LESION CLASSIFICATION MODEL TRAINING METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM

摘要

The present application discloses a lesion classification model training method and apparatus, a computer device and a storage medium. The lesion classification model training method comprises: acquiring a sample data set, the sample data set containing several sample pictures respectively marked with lesion areas, and each of the lesion areas being respectively marked with a corresponding classification label; performing local image information acquisition processing on each of the lesion areas, so as to obtain local image information of each of the lesion areas; performing global image information acquisition processing on each of the lesion areas, so as to obtain global image information of each of the lesion areas; using the local image information and the global image information of the lesion areas and the classification labels corresponding to the lesion areas to train a pre-established lesion classification model having a dual-input channel, so as to obtain a target lesion classification model. The present application can reduce the requirements for the amount of sample data while implementing accurate classification of lesions.