内容来源：https://research.google/blog/empowering-frontline-maternal-care-with-ai-assisted-ultrasound/

内容总结：

谷歌研究团队与谷歌健康团队日前在《美国医学会杂志网络开放版》发表一项前瞻性多中心研究成果。研究显示，基于人工智能的“盲扫”超声评估系统，可让未接受专业超声培训的操作人员使用低成本便携式超声探头，完成达到专家水平的孕龄评估，这被视为在全球范围内扩大母婴救命护理覆盖面的重要一步。

世界卫生组织估计，全球每年有超过25万例可预防死亡由妊娠相关并发症导致。产前超声检查虽能改善妊娠结局、降低胎儿和孕产妇死亡率，但全球约三分之二的人口无法获得超声等诊断性医学影像服务。现有支持孕产妇健康的方法高度依赖专业临床培训，导致大量低收入地区人群在整个孕期都无法接受一次超声检查。

为此，研究团队开发了可解读“盲扫”超声图像的机器学习系统。所谓“盲扫”，是指未接受专业超声培训的一线卫生工作者按照标准化模式，在腹部滑动低成本便携式超声探头完成扫描。由于许多地区专业超声人员严重短缺，而传统超声技师培训费用高昂且需多年投入，让基层卫生工作者在最短培训后即可开展评估，有望显著扩大产前筛查覆盖面。将最低限度培训与人工智能解读相结合，最终有望提高基于超声的妊娠评估可及性，从而改善高质量母婴健康服务的获取。

在发表于《美国医学会杂志网络开放版》的论文《基于盲扫超声的人工智能孕龄评估的泛化性》中，研究团队评估了孕龄评估人工智能模型在不同临床环境和硬件设备上的泛化效果。此前的回顾性研究已在该模型学习队列中的未见患者身上验证其性能，而此次前瞻性研究则显示，该人工智能系统在真实诊所的移动设备上实时运行，仅由新手操作员使用不熟悉的超声设备、经少量微调即可保持稳定表现。

研究指出，孕龄基本上是指女性怀孕的时间进程，所有筛查、大量治疗以及许多分娩指征，都基于这一核心时间线。医疗人工智能系统若要在全球安全推广，必须证明其泛化能力，即在进入患者人群、临床流程和超声硬件均不同于训练环境的新场景时，仍能保持准确的诊断性能。

在这项研究中，原始人工智能模型仅在目标人群之一中进行少量调优，随后在两个目标环境中进行前瞻性测试。该模型最初使用在美国北卡罗来纳州和赞比亚采集的超声数据训练，数据来自Sonosite、GE和Butterfly Networks商用超声探头。研究中，该人工智能系统与Clarius C3商用掌上经腹探头配合使用。各研究点在产前保健启动时间、常规超声检查次数以及孕龄推算方式等护理维度上均存在差异。

为评估系统调优效率，研究利用芝加哥120名参与者的小型试点数据集（约占原始训练集的6%）对模型进行适配，使其适应新探头硬件并将孕龄预测范围扩展至36周以上。为考察泛化性，研究未使用内罗毕研究点的任何数据进行微调，从而将肯尼亚的临床验证保持为严格独立的外部测试。为评估综合实用性，研究还纳入了多胎妊娠病例，此类情况可能给人工操作者和自动化系统带来追踪和测量挑战。

研究将人工智能系统基于盲扫超声估算胎儿孕龄的能力，与临床标准专家方法所采用的公式估算进行了比较。专家方法依赖专业超声技师定位多个特定胎儿横断面以进行精确生物测量，这一任务难以规模化，需要多年培训且高度依赖操作者水平。

在针对385名孕16至36周参与者的主要队列评估中，该诊断研究显示人工智能系统取得良好结果。除准确性外，探索性指标还显示该人工智能系统在复杂场景中具有韧性。例如，在胎儿体重极端（高于第90百分位）的病例中，模型表现优于传统生物测量公式，显示出对胎儿体型变化的稳健性。

除凸显人工智能扩大超声可及性的巨大机会外，这项前瞻性多中心研究还使团队能够实时观察并优化人工智能在真实临床环境中的表现。通过将系统直接部署到日常临床流程中，研究团队获得了有助于面向真实世界应用设计的实践洞察。例如，他们观察到，在连续接诊患者之间保持设备充电，可更换电池比插接式充电底座更重要。

研究还表明，部署此类人工智能系统需要与临床医生和患者建立深度信任。实现这一目标的重要方式之一是在应用程序中内置明确的保障措施，例如模型置信度估计，用于拒绝质量较差的扫描图像并向临床用户传达模型的不确定性。

