Presently morphological evaluation and special staining scoring system are important components of basic and clinical research, and are very important for judging the efficacy of drugs and gene intervention. However, the current visual scoring system has some disadvantages such as strong subjectivity, poor repeatability and low accuracy, and is prone to missed diagnosis and misdiagnosis. Artificial intelligence technology based on deep learning is expected to overcome these problems. In our study, we found that the convolutional neural network can be used to accurately extract internal features related to the treatment and prognosis of tumors, such as tumor-stroma ratio, nerve invasion and spatial distribution of lymphatic cells in tumor specimens, visualizing and digitalizing the curative effect of drug intervention on disease progression, and can quantify and automatic evaluate the expression of molecular biomarkers related to clinical treatment, classification and prognosis. The application of artificial intelligence technology in tissue and cell morphology assessment will promote the consistency, repeatability and accuracy of clinical drug evaluation and basic scientific research evaluation, and is expected to further promote the development of medical research.