa results were compared to POa quantified on CXR by two expert readers and to the POv ground-truth, by computing correlations and mean absolute errors. Results: Bootstrap mean absolute error (MAE) and correlations between POa and POv were 11.98% [11.05%-12.47%] and 0.77 [0.70-0.82] for average of expert readers, and 9.56%-9.78% [8.83%-10.22%] and 0.78-0.81 [0.73-0.85] for the CNN, respectively. Conclusion: Our CNN trained with DRR using CT-derived airspace quantification achieved expert radiologist level of accuracy in the quantification of airspace disease on CXR, in patients with positive RT-PCR for COVID-19.
研究动机与目标
- 开发一种基于深度学习的准确量化方法,用于胸部X光片(CXR)上COVID-19相关肺泡病变(AD)的评估。
- 利用胸部CT获得的三维肺泡病变分割作为真值,并将其投影至二维DRRs以用于训练。
- 在DRRs上训练卷积神经网络(CNN),以预测CXR上基于面积的肺泡病变百分比(POa)。
- 将CNN的性能与专家放射科医生在检测和量化CXR上AD的表现进行比较。
- 建立一种临床可行的自动化工具,利用标准CXR对确诊COVID-19患者的疾病进展进行监测。
提出的方法
- 获取了86例确诊COVID-19患者组成的回顾性队列,其CT与CXR在48小时内内完成采集。
- 在CT扫描上进行手动三维肺泡病变(AD)分割,以建立基于体积的真值百分比(POv)。
- 将CT上的三维AD掩膜投影至二维前后位DRRs上,计算基于面积的AD百分比(POa),作为CXR的替代指标。
- 在更大规模的CT数据集(包含COVID-19和非COVID-19患者)生成的DRRs图像上训练卷积神经网络(CNN)。
- CNN经过优化,可自动分割肺部和AD,并输出CXR上的POa。
- 通过将CNN的POa预测结果与基于CT的真值(POv)以及两位专家放射科医生测量的POa进行比较,评估CNN的性能。
实验结果
研究问题
- RQ1在基于CT真值生成的DRRs上进行训练的CNN,能否实现对CXR上肺泡病变的准确量化?
- RQ2基于DRRs训练的CNN在测量CXR上AD负荷方面的表现,与专家放射科医生相比如何?
- RQ3使用基于CT的体积分割作为真值,在多大程度上提升了基于CXR的疾病量化准确性?
- RQ4DRR投影方法是否能有效模拟CXR的外观,同时保留疾病负荷信息以用于训练?
- RQ5CNN的性能是否足够稳健,能够在临床评估中达到放射科医生水平的准确性,用于评估COVID-19相关肺部受累情况?
主要发现
- 当将CNN预测的POa与基于CT的真值(POv)比较时,CNN的自 resampling 平均绝对误差(MAE)为9.56%–9.78%。
- CNN在预测POa与POv之间表现出0.78–0.81的相关系数,表明与真值具有高度一致性。
- 两位专家读者的平均值的MAE为11.98% [11.05%–12.47%],与POv的相关系数为0.77 [0.70–0.82]。
- CNN的性能在统计学上与专家放射科医生相当,且具有更低的MAE和略高的相关系数。
- 基于DRR的训练方法使CNN能够有效泛化至真实CXR图像,尽管其训练数据来自CT投影。
- 该方法成功将高精度的CT体积分割迁移至二维CXR,实现了自动化且准确的疾病量化。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。