“AI救了他的命”：中国医生借助人工智能识别胰腺癌
In China, A.I. Is Finding Deadly Tumors That Doctors Might Miss
Three days after Qiu Sijun, a retired bricklayer in eastern China, went for a routine diabetes checkup, he received a call from a doctor he hadn’t met before. The doctor, the head of the hospital’s pancreatic department, wanted him to come in for a follow-up.
中国东部的退休泥瓦工邱嗣军去做了常规的糖尿病检查，三天后接到了一位素未谋面的医生来电。那位医生是这家医院胰腺科的主任，让他再来做一次复查。
“I knew it couldn’t be anything good,” Mr. Qiu, 57, recalled.
“我知道，肯定是没有好东西的，”57岁的邱先生回忆说。
He was partly right. The bad news was that Mr. Qiu had pancreatic cancer. But there was good news, too: The tumor had been detected early. The doctor, Zhu Kelei, was able to remove it.
他只猜对了一半。坏消息是邱先生得了胰腺癌。好消息是肿瘤发现得很早。这位名叫朱柯磊的大夫成功地把它切除了。
This was possible only because of a new artificial-intelligence-powered tool that the hospital was testing, which had flagged Mr. Qiu’s routine CT scan before he had any symptoms. The tool is one example of how Chinese tech companies and hospitals are racing to apply A.I. to some of medicine’s most stubborn problems.
这都是因为医院当时正在测试一款新的人工智能工具——该工具在邱先生尚未出现任何症状前，就在他的常规CT扫描结果中标出了问题。这一工具是中国科技公司与医院竞相将人工智能应用于医学领域一些最棘手难题的一个实例。
Pancreatic cancer is one of the deadliest forms of cancer, with a five-year survival rate of around 10 percent, largely because early detection is so hard. Symptoms often do not appear until the cancer has advanced.
胰腺癌是最凶险的癌症之一，五年生存率仅约10%，很大程度上是因为早期发现极其困难。症状往往要等到癌症恶化之后才会出现。
Tests used to confirm its presence, such as contrast CT scans, involve large amounts of radiation, so many experts advise against widespread screening. But lower-radiation alternatives, such as noncontrast CTs — in which no contrast dye is injected into patients’ bloodstreams — produce less clearly defined pictures, making it hard for radiologists to identify abnormalities.
增强CT扫描等确诊手段涉及大量辐射，因此许多专家不建议普及这种筛查。而低辐射替代方案——比如不注射造影剂的平扫CT——生成的图像清晰度较低，导致放射科医生难以识别异常病变。
Artificial intelligence may change that. The tool at Dr. Zhu’s hospital, which was developed by researchers affiliated with the Chinese tech giant Alibaba, was trained to look for pancreatic cancer in noncontrast CTs.
人工智能也许会改变这一切。朱柯磊所在医院使用的这款工具由中国科技巨头阿里巴巴集团的研究人员开发，经过训练后可用于在平扫CT中识别胰腺癌。
The tool is called PANDA, short for “pancreatic cancer detection with artificial intelligence.” At the hospital where Dr. Zhu works, the Affiliated People’s Hospital of Ningbo University in eastern China, doctors started using it as part of a clinical trial in November 2024.
这款名为PANDA（“人工智能胰腺癌检测系统”的缩写）的工具，于2024年11月在朱柯磊所在的宁波大学附属人民医院投入临床试验。
The tool has since analyzed more than 180,000 abdominal or chest CTs, helping doctors detect about two dozen cases of pancreatic cancer, 14 of which were in the early stage, Dr. Zhu said. The tool found 20 cases of ductal adenocarcinoma, the most common and deadliest type of pancreatic cancer. (Mr. Qiu had a neuroendocrine tumor, which is a rarer and less aggressive cancer.)
据他介绍，到目前为止，这个工具已经分析了逾18万例腹部或胸部CT，帮助医生发现了二十多例胰腺癌，其中14例为早期。工具共发现了20例胰腺导管腺癌——这是最常见、也最致命的一种胰腺癌。（邱先生所患的神经内分泌肿瘤则属较罕见且侵袭性较低的类型。）
All of those patients had come to the hospital with complaints like bloating or nausea and had not initially seen a pancreatic specialist, Dr. Zhu said. Several of their CT scans had raised no alarms until they were flagged by the A.I. tool.
