Automatic sketching method for CT image breast cancer clinical target region based on deep learning

The invention discloses an automatic sketching method for a CT image breast cancer clinical target region based on deep learning. The method comprises the following steps of data acquisition: firstly, acquiring the CT image of a breast cancer patient before radiotherapy and the contour data of the clinical target region sketched manually by a doctor from a hospital; data preprocessing: after preprocessing the acquired contour data of the clinical target region, dividing the contour data into a training set and a test set according to a proportion of 8: 2; model training: sending the preprocessed training set into a constructed convolutional neural network for model training, and stopping training when the loss function of the test set reaches the minimum; and prediction result fusion: performing prediction by using the model to obtain a mask of a neck drainage area, a mask of a breast target area and a mask of an inner breast drainage area, and performing post-processing on the three masks to fuse into the in