Objective:To investigate the denoising performance of different deep learning (DL) strategies on low-dose brain 18F-FDG PET images. Methods:This retrospective methodological study was conducted on brain PET/CT images of 50 patients (35 males, 15 females, age 20-87 years) who received 3.7MBq/kg 18F-FDG at the Fifth Affiliated Hospital of Sun Yat-sen University between May 2023 and January 2024. Full-dose PET data were acquired with 2min scan. CT scans were acquired before PET scanning. Low-dose PET sinograms were generated by down-sampling the full-dose list mode data to 1/2, 1/4, and 1/20 of full-dose count level. Both full-dose and low-dose sinograms were reconstructed with random, CT-based attenuation and scatter corrections using the three-dimensional (3D) ordered-subsets expectation maximization (OSEM) algorithm (2 iterations, 20 subsets). A total of 4 DL denoising methods were established: (1) 3D conditional generative adversarial networks (GAN) using only low-dose PET as input (GAN-1); (2) 3D attention-based GAN (AttGAN) with low-dose PET input (AttGAN-1); (3) 3D AttGAN with low-dose PET and CT inputs (AttGAN-2); (4) 3D AttGAN with frequency-separation using low-dose PET and CT inputs (AttGAN-FS-2). For AttGAN-FS-2, during the frequency division process, high- and low-frequency components were extracted from the PET reconstructed images via Fourier transform, then inversed Fourier transform, denoised separately, and finally combined to produce the final denoised images. The dataset was separated into training (70%), validation (10%) and testing (20%) sets using simple random sampling without replacement with a fixed random seed. A 5-fold cross-validation scheme was then applied to test all 50 patients. Performance was evaluated against full-dose PET using normalized mean square error (NMSE), structural similarity (SSIM), peak signal-to-noise ratio (PSNR), contrast-to-noise ratio (CNR), SUV mean and SUV max bias of selected brain ROIs. Wilcoxon signed rank test was used to analyze the differences between the denoising methods. Results:AttGAN-FS-2 showed the best performance among all dose levels, with statistical difference as compared by low-dose PET and GAN-1 denoised images for NMSE, SSIM, PSNR, and CNR ( Z values: 2.92-6.15, all P<0.005). NMSE, SSIM quantitative evaluation results (median) of each model at 1/20 dose were: GAN-1: 0.08, 0.87, AttGAN-1: 0.08, 0.88, AttGAN-2: 0.07, 0.89, AttGAN-FS-2: 0.06, 0.91, respectively ( Z values: 3.24-5.77, all P<0.005). Conclusion:The DL-based method combined with multiple strategies AttGAN-FS-2 shows improved denoising performance for low-dose brain PET images.

Objective:To investigate the denoising performance of different deep learning (DL) strategies on low-dose brain 18F-FDG PET images. Methods:This retrospective methodological study was conducted on brain PET/CT images of 50 patients (35 males, 15 females, age 20-87 years) who received 3.7MBq/kg 18F-FDG at the Fifth Affiliated Hospital of Sun Yat-sen University between May 2023 and January 2024. Full-dose PET data were acquired with 2min scan. CT scans were acquired before PET scanning. Low-dose PET sinograms were generated by down-sampling the full-dose list mode data to 1/2, 1/4, and 1/20 of full-dose count level. Both full-dose and low-dose sinograms were reconstructed with random, CT-based attenuation and scatter corrections using the three-dimensional (3D) ordered-subsets expectation maximization (OSEM) algorithm (2 iterations, 20 subsets). A total of 4 DL denoising methods were established: (1) 3D conditional generative adversarial networks (GAN) using only low-dose PET as input (GAN-1); (2) 3D attention-based GAN (AttGAN) with low-dose PET input (AttGAN-1); (3) 3D AttGAN with low-dose PET and CT inputs (AttGAN-2); (4) 3D AttGAN with frequency-separation using low-dose PET and CT inputs (AttGAN-FS-2). For AttGAN-FS-2, during the frequency division process, high- and low-frequency components were extracted from the PET reconstructed images via Fourier transform, then inversed Fourier transform, denoised separately, and finally combined to produce the final denoised images. The dataset was separated into training (70%), validation (10%) and testing (20%) sets using simple random sampling without replacement with a fixed random seed. A 5-fold cross-validation scheme was then applied to test all 50 patients. Performance was evaluated against full-dose PET using normalized mean square error (NMSE), structural similarity (SSIM), peak signal-to-noise ratio (PSNR), contrast-to-noise ratio (CNR), SUV mean and SUV max bias of selected brain ROIs. Wilcoxon signed rank test was used to analyze the differences between the denoising methods. Results:AttGAN-FS-2 showed the best performance among all dose levels, with statistical difference as compared by low-dose PET and GAN-1 denoised images for NMSE, SSIM, PSNR, and CNR ( Z values: 2.92-6.15, all P<0.005). NMSE, SSIM quantitative evaluation results (median) of each model at 1/20 dose were: GAN-1: 0.08, 0.87, AttGAN-1: 0.08, 0.88, AttGAN-2: 0.07, 0.89, AttGAN-FS-2: 0.06, 0.91, respectively ( Z values: 3.24-5.77, all P<0.005). Conclusion:The DL-based method combined with multiple strategies AttGAN-FS-2 shows improved denoising performance for low-dose brain PET images.

