文献速递儿科影像腹部技术与安全US

通用视觉语言模型零样本诊断儿童阑尾炎

Zero-shot performance of a general-purpose vision-language model for pediatric appendicitis diagnosis.
PubMed 文献 · Pediatr Radiol · 2026-06-08

本研究回顾性评估通用视觉语言模型Llama 4 Maverick在Regensburg儿童阑尾炎数据集中零样本诊断儿童阑尾炎的能力。研究比较了仅图像、仅超声报告文本、图像加文本、图像加临床数据及全部多模态输入五种条件下的诊断表现。结果显示仅图像输入特异性极低,而基于超声报告文本的诊断性能良好,加入图像未能进一步改善。

要点

  • 仅凭超声图像时模型特异性仅13.5%,不可用于临床诊断阑尾炎。
  • 超声报告文本是模型诊断性能的主要驱动因素,AUROC达0.883。
  • 模型适合作为基于文本的决策支持工具,而非自主超声图像判读者。

核心结论

  • 通用视觉语言模型零样本解读儿童腹部超声图像不足以安全诊断阑尾炎。
  • 模型性能主要由结构化超声影像报告文本驱动,支持其作为基于文本的决策支持工具,而非自主超声图像判读者。

研究设计与样本

  • 回顾性研究,在Regensburg Pediatric Appendicitis Dataset上评估Llama 4 Maverick的诊断能力。
  • 782例患者中294例符合纳入标准;4个实验使用293例,第5个实验使用284例。
  • 参考标准为手术切除患者的组织病理学结果及保守治疗患者的临床随访结果。
  • 在患者水平评估准确率、敏感度、特异度、阳性预测值、阴性预测值及F1-score,次要评估AUROC。

关键影像表现/征象

  • 仅图像输入条件下模型诊断特异性极低,为13.5%,判别能力最差,AUROC为0.567。
  • 加入超声报告文本后特异性提高至63.5%,同时保持高敏感度,AUROC为0.883。
  • 在超声文本基础上加入图像或组合全部可用输入均未带来进一步有意义的改善。

诊断标准与关键数值

  • 仅图像条件:特异性13.5%,AUROC 0.567。
  • 仅超声报告文本条件:特异性63.5%,AUROC 0.883,敏感度保持高水平。
  • 仅图像实验与含文本实验之间的差异具有统计学意义,P≤0.002。

临床应用与阅片要点

  • 不应将通用视觉语言模型对儿童腹部超声图像的零样本视觉判读用于阑尾炎临床诊断。
  • 结构化超声报告文本是此类模型可用的可靠输入,可用于构建文本驱动的决策支持工具。

局限性

  • 回顾性研究设计本身存在偏倚风险。
  • 为单中心数据集研究,样本量有限。

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)。

英文原文(摘要)· 点击展开

BACKGROUND: General-purpose vision-language models can analyze medical images without task-specific training, but their value for pediatric abdominal ultrasound is unknown.

OBJECTIVE: To investigate the zero-shot performance of a general-purpose vision-language model to diagnose pediatric appendicitis using multimodal inputs, including images, report text, and clinical information.

MATERIALS AND METHODS: In this retrospective study, diagnostic capabilities of Llama 4 Maverick were evaluated on the Regensburg Pediatric Appendicitis Dataset. Five experiments were conducted using the following inputs as well as input combinations: images only, ultrasound report text only, images and ultrasound text, images and clinical data, entire multimodal input. Reference standard of appendicitis was defined based on histopathology in patients who underwent surgical resection and on clinical follow-up in patients managed conservatively. Performance was assessed at the patient level using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. Area under the receiver operating characteristic curve (AUROC) was evaluated secondarily as a measure of discrimination.

RESULTS: Of 782 patients, 294 met inclusion criteria; based on data availability, four experiments are conducted using 293 patients and in the fifth experiment, 284. Images-only experiment showed very low specificity (13.5%) and had the poorest discrimination (AUROC, 0.567). Ultrasound report text improved classification performance, with specificity increasing to 63.5% while maintaining high sensitivity; discrimination was also strong (AUROC, 0.883). Adding images to ultrasound text or combining all available inputs did not yield further meaningful improvement. Differences between images-only experiment and text-containing experiments were statistically significant (P≤0.002).

CONCLUSION: Zero-shot visual interpretation of pediatric abdominal ultrasound by a general-purpose vision-language model is inadequate for safe appendicitis diagnosis. Performance is driven primarily by a structured sonographic imaging report, supporting a role for such models as text-based decision support tools rather than autonomous ultrasound image interpreters.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Altintas Mese, Mese, Akinci D'Antonoli, et al. Zero-shot performance of a general-purpose vision-language model for pediatric appendicitis diagnosis. Pediatr Radiol. 2026. PMID: 42257728. doi:10.1007/s00247-026-06687-y

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。