Maurice P, Dhombres F, Blondiaux E, Friszer S, Guilbaud L, Lelong N, Khoshnood B, Charlet J, Perrot N, Jauniaux E, Jurkovic D, Jouannic J-M
Inserm U1142 (Limics), UPMC medical faculty (Paris 6), department of fetal medicine, service de médecine fœtale, hôpital Armand-Trousseau, AP-HP, 26, avenue A.-Netter, 75012 Paris, France.
Inserm U1142 (Limics), UPMC medical faculty (Paris 6), department of fetal medicine, service de médecine fœtale, hôpital Armand-Trousseau, AP-HP, 26, avenue A.-Netter, 75012 Paris, France.
J Gynecol Obstet Hum Reprod. 2017 May;46(5):423-429. doi: 10.1016/j.jogoh.2017.03.004. Epub 2017 Mar 31.
We have developed a new knowledge base intelligent system for obstetrics and gynecology ultrasound imaging, based on an ontology and a reference image collection. This study evaluates the new system to support accurate annotations of ultrasound images. We have used the early ultrasound diagnosis of ectopic pregnancies as a model clinical issue.
The ectopic pregnancy ontology was derived from medical texts (4260 ultrasound reports of ectopic pregnancy from a specialist center in the UK and 2795 Pubmed abstracts indexed with the MeSH term "Pregnancy, Ectopic") and the reference image collection was built on a selection from 106 publications. We conducted a retrospective analysis of the signs in 35 scans of ectopic pregnancy by six observers using the new system.
The resulting ectopic pregnancy ontology consisted of 1395 terms, and 80 images were collected for the reference collection. The observers used the knowledge base intelligent system to provide a total of 1486 sign annotations. The precision, recall and F-measure for the annotations were 0.83, 0.62 and 0.71, respectively. The global proportion of agreement was 40.35% 95% CI [38.64-42.05].
The ontology-based intelligent system provides accurate annotations of ultrasound images and suggests that it may benefit non-expert operators. The precision rate is appropriate for accurate input of a computer-based clinical decision support and could be used to support medical imaging diagnosis of complex conditions in obstetrics and gynecology.
我们基于本体和参考图像集开发了一种用于妇产科超声成像的新知识库智能系统。本研究评估该新系统以支持超声图像的准确标注。我们将异位妊娠的早期超声诊断作为一个典型临床问题。
异位妊娠本体源自医学文本（来自英国一个专科中心的4260份异位妊娠超声报告以及2795篇标有MeSH术语“异位妊娠”的PubMed摘要），参考图像集基于从106篇出版物中挑选的内容构建。我们使用新系统对6名观察者的35例异位妊娠扫描中的体征进行了回顾性分析。
生成的异位妊娠本体包含1395个术语，参考图像集收集了80幅图像。观察者使用知识库智能系统共提供了1486个体征标注。标注的精确率、召回率和F值分别为0.83、0.62和0.71。总体一致比例为40.35% 95%置信区间[38.64 - 42.05]。
基于本体的智能系统能对超声图像进行准确标注，表明它可能使非专业操作人员受益。精确率适用于基于计算机的临床决策支持的准确输入，可用于支持妇产科复杂病症的医学影像诊断。