Venous adventitial cystic disease(VACD)is a rare vascular disease which often manifests as unilateral limb swelling,and so misdiagnosed as other diseases such as deep vein thrombosis.Color Doppler ultrasound,CT angiography and magnetic resonance imaging play a crucial role in the diagnosis of VACD.Surgical treatment is the main method for VACD,including cyst incision,cyst wall resection,cyst puncture,aspiration and cyst and vessel resection.The recurrence rate of VACD is relatively high,ranging from 20%to 83%.Enhancing the understanding of VACD,making accurate diagnoses and appropriate surgical operation are of great significance for improving treat-ment outcomes and reducing the recurrence rate.

Objective:To explore the intervention effect of Shumu Peitu herb-partitioned moxibustion on clinical signs and symptoms and negative emotions of diarrhea-predominant irritable bowel syndrome (IBS-D) patients with liver-stagnation and spleen-deficiency pattern.Methods:A total of 72 patients with IBS-D of liver-stagnation and spleen-deficiency pattern treated in the Department of Gastroenterology of Nanjing Vniversity of Chinese Medicine from September 2021 to June 2022 were selected for randomized controlled trial. The patients were randomly divided into the observation group (2 cases dropped off, 34 cases in total) and control group (1 case dropped off, 35 cases in total) by random number table method. The patients in control group were treated with Tongxieyaofang (TXYF). The patients in observation group were treated with oral administration of TXYF and Shumu Peitu herb-partitioned moxibustion, and both groups were treated for 4 weeks. The clinical efficacy, Traditional Chinese Medicine (TCM) syndrome integral, IBS Quality of Life Questionnaire (IBS-QOL), IBS Symptom Severity Scale (IBS-SSS), Bristol Stool Form Scale and Hospital Anxiety and Depression Scale (HADS) were compared before and after treatment.Results:After treatment, the total effective rate of the observation group was 94.12%(32/34), which was higher than the 71.43%(25/35) in the control group, the difference was significant ( χ2 = 6.18, P<0.05). After treatment, the TCM syndrome integral in the observation group was (7.62 ± 4.08), which was lower than the (9.89 ± 4.71) in the control group, the difference was significant ( t = 2.14, P<0.05). After treatment of 3 days, the scores of quality of life in the five dimensions of dysthymia, behavior disorder, health worry, avoidance of eating and social function in the observation group were (82.44 ± 11.46), (80.25 ± 11.67), (76.23 ± 12.67), (59.80 ± 15.14) and (79.23 ± 11.59) points, which were different with the (73.57 ± 12.39), (72.35 ± 15.48), (69.76 ± 13.11), (50.00 ± 16.17) and (73.04 ± 13.11) points in the control group, the difference were significant ( t values were -3.09 - -2.08, all P<0.05). Three days after treatment, the score of IBS-SSS and Bristol fecal character in the observation group were (118.24 ± 40.64) and (5.09 ± 0.62) points, which were lower than the (146.86 ± 60.09) and (5.51 ± 0.66) points in the control group, the difference were significant ( t = 2.31 and 2.76, both P<0.05). After treatment, the score of HADS-A and HADS-D in the observation group were (6.26 ± 1.75) and (5.29 ± 1.47), which were different with the (7.26 ± 2.19) and (6.17 ± 2.11) in the control group, the difference were significant ( t = 2.08 and 2.00, both P<0.05). Conclusions:Shumu Peitu herb-partitioned moxibustion can effectively improve IBS-D patients with liver-stagnation and spleen-deficiency pattern, relieve clinical symptoms, reduce negative emotions, and improve quality of life.

