INTRODUCTION Asbestos is a global occupational health hazard and exposure to it by inhalation predisposes to interstitial as well as malignant pulmonary morbidity. Over time, asbestos fibers embedded in lung tissue can become coated with iron-rich proteins and mucopolysaccharides, after which they are called asbestos bodies and can be detected in light microscopy. Bronchoalveolar lavage, a cytological sample from the lower airways, is one of the methods for diagnosing lung asbestosis and related morbidity. Search for asbestos bodies in these samples is generally laborious and time-consuming. We describe a novel diagnostic method, which implements deep-learning neural network technology for the detection of asbestos bodies in bronchoalveolar lavage samples. METHODS Bronchoalveolar lavage samples with suspicion of asbestos exposure were scanned as whole slide images and uploaded to a cloud-based virtual microscopy platform with a neural network training interface. The images were used for training and testing a neural network model capable of recognizing asbestos bodies. To prioritize the model's sensitivity, we allowed it to also make false-positive suggestions. To test the model, we compared its performance to standard light microscopy diagnostic data as well as the ground truth number of asbestos bodies, which we established by a thorough manual search of the whole slide images. RESULTS We were able to reach overall sensitivity of 93.4 % (95% CI 90.3 - 95.7 %) in the detection of asbestos bodies in comparison to their ground truth number. Compared to standard light microscopy diagnostic data, our model showed equal to or higher sensitivity in most cases. CONCLUSION Our results indicate that deep learning neural network technology offers promising diagnostic tools for routine assessment of bronchoalveolar lavage samples. However, at this stage, a human expert is required to confirm the findings.

中文翻译：

---

深度学习神经网络引导支气管肺泡灌洗样本中石棉体的检测。

简介 石棉是一种全球性的职业健康危害，吸入石棉容易导致间质性和恶性肺部疾病。随着时间的推移，嵌入肺组织中的石棉纤维会被富含铁的蛋白质和粘多糖覆盖，之后它们被称为石棉体，可以在光学显微镜下检测到。支气管肺泡灌洗是来自下呼吸道的细胞学样本，是诊断肺石棉沉着症和相关发病率的方法之一。在这些样本中寻找石棉尸体通常既费力又费时。我们描述了一种新颖的诊断方法，该方法采用深度学习神经网络技术来检测支气管肺泡灌洗样本中的石棉体。方法 将怀疑石棉暴露的支气管肺泡灌洗样本扫描为整个幻灯片图像，并上传到具有神经网络训练接口的基于云的虚拟显微镜平台。这些图像用于训练和测试能够识别石棉体的神经网络模型。为了优先考虑模型的敏感性，我们允许它也提出误报建议。为了测试该模型，我们将其性能与标准光学显微镜诊断数据以及石棉体的地面真实数量进行了比较，这些数据是我们通过对整个幻灯片图像进行彻底的手动搜索而建立的。结果 与地面实况数据相比，我们在检测石棉体时能够达到 93.4%（95% CI 90.3 - 95.7%）的总体灵敏度。与标准光学显微镜诊断数据相比，我们的模型在大多数情况下表现出相同或更高的灵敏度。结论我们的结果表明深度学习神经网络技术为支气管肺泡灌洗样本的常规评估提供了有前途的诊断工具。然而，现阶段需要人类专家来确认研究结果。