Objective To explore the influencing factors of coronary artery lesion severity in patients with acute coronary syndrome (ACS). Methods Clinical data of ACS patients admitted to Zhongshan Hospital, Fudan University from December 2017 to December 2019 were consecutively collected. The modified Gensini score was used to assess the severity of coronary artery lesions. Univariate and multivariate linear regression analyses were performed to identify independent factors associated with coronary artery lesion severity. Results A total of 1 689 ACS patients were included, with an average age of (64.04±11.45) years; 1 353 (80.11%) were male, and the mean modified Gensini score was (8.12±4.03). Multivariate linear regression analysis revealed that sex (β＝0.97, P＝0.001), age (β＝0.03, P＝0.021), estimated glomerular filtration rate (eGFR; β＝－0.03, P＜0.001), low-density lipoprotein cholesterol (LDL-C; β＝0.58, P＜0.001), apolipoprotein A1 (Apo A1; β＝－1.28, P＝0.012), lipoprotein(a) [Lp(a); β＝0.001, P＝0.033], and glycated hemoglobin A_1C (HbA_1C; β＝0.45, P＜0.001) were independent influencing factors of the modified Gensini score. Conclusions Metabolic indicators, including Apo A1, LDL-C, HbA_1C, and Lp(a), may serve as risk factors for coronary artery lesion severity in ACS patients, with Apo A1 demonstrating the strongest impact.

Objective:To develop a deep learning method to predict the anatomical images of nasopharyngeal carcinoma patients during the treatment course, which could detect the anatomical variation for specific patients in advance.Methods:Imaging data including planning CT (pCT) and cone-beam CT (CBCT) for each fraction of 230 patients with T 3-T 4 staging nasopharyngeal carcinoma who treated in Cancer Hospital Chinese Academy of Medical Sciences from January 1, 2020 to December 31, 2022 were collected. The anatomical images of week k+1 were predicted using a 3D Unet model with inputs of pCT, CBCT on days 1-3, and CBCT of weeks 2- k. In this experiment, we trained four models to predict anatomical images of weeks 3-6, respectively. The nasopharynx gross tumor volume (GTV nx) and bilateral parotid glands were delineated on the predicted and real images (ground truth). The performance of models was evaluated by the consistence of the delineation between the predicted and ground truth images. Results:The proposed method could predict the anatomical images over the radiotherapy course. The contours of interest in the predicted image were consistent with those in the real image, with Dice similarity coefficient of 0.96, 0.90, 0.92, mean Hausdorff distance of 3.28, 4.18 and 3.86 mm, and mean distance to agreement of 0.37, 0.70, and 0.60 mm, for GTV nx, left parotid, and right parotid, respectively. Conclusion:This deep learning method is an accurate and feasible tool for predicting the patient's anatomical images, which contributes to predicting and preparing treatment strategy in advance and achieving individualized treatment.

Objective:To evaluate the feasibility of using MRI-only simulation images for dose calculation of both photon and proton radiotherapy for nasopharyngeal carcinoma cases.Methods:T 1-weighted MRI images and CT images of 100 patients with nasopharyngeal carcinoma treated with radiotherapy in Cancer Hospital of Chinese Academy of Medical Sciences from January 2020 to December 2021 were retrospectively analyzed. MRI images were converted to generate pseudo-CT images by using deep learning network models. The training set, validation set and test set included 70 cases, 10 cases and 20 cases, respectively. Convolutional neural network (CNN) and cycle-consistent generative adversarial neural network (CycleGAN) were exploited. Quantitative assessment of image quality was conducted by using mean absolute error (MAE) and structural similarity (SSIM), etc. Dose assessment was performed by using 3D-gamma pass rate and dose-volume histogram (DVH). The quality of pseudo-CT images generated was statistically analyzed by Wilcoxon signed-rank test. Results:The MAE of the CNN and CycleGAN was (91.99±19.98) HU and (108.30±20.54) HU, and the SSIM was 0.97±0.01 and 0.96±0.01, respectively. In terms of dosimetry, the accuracy of pseudo-CT for photon dose calculation was higher than that of the proton plan. For CNN, the gamma pass rate (3 mm/3%) of the photon radiotherapy plan was 99.90%±0.13%. For CycleGAN, the value was 99.87%±0.34%. The gamma pass rates of proton radiotherapy plans were 98.65%±0.64% (CNN, 3 mm/3%) and 97.69%±0.86% (CycleGAN, 3 mm/3%). For DVH, the dose calculation accuracy in the photon plan of pseudo-CT was better than that of the proton plan.Conclusions:The deep learning-based model generated accurate pseudo-CT images from MR images. Most dosimetric differences were within clinically acceptable criteria for photon and proton radiotherapy, demonstrating the feasibility of an MRI-only workflow for radiotherapy of nasopharyngeal cancer. However, compared with the raw CT images, the error of the CT value in the nasal cavity of the pseudo-CT images was relatively large and special attention should be paid during clinical application.