朱柯磊指出，这些患者均因腹胀或恶心等症状就诊，一开始并未接受胰腺专科检查。其中多例CT影像在经AI工具标记前未引发任何警报。
“I think you can 100 percent say A.I. saved their lives,” he said.
“这些人我可以说百分之一百是AI救了他的命，”他表示。
In April, Alibaba said the U.S. Food and Drug Administration had granted PANDA “breakthrough device” status, meaning that its review would be expedited to help it get to market. It is also the subject of several clinical trials in China.
今年4月，阿里巴巴宣布美国食品药品监督管理局已认定PANDA为“突破性医疗器械”，意味着其评审流程将加速，以便更快进入市场。该系统目前也在中国进行多个临床试验。
Researchers cautioned that more real-world data was needed to show whether the tool could detect enough early-stage cases to outweigh the risks of false positives and unnecessary testing. Scientists elsewhere are studying other A.I.-assisted approaches to early pancreatic cancer detection that focus more narrowly on high-risk groups, in large part because the cancer’s prevalence is low.
研究人员提醒说，还需要更多真实世界的数据，来证明这款工具能否发现足够多的早期病例，从而抵消误报和不必要检查带来的风险。由于胰腺癌总体发病率较低，世界各地的科学家正在研究其他借助人工智能的早期筛查方法，而且更侧重于高风险人群。
Several experts not involved with the Chinese research said they were skeptical that noncontrast CTs could offer as much valuable information as other forms of imaging.
对于平扫CT能否提供与其他影像检查同等价值的信息，多位未参与中国这项研究的专家持怀疑态度。
Even the engineers behind PANDA initially shared that concern, said Ling Zhang, a senior staff algorithm engineer at Damo Academy, Alibaba’s research arm, who is one of the tool’s creators.
阿里巴巴研究机构达摩院资深算法专家、PANDA的研发者之一张灵坦言，就连研发团队最初也有同样担忧。
To address it, they asked a radiologist to manually annotate the contrast CTs of more than 2,000 known pancreatic patients with the locations of their lesions. The engineers then algorithmically mapped the highlighted lesions onto the same patients’ noncontrast CTs. Those noncontrast scans were then fed to the A.I. model, so that it could learn to detect potential cancer even in less detailed images.
为解决这个问题，他们请一名放射科医生在2000多名已知胰腺癌患者的增强CT影像上手动标注了病灶位置。工程师随后通过算法将这些标注病灶映射至同一患者的平扫CT影像上，再将平扫影像输入AI模型进行训练，使其能在清晰度较低的图像中识别潜在癌症。
When the tool was subsequently tested on more than 20,000 noncontrast CTs, it correctly identified 93 percent of people who had pancreatic lesions, according to a study published in Nature Medicine in 2023.
根据2023年发表在《自然·医学》上的研究论文，当这款工具随后在超过20000例平扫CT上进行测试时，它能够准确识别出93%的胰腺病灶患者。
“The effectiveness actually surprised us,” Mr. Zhang said.
“这样的效果其实让我们很惊讶，”张灵说。
At the Ningbo hospital, the system is being used to analyze scans that doctors had already ordered for other reasons, so there is no additional testing cost to the hospital or patients. (In China, many people routinely undergo noncontrast CTs as part of their annual checkups; at the Ningbo hospital, a noncontrast CT costs about $25, before insurance.)
在宁波这家医院，该系统只用于分析医生本来就已经开具检查的影像，因此不会给医院或患者增加额外的检测成本。（在中国，很多人把平扫CT作为年度体检的一部分；在宁波这家医院，一次平扫CT检查在保险报销前的费用大约是180元。）
Dr. Zhu and his team review any scans that the system marks as high-risk, and if necessary, they call the patients in for more detailed testing.
朱柯磊及他的团队会复核所有系统标记为高风险的患者扫描影像，必要时将通知患者做进一步检查。
The model still can’t compare to a pancreatic specialist, Dr. Zhu said.
