AbstractAntenatal hydronephrosis (HN) impacts up to 5% of pregnancies and requires close, frequent follow-up monitoring to determine who may benefit from surgical intervention. To create an automated HN Severity Index (HSI) that helps guide clinical decision-making directly from renal ultrasound images.

摘要产前肾积水（HN）影响高达5%的妊娠，需要密切，频繁的随访监测，以确定谁可能从手术干预中受益。创建一个自动的HN严重程度指数（HSI），直接从肾脏超声图像中帮助指导临床决策。

We applied a deep learning model to paediatric renal ultrasound images to predict the need for surgical intervention based on the HSI. The model was developed and studied at four large quaternary free-standing paediatric hospitals in North America. We evaluated the degree to which HSI corresponded with surgical intervention at each hospital using area under the receiver-operator curve, area under the precision-recall curve, sensitivity, and specificity.

我们将深度学习模型应用于儿科肾脏超声图像，以预测基于HSI的手术干预需求。该模型是在北美四家大型四级独立儿科医院开发和研究的。我们使用接受者-操作者曲线下的面积，精确回忆曲线下的面积，敏感性和特异性评估了HSI与每家医院手术干预相对应的程度。

HSI predicted subsequent surgical intervention with > 90% AUROC, > 90% sensitivity, and > 70% specificity in a test set of 202 patients from the same institution. At three external institutions, HSI corresponded with AUROCs ≥ 90%, sensitivities ≥ 80%, and specificities > 50%. It is possible to automatically and reliably assess HN severity directly from a single ultrasound.

HSI预测随后的手术干预，在同一机构的202名患者的测试集中，AUROC为90%，敏感性为90%，特异性为70%。在三个外部机构中，HSI对应于AUROC≥90%，敏感性≥80%，特异性>50%。可以直接从单个超声波自动可靠地评估HN的严重程度。

The HSI stratifies low- and high-risk HN patients thus helping to triage low-risk patients while maintaining very high sensitivity to surgical cases. HN severity can be predicted from a single patient ultrasound using a novel image-based artificial intelligence system..

HSI对低风险和高风险HN患者进行分层，从而有助于对低风险患者进行分类，同时对手术病例保持非常高的敏感性。使用一种新型的基于图像的人工智能系统，可以从单个患者的超声波中预测HN的严重程度。。

IntroductionAntenatal hydronephrosis (HN) is a common prenatal ultrasound finding, detected in up to 2–5% of fetuses1. After birth, the condition is closely monitored with up to 80% of cases experiencing resolution without intervention. In the remaining patients, HN may be secondary to a pathologic process, such as ureteropelvic junction obstruction (UPJO), ureterovesical junction obstruction (UVJO), or vesicoureteral reflux (VUR), which may benefit from surgical intervention.

引言产前肾积水（HN）是一种常见的产前超声检查结果，在高达2-5%的胎儿中检测到1。出生后，密切监测病情，高达80%的病例在没有干预的情况下得到解决。在其余患者中，HN可能继发于病理过程，例如输尿管肾盂交界处梗阻（UPJO），输尿管膀胱交界处梗阻（UVJO）或膀胱输尿管反流（VUR），这可能受益于手术干预。

The challenge is to risk-stratify patients early in life. However this is currently not possible, therefore babies with HN are monitored with serial ultrasounds, and many will undergo invasive testing, requiring urethral catheterization, intravenous access, and exposure to radioisotopes and radiation.

面临的挑战是在生命早期对患者进行风险分层。然而，目前这是不可能的，因此用连续超声波监测患有HN的婴儿，并且许多婴儿将接受侵入性测试，需要导尿，静脉通路以及暴露于放射性同位素和辐射。

In addition to the anxiety, discomfort, and morbidity related to these additional tests, there is growing concern about the potential link between radiation exposure and future malignancies2. Risk stratification using ultrasound images alone has the potential to streamline care for low-risk patients, reduce the number of patients investigated with invasive tests and help providers to comply with the as low as reasonably achievable (ALARA) radiation principle, while expediting interventions for those that may benefit.Machine learning (ML) models have shown tremendous promise in healthcare, including for those with HN.

