Objective:To explore the feasibility of automatic target volume tracing in the Elekta Unity magnetic resonance imaging (MRI)-guided radiotherapy system and to further enhance the real-time target volume tracing performance of MRI-guided radiotherapy by introducing the deep learning technology based on a large Transformer model.Methods:A total of 4 661 frames of cine MRI binary images from 75 patients with malignant tumors in the chest/abdomen who were treated with MRI-guided radiotherapy were retrospectively collected as a training set. Another 500 frames of cine MRI binary images from 10 patients were collected as an independent test set. A module for medical image format conversion was developed to convert binary images into medical meta-images. The outer contours of tumor target volumes in the cine MRI images of the test set were manually delineated as actual control labels. With the first frame of the cine MRI images of each patient as the reference image and the other frames as motion images, a Transformer-based deep learning model was constructed to describe the deformable vector field (DVF) of motion images relative to the reference image. The Dice similarity coefficient (DSC), the 95% Hausdorff distance (HD 95), the negative Jacobian determinant (NegJ), and the average processing time per frame of cine MRI images were calculated. These values were compared to those of the conventional B-Spline scheme to quantitatively assess the target volume tracing accuracy, DVF physical plausibility, and execution efficiency of the Transformer-based deep learning model. Results:The Transformer-based deep learning model constructed in this study delivered superior target volume tracing performance, with improved DSC [(0.84 ± 0.05) vs. (0.74 ± 0.16), t = 11.44, P < 0.05] and HD 95 [(9.25 ± 2.98) vs. (14.70 ± 8.55) mm, t = -11.83, P < 0.05]. Furthermore, this model reduced the average image processing time from 1.95 s to 30.99 ms, enhancing the efficiency by two orders of magnitude. Besides, this model yielded NegJ similar to that of the B-Spline scheme. This suggests that the DVF extracted using this model had comparable physical plausibility with that obtained using the B-Spline scheme. Conclusions:The Transformer-based deep learning model for automatic target volume tracing fills the functional gap of the Elekta Unity MRI-guided radiotherapy system, facilitating relatively accurate, efficient automatic tracing of moving tumor targets in the chest and abdomen.

Objective:To explore the feasibility of automatic target volume tracing in the Elekta Unity magnetic resonance imaging (MRI)-guided radiotherapy system and to further enhance the real-time target volume tracing performance of MRI-guided radiotherapy by introducing the deep learning technology based on a large Transformer model.Methods:A total of 4 661 frames of cine MRI binary images from 75 patients with malignant tumors in the chest/abdomen who were treated with MRI-guided radiotherapy were retrospectively collected as a training set. Another 500 frames of cine MRI binary images from 10 patients were collected as an independent test set. A module for medical image format conversion was developed to convert binary images into medical meta-images. The outer contours of tumor target volumes in the cine MRI images of the test set were manually delineated as actual control labels. With the first frame of the cine MRI images of each patient as the reference image and the other frames as motion images, a Transformer-based deep learning model was constructed to describe the deformable vector field (DVF) of motion images relative to the reference image. The Dice similarity coefficient (DSC), the 95% Hausdorff distance (HD 95), the negative Jacobian determinant (NegJ), and the average processing time per frame of cine MRI images were calculated. These values were compared to those of the conventional B-Spline scheme to quantitatively assess the target volume tracing accuracy, DVF physical plausibility, and execution efficiency of the Transformer-based deep learning model. Results:The Transformer-based deep learning model constructed in this study delivered superior target volume tracing performance, with improved DSC [(0.84 ± 0.05) vs. (0.74 ± 0.16), t = 11.44, P < 0.05] and HD 95 [(9.25 ± 2.98) vs. (14.70 ± 8.55) mm, t = -11.83, P < 0.05]. Furthermore, this model reduced the average image processing time from 1.95 s to 30.99 ms, enhancing the efficiency by two orders of magnitude. Besides, this model yielded NegJ similar to that of the B-Spline scheme. This suggests that the DVF extracted using this model had comparable physical plausibility with that obtained using the B-Spline scheme. Conclusions:The Transformer-based deep learning model for automatic target volume tracing fills the functional gap of the Elekta Unity MRI-guided radiotherapy system, facilitating relatively accurate, efficient automatic tracing of moving tumor targets in the chest and abdomen.

Heart failure is a fatal stage of end-stage cardiovascular disease,which brings a huge medical burden to the society because of its high mortality and re-hospitalisation rates.Intestinal microecology is the largest and most com-plex microecosystem of human body.It is inhabited by tens of thousands of microorganisms in human gastrointestinal tract.In recent years,with the deepening of the study of intestinal flora,more and more studies have found that the im-balance of intestinal microecology can cause changes of metabolites in heart failure patients,which is one of the key triggers for the development of heart failure,therefore,using the intestinal microbial homeostasis as a new entry point for the treat-ment of heart failure will be a hotspot in medical research.However,the theory of Chinese medicine,"the spleen is the guardian",covers the physiological functions of the spleen,such as the spleen's main function of transporting,spleen's main function of ascending and clearing,and its main function of hiding camping,etc.,and the functions of intestinal flora and the"spleen is the guardian"are similar to a certain extent.Therefore,this paper starts from a holistic viewpoint and takes the theory of"spleen as the guardian"in Chinese medicine as an entry point to elaborate on the pathogenesis of intes-tinal microecological imbalance and heart failure,so as to provide a reference for Chinese medicine treatment or drug re-search.