近年来，随着人工智能（artificial intelligence， AI）算法模型的快速发展，出现了以图像分类为主要功能的卷积神经网络（convolutional neural network， CNN）算法、决策分类的决策树和支持向量机模型、提高模型识别精准性的注意力机制模型、完成图像中病灶识别定位的目标检测模型，以及实现图像中病灶精准分割的语义分割和实例分割模型等。AI的CNN与医学影像深度融合，显著提高了疾病诊断的效率和精准率。随着数字医学水平提高，AI在疾病诊疗路径中图像数据结合点进一步拓宽。除了传统的放射学、超声学、内镜学和病理学等图像，手术切除标本图像和类器官图像等非经典图像也逐步被纳入了AI研究范畴。AI的深度介入有助于解码多维数据中的隐性信息，不断改变疾病的诊治模式。可以预见，未来AI算法与各类疾病诊疗设备镶嵌整合，将成为疾病诊断、治疗乃至发展趋势预判的有力工具。

In recent years, with the rapid development of artificial intelligence (AI) algorithm models, a variety of approaches have emerged, such as convolutional neural networks (CNN) algorithms mainly for image classification, decision trees and support vector machine models for decision classification, attention mechanism models for impro-ving identification accuracy, object detection models for lesion identification and localization in images, and semantic segmentation and instance segmentation models for precise lesion segmentation in images. The deep integration of AI-based CNN with medical imaging has significantly improved the efficiency and accuracy of disease diagnosis. With the improvement of digital medicine, the integration points of image data with AI in disease diagnosis and treatment pathways have further expanded. Besides traditional images, (radiology, ultrasonography, endoscopy, pathology), non-classical images, such as surgical resection specimen images and organoid images, are gradually incorporated into the scope of AI research. The deep involvement of AI helps decode hidden information in multi-dimensional data, conti-nuously transforming disease diagnosis and treatment patterns. In the foreseeable future, the integration of AI algorithms with various disease diagnosis and treatment devices will become powerful tools for disease diagnosis, treatment, and even prediction of development trends.