Objective:To evaluate whether the reconstructed image on the basis of deep learning(DL)can improve the success rate and display quality of automatic segmentation of computed tomography(CT)with ultralow dose for chest of children on airway.Methods:The clinical data of 41 consecutive cases who adopted ultralow dose CT to underwent reexamination on chest at Beijing Children's Hospital,Capital Medical University from February 2020 to September 2020 were selected,whose average age was(4.43±1.61 years).The scan protocol of ultralow dose CT was(0.05 mGy).The reconstructed images included 6 groups,which were respectively filtered reflection projection(FBP)image with 0.625 mm thickness,50%adaptive iterative recombination(ASIR-V)images,100%ASIR-V images,low energy DL(DL-L),medium energy DL(DL-M),and high energy DL(DL-H).The automatically segmentation software was used to conduct automatically segmentation for airway,and the success rate of automatic segmentation was recorded.For images that were successful segmented,a 5-point scale was adopted to subjectively evaluate the displayed quality for airway(5 point is the best).In addition,the CT values and noise values of the images of 6 groups for airway were objectively measured.Results:The success rate of automatic segmentation of DL-H image was the highest(60.98%),and that of the 100%ASIR-V was the lowest(39.02%).The subjective score of DL-H image of the automatic segmentation was the highest(4.06±0.55)point,and that of 100%ASIR-V was the lowest(2.44±0.76)point.DL-H can display more fine and small airways.The noise values of objective measurement showed that both of DL-H and 100%ASIR-V had the lowest noise value,and there was no statistical difference in that between them.Conclusion:The use of high energy deep learning iterative reconstruction(DLIR)algorithm can improve the success rate and display effect of automatic segmentation of ultralow dose CT for chest of children on airway,and DLIR is contribute to improve the accuracy of automatic segmentation algorithm of artificial intelligence.

CT is a commonly examination method in pediatric clinical practice.Formulating and popularizing low-dose pediatric CT scanning protocols and constructing a standard image quality evaluation system are the key directions of low-dose pediatric CT imaging.In recent years,domestic CT equipment achieved technological breakthroughs in hardware performance and image reconstruction algorithms,which could provide new paths for pediatric low-dose CT imaging in children combining with artificial intelligence technology.The current status of scanning protocols,the establishment of imaging quality evaluation system and the clinical promotion,as well as challenges of domestic CT in pediatric low-dose CT imaging were reviewed in this article.

Objective:To evaluate whether the reconstructed image on the basis of deep learning(DL)can improve the success rate and display quality of automatic segmentation of computed tomography(CT)with ultralow dose for chest of children on airway.Methods:The clinical data of 41 consecutive cases who adopted ultralow dose CT to underwent reexamination on chest at Beijing Children's Hospital,Capital Medical University from February 2020 to September 2020 were selected,whose average age was(4.43±1.61 years).The scan protocol of ultralow dose CT was(0.05 mGy).The reconstructed images included 6 groups,which were respectively filtered reflection projection(FBP)image with 0.625 mm thickness,50%adaptive iterative recombination(ASIR-V)images,100%ASIR-V images,low energy DL(DL-L),medium energy DL(DL-M),and high energy DL(DL-H).The automatically segmentation software was used to conduct automatically segmentation for airway,and the success rate of automatic segmentation was recorded.For images that were successful segmented,a 5-point scale was adopted to subjectively evaluate the displayed quality for airway(5 point is the best).In addition,the CT values and noise values of the images of 6 groups for airway were objectively measured.Results:The success rate of automatic segmentation of DL-H image was the highest(60.98%),and that of the 100%ASIR-V was the lowest(39.02%).The subjective score of DL-H image of the automatic segmentation was the highest(4.06±0.55)point,and that of 100%ASIR-V was the lowest(2.44±0.76)point.DL-H can display more fine and small airways.The noise values of objective measurement showed that both of DL-H and 100%ASIR-V had the lowest noise value,and there was no statistical difference in that between them.Conclusion:The use of high energy deep learning iterative reconstruction(DLIR)algorithm can improve the success rate and display effect of automatic segmentation of ultralow dose CT for chest of children on airway,and DLIR is contribute to improve the accuracy of automatic segmentation algorithm of artificial intelligence.