Objective:To understand the status of health-promoting lifestyle of middle-aged and elderly patients with knee osteoarthritis, and to comprehensively analyze the influencing factors based on the biological-psychological-social medicine model, to explore controllable factors.Methods:Using convenient sampling method, 177 middle-aged and elderly patients with knee osteoarthritis who were hospitalized in First Affiliated Hospital of Shandong First Medical University (Shandong Provincial Qianfoshan Hospital) from July 2020 to November 2020 were selected for questionnaire survey. The Health Promotion Lifestyle Profile Ⅱ (HPLP-Ⅱ) was used to evaluate their health promotion lifestyle status, the influencing factors were measured by general data sheet, Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), disease recognition questionnaire for knee osteoarthritis patients, Social Support Rating Scale (SSRS), Hamilton Anxiety Scale (HAMA), Hamilton Depression Scale (HAMD) and Self-efficacy for Managing Chronic Disease (CDSES), respectively.Results:The total score of HPLP-Ⅱ, the total score of WOMAC, the score of disease recognition questionnaire, the total score of SSRS, the score of HAMA, HAMD, CDSES were (117.52 ± 15.58), (105.63 ± 31.64), (14.21 ± 3.23), (38.60 ± 5.18), (7.76 ± 4.41), (6.01 ± 4.54), (33.77 ± 6.04) points for middle-aged and elderly patients with knee osteoarthritis. The results of multiple linear regression analysis showed that the influencing factors were disease cognition, per capita monthly income, imaging grade, self-efficacy, support utilization, objective support, a total of 71.9% variation of regression equation could be explained.Conclusions:Middle-aged and elderly knee osteoarthritis patients health promotion lifestyle score at a low level, to improve, affected by disease cognition, imaging grading, self-efficacy, social support, medical staff should combine the degree of disease and individualized factors for disease health education, improve patients′ self-efficacy and social support level, prompting patients to adopt a healthy lifestyle.

Successful aging is an important strategy to actively deal with aging as well as a crucial measure to maintain national security and social harmony and stability, and the assessment of successful aging is the prerequisite and basis for relevant measures. However, standardized assessment tools for successful aging have not yet been formed by far, which has had a certain impact on the in-depth research in successful aging. This article summarizes and analyzes the comprehensive assessment methods and tools for successful aging at home and abroad, and provides references for the research into comprehensive assessment tools for successful aging, with a view to promoting the formation of standardized and comprehensive assessment tools for successful aging and developing comprehensive assessment tools for successful aging for Chinese elderly based on China's conditions.

A 69-year-old male patient with retroperitoneal sarcoma received anlotinib capsules (12 mg orally once daily for 14 days, interruption for 7 days) and sintilimab injection (IV infusion of 200 mg on the first day) and 21 days was a cycle. He had no history of diarrhea and previous enteroscopy showed no obvious abnormality. So the diarrhea, which occurred after 18 days of treatments, was considered to be related to the combination use of anlotinib capsules and sintilimab injection. Above 2 drugs were stopped and hormone and symptomatic treatments were given. Six days later, the patient′s diarrhea was improved, and enteroscopy showed colitis. Considering the primary disease, the patient was treated with oral anlotinib capsule monotherapy with the same dose as before. Two days later, the patient had diarrhea again, which was more serious than before, and the anlotinib capsules were stopped again. After 14 days of hormone shock therapy, anti-infection therapy, and symptomatic treatments, the patient′s diarrhea was improved.

