We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7,194 CT images (3,597 with COPD; 3,597 healthy controls) from 78 subjects (43 with COPD; 35 healthy controls) were selected retrospectively (10.2018-12.2019) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3,392, 1,114, and 2,688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n=7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

翻译：我们旨在通过探索计算机断层扫描（CT）图像中手动调整与自动窗宽优化（WSO），利用卷积神经网络（CNN）优化基于肺气肿存在的慢性阻塞性肺疾病（COPD）二分类检测。回顾性选取2018年10月至2019年12月期间78名受试者（43例COPD患者；35例健康对照）的7,194张CT图像（3,597张COPD图像；3,597张健康对照图像）并进行预处理。对每张图像，强度值被手动裁剪至肺气肿窗宽范围及基线"全范围"窗宽设置。类别平衡的训练集、验证集和测试集分别包含3,392张、1,114张和2,688张图像。通过比较多种CNN架构优化网络骨干结构。此外，通过向模型添加定制化层实现自动窗宽优化。采用图像级别的受试者工作特征曲线下面积（AUC）[95%置信区间下限，上限]比较模型变体。对测试集进行七次重复推理显示，DenseNet为最高效骨干网络，在未使用窗宽优化时平均AUC达0.80 [0.76, 0.85]。相比之下，当输入图像手动调整至肺气肿窗宽范围时，DenseNet模型预测COPD的平均AUC为0.86 [0.82, 0.89]。通过向DenseNet添加定制化窗宽优化层，模型自动学习到接近肺气肿窗宽设置的最优窗宽，平均AUC达0.82 [0.78, 0.86]。将CT数据窗宽优化至肺气肿窗宽范围可改善DenseNet模型对COPD的检测性能。