CT is a commonly examination method in pediatric clinical practice.Formulating and popularizing low-dose pediatric CT scanning protocols and constructing a standard image quality evaluation system are the key directions of low-dose pediatric CT imaging.In recent years,domestic CT equipment achieved technological breakthroughs in hardware performance and image reconstruction algorithms,which could provide new paths for pediatric low-dose CT imaging in children combining with artificial intelligence technology.The current status of scanning protocols,the establishment of imaging quality evaluation system and the clinical promotion,as well as challenges of domestic CT in pediatric low-dose CT imaging were reviewed in this article.

Purpose To evaluate the image quality improvement of deep learning iterative reconstruction(DLIR)on pediatric head CT images of head injury and to evaluate the performance of DLIR and conventional adaptive statistical iterative reconstruction-veo(ASIR-V)of noise and image texture of CT image in children's head trauma.Materials and Methods A total of 80 cases in Beijing Children's Hospital,Capital Medical University from December 7th to 11th 2020 of children's head low-dose CT were retrospectively selected.Scan voltage was 120 kV.Scan current was 150-220 mA.The raw data were reconstructed into 5 mm thick slice and 0.625 mm thin slice brain window and bone window images.50%ASIR-V and high weight DLIR images(DL-H)were reconstructed,respectively.A 4-point system was used to subjectively evaluate the display of sulcus,brain matter and bone.The number of lesions in each group was counted.The CT value and image noise values of gray matter and white matter were measured,and the contrast to noise ratio was calculated,then measured the blur metric index was measured in the same slice.The differences between the two image reconstruction methods were compared.Results Compared to 50%ASIR-V images,DL-H significantly improved the display ability of the sulcus and ventricles,as well as the display ability of the brain parenchyma(W=5.5-22.2,all P<0.05)in both slice thickness.There was no statistically significant difference in the display ability of the sulcus and ventricles between 5 mm 50%ASIR-V and 0.625 mm DL-H images(W=0.9,2.0,P=0.32,0.05,respectively).In terms of bone display ability,all images could achieve a maximum score of 4.0.A total of 35 lesions were found in 80 patients via 5 mm 50%ASIR-V and DL-H images,including 12 hemorrhagic lesions,1 intracranial gas,9 fractures,and 13 soft tissue swelling.In terms of objective evaluation,the noise level of DL-H images was significantly lower than that of 50%ASIR-V images(t=21.4-35.7,all P<0.05),and there was no statistically significant difference in noise and contrast noise ratio between 5 mm 50%ASIR-V and 0.625 mm DL-H images(t=1.7-2.2,all P≥0.05).The blur metric index showed that DL-H was superior to 50%ASIR-V images(t=6.1,10.0,both P<0.05),and there was no statistically significant difference in blur metric index between 0.625 mm DL-H and 5 mm 50%ASIR-V images(t=2.6,P=0.28).Conclusion DLIR can improve the CT image quality and image texture of children's head trauma,0.625 mm DL-H image quality is close to 5 mm 50%ASIR-V image,which can meet the diagnostic requirements,and possible to further reduce the radiation dose.

