深度学习模型在产前先天性心脏病筛查中泛化至社区环境并优于临床检测
本研究评估了既往在三级中心图像上训练的深度学习模型在低风险人群孕中期标准畸形筛查中的表现,并与实时临床诊断及仅基于存储图像的盲法人类专家诊断进行比较。模型灵敏度91%、特异度78%,高于初始临床诊断灵敏度53%及盲法专家平均灵敏度55±10%。模型在社区来源图像及训练中未见的病变类型上表现良好。
要点
- 模型灵敏度91%、特异度78%,初始临床诊断灵敏度53%。
- 盲法人类专家平均灵敏度55±10%、特异度71±13%,模型优于专家。
- 模型对训练中未见的19种病变正确识别16例,与已知病变表现无显著差异。
核心结论
- 既往训练的深度学习算法在初始临床漏诊超过50%的先天性心脏病队列中,检测灵敏度高于初始临床评估。
- 该算法在低风险人群的社区来源图像上表现良好,包括训练中未接触过的病变类型。
- 当模型与盲法人类专家均仅能获取存储图像时,模型表现优于人类专家。
- 上述发现支持使用深度学习模型可改善先天性心脏病的产前检测。
研究设计与样本
- 评估2015至2016年荷兰西北地区所有具有可用存储图像的孤立性严重先天性心脏病妊娠,以及同期同地区正常胎儿检查样本。
- 比较初始临床诊断(实时结合动态成像)、模型(仅存储图像)及三名盲法人类专家(仅存储图像)的准确性。
- 分析模型表现与超声检查特征的关系,包括检查时长、质量(由研究者独立评分)、存储图像数量及筛查切面可用性。
主要发现
- 共分析42例正常胎儿和66例出生时孤立性先天性心脏病病例。
- 异常病例中31例在临床解剖扫描时漏诊、35例检出,临床灵敏度53%。
- 模型灵敏度91%、特异度78%。
- 盲法人类专家(n=3)平均灵敏度55±10%(范围47-67%)、平均特异度71±13%(范围57-83%)。
- 模型正确性按专家评分的图像质量存在统计学显著差异(P=0.03)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: Despite nearly universal prenatal ultrasound screening programs, congenital heart defects (CHD) are still missed, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The main aim of this study was to assess the performance of a previously developed DL model, trained on images from a tertiary center, using fetal ultrasound images obtained during the second-trimester standard anomaly scan in a low-risk population. A secondary aim was to compare initial screening diagnosis, which made use of live imaging at the point-of-care, with diagnosis by clinicians evaluating only stored images. METHODS: All pregnancies with isolated severe CHD in the Northwestern region of The Netherlands between 2015 and 2016 with available stored images were evaluated, as well as a sample of normal fetuses' examinations from the same region and time period. We compared the accuracy of the initial clinical diagnosis (made in real time with access to live imaging) with that of the model (which had only stored imaging available) and with the performance of three blinded human experts who had access only to the stored images (like the model). We analyzed performance according to ultrasound study characteristics, such as duration and quality (scored independently by investigators), number of stored images and availability of screening views. RESULTS: A total of 42 normal fetuses and 66 cases of isolated CHD at birth were analyzed. Of the abnormal cases, 31 were missed and 35 were detected at the time of the clinical anatomy scan (sensitivity, 53%). Model sensitivity and specificity were 91% and 78%, respectively. Blinded human experts (n = 3) achieved mean ± SD sensitivity and specificity of 55 ± 10% (range, 47-67%) and 71 ± 13% (range, 57-83%), respectively. There was a statistically significant difference in model correctness according to expert-graded image quality (P = 0.03). The abnormal cases included 19 lesions that the model had not encountered during its training; the model's performance in these cases (16/19 correct) was not statistically significantly different from that for previously encountered lesions (P = 0.41). CONCLUSIONS: A previously trained DL algorithm had higher sensitivity than initial clinical assessment in detecting CHD in a cohort in which over 50% of CHD cases were initially missed clinically. Notably, the DL algorithm performed well on community-acquired images in a low-risk population, including lesions to which it had not been exposed previously. Furthermore, when both the model and blinded human experts had access to only stored images and not the full range of images available to a clinician during a live scan, the model outperformed the human experts. Together, these findings support the proposition that use of DL models can improve prenatal detection of CHD. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.
引用
- Athalye C, van Nisselrooij A, Rizvi S, et al. Deep-learning model for prenatal congenital heart disease screening generalizes to community setting and outperforms clinical detection. Ultrasound Obstet Gynecol. 2024. PMID: 37774040. doi:10.1002/uog.27503
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。