Objective:To investigate the correlation of serum high-sensitivity cardiac troponin T (hs-cTnT) level with major adverse cardiovascular events (MACE) in patients with chronic coronary syndrome (CCS) undergoing percutaneous coronary intervention (PCI) and to explore its predictive value.Methods:It was a case-control study. Clinical data of 731 patients with CCS who underwent PCI in the Affiliated Zhongshan Hospital of Fudan University between May 2019 and April 2020 were retrospectively analyzed. Baseline clinical characteristics and pre/postoperative laboratory results were gathered, and patients were followed up and the incidence of MACE was documented. The correlation of serum hs-cTnT levels with MACE was analyzed, and the threshold of hs-cTnT for predicting the occurrence of MACE was determined.Results:Among 731 patients there were 560 males (76.61%) with the age of (64.05±9.48) years. Patients were followed up for 29.9 (18.8, 35.3) months, and MACE occurred in 216 cases (MACE group), and did not occur in 515 cases (control group). The X-tile software analysis showed that the optimal cutoff value of post-PCI hs-cTnT was 4.17×upper reference limit (URL) for predicting MACE ( P=0.033). Multivariate Cox regression analysis revealed that postoperative cTnT>6×URL was an independent risk factor for MACE in CCS patients after PCI ( HR=1.87, 95% CI: 1.19-2.94, P=0.007). The net reclassification index pairwise comparison results indicated that hs-cTnT>6×URL had the better predictive performance for MACE in CCS patients after PCI compared to 7×URL, 8×URL, 9×URL, 10×URL and 15×URL (all P<0.05). Conclusion:Postoperative hs-cTnT>6×URL is an independent risk factor for MACE in CCS patients after PCI, and hs-cTnT>6×URL is the optimal threshold for predicting the risk of MACE.

Objective To improve the performance of auto-segmentation of prostate target area and organs-at-risk in online magnetic resonance image and enhance the efficiency of magnetic resonance imaging-guided adaptive radiotherapy(MRIgART)for prostate cancer.Methods A retrospective study was conducted on 40 patients who underwent MRIgART for prostate cancer,including 25 in the training set,5 in the validation set,and 10 in the test set.The planning CT images and corresponding contours,along with online MR images,were registered and input into a deep learning network for online MR image auto-segmentation.The proposed method was compared with deformable image registration(DIR)method and single-MR-input deep learning(SIDL)method.Results The overall accuracy of the proposed method for auto-segmentation was superior to those of DIR and SIDL methods,with average Dice similarity coefficients of 0.896 for clinical target volume,0.941 for bladder,0.840 for rectum,0.943 for left femoral head and 0.940 for right femoral head,respectively.Conclusion The proposed method can effectively improve the accuracy and efficiency of auto-segmentation in MRIgART for prostate cancer.

Objective:To investigate a time series deep learning model for respiratory motion prediction.Methods:Eighty pieces of respiratory motion data from lung cancer patients were used in this study. They were divided into a training set and a test set at a ratio of 8∶2. The Informer deep learning network was employed to predict the respiratory motions with a latency of about 600 ms. The model performance was evaluated based on normalized root mean square errors (nRMSEs) and relative root mean square errors (rRMSEs).Results:The Informer model outperformed the conventional multilayer perceptron (MLP) and long short-term memory (LSTM) models. The Informer model yielded an average nRMSE and rRMSE of 0.270 and 0.365, respectively, at a prediction time of 423 ms, and 0.380 and 0.379, respectively, at a prediction time of 615 ms.Conclusions:The Informer model performs well in the case of a longer prediction time and has potential application value for improving the effects of the real-time tracking technology.

Objective:To investigate the pseudo-CT generation from cone beam CT (CBCT) by a deep learning method for the clinical need of adaptive radiotherapy.Methods:CBCT data from 74 prostate cancer patients collected by Varian On-Board Imager and their simulated positioning CT images were used for this study. The deformable registration was implemented by MIM software. And the data were randomly divided into the training set ( n=59) and test set ( n=15). U-net, Pix2PixGAN and CycleGAN were employed to learn the mapping from CBCT to simulated positioning CT. The evaluation indexes included mean absolute error (MAE), structural similarity index (SSIM) and peak signal to noise ratio (PSNR), with the deformed CT chosen as the reference. In addition, the quality of image was analyzed separately, including soft tissue resolution, image noise and artifacts, etc. Results:The MAE of images generated by U-net, Pix2PixGAN and CycleGAN were (29.4±16.1) HU, (37.1±14.4) HU and (34.3±17.3) HU, respectively. In terms of image quality, the images generated by U-net and Pix2PixGAN had excessive blur, resulting in image distortion; while the images generated by CycleGAN retained the CBCT image structure and improved the image quality.Conclusion:CycleGAN is able to effectively improve the quality of CBCT images, and has potential to be used in adaptive radiotherapy.

