RESUMO
Background: In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using a convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, upon which our study is based, lacked a gold standard for comparison and had not undergone thorough evaluation in different working environments. Methods: To further verify the applicability of the AI system in clinical bone age assessment (BAA) and to enhance the accuracy and homogeneity of BAA, a prospective multi-center validation was conducted. This study utilized 744 left-hand radiographs of patients, ranging from 1 to 20 years of age, with 378 boys and 366 girls. These radiographs were obtained from nine different children's hospitals between August and December 2020. The BAAs were performed using the TW3 AI system and were also reviewed by experienced reviewers. Bone age accuracy within 1 year, root mean square error (RMSE), and mean absolute error (MAE) were statistically calculated to evaluate the accuracy. Kappa test and Bland-Altman (B-A) plot were conducted to measure the diagnostic consistency. Results: The system exhibited a high level of performance, producing results that closely aligned with those of the reviewers. It achieved a RMSE of 0.52 years and an accuracy of 94.55% for the radius, ulna, and short bones series. When assessing the carpal series of bones, the system achieved a RMSE of 0.85 years and an accuracy of 80.38%. Overall, the system displayed satisfactory accuracy and RMSE, particularly in patients over 7 years old. The system excelled in evaluating the carpal bone age of patients aged 1-6. Both the Kappa test and B-A plot demonstrated substantial consistency between the system and the reviewers, although the model encountered challenges in consistently distinguishing specific bones, such as the capitate. Furthermore, the system's performance proved acceptable across different genders and age groups, as well as radiography instruments. Conclusions: In this multi-center validation, the system showcased its potential to enhance the efficiency and consistency of healthy delivery, ultimately resulting in improved patient outcomes and reduced healthcare costs.
RESUMO
OBJECTIVE: To explore the feasibility of inducing human umbilical cord mesenchymal stem cells (HuMSCs) to differentiate into Leydig cells through conditioned medium derived from Leydig cells. METHODS: HuMSCs and Leydig cells were obtained by tissue blocks culture attachment and enzymatic digestion respectively. HuMSCs were induced by conditioned medium of Leydig cells as an experiment group while those before induction were cultured as a control group. The expressions of LHR, 3ß-HSD and StAR in the induced HuMSCs were determined by RT-PCR after 3, 7 and 10 days of culture; those of CYP11A1, CYP17A1 and 3ß-HSD measured by immunofluorescence staining after 2 weeks; and that of 3ß-HSD detected by Western blot after 4 weeks. RESULTS: The experimental group showed positively expressed LHR, 3ß-HSD and StAR at 3, 7 and 10 days, CYP11A1, CYP17A1 and 3ß-HSD at 2 weeks, and 3ß-HSD at 4 weeks, while the control group revealed negative expressions at all the time points. CONCLUSION: Induced with conditioned culture medium derived from Leydig cells, HuMSCs are likely to differentiate into steroidogenic cells and eventually into Leydig cells.