Objective To observe the impact of ultrasonic image quality on the consistency of artificial intelligence(Al)assisted diagnosis system and manual measurements of biological indicators of developmental dysplasia of hip(DDH).Methods Hip ultrasonic data of 75 DDH and 345 non-DDH children were retrospectively analyzed,and the quality of ultrasonic images were subjectively scored.An evaluation model of ultrasonic image quality was constructed based on 140 ultrasonic images acquired from 140 cases(group A,containing 25 DDH and 115 non-DDH)using entropy weighting method,the weight of anatomic structures and impact factors related to DDH were obtained.The comprehensive image quality scores of other ultrasonic images acquired from 280 cases(group B,including 50 DDH and 230 non-DDH)were calculated,and the images in group B were classified into grade A,B and C in descending order.The consistency of AI and manual measurements of DDH biological indicators in group B was assessed.Results The weight of each anatomic structure and impact factors of DDH obtained with the model were as follows:The lower edge of iliac branch＞ilium＞glenoid labrum＞bony margin＞femoral head＞motion artifacts.In group B,grade A was observed in 67(9 DDH and 58 non-DDH),grade B was found in 160(26 DDH and 134 non-DDH),while grade C was noticed in 53(15 DDH and 38 non DDH)images.Except for β,femoral head coverage(FHC)and femoral head length diameter,the consistencies between AI and manual measurements of other indicators of DDH were grade A＞B＞C.In group B,AI and manual measurements were more consistent in DDH than in non-DDH cases.Conclusion Ultrasonic image quality affected the consistency between AI and manual measurements of biological indicators of DDH.When image quality was not good enough,further attention should be paid to measurement of FHC and sizes of femoral head.

Objective To analysis the change of hip joint in healthy infants by ultrasound,and establish the normal reference value of the developmental dysplasia of the hip(DDH). Methods A total of 8 000 healthy infants from 0 to 24 weeks were collected from the Multi-center study of 10 children′s medical centers. Among them,3 855 infants(2 065 females and 1 790 males) with complete data and follow-up were included in this study. All subjects were divided into 6 groups ( ＜4,4～7,8～11,12～15,16～19 and≥20 weeks group). α angle,femoral head length and width,femoral head coverage ratio by acetabulum ( FHC) were measured in the coronal view on the neutral position;distance from pubis to femoral head ( P-H) and distance from ischium to femoral head ( I-H ) were measured in the transverse view on neutral position;distance from femoral head topubis ( H-P) was measured in the posterolateraltransverse view on the flexion position. The results of each group changes with age were analysised. Results ① The α angle of healthy infants from 0 to 20 weeks were increased with age,the difference among the groups were statistically significant( P ＜0.05),but there was no significant difference between 16～19 and ≥20 weeks group( P ＞0.05). ②The femoral head length and width of all age groups were increased with age,the difference among all the groups was statistically significant( all P ＜0.05). ③ FHC from 0 to 20 weeks were increased with age,the difference among the groups were statistically significant( P ＜0.05) except between 16～19 and ≥20 weeks group( P ＞0.05). ④ The P-H and I-H in all age groups showed no statistically significant ( all P＞0.05). ⑤The H-P of all age groups were increased with age,the difference between the groups were statistically significant(all P ＜0.05).Conclusions The development of hip joints have the certain regular developmental pattern in healthy infants less than 5 months of birth and are relatively constant after birth more than 5 months. The ultrasound normal reference value of the hip joints can be used for the early diagnosis of the DDH.