研究结果表明，基于人工智能的系统能够分析由未接受专业超声培训的操作员采集的标准化“盲扫”图像。人工智能对胎儿孕龄的估算准确性，与当前由专家操作员使用更昂贵的传统推车式超声设备所达到的诊疗标准相当。该研究在多样临床环境、硬件设备和不断变化的人群中展示了技术泛化能力，标志着在凸显其扩大这一母婴健康关键能力可及性潜力方面迈出关键一步。

通过赋能仅接受最低限度培训的社区卫生工作者开展可靠的超声评估，这项研究展示了扩大资源匮乏地区数百万人口产前覆盖的潜力。研究这种可扩展技术的能力，为构建更具韧性、更可及的医疗体系奠定基础，确保每位母亲无论身处何地，都有机会实现健康妊娠和安全分娩。

这项即时检验研究代表了团队通过人工智能扩大医疗可及性更广泛愿景的一个潜在应用。研究获得的洞察将为下一代多模态医学智能研究的发展提供参考。通过持续工作，团队致力于为开发社区和科学家提供改善临床护理所需的答案，使医疗服务对所有人有益且可及。

研究团队还感谢谷歌研究、Jacaranda Health和西北大学范伯格医学院的各位共同作者，以及审阅此项工作的相关人员。

中文翻译：

2026年10月21日

作者：Angelica Willis，Google Research 研究工程师；Nichole Young-Lin，Google for Health 临床负责人

一项前瞻性多中心研究表明，基于人工智能的盲扫超声评估可使未经超声技师培训的操作者借助低成本探头，实现专家级胎龄评估，这标志着在全球范围内扩大挽救生命的孕产妇护理方面迈出了重要一步。

据世界卫生组织（WHO）估计，全球每年有超过25万例可预防的死亡由妊娠相关并发症导致。虽然产前超声可以改善妊娠结局、降低胎儿和孕产妇死亡率，但全球三分之二的人口无法获得超声等诊断性医学影像服务。当前支持孕产妇健康的方法高度依赖专业临床培训，导致低资源环境中的数百万人在整个孕期都无法接受一次超声检查。

我们看到了一个机会，可以针对这一现实需求开展研究，开发能够解读“盲扫”超声图像的机器学习系统。这种扫描方式使未经专业超声培训的一线医护人员只需按照标准化模式，将低成本便携式超声探头在腹部滑动即可完成扫描。

由于许多地区面临专家严重短缺的问题，而传统的超声技师培训既昂贵又需要多年的投入，因此让这些医护人员在最少培训下即可完成评估，有可能显著扩大产前筛查的覆盖范围。

将最低培训要求与人工智能解读相结合，最终可能意味着成功开发出一种工具，有望提高基于超声的妊娠评估的可及性，从而改善人们获得更高质量孕产妇护理的机会。

在发表于《JAMA Network Open》的论文《基于盲扫超声的胎龄评估人工智能模型的泛化能力》中，我们评估了胎龄评估人工智能模型（判断妊娠进展到何种程度）在不同临床环境和硬件条件下的泛化效果。我们此前的研究已验证该模型在其学习所基于的同一回顾性队列中的未见患者上的表现，而这项新的前瞻性研究则展示了该人工智能系统在真实诊所的移动设备上实时运行时的可靠表现——仅由新手操作者使用不熟悉的超声设备，且只需最少的微调。

“胎龄基本上就是一名女性怀孕到了什么阶段。我们所有的筛查、很多治疗、很多分娩指征，都基于你从胎龄中获得的这条主时间线。”

一个医学人工智能系统要在全球范围内安全推广，必须证明其泛化能力——即在引入新的临床环境时，面对与模型训练时不同的患者群体、临床工作流程和超声硬件差异，仍能保持准确的诊断性能。

在本研究中，我们原始的人工智能模型仅在我们目标人群中的一个群体上进行了最少量的调优，随后在两个目标环境中进行了前瞻性测试：

该研究人工智能系统最初使用在北卡罗来纳州和赞比亚采集的超声数据进行训练，数据采集使用了Sonosite、GE和Butterfly Networks的一组商用超声探头，随后该系统与Clarius C3——一款商用掌上经腹探头——配合使用。所有这些站点在多个护理维度上存在差异，包括女性首次产前检查的时间、接受常规超声检查的次数，以及胎龄通常的确定方式。

为评估系统调优的效率，本研究利用了一个来自芝加哥的120名参与者的小型试点数据集——约占原始训练集的6%——来使模型适应新的探头硬件，并将胎龄预测范围扩展至36周以上。为了解泛化能力，内罗毕站点的数据未用于微调，从而保持肯尼亚的临床验证作为严格独立的外部测试。为评估综合实用性，本研究还纳入了多胎妊娠，这对人工操作者和自动化系统都可能带来追踪和测量方面的挑战。

我们将人工智能系统通过盲扫超声估算胎儿年龄的能力，与临床标准专家方法中基于公式的估算进行了比较。这种专家方法依赖超声专家定位胎儿的多个特定横截面以进行精确的生物测量，这是一项难以规模化推广的任务，需要多年培训，且高度依赖操作者。

