RESUMEN
Objective To explore the value of Fast Dixon in improving the quality of thyroid turbo spin echo(TSE)T2WI images via comparing the quality of thyroid MR T2WI images based on Fast Dixon,Dixon,and BLADE sequences.Methods The prospective study included 11 healthy volunteers,who underwent neck MR scanning.The evaluation of image quality was performed via a combination of objective measures and subjective ratings.Objective measures included signal-to-noise ratio(SNR)of bilateral thyroid and muscles,and contrast-to-noise ratio(CNR).Subjective measures included overall image quality,uniformity of fat suppression,sharpness of thyroid margins and muscles surrounding the thyroid,image noise in the neck region,image background noise,and image quality of the nasopharynx.Two diagnostic physicians with over 10 years of thyroid diagnostic experience independently evaluated the images via a 5-point scale.Inter-observer agreement was analyzed via Spearman correlation coefficient.Statistical analysis was performed using SPSS 22.0 software,including normality and homogeneity of variance tests for continuous data.Kruskal-Wallis one-way ANOVA was used for statistical analysis of subjective measures,followed by post hoc pairwise comparisons.A significance level of P<0.05 was considered statistically significant.Results Eleven healthy volunteers,the SNR of bilateral thyroid and muscles was significantly higher in Fast Dixon sequence than that in Dixon and BLADE sequences.For bilateral CNR,Fast Dixon sequence was also significantly higher than that of Dixon and BLADE sequences.Fast Dixon sequence also had significant advantages in seven subjective ratings indicators(P<0.001).Conclusion The Fast Dixon sequence shows the highest image quality and important application value in the display and evaluation of thyroid lesions.
RESUMEN
Objective@#To evaluate the performance of a deep learning (DL) based mammogram calcification detection system.@*Methods@#Screening digital mammographic examinations with standard cranio-caudal (CC) and medio-lateral oblique (MLO) views were performed in 1 431 women (5 488 mammogram images) who were enrolled between January and December in 2013. The DL system and a radiologist detect calcifications separately, and then both results are reviewed by a moreexperiencedradiologist. Sensitivities of the DL model and radiologist were compared. Different calcification morphology, distribution, BI-RADS categories, breast density and patient age were investigated by χ2 tests.@*Results@#For DL system, sensitivity of all kinds of calcifications were 96.76% (7 649/7 905). The average false positive was 1.04 per image (5 706/5 488), 3.99 per case (5 706/1 431). The false positive rate was 42.73% (5 706/13 355). There was no significant differences for DL system with different calcification distribution, BI-RADS categories, breast densities and patient ages (P>0.05).@*Conclusion@#Deep learning based mammogram calcification detection system shows high sensitivity and stability, which may help to reduce the missing rate of calcification (especially the suspicious ones).