Objective To investigate the value of ultrasound in tethered cord syndrome (TCS) in infants. Methods From December 2005 to July 2013, 25 cases TCS were confirmed by surgery in Shenzhen children's hospital. The ultrasonogram and MRI of 25 infants were analysed retrospectively. The diagnostic accuracy of ultra-sound and its clinical significance were evaluated. Results In 25 cases of TCS confirmed by surgery, the coincidence rate of conus level detected by ultrasound [96%(23/24)] was lower than that by MRI (100%(25/25)). Ultrasound showed reduced spinal cord vibration in 4 cases, disappeared spinal cord vibration in 21 cases. Two cases of reduced spinal cord vibration detected by ultrasound were confirmed as disappeared spinal cord vibration by surgery. The coincidence rate of disappeared spinal cord vibration detected by ultrasound was 91%(21/23). The sacral spinal seg-ments form showed by ultrasound were entirely consistent with those of MRI, including 4 cases of enlarged spinal cord, 13 cases of spinal cord without enlargement and 8 cases of spinal cord ended with rat caudate. Twenty-five cases of TCS had malformations:7 cases meningocele (3 cases combined lipoma), 14 cases myelomeningocele (5 cases combined lipoma, 1 case combined hydromyelia), 3 cases spinal canal-epidermis fistula (all combined lipoma) and 1 case solitary lipoma. Compared with the operation findings, ultrasound misdiagnosed 2 cases of myelomeningo-cele as meningocele, missed 1 of case lipoma which combined with meningocele. MRI missed two cases of spinal canal-epidermis fistula. Conclusions Infantile spinal ultrasound examination can accurately locate the position of conus, accurately display the spinal cord. Compared with MRI, ultrasound examination can real-time visually display spinal cord vibration and help to diagnose tethered cord. Ultrasound examination are convenient, repeatable opera-tion with low cost, therefore it can be used as the preferred screening method to diagnose of tethered spinal cord.

Objective To investigate the clinical value of coronary artery Z-scores on echocardiography in diagnosing coronary artery abnormalities. Methods The echocardiography results of 612 patients with Kawasaki disease (KD) at the acute and recovery phase were retrospectively studied. Coronary artery luminal diameters were converted to body-surface-area-adjusted Z-scores. According to coronary Z-scores classiifcation, all the subjects were divided to four groups:415 cases with no dilation (ND), 133 cases with small coronary artery abnormalities (SCAAs), 47 cases with large coronary artery abnormalities (LCAAs), and 17 cases with giant coronary artery abnormalities (GCAAs). Clinical features (gender, age, typical clinical manifestations, fever duration) and laboratory results (CRP, ESR, WBC, PLT) were compared among all the four groups. Coronary artery diameters and the Z-scores were compared between acute and convalescence phase. Results Along with the increase of coronary Z-score, fever duration was prolonged [ND group:(7.75±3.12) d, SCAAs group (8.50±4.12) d, LCAAs group: (8.57±3.58) d, GCAAs group: (11.88±4.33) d, F=22.375, P<0.05]. With coronary Z-score increasing, PLT also increased (F=22.029, P=0.000), and the highest PLT was observed in GCAAs group. There were no significant differences in the CRP, ESR and WBC among all the four groups (F=0.236, 1.116, 0.121, all P>0.05). No significant different coronary diameters were found in ND cases between recovery and acute phase [(2.24±0.34) mm vs (2.33±0.36) mm, t=1.926, P > 0.05]. But there were significant difference in the coronary Z-scores of ND patients between recovery and acute phase (0.41±0.82 vs 1.17±0.75, t=8.332, P < 0.05). The coronary Z-scores in SCAAs group (1.32±0.89 vs 3.40±0.62, t=11.073, P < 0.05), LCAAs group (3.12±2.27 vs 6.20±1.28, t=4.579, P<0.05) and GCAAs group (11.88±6.77 vs 20.4±9.70, t=3.480, P<0.05) at recovery phase were smaller than values at acute phase. Conclusions The KD coronary Z-scores are the body-surface-area-adjusted standard value, and not subject to the influence of children growth and development. Therefore, it may accurately evaluate the severity of coronary artery abnormalities and its recovery process. Accurate quantitative of the coronary artery luminal dimensions is important in KD clinical management and prognosis prediction.