目的 探讨超声成像参数对S-Detect技术诊断结果产生的影响。 方法 前瞻性收集2021年10月至2022年3月因乳腺结节在浙江大学医学院附属邵逸夫医院就诊的患者，共纳入133例患者（143个结节）。设置5种超声成像参数条件，包括基准（单焦点、焦点位于病灶中部水平、病灶深度适合）、双焦点、焦点位置过浅、焦点位置过深、扫查深度过深。分别存储在不同超声成像参数下获得的超声图像，并应用S-Detect技术对图像进行分析解读。比较基准参数设置与其他参数设置之间的诊断结果一致性及超声特征判读的一致性。并以病理结果为“金标准”，比较各个参数设置条件下的诊断效能。 结果 扫查深度过深与基准条件的诊断一致性（ kappa=0.771）较其他设置更低，对于形状（ kappa=0.489）及内部回声（ kappa=0.442）这两个超声特征判读的一致性也较其他设置低。同时诊断效能（AUC=0.716）为各个设置中的最低者，且与基准设置的诊断效能差距最大。其他各项参数条件与基准条件的一致性较好，诊断效能与基准条件之间无显著性差异。 结论 对比基准参数设置，在不同成像参数设置中，扫查深度过深条件下的诊断一致性、超声特征判读一致性、诊断效能均较其他条件更低。因此应用S-Detect技术时应避免采用过深的扫查深度。

Objective To investigate the influence of ultrasound imaging parameters on the diagnosis of S?Detect technology. Methods Between October 2021 and March 2022， a total of 143 breast nodules from 133 patients were included in this study. Five ultrasound imaging parameters were set， including basic parameter （single focus， focus located at the middle level of the lesion， and suitable depth of the lesion）， dual focus parameter， superficial focus location， over?depth focus location， and scanning over?depth parameter. The ultrasound images were preserved in different ultrasound imaging parameters to obtain the results of S?Detect. The consistency of diagnosis and ultrasonographic feature interpretation under different ultrasound imaging parameters were investigated. And the diagnostic performance under the four parameters were compared with the basic one. The pathologic results were used as a “golden standard”. Results The diagnostic consistency （kappa = 0.771） of the scanning over?depth parameter was lower than the other settings. The consistency of interpretation of the two ultrasonographic features ［shape （kappa = 0.489） and internal echo （kappa = 0.442）］ were also lower than the other settings. Meanwhile， the diagnostic performance of the scanning over?depth parameter （AUC = 0.716） was the lowest among those ultrasound imaging parameters， and it has the largest gap with the diagnostic efficacy of the basic parameter setting. The other parameter conditions was consistent with the basic parameter， and there was no significant difference between the diagnostic efficacy and basic parameter setting. Conclusions As compared with the basic imaging parameter setting， the consistency of diagnosis， the ultrasonographic feature interpretation and diagnostic performance of the scanning over?depth setting were lower than other ultrasound imaging settings. Therefore， the scanning over?depth settings should be avoided when applying the S?Detect technology.