除了与这些额外测试相关的焦虑，不适和发病率外，人们越来越担心辐射暴露与未来恶性肿瘤之间的潜在联系2。仅使用超声图像进行风险分层有可能简化对低风险患者的护理，减少接受侵入性检测的患者数量，并帮助提供者遵守尽可能低的合理可行（ALARA）辐射原则，同时加快干预可能受益的人。机器学习（ML）模型在医疗保健领域显示出巨大的前景，包括那些患有HN的人。

Predicting patients most likely to progress to surgery, or those at risk for urinary tract infection (UTI) has been explored using clinical variables3,4. Standardized assessment of anatomical regions of the kidney in ultrasound images has been explored in multiple works including the parenchyma to hydronephrosis area5 the hydronephrosis index using comparing the total kidney area with th.

使用临床变量3,4已经探索了预测最有可能进行手术的患者或有尿路感染（UTI）风险的患者。超声图像中肾脏解剖区域的标准化评估已经在多项工作中进行了探索，包括肾实质积水区域5，使用比较总肾脏面积和肾积水指数。

Data availability

数据可用性

Code for the models and tables of this work can be found at https://github.com/larunerdman/HN_Replicate and power scripts can be found in https://github.com/ErikinBC/power_roc. As the data for this work contains de-identified private health information, it has undergone approval for ethical use at each institution and can be accessed via reasonable request from the authors and further institution-level ethical and data transfer approval for use..

这项工作的模型和表格的代码可以在https://github.com/larunerdman/HN_Replicate电源脚本可以在https://github.com/ErikinBC/power_roc.由于这项工作的数据包含未识别的私人健康信息，因此它已在每个机构获得道德使用批准，并且可以通过作者的合理要求以及进一步的机构级道德和数据传输批准来访问。。

ReferencesNguyen, H. T. et al. The Society for Fetal Urology consensus statement on the evaluation and management of antenatal hydronephrosis. J. Pediatr. Urol. 6, 212–231 (2010).Article

参考文献Nguyen，H.T.等人，《胎儿泌尿外科学会关于产前肾积水评估和管理的共识声明》。J、 儿科。乌洛尔。6212-231（2010）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Little, M. P. et al. Leukaemia and myeloid malignancy among people exposed to low doses (<100 mSv) of ionising radiation during childhood: a pooled analysis of nine historical cohort studies. Lancet Haematol. 5, e346–e358 (2018).Article

Little，M.P.等人，《儿童时期接触低剂量（<100 mSv）电离辐射的人群中的白血病和髓系恶性肿瘤：对9项历史队列研究的汇总分析》。柳叶刀血液。5，e346–e358（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Bertsimas, D., Li, M., Estrada, C., Nelson, C. & Scott Wang, H.-H. Selecting children with vesicoureteral reflux who are most likely to benefit from antibiotic prophylaxis: Application of machine learning to RIVUR. J. Urol. 205, 1170–1179 (2021).Article

Bertsimas，D.，Li，M.，Estrada，C.，Nelson，C。＆Scott Wang，H.-H。选择最有可能从抗生素预防中受益的膀胱输尿管反流儿童：将机器学习应用于RIVUR。J、 乌洛尔。2051170-1179（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Lorenzo, A. J., Rickard, M., Braga, L. H., Guo, Y. & Oliveria, J.-P. Predictive analytics and modeling employing machine learning technology: The next step in data sharing, analysis, and individualized counseling explored with a large, Prospective Prenatal Hydronephrosis Database. Urology.

Lorenzo，A.J.，Rickard，M.，Braga，L.H.，Guo，Y.＆Oliveria，J.-P。使用机器学习技术的预测分析和建模：数据共享，分析和个性化咨询的下一步探索与大型前瞻性产前肾积水数据库。泌尿外科。

123, 204–209 (2019).Article .

