National Institute of Parasitic Diseases, Chinese Center for Disease Control and Prevention (Chinese Center for Tropical Diseases Research); NHC Key Laboratory of Parasite and Vector Biology; WHO Collaborating Centre for Tropical Diseases, National Center for International Research On Tropical Diseases, Shanghai, 200025, China.
School of Global Health, Chinese Center for Tropical Diseases Research, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
Infect Dis Poverty. 2023 Feb 7;12(1):6. doi: 10.1186/s40249-023-01060-9.
China is progressing towards the goal of schistosomiasis elimination, but there are still some problems, such as difficult management of infection source and snail control. This study aimed to develop deep learning models with high-resolution remote sensing images for recognizing and monitoring livestock bovine, which is an intermediate source of Schistosoma japonicum infection, and to evaluate the effectiveness of the models for real-world application.
The dataset of livestock bovine's spatial distribution was collected from the Chinese National Platform for Common Geospatial Information Services. The high-resolution remote sensing images were further divided into training data, test data, and validation data for model development. Two recognition models based on deep learning methods (ENVINet5 and Mask R-CNN) were developed with reference to the training datasets. The performance of the developed models was evaluated by the performance metrics of precision, recall, and F1-score.
A total of 50 typical image areas were selected, 1125 bovine objectives were labeled by the ENVINet5 model and 1277 bovine objectives were labeled by the Mask R-CNN model. For the ENVINet5 model, a total of 1598 records of bovine distribution were recognized. The model precision and recall were 81.9% and 80.2%, respectively. The F1 score was 0.81. For the Mask R-CNN mode, 1679 records of bovine objectives were identified. The model precision and recall were 87.3% and 85.2%, respectively. The F1 score was 0.87. When applying the developed models to real-world schistosomiasis-endemic regions, there were 63 bovine objectives in the original image, 53 records were extracted using the ENVINet5 model, and 57 records were extracted using the Mask R-CNN model. The successful recognition ratios were 84.1% and 90.5% for the respectively developed models.
The ENVINet5 model is very feasible when the bovine distribution is low in structure with few samples. The Mask R-CNN model has a good framework design and runs highly efficiently. The livestock recognition models developed using deep learning methods with high-resolution remote sensing images accurately recognize the spatial distribution of livestock, which could enable precise control of schistosomiasis.
中国在实现消除血吸虫病目标的进程中，仍面临着传染源管理和钉螺控制等难题。本研究旨在利用高分辨率遥感图像开发深度学习模型，以识别和监测家畜牛，因为家畜牛是日本血吸虫感染的中间宿主，并评估模型在实际应用中的有效性。
家畜牛的空间分布数据集来源于中国国家地理空间信息公共服务平台。利用高分辨率遥感图像进一步划分为训练数据、测试数据和验证数据，用于模型开发。参考训练数据集，开发了两种基于深度学习方法的识别模型（ENVINet5 和 Mask R-CNN）。通过精度、召回率和 F1 分数等性能指标来评估开发模型的性能。
共选择了 50 个典型图像区域，ENVINet5 模型标记了 1125 头牛，Mask R-CNN 模型标记了 1277 头牛。对于 ENVINet5 模型，共识别了 1598 条牛的分布记录。模型的精度和召回率分别为 81.9%和 80.2%，F1 分数为 0.81。对于 Mask R-CNN 模型，共识别了 1679 条牛的目标。模型的精度和召回率分别为 87.3%和 85.2%，F1 分数为 0.87。将开发的模型应用于实际血吸虫病流行地区，原始图像中有 63 头牛，ENVINet5 模型提取了 53 条记录，Mask R-CNN 模型提取了 57 条记录。两个模型的成功识别率分别为 84.1%和 90.5%。
当牛的分布结构简单、样本较少时，ENVINet5 模型非常可行。Mask R-CNN 模型具有良好的框架设计，运行效率高。利用高分辨率遥感图像和深度学习方法开发的家畜识别模型能够准确识别家畜的空间分布，从而实现血吸虫病的精准防控。