在一项纳入385名孕16至36周参与者的主要队列评估中，该诊断研究展示了人工智能系统的强劲结果：

除准确性外，探索性指标显示该研究人工智能系统在复杂场景中具有韧性。例如，在胎儿体重极端（高于第90百分位）的情况下，该模型的表现优于传统生物测量公式，展现出对胎儿体型变化的稳健性。

除了凸显通过人工智能扩大超声可及性的巨大机会外，这项前瞻性多中心研究还使我们能够主动观察并优化人工智能在真实临床环境中的表现。通过将我们的系统直接部署到日常临床工作流程中，我们获得了有助于面向真实世界使用进行设计的实践洞察。例如，我们观察到可更换电池比插入式充电底座更能确保设备在连续患者之间保持充电状态的重要性。

这些研究还表明，部署此类人工智能系统还需要与临床医生和患者建立深厚的信任。最终实现这一目标的一个重要方式是在应用中内置明确的保障机制，例如我们的模型生成的模型置信度估计，用于拒绝质量较差的扫描，并向临床医生用户传达模型的不确定性。

这些研究结果表明，基于人工智能的系统可以分析由未经专业超声培训的操作者采集的标准化“盲扫”图像。人工智能对胎儿年龄的估算准确性可与当前由专家操作者使用更昂贵的传统推车式超声设备所提供的标准护理相媲美。在不同临床环境、硬件和不断变化的人群中展示技术泛化能力，标志着在凸显其扩大这一孕产妇健康关键能力可及性方面的潜力上迈出了关键一步。

通过赋能仅接受过最低限度培训的社区卫生工作者开展可靠的超声评估，这项研究展示了为资源匮乏地区数百万民众扩大产前覆盖的潜力。研究这一可扩展技术的能力，为构建更具韧性、更可及的医疗保健系统奠定了基础，确保每一位母亲无论身处何地，都有机会实现健康妊娠和安全分娩。

这项即时检验研究代表了我们通过人工智能扩大医疗保健可及性这一更宏大愿景的潜在应用。从这项研究中获得的洞察将为我们的下一代多模态医学智能研究提供参考。通过持续的工作，我们致力于为开发社区和科学家提供他们所需的答案，以改善临床护理，并使其对所有人都有帮助且可及。

感谢我们在Google Research、Jacaranda Health和西北大学范伯格医学院的各位合著者：Chace Lee、Justin Krogue、Anneka Wickramanayake、Stacey Caron、Priscah Cheruiyot、Amber Watters、Alicia Martín、Tiya Tiyasirichokchai、Akib Uddin、Yun Liu、Patricia Strachan、Sunny Jansen、Alyssa Santi、Preeti Singh、Catherine Arguelles、Kenneth Hudson、David Melnick、Mahesh Vaidyanathan、Mozziyar Etemadi、Yossi Matias、Avinatan Hassidim、Greg Corrado、Shruthi Prabhakara、Daniel Golden、Ryan G. Gomes和Shravya Shetty。感谢Pi-Chuan Chang和Dale Webster审阅本项工作。

