Abstract: A method and system for segmenting three-dimensional images of pancreases and tumors, including: acquiring 3D images of the pancreas and the tumor and preprocessing same with a soft tissue window to control the intensity value of the image within a set range; cropping all images into block-shaped regions of a set size and feeding same into a trained convolutional neural network model, and when training a network, dynamically adjusting the learning weight between the pancreas and the tumor under the guidance of temperature to learn the features of the pancreas and the tumor; and after performing data preprocessing on the 3D images of the pancreas and labels, using the trained network model for online testing and evaluating, and outputting the segmentation result.