A 69-year-old male patient with retroperitoneal sarcoma received anlotinib capsules (12 mg orally once daily for 14 days, interruption for 7 days) and sintilimab injection (IV infusion of 200 mg on the first day) and 21 days was a cycle. He had no history of diarrhea and previous enteroscopy showed no obvious abnormality. So the diarrhea, which occurred after 18 days of treatments, was considered to be related to the combination use of anlotinib capsules and sintilimab injection. Above 2 drugs were stopped and hormone and symptomatic treatments were given. Six days later, the patient′s diarrhea was improved, and enteroscopy showed colitis. Considering the primary disease, the patient was treated with oral anlotinib capsule monotherapy with the same dose as before. Two days later, the patient had diarrhea again, which was more serious than before, and the anlotinib capsules were stopped again. After 14 days of hormone shock therapy, anti-infection therapy, and symptomatic treatments, the patient′s diarrhea was improved.

Objective: To investigate the role of epidemiological history in the screening of Corona Virus Disease 2019 (COVID-19) in fever clinic, to improve the efficiency in fever clinic and reduce the incidence of cross infection. Methods: This is a retrospective study. Patients who were admitted to the fever clinic in West China Hospital of Sichuan University from January 23^th, 2020 to February 11^th, 2020 included the study. According to epidemiological history, the patients were divided into epidemiological history group (the experimental group) and no epidemiological history group (the control group). The two groups of patients were admitted and treated separately. The clinical data, NEWS score, etiology results, viral pneumonia showed on CT, time of visit, COVID-19 patient ratio, and admission composition ratio were compared between the two groups. The measurement data were presented as the mean ± standard deviation (SD), and the numeration data were expressed as ratio or constituent ratio. The measurement data of normal distribution between the two groups were compared by independent sample t test. The measurement data of skewed distribution are expressed by the median (interquartile range), and the comparison between the two groups is tested by non-parameter. The differences between enumeration data were assessed by chi-square test. A P<0.05 was considered statistically significant. Results: A total of 2423 patients were included, including 927 patients in the experimental group and 1296 patients in the control group. There were no significant differences in gender, NEWS score and clinical symptoms between the two groups (P> 0.05). The age (35.00 ± 12.80 vs 38.13 ± 15.57 years) , the proportion of fever patients (28.80% vs 32.75%) and waiting time (31.72 vs 58.08 min) of the experimental group were lower than the control group, the difference was statistically significant (P <0.05). The CT examination ratio (37.54% vs 20.39%), viral pneumonia ratio showed on CT (9.77% vs 2.95%), ratio of examined COVID-19 nucleic acid test (85.44% vs 56.75%), and the admission ratio (16.72% vs 9.63%) of the experimental group were higher than the control group, and the differences were statistically significant (P <0.05); There was no significant difference in the positive rates of influenza virus and rhinovirus between the two groups (P> 0.05). Conclusion It is necessary to adjust the management mode of fever clinic during the Corona Virus Disease 2019, and to manage the patients according to the epidemiological history which can improve the screening efficiency and reduce the risk of cross infection.

Objective:To explore the effect of artificial intelligence teaching-picture system in training the bone marrow cell morphological reading ability of clinical medical students.Methods:A total of 110 five-year undergraduate students were divided into experimental group (artificial intelligence picture teaching method) and control group (traditional teaching method) in the bone marrow cell morphology reading ability training. On the basis of multimedia teaching, the experimental group was given the teaching by using the bone marrow cell morphology picture storage and transmission system for retrieval, learning and computer adaptive test. Then objective evaluation of image recognition ability and questionnaire were used to compare the teaching effect.Results:The image recognition ability was significantly better in the experimental group than in the control group [(89.6±5.7) vs. (81.4±4.9), P<0.01]. Furthermore, the experimental group showed more obvious advantages in cell morphology recognition [(74.7±4.0) vs. (68.7±4.9)] and diagnosis of hematological diseases [(14.9±3.0) vs. (12.9±2.4)] than the control group (both P<0.01). Questionnaire survey showed that the students expressed their affirmation and support for the artificial intelligence teaching-picture system in the bone marrow cell morphological reading ability training. Conclusion:The application of artificial intelligence teaching-picture system can greatly improve the teaching effect, mobilize students' learning enthusiasm and expand learning resources, which is worthy of further promotion and application.