英文来源：

October 21, 2026
Angelica Willis, Research Engineer, Google Research, and Nichole Young-Lin, Clinical Lead, Google for Health
A prospective multi-center study demonstrates how AI-based blind sweep ultrasound assessment can enable non-sonographer operators with low-cost probes to deliver expert-level gestational age assessments, marking a significant step toward expanding life-saving maternal care globally.
The World Health Organization (WHO) estimates that more than 250,000 preventable deaths occur worldwide each year due to pregnancy-related complications. While prenatal ultrasound can improve outcomes and reduce fetal and maternal mortality, two-thirds of people globally lack access to diagnostic medical imaging like ultrasound. Current methods that support maternal health rely heavily on specialized clinical training, leaving millions in low-resource settings without access to a single ultrasound during their entire pregnancy.
We saw an opportunity to conduct research towards addressing this real-world need, by developing machine learning systems that interpret "blind sweep" ultrasounds. This way of scanning allows frontline healthcare workers without specialized sonography training to perform scans by simply gliding low-cost, portable ultrasound probes across the abdomen in a standardized pattern.
Because many regions face critical shortages of experts, and traditional sonographer training is both expensive and requires a multi-year commitment, enabling these health workers to perform assessments with minimal training has the potential to significantly expand prenatal screening coverage.
Combining the minimal training requirement with AI interpretations could ultimately mean a successfully developed tool that has the potential to increase availability of ultrasound-based pregnancy assessment, and thereby improve access to higher quality maternal health.
In “Generalization of AI-Based Gestational Age Assessment Using Blind Sweep Ultrasonography”, published in JAMA Network Open, we evaluated how effectively an AI model for gestational age assessment (how far along the pregnancy is) generalizes across diverse clinical settings and hardware. While our previous research validated the model's performance on unseen patients from the same retrospective cohort it learned from, this new prospective study shows how the AI system performs reliably running live on mobile devices in real clinics, with only novice operators and unfamiliar ultrasound equipment, and minimal fine-tuning.
“The gestational age is basically how far along a woman is in pregnancy. All of our screening, a lot of our treatments, a lot of our indications for delivery are all based on this master timeline that you get from the gestational age.”
For a medical AI system to safely scale globally, it must demonstrate generalizability — maintaining accurate diagnostic performance when introduced to new clinical settings with different patient populations, clinical workflows, and ultrasound hardware variations than those on which the model was trained.
In this study, our original AI model was minimally tuned on only one of our target populations, and then prospectively tested across both target environments:
Originally trained on ultrasound data collected in North Carolina and Zambia using a set of Sonosite, GE, and Butterfly Networks commercial ultrasound probes, the research AI system was paired with Clarius C3, a commercial handheld transabdominal probe. All of these sites differed in various care dimensions, including when women first come in for prenatal care, how many routine ultrasounds they receive, and how gestational age is usually dated.
To evaluate efficient system tuning, the study leveraged a small pilot dataset of 120 participants from Chicago — approximately 6% of the original training set—to adapt the model to new probe hardware and extend the gestational age prediction range beyond 36 weeks. To understand generalizability, no data from the Nairobi site was used for fine-tuning, maintaining the Kenyan clinical validation as a strictly independent, external test. To evaluate comprehensive utility, the study also included multiple gestation pregnancies, which could present tracking and measurement challenges for both human operators and automated systems.
We compared the AI system’s ability to estimate fetal age from blind sweep ultrasounds to formula-based estimation from the clinically standard expert approach. This expert approach relies on an expert sonographer locating multiple specific cross-sections of the fetus(es) to take precise biometry measurements, a difficult-to-scale task that requires years of training and is highly operator-dependent.
Evaluating a primary cohort of 385 participants between 16 and 36 weeks of pregnancy, the diagnostic study demonstrated strong AI system results:
Beyond accuracy, exploratory metrics showed that the research AI system was resilient in complex scenarios. For instance, in cases of fetal weight extremes (above the 90th percentile), the model outperformed traditional biometry formulas, demonstrating robustness against variations in fetal size.
In addition to highlighting an immense opportunity to expand ultrasound access through AI, the prospective multi-center study allowed us to actively observe and optimize how AI behaves in live clinical environments. By deploying our system directly into everyday clinical workflows, we gained practical insights that help us design for real world use. For example, we observed the importance of swappable batteries over plug-in docking stations for keeping devices charged between consecutive patients.
These studies also demonstrated how deploying AI systems like this will also require building deep trust with both clinicians and patients. One important way to ultimately achieve this would be by building clear safeguards into the app, like model confidence estimates produced by our model to reject poor-quality sweeps and convey model uncertainty to the clinician user.
These study findings indicate that AI-based systems can analyze standardized “blind sweeps” images acquired by operators without specialized sonography training. The AI estimate of fetal age had accuracy comparable to the current standard of care from expert operators and more expensive traditional, cart-based ultrasound machines. Demonstrating technical generalizability across diverse clinical settings, hardware, and changing populations, marks a key step in highlighting their potential to expand access to this critical capability for maternal health.
By empowering minimally trained community health workers to perform reliable ultrasonography assessments, this research demonstrates the potential to expand prenatal coverage for millions in under-resourced areas. Studying the capabilities of this scalable technology lays the groundwork for more resilient, accessible healthcare systems, ensuring that every mother, regardless of location, has the chance for a healthy pregnancy and a safe delivery.
This point-of-care research represents a potential application of our broader vision for expanding healthcare accessibility through AI. The insights gained from this research inform the development of our next-generation, multimodal medical intelligence research. Through our continued work, we strive to provide the development community and scientists with the answers they need to improve clinical care and make it helpful and accessible to all.
Thank you to our co-authors across Google Research, Jacaranda Health and Northwestern University Feinberg School of Medicine: Chace Lee, Justin Krogue, Anneka Wickramanayake, Stacey Caron, Priscah Cheruiyot, Amber Watters, Alicia Martín, Tiya Tiyasirichokchai, Akib Uddin, Yun Liu, Patricia Strachan, Sunny Jansen, Alyssa Santi, Preeti Singh, Catherine Arguelles, Kenneth Hudson, David Melnick, Mahesh Vaidyanathan, Mozziyar Etemadi, Yossi Matias, Avinatan Hassidim, Greg Corrado, Shruthi Prabhakara, Daniel Golden, Ryan G. Gomes, and Shravya Shetty. Thank you to Pi-Chuan Chang and Dale Webster for reviewing this work.