123204-209（2019）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Rickard, M., Lorenzo, A. J. & Braga, L. H. Renal Parenchyma to hydronephrosis area ratio (PHAR) as a predictor of future surgical intervention for infants with high-grade prenatal hydronephrosis. Urology. 101, 85–89 (2017).Article

Rickard，M.，Lorenzo，A.J。＆Braga，L.H。肾实质与肾积水面积比（PHAR）可作为高度产前肾积水婴儿未来手术干预的预测指标。。101,85-89（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Shapiro, S. R., Wahl, E. F., Silberstein, M. J. & Steinhardt, G. Hydronephrosis index: A new method to track patients with hydronephrosis quantitatively. Urology. 72, 536–538 (2008) (discussion 538–9).Article

Shapiro，S.R.，Wahl，E.F.，Silberstein，M.J。＆Steinhardt，G。肾积水指数：定量追踪肾积水患者的新方法。。72536-538（2008）（讨论538-9）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Roshanitabrizi, P., Zember, J., Sprague, B. M., Hoefer, S., Sanchez-Jacob, R., Jago, J., et al. In Standardized Analysis of Kidney Ultrasound Images for the Prediction of Pediatric Hydronephrosis Severity. Machine Learning in Medical Imaging 366–375 (Springer International Publishing, 2021).Cerrolaza, J.

Roshanitabrizi，P.，Zember，J.，Sprague，B.M.，Hoefer，S.，Sanchez-Jacob，R.，Jago，J。等人在肾脏超声图像的标准化分析中预测小儿肾积水的严重程度。医学成像中的机器学习366-375（Springer International Publishing，2021）。塞罗拉扎，J。

J. et al. Quantitative ultrasound for measuring obstructive severity in children with hydronephrosis. J. Urol. 195, 1093–1099 (2016).Article .

J、 定量超声测量肾积水患儿梗阻严重程度。J、 乌洛尔。1951093-1099（2016）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Smail, L. C., Dhindsa, K., Braga, L. H., Becker, S. & Sonnadara, R. R. Using deep learning algorithms to grade hydronephrosis severity: Toward a clinical adjunct. Front. Pediatr. 8, 1 (2020).Article

Smail，L.C.，Dhindsa，K.，Braga，L.H.，Becker，S。＆Sonnadara，R.R。使用深度学习算法对肾积水的严重程度进行分级：走向临床辅助。正面。儿科。8，1（2020年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rickard, M. et al. Six of one, half a dozen of the other: A measure of multidisciplinary inter/intra-rater reliability of the society for fetal urology and urinary tract dilation grading systems for hydronephrosis. J. Pediatr. Urol. 13(80), e1-80.e5 (2017).

Rickard，M.等人，《六分之六，六分之六：胎儿泌尿外科学会和尿路扩张肾积水分级系统的多学科评估者间/内部可靠性的衡量标准》。J、 儿科。乌洛尔。13（80），e1-80.e5（2017）。

Google Scholar

谷歌学者

Keays, M. A. et al. Reliability assessment of Society for Fetal Urology ultrasound grading system for hydronephrosis. J Urol. 180, 1680–1682 (2008) (discussion 1682–3).Article

Keays，M.A.等人，《胎儿泌尿外科超声分级系统对肾积水的可靠性评估》。J乌拉尔。1801680-1682（2008）（讨论1682-3）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Kim, S.-Y. et al. Comparison of the reliability of two hydronephrosis grading systems: The Society for Foetal Urology grading system vs. the Onen grading system. Clin. Radiol. 68, e484–e490 (2013).Article

Kim，S.-Y.等人。两种肾积水分级系统的可靠性比较：胎儿泌尿外科学会分级系统与Onen分级系统。。放射性。68，e484–e490（2013）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Erdman, L., Skreta, M., Rickard, M., McLean, C., Mezlini, A., Keefe, D. T., et al. Predicting Obstructive Hydronephrosis Based on Ultrasound Alone. Medical Image Computing and Computer Assisted Intervention—MICCAI 2020 493–503 (Springer International Publishing, 2020).Kwong, J. C. C.

