Department of Radiology.
Department of Bioengineering, and.
Am J Respir Cell Mol Biol. 2023 Aug;69(2):126-134. doi: 10.1165/rcmb.2023-0051MA.
Chord length is an indirect measure of alveolar size and a critical endpoint in animal models of chronic obstructive pulmonary disease (COPD). In assessing chord length, the lumens of nonalveolar structures are eliminated from measurement by various methods, including manual masking. However, manual masking is resource intensive and can introduce variability and bias. We created a fully automated deep learning-based tool to mask murine lung images and assess chord length to facilitate mechanistic and therapeutic discovery in COPD called Deep-Masker (available at http://47.93.0.75:8110/login). We trained the deep learning algorithm for Deep-Masker using 1,217 images from 137 mice from 12 strains exposed to room air or cigarette smoke for 6 months. We validated this algorithm against manual masking. Deep-Masker demonstrated high accuracy with an average difference in chord length compared with manual masking of -0.3 ± 1.4% (s = 0.99) for room-air-exposed mice and 0.7 ± 1.9% (s = 0.99) for cigarette-smoke-exposed mice. The difference between Deep-Masker and manually masked images for change in chord length because of cigarette smoke exposure was 6.0 ± 9.2% (s = 0.95). These values exceed published estimates for interobserver variability for manual masking (s = 0.65) and the accuracy of published algorithms by a significant margin. We validated the performance of Deep-Masker using an independent set of images. Deep-Masker can be an accurate, precise, fully automated method to standardize chord length measurement in murine models of lung disease.
弦长是肺泡大小的间接测量指标，也是慢性阻塞性肺疾病（COPD）动物模型的一个关键终点。在评估弦长时，通过各种方法（包括手动掩蔽）消除非肺泡结构的腔隙进行测量。然而，手动掩蔽需要大量的资源，并且可能会引入变异性和偏差。我们创建了一种完全自动化的深度学习工具，称为 Deep-Masker，用于掩蔽鼠肺图像并评估弦长，以促进 COPD 的机制和治疗发现（可在 http://47.93.0.75:8110/login 获得）。我们使用来自 12 个品系的 137 只暴露于室内空气或香烟烟雾 6 个月的小鼠的 1217 张图像对 Deep-Masker 的深度学习算法进行了训练。我们通过手动掩蔽对该算法进行了验证。Deep-Masker 表现出很高的准确性，与手动掩蔽相比，暴露于室内空气的小鼠的弦长平均差异为-0.3±1.4%（s=0.99），暴露于香烟烟雾的小鼠的弦长平均差异为 0.7±1.9%（s=0.99）。由于香烟烟雾暴露而导致的弦长变化，Deep-Masker 与手动掩蔽图像之间的差异为 6.0±9.2%（s=0.95）。这些值超过了手动掩蔽的观察者间变异性（s=0.65）和已发表算法的准确性的公布估计值。我们使用独立的图像集验证了 Deep-Masker 的性能。Deep-Masker 可以成为一种准确、精确、完全自动化的方法，用于标准化肺部疾病的鼠模型中的弦长测量。