Objective:To analyze the risk factors of three-vessel disease (TVD) in patients with stable coronary artery disease (SCAD).Methods:The clinical data of 447 patients with SCAD diagnosed in Zhongshan Hospital from May 2019 to April 2020 were retrospectively analyzed, including 108 cases with the single-vessel disease (SVD), 136 cases with the two-vessel disease, and 203 cases with three-vessel disease. The general data and hematological indexes were compared between patients with SVD and those with TVD; the related factors for TVD in SCAD patients were analyzed with univariate and multivariate logistic regression.Results:There were 244 males (78.5%) and 67 females (21.5%) with a median age of 57 years (64, 69). Univariate analysis showed that there were significant differences in diabetes history ( χ2=7.75, P=0.005), uric acid ( Z=-2.10, P=0.036), glycosylated hemoglobin ( Z=-2.77, P=0.006) and high density lipoprotein cholesterol (HDL-C) ( Z=-2.99, P=0.003) levels between SVD and TVD groups. Multivariate analysis showed that the high level of blood uric acid ( OR=1.01, 95% CI: 1.00-1.01, P<0.05) and the low level of HDL-C ( OR=3.29, 95% CI:1.23-8.85, P<0.05) were related risk factors of TVD. Conclusion:High blood uric acid level and low HDL-C level are related factors for TVD in patients with SCAD.

This article summarized the overview of diagnosis related groups (DRGs), the necessity of comprehensively popularizing and applying DRGs in specialized hospitals and general hospitals, the different methods and effects of nursing human resource allocation based on DRGs in specialized hospitals and general hospitals at home and abroad, and analyzed the different challenges and opportunities faced by DRGs in the implementation of human resource allocation in two types of hospitals. According to the types and characteristics of hospitals, this paper put forward some corresponding suggestions and prospects for the future, such as intelligent human resource prediction system and the construction of information sharing platform, so as to provide reference for the comprehensive promotion of DRGs in different types of hospitals in China.

Objective:To analyze the predictive value of enhanced MRI in the outcome of prolapsed and sequestrated lumbar disc herniation through a retrospective analysis.Methods:A retrospective analysis of the data of 64 patients with prolapsed and sequestrated lumbar disc herniation from January 2015 to December 2018, including 38 males and 26 females; age 35.72±12.44 years (range, 22-64 years) ; 43 cases of prolapsed type, 21 cases of sequestrated type. Conservative treatment was the first choice for all patients, in case of surgical indications during the treatment, percutaneous endoscopic lumbar discectomy or fenestration discectomy will be performed. Enhanced MRI was performed at the first and last inspections, the volume of the protrusion, the thickness of rim enhancement (Tr), and the extent of rim enhancement (Er) were measured and calculated at the same time. According to the ring around the protrusion, the size of the rim-enhancement area was divided into type I-III; then compared the relationship between the rim-enhancement signal differentiation and the resorption rate of protrusions, and the correlation between Tr, Er values and the resorption rate of protrusions during the initial inspection.Results:Among the 64 patients, 42 patients completed conservative treatment, and 22 received surgical treatment. According to the rim-enhancement signal differentiation, 23 cases were treated conservatively for type I, 3 cases were treated by surgery; 16 cases were treated for type II conservatively, 7 cases were treated by surgery; 3 cases were treated for type III conservatively, and 12 cases were treated by surgery. All patients were followed up for 12 to 34 months. Among 42 conservatively treated patients, The volume of the protrusion before treatment was 2 645.67±690.86 mm 3, and the volume of the protrusion after treatment was 842.76±573.35 mm 3. The volume of protrusions before and after treatment was statistical significance ( t=11.897, P<0.001), Tr was 1.38±0.83 mm, and Er was 73.08%±34.39%, the resorption rate of protrusions was 65.10%±24.50%, and 39 cases (92.86%, 39/42) reached the standard for protrusion resorption (resorption rate ≥30%); 23 cases of type I , the resorption rate was 76.54%±18.62%; 16 cases of type II had an resorption rate of 56.81%±21.44%; 3 cases of type III had an resorption rate of 21.58%±12.19%. The resorption rate of type III were compared by single factor analysis of variance, and the difference was statistically significant ( F=12.885, P<0.001); 32 cases of both type I and II (82.05%, 32/39) had significant resorption (resorption rate ≥50%), and no case of type Ⅲ had significant resorption, comparing with type I and II, the difference was statistically significant ( P=0.010); Tr was positively correlated with resorption rate ( r=0.569, P<0.001), Er was positively correlated with resorption rate ( r=0.677, P<0.001). Conclusion:Under close clinical observation, parts of the prolapsed or sequestrated lumbar disc herniations can be conservatively treated, and the herniated disc can be resorption in many people and the clinical symptoms were alleviated. Rim-enhancement signal differentiation by enhanced MR has a better predictive value for the outcome of the herniation, type I is more prone to resorption, preferred conservative treatment, type Ⅲ is not easy to resorption, preferred surgery treatment, and the higher thickness of rim enhancement, the greater extend the rim-enhancement, the more prone to resorption phenomenon.