Erdman，L.，Skreta，M.，Rickard，M.，McLean，C.，Mezlini，A.，Keefe，D.T。等人。仅基于超声波预测阻塞性肾积水。医学图像计算和计算机辅助干预MICCAI 2020 493-503（Springer International Publishing，2020）。Kwong，J.C.C。

et al. Standardized reporting of machine learning applications in urology: The STREAM-URO framework. Eur. Urol. Focus. https://doi.org/10.1016/j.euf.2021.07.004 (2021).Article .

等人，《泌尿外科机器学习应用的标准化报告：STREAM-URO框架》。欧洲泌尿外科杂志。专注。https://doi.org/10.1016/j.euf.2021.07.004（2021年）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Palmer, L. S., Maizels, M., Cartwright, P. C., Fernbach, S. K. & Conway, J. J. Surgery versus observation for managing obstructive grade 3 to 4 unilateral hydronephrosis: A report from the Society for Fetal Urology. J. Urol. 159, 222–228 (1998).Article

Palmer，L.S.，Maizels，M.，Cartwright，P.C.，Fernbach，S.K。＆Conway，J.J。手术与观察治疗阻塞性3至4级单侧肾积水：胎儿泌尿外科学会的报告。J、 乌洛尔。159222-228（1998）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Rickard, M. et al. Evolving trends in peri-operative management of pediatric ureteropelvic junction obstruction: Working towards quicker recovery and day surgery pyeloplasty. World J. Urol. https://doi.org/10.1007/s00345-021-03621-9 (2021).Article

Rickard，M.等人。小儿肾盂输尿管连接部梗阻围手术期管理的发展趋势：致力于更快的恢复和日间手术肾盂成形术。世界J.Urol。https://doi.org/10.1007/s00345-021-03621-9（2021年）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Shrestha, A. L., Bal, H. S., Kisku, S. M. C. & Sen, S. Outcome of end cutaneous ureterostomy (ECU) as a non conservative option in the management of primary obstructive megaureters (POM). J. Pediatr. Urol. 14(541), e1-541.e5 (2018).

Shrestha，A.L.，Bal，H.S.，Kisku，S.M.C.＆Sen，S。末端皮肤输尿管造口术（ECU）作为治疗原发性梗阻性巨输尿管（POM）的非保守选择的结果。J、 儿科。乌洛尔。14（541），e1-541.e5（2018）。

Google Scholar

谷歌学者

Farrugia, M.-K. et al. British Association of Paediatric Urologists consensus statement on the management of the primary obstructive megaureter. J. Pediatr. Urol. 10, 26–33 (2014).Article

Farrugia，M.-K.等人。英国儿科泌尿科医生协会关于原发性梗阻性巨输尿管管理的共识声明。J、 儿科。乌洛尔。10,26-33（2014）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Alyami, F. A. et al. Side-to-side refluxing nondismembered ureterocystotomy: A novel strategy to address obstructed megaureters in children. J. Urol. 198, 1159–1167 (2017).Article

Alyami，F.A.等人，《侧对侧回流非离断输尿管膀胱切开术：一种治疗儿童梗阻性巨输尿管的新策略》。J、 乌洛尔。1981159-1167（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 4700–4708 (2017).He, K., Zhang, X., Ren, S., Sun, J. Deep Residual Learning for Image Recognition. arXiv [cs.CV].

Huang，G.，Liu，Z.，Van Der Maaten，L.，Weinberger，K.Q。密集连接的卷积网络。在IEEE计算机视觉和模式识别会议论文集4700-4708（2017）中。He，K.，Zhang，X.，Ren，S.，Sun，J。用于图像识别的深度残差学习。arXiv[简历]。

2015. http://arxiv.org/abs/1512.03385.Simonyan, K., Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv [cs.CV]. 2014. http://arxiv.org/abs/1409.1556.Robin, X. et al. pROC: An open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform. 12, 77 (2011).Article .

