Objective:To explore the feasibility of autosegmentation and reconstruction of interstitial needles in intracavitary / interstitial brachytherapy (IC-ISBT) for cervical cancer based on deep learning.Methods:The data of 180 treatment plans from 98 patients who received IC-ISBT were retrospectively collected and divided into the training, validation, and testing sets in a 16:1:1 ratio. Masks of needles were created using the dwell positions of radiation sources, and a 3D U-Net model was trained. The performance of the model was evaluated using the Dice similarity coefficient (DSC). Absolute and relative accuracy rates were used to assess the results of this method, and the position bias was used to evaluate the precision of predictions in the transversal plan of CT scans. Wilcoxon rank-sum test was performed to evaluate the reconstruction efficiency by comparing the time required for automated versus manual reconstruction.Results:DSC of the model was 0.93 ± 0.02. The absolute and relative accuracy rates were 0.44 ± 0.09 and 0.95 ± 0.03, respectively. The distance deviation on the CT horizontal plane was (0.58 ± 0.54) mm. The average time of autosegmentation and reconstruction was (6.2 ± 0.4) s, leading to a significant reduction in time consumption compared with manual construction ( P<0.001). Conclusions:Based on deep learning, using the dwell positions of radiation sources for data annotation, combined with post-processing algorithms, accurate automated segmentation and digital reconstruction of needles in IC-ISBT three-dimensional CT images can be achieved, significantly improving reconstruction efficiency.

Objective:To explore the feasibility of autosegmentation and reconstruction of interstitial needles in intracavitary / interstitial brachytherapy (IC-ISBT) for cervical cancer based on deep learning.Methods:The data of 180 treatment plans from 98 patients who received IC-ISBT were retrospectively collected and divided into the training, validation, and testing sets in a 16:1:1 ratio. Masks of needles were created using the dwell positions of radiation sources, and a 3D U-Net model was trained. The performance of the model was evaluated using the Dice similarity coefficient (DSC). Absolute and relative accuracy rates were used to assess the results of this method, and the position bias was used to evaluate the precision of predictions in the transversal plan of CT scans. Wilcoxon rank-sum test was performed to evaluate the reconstruction efficiency by comparing the time required for automated versus manual reconstruction.Results:DSC of the model was 0.93 ± 0.02. The absolute and relative accuracy rates were 0.44 ± 0.09 and 0.95 ± 0.03, respectively. The distance deviation on the CT horizontal plane was (0.58 ± 0.54) mm. The average time of autosegmentation and reconstruction was (6.2 ± 0.4) s, leading to a significant reduction in time consumption compared with manual construction ( P<0.001). Conclusions:Based on deep learning, using the dwell positions of radiation sources for data annotation, combined with post-processing algorithms, accurate automated segmentation and digital reconstruction of needles in IC-ISBT three-dimensional CT images can be achieved, significantly improving reconstruction efficiency.

【Objective】 To evaluate the suitability of current quality standard for end-stage hemolytic rate required by Quality Requirements for Whole Blood and Blood Components in Taiyuan through a 5- year retrospective analysis of leukocyte-reduced RBCs in additive solution in Taiyuan Blood Center. 【Methods】 A total of 240 packs of leukocyte-reduced RBCs in additive solution were collected from January 2007 to December 2021. Hb concentration, hematocrit(Hct) and free Hb in supernatant at end-stage were detected to measure the hemolytic rate. And the hemolytic rate was then compared with the current standard(0.8%) to analyze whether statistical differences existed. 【Results】 The hemolytic rate of leukocyte-reduced RBCs in additive solution were 0.109±0.123 in 2017, 0.113±0.085 in 2018, 0.121±0.076 in 2019, 0.101±0.057 in 2020, and 0.128±0.089 in 2021, with no significant difference among each other (P>0.05). And 97.5% of the products showed an end-stage hemolytic rate below 0.4%, 0.83% among 0.6%~0.7%, and none over the standard of 0.8%. 【Conclusion】 The current national standard for end-stage hemolytic rate of leukocyte-reduced RBCs in additive solution might not be suitable for blood quality control in Taiyuan, and a much stricter criteria should be considered.

Objective To investigate the disease progression and influencing factors of human immunodeficiency virus (HIV)-infected persons in Sanya area from 2010-2020. Methods Data of HIV infected cases reported in XX region from January 2014 to January 2020 were collected through the National AIDS Comprehensive Prevention and Control Information System. The incidence of AIDS was calculated by the life expectancy method, and the single factors influencing the progression of HIV infection were analyzed from the aspects of sex, age, BMI, nationality, marital status, educational level, highly active anti-retroviral therapy (HAART), anemia, route of transmission, CD4⁺ cell count, and co-infection of other viruses. Results A total of 761 HIV-infected cases were reported in Sanya areaFrom January 2010 to January 2020, of which 103 had progressed to AIDS (13.53%), the incidence of AIDS was 6.01/100 person-years, the average incubation period was 4.63 years; There were 31 death cases, and the all-cause mortality rate was 1.81/100 person years; Gender, age, HAART treatment status, anemia, CD4⁺ cell count, and other viral infections were single factors that affect the disease progression of HIV-infected persons (χ²=16.803, 13.362, 15.954, 20.119, 16.039, 15.711, P<0.05), meanwhile, age, HAART treatment status, anemia, CD4⁺ cell count, and other viral infections were independent risk factors that affect the disease progression of HIV-infected persons (P=0.014, 0.007, 0.017, 0.009, 0.001, 0.001). Conclusion The incubation period is an important stage of the disease progression of HIV-infected patients, moreover, age, HAART treatment status, anemia, CD4⁺ cell count, and other viral infections are all independent risk factors that affect the disease progression of HIV-infected patients.