Objective:To understand the current situation of CT radiation dose in children all over our country, and to explore the diagnostic reference level (DRL) of CT in children.Methods:The radiation dose reports of pediatric CT examination were collected end to November 30, 2021 and divided into five age groups: 0-1 month,>1 month-4 years,>4-10 years,>10-14 years and >14-18 years. There were 9 scanning item such as head, nasal sinus, temporal bone, neck, chest, abdomen, head enhanced CT, chest enhanced CT and abdomen enhanced CT. In each item, volume CT dose index (CTDI vol) and dose length product (DLP) were selected as radiation dose parameters, the 75% percentile were selected for DRL. The DRL results of head, chest and abdomen were compared with the DRL published by Chinese Society of Radiology and European Commission. Results:From March 2019 to November 2021, a total of 33 hospitals in 23 provinces were collected, including 20 children′s specialized hospitals, 11 women′s and children′s hospitals and 2 general hospitals, including 19 135 children′s CT scans. The DRL of 45 subgroups according to 5 age groups and 9 scanning items were obtained. The DRL results showed that the CTDI vol in five age groups was 26.9-42.8 mGy, and the DLP was 347-694 mGy·cm for head; 3.5-8.0 mGy, 54-293 mGy·cm for chest; and 6.3-13.2 mGy, 155-564 mGy·cm for abdomen. The DRL of the age group >4-10 years group in this investigation was agreed to the DRL of Chinese Society of Radiology. Compared with the European guidelines, there was little difference in the radiation dose of head scan, while the radiation dose of chest and abdomen in the young age group increased significantly. Conclusion:This survey reveals the radiation dose level distribution of children CT in our country. The radiation dose level of some items was inconsistent with the DRL of relevant international organizations. So our own DRL is needed to be set up according to the actual clinical reality of our country as a guideline.

Objective:Gasless laparoscopic surgery using lifting device was first introduced in 1993 mainly for general surgery and gynecology. Here we report its application in bifid rib treatment and explore the feasibility and safety of the surgery.Methods:From July 2008 to December 2019, according to the enrollment criteria, 278 patients of bifid ribs were treated at the Department of Thoracic Surgery, Beijing Children’s Hospital, Capital Medical University, including 183 males and 95 females, the mean age was(5.7±2.5) years old. There were 242 cases of single bifid rib and 36 cases of multiple bifid ribs. The bifid ribs were more common on the right side, as 184 cases had bifid ribs on right side, while only 68 cases on the left side and 26 cases on both sides. Patients’ clinical data were retrospectively summarized and analyzed, including the patients’ gender, age, location and type of bifid rib, perioperative outcome, and follow-up.Results:All the 278 patients successfully completed the operation. The abnormality was most frequently found in the fifth rib(incidence ranking: fifth > fourth > third > sixth). The mean operation time was(64.5±16.1)min, and the mean blood loss was(4.8±2.1)ml. No serious complications occurred during the surgery. Follow-up was done for 7 to 120 months, and no recurrent patients were observed.Conclusion:Gasless endoscopy with lifting device has been used as a safe and effective method to treat bifid ribs in our hospital. This surgery leads to less injury, smaller incision, and no scars on the front chest. Gasless endoscopic surgery with lifting device can be one of the options for correcting bifid ribs.

Objective:To investigate the clinical efficacy of TiRobot-assisted minimally invasive percutaneous screw fixation for pelvic fractures.Methods:The clinical data of 44 patients with pelvic fracture were retrospectively analyzed who had undergone TiRobot-assisted minimally invasive percutaneous screw fixation from May 2018 to April 2021 at Department of Orthopedic Traumatology, The First Hospital of Jilin University. There were 30 males and 14 females, aged from 11 to 78 years (average, 40.6 years). According to the Tile classification, there were 20 type C1 fractures, 23 type C2 fractures and one type C3 fracture. The time from injury to operation averaged 8.2 days (from 1 to 41 days). The minimally invasive percutaneous screw fixation was assisted by the orthopaedic TiRobot in all patients. Operation time, fluoroscopy time, reduction quality, complications and functional recovery at the final follow-up were recorded and analyzed.Results:A total of 96 screws were implanted in this cohort. The total fluoroscopy time ranged from 17 to 66 s, with an average of 17.8 s for each single screw. The operation time ranged from 50 to 355 min, averaging 179.7 min. According to the Matta criteria, the reduction quality was rated as excellent in 36 cases, as good in 5 and as fair in 3, yielding an excellent and good rate of 93.2%(41/44). All the 44 patients were followed up for 6 to 42 months (average, 20.4 months). The fracture healing time ranged from 2 to 6 months, averaging 3.3 months. The Majeed scores at the final follow-up ranged from 51 to 100 points (average, 83.7 points); there were 28 excellent, 8 good, 7 fair and one poor cases, giving an excellent to good rate of 81.8% (36/44). Follow-up found no such complications as iatrogenic neurovascular injury, incision infection, malunion, implant loosening or fracture re-displacement in all the 44 patients.Conclusion:TiRobot-assisted minimally invasive internal fixation can result in fine clinical efficacy for pelvic fractures, showing advantages of accuracy, minimal invasion and safety.