2015http://arxiv.org/abs/1512.03385.Simonyan，K.，Zisserman，A。用于大规模图像识别的非常深的卷积网络。arXiv[简历]。2014http://arxiv.org/abs/1409.1556.Robin，X。等人。pROC：R和S+的开源软件包，用于分析和比较ROC曲线。BMC生物信息。12，77（2011）。文章。

Google Scholar

谷歌学者

Ballouz, S., Weber, M., Pavlidis, P. & Gillis, J. EGAD: Ultra-fast functional analysis of gene networks. Bioinformatics. 33, 612–614 (2017).Article

Ballouz，S.，Weber，M.，Pavlidis，P。＆Gillis，J。EGAD：基因网络的超快速功能分析。生物信息学。33612-614（2017）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Whitley, J. A. et al. Availability of common pediatric radiology studies: Are rural patients at a disadvantage?. J. Surg. Res. 234, 26–32 (2019).Article

Whitley，J.A.等人，《普通儿科放射学研究的可用性：农村患者处于不利地位吗？》？。J、 Surg.Res.234，26–32（2019）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Otis-Chapados, S., Coderre, K., Bolduc, S. & Moore, K. Evaluating the distance travelled for urological pediatric appointments. Can. Urol. Assoc. J. 13, 391–394 (2019).PubMed

Otis Chapados，S.，Coderre，K.，Bolduc，S。＆Moore，K。评估泌尿科儿科预约的旅行距离。可以。乌洛尔。Assoc.J.13391–394（2019）。PubMed出版社

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Chandrasekharam, V. V. S., Babu, R., Arlikar, J., Satyanarayana, R. & Murali, K. N. Functional outcomes of pediatric laparoscopic pyeloplasty: Post-operative functional recovery is superior in infants compared to older children. Pediatr. Surg. Int. 37, 1135–1139 (2021).Article

Chandrasekharam，V.V.S.，Babu，R.，Arlikar，J.，Satyanarayana，R。＆Murali，K.N。小儿腹腔镜肾盂成形术的功能结果：与年龄较大的儿童相比，婴儿术后功能恢复更好。儿科。外科国际杂志371135-1139（2021）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Blanc, T. et al. Retroperitoneal laparoscopic pyeloplasty in children: long-term outcome and critical analysis of 10-year experience in a teaching center. Eur. Urol. 63, 565–572 (2013).Article

Blanc，T.等人，《儿童腹膜后腹腔镜肾盂成形术：长期结果和教学中心10年经验的批判性分析》。欧元Urol。63565-572（2013）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Cost, N. G., Prieto, J. C. & Wilcox, D. T. Screening ultrasound in follow-up after pediatric pyeloplasty. Urology. 76, 175–179 (2010).Article

Cost，N.G.，Prieto，J.C。和Wilcox，D.T。在小儿肾盂成形术后的随访中筛查超声波。。76175-179（2010）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Nelson, C. P. Evidence of variation by race in the timing of surgery for correction of pediatric ureteropelvic junction obstruction. J. Urol. 178, 1463–1468 (2007).Article

Nelson，C.P。儿童肾盂输尿管连接部梗阻矫正手术时机种族差异的证据。J、 乌洛尔。1781463-1468（2007）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Jetty, A. et al. Patient-physician racial concordance associated with improved healthcare use and lower healthcare expenditures in minority populations. J. Racial Ethn. Health Dispar. 9, 68–81 (2022).Article

Jetty，A。等人。患者-医生种族一致性与少数民族人群医疗保健使用的改善和医疗保健支出的降低有关。J、 。健康Dispar。9，68-81（2022）。文章

Google Scholar

谷歌学者

Street, R. L. Jr., O’Malley, K. J., Cooper, L. A. & Haidet, P. Understanding concordance in patient-physician relationships: Personal and ethnic dimensions of shared identity. Ann. Fam. Med. 6, 198–205 (2008).Article

