Lung focus detection method and device and training method of image detection model

The invention provides a lung lesion detection method and device and a training method of an image detection model, and the method comprises the steps: carrying out the segmentation of chest radiography image data, and obtaining segmented lung detection image data; inputting the lung detection image data into an image detection model to obtain multilayer feature layer data; inputting the multilayer feature layer data into a first detection sub-model in the image detection model, and outputting a detection frame of a focus of the lung detection image and a first prediction probability of accurately predicting the focus of the lung detection image by the detection frame; and inputting the multilayer feature layer data into a second detection sub-model in the image detection model, and outputting a second prediction probability for predicting whether a focus of the lung detection image exists or not and/or a thermodynamic diagram of a focus area of the lung detection image. 本申请提供了一种肺部病灶检测的方法及装置，和图像检测模型的训练方法，所述肺部