Objective:To investigate the feasibility, clinical efficacy and safety of endobronchial ultasound (EBUS) in children.Methods:The radiological features, EBUS images, pathological results and intraoperative and postoperative complications of 3 cases who underwent EBUS examination and 1 case who underwent EBUS guided transbronchial needle aspiration (EBUS-TBNA) were retrospectively analyzed.Results:Among the 4 cases, 2 were males and 2 were females, with the onset age of 7.4-9.2 years. The child who underwent successful EBUS-TBNA was presented with fever and diagnosed with mediastinal lymphadenopathy before the operation, and the postoperative pathology indicated histiocytic necrotic lymphadenitis (HNL). The other 3 children diagnosed with primary airway tumors, whose pre-operative CT imaging found no infiltration in extra-bronchial structures, had the masses resected through EBUS. According to postoperative pathological findings, two were diagnosed with mucoepidermoid carcinoma and one with bronchial leiomyoma. The lesions were located at the opening of the right main bronchus in 1 case and at the main airway in 2 cases. EBUS showed abnormal echogenicity of the tracheal wall in the 3 cases, including hyperechoic area in the water capsule and mucous layer, relatively hypoechoic area in the submucosal smooth muscle layer, hyperechoic area in the inner cartilage layer, hypoechoic in the cartilage layer and hyperechoic in the outer cartilage layer. In one case, structural disorder of the submucosal smooth muscle layer and partial disruption of the cartilage layer of the tracheal wall were found at the lesion site, while the other 2 cases had intact tracheal wall structure. There were no postoperative complications such as pneumothorax or hemoptysis in the 4 children.Conclusion:EBUS is a safe and feasible technique for evaluating mediastinal lymph node enlargement and the degree of airway wall infiltration in primary airway tumor.

Objective:To evaluate clinical characteristics and treatment of postoperative anastomotic stricture in pediatric congenital biliary dilatation patients.Methods:The clinical data of 24 children with postoperative anastomotic stricture from Apr 2012 to Oct 2019 in Beijing Children's Hospital was retrospectively analyzed.Results:There were 6 males and 18 females. Patients were divided into bile- leak group (BL, n=6) and non bile-leak group (NBL, n=18) based on whether there was anastomotic leakage after primary surgery. The main symptoms in BL group was persistent obstructive jaundice, and recurrent cholangitis in NBL group. Postoperative symptoms were first shown in an average of 7.0 months in BL group, compared to 59.0 months in NBL group, P<0.05. In BL group, 4 underwent redoing hepaticojejunostomy, 2 underwent anastomosis plasty. In NBL group, 3 underwent redoing hepaticojejunostomy, 15 did anastomosis plasty with multiple biliary stones found necessitating extraction. After reoperation, one patient had bile leakage, 2 patients had recurrent cholangitis within one-month, 21 patients had uneventful recovery. Five were found to have biliary stones in long-term follow-up. Conclusions:Biliary-enteric anastomotic leakage can cause stricture in postoperative patients of congenital biliary dilatation ,reoperation is necessary in symptomatic patients.