Street，R.L.Jr.，O'Malley，K.J.，Cooper，L.A。＆Haidet，P。理解医患关系的一致性：共享身份的个人和种族层面。安。家人。医学杂志6198-205（2008）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Shen, M. J. et al. The effects of race and racial concordance on patient-physician communication: A systematic review of the literature. J. Racial Ethn. Health Dispar. 5, 117–140 (2018).Article

Shen，M.J.等人。种族和种族一致性对医患沟通的影响：文献的系统综述。J、 。健康Dispar。5117-140（2018）。文章

Google Scholar

谷歌学者

Curth, A., Thoral, P., van den Wildenberg, W., Bijlstra, P., de Bruin, D., Elbers, P. W. G., et al. Transferring clinical prediction models across hospitals and electronic health record systems. In PKDD/ECML Workshops (1) 605–621 (2019).Download referencesAcknowledgementsWe would like to thank the Bitove Family and the Hospital for Sick Children’s Women’s Auxilliary Volunteers for their generous financial support for this project.FundingCanadian Institutes of Health Research (LE, AG).Author informationAuthor notesThese authors contributed equally: Lauren Erdman and Mandy Rickard.These authors jointly supervised this work: Armando J.

Curth，A.，Thoral，P.，van den Wildenberg，W.，Bijlstra，P.，de Bruin，D.，Elbers，P.W.G。等人。跨医院和电子健康记录系统转移临床预测模型。在PKDD/ECML研讨会（1）605-621（2019）中。下载参考文献致谢我们要感谢Bitove家庭和病童女性辅助志愿者医院为该项目提供的慷慨财政支持。资助加拿大卫生研究院（LE，AG）。作者信息作者注意到这些作者做出了同样的贡献：劳伦·埃尔德曼和曼迪·里卡德。这些作者共同监督了这项工作：阿曼多J。

Lorenzo and Anna Golenberg.Authors and AffiliationsDivision of Genetics and Genome Biology, Hospital for Sick Children Research Institute, Toronto, ON, USALauren Erdman, Erik Drysdale, Marta Skreta, Stanley Bryan Hua & Anna GolenbergCentre for Computational Medicine, Hospital for Sick Children Research Institute, Toronto, ON, USALauren Erdman & Marta SkretaVector Institute for Artificial Intelligence, Toronto, ON, USALauren Erdman, Marta Skreta & Anna GolenbergDepartment of Computer Science, University of Toronto, Toronto, ON, USALauren Erdman, Marta Skreta, Stanley Bryan Hua & Anna GolenbergJames M.

洛伦佐（Lorenzo）和安娜·戈伦伯格（AnnaGolenberg）。作者和附属机构安大略省多伦多市病童研究所遗传学和基因组生物学系，美国劳伦·埃尔德曼（USALauren Erdman），埃里克·德莱斯代尔（Erik Drysdale），玛尔塔·斯克雷塔（Marta Skreta），斯坦利·布莱恩·华（Stanley Bryan Hua）和安娜·戈伦伯格（Anna Golenberg Centre for Computational Medicine），安大略省多伦多市病童研究所，安大略省多伦多市，美国劳伦·埃尔德曼（Lauren Erdman），玛尔塔·斯克雷塔（Marta Skreta），斯坦利·布莱恩·华（Stanley Bryan Hua）和安娜·戈伦。

Anderson Center for Health Systems Excellence, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USALauren ErdmanSchool of Medicine, University of Cincinnati, Cincinnati, OH, USALauren ErdmanDivision of Urology, Hospital for Sick Children, Toronto, ON, USAMandy Rickard, Michael E. Chua, Joana Dos Santos, Daniel Keefe & Armando J.

