Abstract：
BACKGROUND: Cooling towers containing Legionella spp are a high-risk source of Legionnaires\' disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak investigations requires expertise, is labour intensive, and can be prone to errors. We aimed to train a deep learning computer vision model to automatically detect cooling towers that are aerially visible.
METHODS: Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.
RESULTS: The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0-96·1) and a PPV of 90·1% (95% CI 90·0-90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2-93·7) and PPV was 80·8% (80·5-81·2). In Athens, sensitivity was 86·9% (75·8-94·2) and PPV was 85·5% (84·2-86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).
CONCLUSIONS: The model could be used to accelerate investigation and source control during outbreaks of Legionnaires\' disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires\' disease.
BACKGROUND: None.
METHODS: Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.
RESULTS: The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0-96·1) and a PPV of 90·1% (95% CI 90·0-90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2-93·7) and PPV was 80·8% (80·5-81·2). In Athens, sensitivity was 86·9% (75·8-94·2) and PPV was 85·5% (84·2-86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).
CONCLUSIONS: The model could be used to accelerate investigation and source control during outbreaks of Legionnaires\' disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires\' disease.
BACKGROUND: None.
摘要：
背景：含有军团菌的冷却塔是军团菌病暴发的高风险来源。在疫情调查期间从航拍图像手动定位冷却塔需要专业知识,是劳动密集型的，并且容易出错。我们旨在训练一个深度学习计算机视觉模型，以自动检测空中可见的冷却塔。
方法：在2021年1月1日至31日之间，我们提取了费城的卫星视图图像（PN，美国）和纽约州（NY，美国）从谷歌地图和带注释的冷却塔创建训练数据集。我们使用合成数据和模型辅助标记其他城市来增强训练数据。使用包含7292个冷却塔的2051图像，我们使用YOLOv5训练了一个两阶段模型，该模型可以检测图像中的物体，和EfficientNet-b5，一种对图像进行分类的模型。我们评估了模型的敏感性和阳性预测值（PPV）的主要结果，并在548张图像的测试数据集上进行了手动标记，包括来自两个没有参加培训的城市(波士顿[马，美国]和雅典[GA，美国])。我们将模型的搜索速度与四位流行病学家的手动搜索速度进行了比较。
结果：该模型确定了可见的冷却塔，其灵敏度为95·1％（95％CI94·0-96·1），PPV为90·1％（95％CI90·0-90·2）在纽约市和费城。在波士顿,灵敏度为91·6%（89·2～93·7），PPV为80·8%（80·5～81·2）。在雅典,灵敏度为86·9%（75·8～94·2），PPV为85·5%（84·2～86·7）。对于纽约市包含45个街区（0·26平方英里）的区域，该模型的搜索速度比人类调查人员快600倍以上(7·6s;351个潜在冷却塔)(平均83·75分钟[SD29·5];平均310·8冷却塔[42·2])。
结论：该模型可用于通过从航空图像中识别冷却塔来加速军团病暴发期间的调查和源头控制。有可能防止额外的疾病传播。该模型已经被公共卫生团队用于疫情调查和初始化冷却塔登记处，这被认为是预防和应对军团病爆发的最佳实践。
背景：无。
方法：在2021年1月1日至31日之间，我们提取了费城的卫星视图图像（PN，美国）和纽约州（NY，美国）从谷歌地图和带注释的冷却塔创建训练数据集。我们使用合成数据和模型辅助标记其他城市来增强训练数据。使用包含7292个冷却塔的2051图像，我们使用YOLOv5训练了一个两阶段模型，该模型可以检测图像中的物体，和EfficientNet-b5，一种对图像进行分类的模型。我们评估了模型的敏感性和阳性预测值（PPV）的主要结果，并在548张图像的测试数据集上进行了手动标记，包括来自两个没有参加培训的城市(波士顿[马，美国]和雅典[GA，美国])。我们将模型的搜索速度与四位流行病学家的手动搜索速度进行了比较。
结果：该模型确定了可见的冷却塔，其灵敏度为95·1％（95％CI94·0-96·1），PPV为90·1％（95％CI90·0-90·2）在纽约市和费城。在波士顿,灵敏度为91·6%（89·2～93·7），PPV为80·8%（80·5～81·2）。在雅典,灵敏度为86·9%（75·8～94·2），PPV为85·5%（84·2～86·7）。对于纽约市包含45个街区（0·26平方英里）的区域，该模型的搜索速度比人类调查人员快600倍以上(7·6s;351个潜在冷却塔)(平均83·75分钟[SD29·5];平均310·8冷却塔[42·2])。
结论：该模型可用于通过从航空图像中识别冷却塔来加速军团病暴发期间的调查和源头控制。有可能防止额外的疾病传播。该模型已经被公共卫生团队用于疫情调查和初始化冷却塔登记处，这被认为是预防和应对军团病爆发的最佳实践。
背景：无。
