Medical artificial general intelligence (MAGI) enables one foundation model to solve different medical tasks, which is very practical in the medical domain. It can significantly reduce the requirement of large amounts of task-specific data by sufficiently sharing medical knowledge among different tasks. However, due to the challenges of designing strongly generalizable models with limited and complex medical data, most existing approaches tend to develop task-specific models. To take a step towards MAGI, we propose a new paradigm called Medical-knOwledge-enhanced mulTimOdal pretRaining (MOTOR). In MOTOR, we combine two kinds of basic medical knowledge, i.e., general and specific knowledge, in a complementary manner to boost the general pretraining process. As a result, the foundation model with comprehensive basic knowledge can learn compact representations from pretraining radiographic data for better cross-modal alignment. MOTOR unifies the understanding and generation, which are two kinds of core intelligence of an AI system, into a single medical foundation model, to flexibly handle more diverse medical tasks. To enable a comprehensive evaluation and facilitate further research, we construct a medical multimodal benchmark including a wide range of downstream tasks, such as chest x-ray report generation and medical visual question answering. Extensive experiments on our benchmark show that MOTOR obtains promising results through simple task-oriented adaptation. The visualization shows that the injected knowledge successfully highlights key information in the medical data, demonstrating the excellent interpretability of MOTOR. Our MOTOR successfully mimics the human practice of fulfilling a "medical student" to accelerate the process of becoming a "specialist". We believe that our work makes a significant stride in realizing MAGI.

Respiratory tumor motion is a major challenge in radiation therapy. Real-time tumor tracking aims to dynamically target the tumor with the radiation beam, allowing a reduction in the volume of healthy tissue exposed to a high dose. Fluoroscopic tracking with implanted fiducial markers is not widely accepted due to its invasiveness and, to a lesser extent, additional imaging dose. Using external respiratory surrogates is an attractive approach to localizing tumors affected by respiratory motion. In this paper, we present a kernel regression approach to the respiratory tumor motion problem. Due to the local nature of the kernel functions, it is inherently robust to outliers in the training data. In addition, both training and adapting to new data is highly efficient and almost free under the kernel regression model. We evaluated the method on respiratory motion data from six patients (three lung and three pancreas patients). It was found that the average 3D error is