安德森健康系统卓越中心，辛辛那提儿童医院医疗中心，俄亥俄州辛辛那提，美国劳伦·埃尔德曼医学院，辛辛那提大学，俄亥俄州辛辛那提，美国劳伦·埃尔德曼泌尿外科，病童医院，多伦多，安大略省，美国曼迪·里卡德，迈克尔·E·蔡，乔安娜·多斯桑托斯，丹尼尔·基夫和阿曼多·J。

LorenzoStanford Children’s Health, Lucile Packard Children’s Hospital, Stanford University, Palo Alto, CA, USAKunj Sheth, Daniel Alvarez, Kyla N. Velaer & Megan A. BonnettHospital for Sick C.

洛伦佐·斯坦福儿童健康中心，斯坦福大学卢西尔·帕卡德儿童医院，加利福尼亚州帕洛阿尔托，USAKunj Sheth，Daniel Alvarez，Kyla N.Velaer＆Megan A.BonnettHospital for Sick C。

PubMed Google ScholarMandy RickardView author publicationsYou can also search for this author in

PubMed Google ScholarMandy RickardView作者出版物您也可以在

PubMed Google ScholarErik DrysdaleView author publicationsYou can also search for this author in

PubMed Google ScholarErik DrysdaleView作者出版物您也可以在

PubMed Google ScholarMarta SkretaView author publicationsYou can also search for this author in

PubMed Google ScholarMarta SkretaView作者出版物您也可以在

PubMed Google ScholarStanley Bryan HuaView author publicationsYou can also search for this author in

PubMed Google ScholarStanley Bryan HuaView作者出版物您也可以在

PubMed Google ScholarKunj ShethView author publicationsYou can also search for this author in

PubMed Google ScholarKunj ShethView作者出版物您也可以在

PubMed Google ScholarDaniel AlvarezView author publicationsYou can also search for this author in

PubMed Google ScholardanielAlvarezview作者出版物您也可以在

PubMed Google ScholarKyla N. VelaerView author publicationsYou can also search for this author in

PubMed Google ScholarKyla N.VelaerView作者出版物您也可以在

PubMed Google ScholarMichael E. ChuaView author publicationsYou can also search for this author in

PubMed Google Scholarmamichael E.ChuaView作者出版物您也可以在

PubMed Google ScholarJoana Dos SantosView author publicationsYou can also search for this author in

PubMed Google ScholarJoana Dos SantosView作者出版物您也可以在

PubMed Google ScholarDaniel KeefeView author publicationsYou can also search for this author in

PubMed Google ScholarDaniel KeefeView作者出版物您也可以在

PubMed Google ScholarNorman D. RosenblumView author publicationsYou can also search for this author in

PubMed Google ScholarNorman D.RosenblumView作者出版物您也可以在

PubMed Google ScholarMegan A. BonnettView author publicationsYou can also search for this author in

PubMed Google ScholarMegan A.BonnettView作者出版物您也可以在

PubMed Google ScholarJohn WeaverView author publicationsYou can also search for this author in

PubMed谷歌学者John WeaverView作者出版物您也可以在

PubMed Google ScholarAlice XiangView author publicationsYou can also search for this author in

PubMed谷歌学术网站XiangView作者出版物您也可以在

PubMed Google ScholarYong FanView author publicationsYou can also search for this author in

PubMed Google ScholarYong FanView作者出版物您也可以在

PubMed Google ScholarBernarda ViteriView author publicationsYou can also search for this author in

PubMed Google ScholarBernarda ViteriView作者出版物您也可以在

PubMed Google ScholarChristopher S. CooperView author publicationsYou can also search for this author in

PubMed Google ScholarChristopher S.CooperView作者出版物您也可以在

PubMed Google ScholarGregory E. TasianView author publicationsYou can also search for this author in

PubMed Google ScholarGregory E.TasianView作者出版物您也可以在

PubMed Google ScholarArmando J. LorenzoView author publicationsYou can also search for this author in

PubMed Google ScholarArmando J.LorenzoView作者出版物您也可以在

PubMed Google ScholarAnna GolenbergView author publicationsYou can also search for this author in

PubMed Google ScholarAnna GolenbergView作者出版物您也可以在

PubMed Google ScholarContributionsConceptualization: L.E., M.R., A.G., A.J.L. Methodology: L.E., M.R., E.D., M.S., A.G., A.J.L. Investigation: M.R., K.S., D.A., K.N.V., M.E.C., J.DS., D.K., M.A.B., C.S.C., G.E.T., J.W., A.X., Y.F., B.V. Formal analysis: L.E., E.D., S.B.H. Visualization: L.E., E.D., S.B.H.