他说，这个模型仍然无法与胰腺专科医生相比。
It sometimes highlights cases of pancreatitis, and it cannot say whether a tumor originated in the pancreas or spread from a different organ. Since its launch, the model has issued alerts for about 1,400 scans, but only about 300 of them needed follow-up, doctors decided.
它有时会把胰腺炎病例标出来，而且无法判断肿瘤是起源于胰腺，还是从其他器官转移而来。自启用以来，该模型对大约1400份扫描影像发出了警报，但医生们认定，其中只有大约300份需要进一步判断。
Dr. Ajit Goenka, a radiologist at Mayo Clinic who is researching the early diagnosis of pancreatic cancer, said it was crucial to reduce the number of false alarms. It is possible that hundreds of people in Ningbo “faced the terror of a potential pancreatic cancer diagnosis, underwent unnecessary callbacks, and likely endured expensive, invasive follow-up testing — only to find out they were healthy,” he wrote in an email.
正在研究胰腺癌早期诊断的梅奥诊所放射科医生阿吉特·戈恩卡说，降低误报率至关重要。他在电邮中写道，宁波可能有数百人“承受着可能患胰腺癌的恐惧，接受了不必要的复查，并且可能还接受了昂贵的、侵入性的后续检查——结果却发现自己是健康的”。
The tool might also be more useful for trainee doctors than for experienced specialists, said Dr. Diane Simeone, a pancreatic surgeon at the University of California San Diego. Some of the tumors that the tool caught in the Nature Medicine study should have been “super obvious” to well-trained radiologists even without A.I., she said.
加州大学圣地亚哥分校的胰腺外科医生黛安·西梅奥内说，相比经验丰富的专家，这个工具对受训中的医生可能更有价值。她表示，在发表在《自然·医学》上的那篇研究论文中，该工具捕捉到的一些肿瘤，对训练有素的放射科医生来说，即便没有人工智能，也应该是“非常明显”的。
But she acknowledged that it could be a valuable backstop for hospitals where specialists are in short supply. (PANDA is also being tested at a clinic in rural Yunnan Province.)
但她承认，在专科医生短缺的医院（PANDA也正在云南农村的一家医院进行实验），这类工具可作为重要的辅助手段。
“You’re going to have different skill sets at different centers, depending on where in the world you are or the clinical volume,” Dr. Simeone said.
西梅奥内说：“不同医疗中心掌握的技术能力会有所不同，具体取决于你身在何处，或者你有多少临床病例。”
In Ningbo, the technology’s apparent success has brought some new challenges. The hospital currently does not have enough staff to contact all the patients who need follow-up, Dr. Zhu said. And its aging hardware has trouble keeping up with the model’s large amounts of data. Several times, when Dr. Zhu tried to pull up PANDA on his computer, it froze.
在宁波，这项看起来成功的技术也带来了一些新挑战。朱柯磊说，医院目前没有足够的人手去联络所有需要做进一步检查的病人。而且老化的硬件难以应付模型产生的大量数据。他有好几次遇到试图在电脑上打开PANDA时死机的问题。
Detecting cancer before patients have symptoms can also create its own problems. In China, widespread medical corruption has eroded public trust in doctors. Some people may refuse to come in for follow-ups, Dr. Zhu said, because they worry that the hospital is simply trying to make money.
在患者出现症状之前发现癌症，本身也会带来问题。在中国，普遍的医疗腐败侵蚀了公众对医生的信任。朱柯磊说，有些人可能会拒绝进一步检查，因为他们担心医院只是为了赚钱。
Mr. Qiu was not one of them. He did not hesitate when Dr. Zhu advised him to have his tumor removed, though he later said he did not use A.I. or understand how it worked. During a follow-up visit with the doctor in November, Mr. Qiu said he felt perfectly healthy and was busy growing vegetables on his family farm.
邱先生不是这样的人。当医生建议他切除肿瘤时，他没有丝毫犹豫，尽管他后来说他没有用过人工智能，也不了解它的原理。在11月的一次随访中，邱先生告诉医生，他感觉非常健康，正忙着在自家的农地里种菜。
“He said I was very lucky,” Mr. Qiu said. “So there was nothing else for me to say. I could only be relieved.”
邱先生说：“（医生）说（我）运气很好的，（发现得）早嘛，那我也没有什么好说的，就放心了。”
