A comparison of two artificial intelligence-based methods for assessing bone age in Turkish children: BoneXpert and VUNO Med-Bone Age.

PURPOSE: This study aimed to evaluate the validity of two artificial intelligence (AI)-based bone age assessment programs, BoneXpert and VUNO Med-Bone Age (VUNO), compared with manual assessments using the Greulich-Pyle method in Turkish children. METHODS: This study included a cohort of 292 pediatric cases, ranging in age from 1 to 15 years with an equal gender and number distribution in each age group. Two radiologists, who were unaware of the bone age determined by AI, independently evaluated the bone age. The statistical study involved using the intraclass correlation coefficient (ICC) to measure the level of agreement between the manual and AI-based assessments. RESULTS: The ICC coefficients for the agreement between the manual measurements of two radiologists indicate almost perfect agreement. When all cases, regardless of gender and age group, were analyzed, a nearly perfect positive agreement was observed between the manual and software measurements. When bone age calculations were separated and analyzed separately for girls and boys, there was no statistically significant difference between the two AI-based methods for boys; however, ICC coefficients of 0.990 and 0.982 were calculated for VUNO and BoneXpert, respectively, and this difference of 0.008 was significant (z = 2.528, P = 0.012) for girls. Accordingly, VUNO showed higher agreement with manual measurements compared with BoneXpert. The difference between the agreements demonstrated by the two software packages with manual measurements in the prepubescent group was much more pronounced in girls compared with boys. After the age of 8 years for girls and 9 years for boys, the agreement between manual measurements and both AI software packages was equal. CONCLUSION: Both BoneXpert and VUNO showed high validity in assessing bone age. Furthermore, VUNO has a statistically higher correlation with manual assessment in prepubertal girls. These results suggest that VUNO may be slightly more effective in determining bone age, indicating its potential as a highly reliable tool for bone age assessment in Turkish children. CLINICAL SIGNIFICANCE: Investigating the most suitable AI program for the Turkish population could be clinically significant.

Splenic cysts: clues in sonographic differential diagnosis and a new role for twinkling artifact.

AIM: Our aim was to investigate the frequency of various splenic cysts, to define the sonographic differential diagnostic clues and to introduce the value of twinkling artefact in the diagnosis of epidermoid splenic cysts. MATERIAL AND METHODS: All the splenic cysts imaged by ultrasound in 3 university hospitals during the period of 2005 to 2022 were recorded, followed-up and analyzed. RESULTS: One hundred seventy-one patients with splenic cysts were detected and these were classified and 73% of the cysts were simple. Ten cysts were epidermoid cysts as proven by post-operative final histology. CONCLUSION: Cystic splenic lesions are rare. Most of them are small simple cysts. Epidermoid cysts are larger in volume, constitute 6% of the total and can be differentiated by the help of twinkling artefact by Doppler ultrasound.

Relationship between hepatic and pancreatic steatosis and the COVID-19 pneumonia total severity score and prognosis with an emphasis on prognostic strength

PURPOSE: To investigate the relationship between hepatic steatosis (HS), pancreatic steatosis (PS), and coexisting HS and PS and the Coronavirus disease-2019 (COVID-19) pneumonia total severity score (TSS) and prognosis, assessed through computed tomography (CT), and to evaluate the degree of effectiveness of the three steatosis conditions on TSS and prognosis. METHODS: This retrospective study involved 461 patients (255 male and 206 female, median age of 53 years) with COVID-19 who underwent unenhanced chest CT. HS, PS, and coexisting HS and PS, assessed through CT, were compared with patient demographics, comorbidities, TSS, hospitalization and intubation requirements, and mortality rates. The parameters were compared using Mann-Whitney U and chi-square tests. The parameters of three groups of patients with only HS, only PS, and both HS and PS were compared using the Kruskal-Wallis test. RESULTS: Results revealed that TSS (P < 0.001 for all) and hospitalization rates (P < 0.001 for all except for HS [P = 0.004]) were higher in patients with HS, PS, and both than in those without. Intubation (P = 0.003) and mortality rates (P = 0.018) were significantly higher solely in patients with PS. However, TSS, hospitalization, and diabetes mellitus were significantly higher than in age-standardized analyses for PS. In a comparison between only HS, only PS, and coexisting HS and PS in 210 patients, the highest TSS was in the coexistence group (P < 0.001). CONCLUSION: The TSS and hospitalization rates correlate with HS, PS, and coexisting HS and PS, whereas intubation and mortality rates only correlate with PS. However, TSS correlates with coexisting HS and PS at the highest rate.