PubMed谷歌学术贡献概念化：L.E.，M.R.，A.G.，A.J.L.方法论：L.E.，M.R.，E.D.，M.S.，A.G.，A.J.L.调查：M.R.，K.S.，D.A.，K.N.V.，M.E.C.，J.DS.，D.K.，M.A.B.，C.S.C.，G.E.T.，J.W.，A.X.，Y.F.，B.V.形式分析：L.E.，E.D.，S.B.H.可视化：L.E.，E.D.，S.B.H。

Project administration: L.E., M.R., K.S., D.A., K.N.V., M.A.B., C.S.C., G.E.T., J.W., A.X., Y.F. Supervision: L.E., M.R., K.S., N.D.R., C.S.C., G.E.T., Y.F., B.V., A.G., A.J.L. Writing—original draft: L.E., M.R., A.G., A.J.L. Writing—review and editing: L.E., M.R., E.D., M.S., N.D.R., C.S.C., G.E.T., Y.F., B.V., A.G., A.J.L.Corresponding authorCorrespondence to.

项目管理：L.E.，M.R.，K.S.，D.A.，K.N.V.，M.A.B.，C.S.C.，G.E.T.，J.W.，A.X.，Y.F.监督：L.E.，M.R.，K.S.，N.D.R.，C.S.C.，G.E.T.，Y.F.，B.V.，A.G.，A.J.L.写作原稿：L.E.，M.R.，A.G.，A.J.L.写作审查和编辑：L.E.，M.R.，E.D.，M.S.，N.D.R.，C.S.C.，G.E.T.，Y.F.，B.V.，A.G.，A.J.L.通讯作者回复。

Lauren Erdman.Ethics declarations

劳伦·埃尔德曼。道德宣言

Competing interests

相互竞争的利益

The authors declare no competing interests.

作者声明没有利益冲突。

Additional informationPublisher's noteSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary InformationSupplementary Information.Rights and permissions

Additional informationPublisher的noteSpringer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充信息。权限和权限

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

开放获取本文是根据知识共享署名非商业性NoDerivatives 4.0国际许可证授权的，该许可证允许以任何媒介或格式进行任何非商业性使用，共享，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出您是否修改了许可材料。

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

根据本许可证，您无权共享源自本文或其部分的改编材料。本文中的图像或其他第三方材料包含在文章的知识共享许可证中，除非该材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by-nc-nd/4.0/..

Reprints and permissionsAbout this articleCite this articleErdman, L., Rickard, M., Drysdale, E. et al. The Hydronephrosis Severity Index guides paediatric antenatal hydronephrosis management based on artificial intelligence applied to ultrasound images alone.

转载和许可本文引用本文Erdman，L.，Rickard，M.，Drysdale，E。等人。肾积水严重程度指数指导基于仅应用于超声图像的人工智能的儿科产前肾积水管理。

Sci Rep 14, 22748 (2024). https://doi.org/10.1038/s41598-024-72271-9Download citationReceived: 19 December 2022Accepted: 05 September 2024Published: 01 October 2024DOI: https://doi.org/10.1038/s41598-024-72271-9Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

科学报告1422748（2024）。https://doi.org/10.1038/s41598-024-72271-9Download引文接收日期：2022年12月19日接收日期：2024年9月5日发布日期：2024年10月1日OI：https://doi.org/10.1038/s41598-024-72271-9Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。