{"title":"Comprehensive images and serum biomarkers for biliary atresia and other cholestasis in pediatrics.","authors":"Shuyi Liu, Rui Zhang, Yongshang Yu, Chunyixue Geng, Hongbin Ma, Yuyun Liu, Wenhua Qin, Yue Zhang, Qiqiao Zhang, Wenjing Gao","doi":"10.1038/s41597-025-05914-9","DOIUrl":null,"url":null,"abstract":"<p><p>Biliary atresia (BA) and other pediatric cholestatic diseases are rare but serious conditions that require early and accurate diagnosis. Ultrasound has become the primary diagnostic method for BA, particularly for evaluating gallbladder contractility through fasting and postprandial comparisons. However, there is currently a lack of publicly available datasets containing paired fasting-postprandial gallbladder ultrasound images, other key sonographic features, and relevant serum biochemical indicators. The dataset consisted of 2,759 ultrasound images obtained from 1,019 infants diagnosed with cholestatic diseases. This included 377 BA cases (664 fasting and 328 post-prandial images) and 642 non-BA cases (1,004 fasting and 580 post-prandial images). Additionally, 183 images documenting abnormal ultrasonographic findings such as triangular cord sign, dilated hepatic artery, and hilar hepatic cysts, and relevant hepatic biochemical indicators were also collected. The study implemented nnU-Net to perform automated gallbladder segmentation across both fasting and postprandial ultrasound examinations. The dataset represents a valuable resource for enhancing the diagnostic accuracy of BA and facilitating the development of clinical decision-support system.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"12 1","pages":"1634"},"PeriodicalIF":6.9000,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientific Data","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.1038/s41597-025-05914-9","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Biliary atresia (BA) and other pediatric cholestatic diseases are rare but serious conditions that require early and accurate diagnosis. Ultrasound has become the primary diagnostic method for BA, particularly for evaluating gallbladder contractility through fasting and postprandial comparisons. However, there is currently a lack of publicly available datasets containing paired fasting-postprandial gallbladder ultrasound images, other key sonographic features, and relevant serum biochemical indicators. The dataset consisted of 2,759 ultrasound images obtained from 1,019 infants diagnosed with cholestatic diseases. This included 377 BA cases (664 fasting and 328 post-prandial images) and 642 non-BA cases (1,004 fasting and 580 post-prandial images). Additionally, 183 images documenting abnormal ultrasonographic findings such as triangular cord sign, dilated hepatic artery, and hilar hepatic cysts, and relevant hepatic biochemical indicators were also collected. The study implemented nnU-Net to perform automated gallbladder segmentation across both fasting and postprandial ultrasound examinations. The dataset represents a valuable resource for enhancing the diagnostic accuracy of BA and facilitating the development of clinical decision-support system.
期刊介绍:
Scientific Data is an open-access journal focused on data, publishing descriptions of research datasets and articles on data sharing across natural sciences, medicine, engineering, and social sciences. Its goal is to enhance the sharing and reuse of scientific data, encourage broader data sharing, and acknowledge those who share their data.
The journal primarily publishes Data Descriptors, which offer detailed descriptions of research datasets, including data collection methods and technical analyses validating data quality. These descriptors aim to facilitate data reuse rather than testing hypotheses or presenting new interpretations, methods, or in-depth analyses.