AI uses non-contrast CT and facial photos to assist cancer screening

AI's fight against cancer has already advanced to "reading faces" | Internet Morning Reading Class Download the client for exclusive early access November 01, 2026 08:13:00 From Anhui Province Updated November 01, 2026 09:25:27

On January 17, 2025, 65-year-old Mr. Qiu walked into the People's Hospital Affiliated to Ningbo University due to three days of dizziness. Dizziness is an extremely common symptom in older adults, possibly caused by insufficient cerebral blood supply, cervical spine problems, or blood pressure fluctuations.

Following routine practice, the doctor arranged color ultrasound and non-contrast CT, and the results showed no obvious abnormalities. Mr. Qiu should have taken the report and gone home to rest.

The system scanned that non-contrast CT and marked a lesion about 1.5 centimeters in diameter in the pancreatic region, indicating a possible malignant lesion. The attending doctor was stunned for a moment; Mr. Qiu's symptom was dizziness, with no sign pointing to the pancreas.

Three days of dizziness, an unexpected encounter with the "king of cancers"

Zhu Kelei, vice president of the People's Hospital Affiliated to Ningbo University and chief physician of the Department of Hepatobiliary and Pancreatic General Surgery, later recalled: "This is something none of us doctors could have imagined, because the patient's chief complaint was dizziness, while pancreatic problems generally cause abdominal pain."

The AI alert prompted the hospital to quickly adjust its approach, and contrast-enhanced CT was arranged immediately, with the results clearly pointing to pancreatic cancer. Mr. Qiu soon underwent surgery, and the pathology report confirmed pancreatic ductal adenocarcinoma. His daughter said: "We are so thankful; my father truly got a second chance at life."

Pancreatic cancer has long been known as the "king of cancers." The pancreas is buried deep in the abdominal cavity, surrounded by the stomach, duodenum, and spleen. Its location is hidden, and early pancreatic cancer has almost no specific symptoms. By the time patients feel obvious discomfort, cancer cells have often already quietly metastasized.

China has more than 130,000 new pancreatic cancer patients each year, and more than 80% are diagnosed at an advanced stage, with a five-year survival rate of less than 10%.

Starting in November 2024, the People's Hospital Affiliated to Ningbo University introduced medical AI from Alibaba DAMO Academy (Hupan Lab) and jointly launched a prospective clinical trial with Professor Jin Gang's team at the Shanghai Pancreatic Disease Institute, becoming the first hospital in Zhejiang Province to open a pancreatic cancer early screening clinic.

To date, the Ningbo project has found 8 cases of pancreatic cancer from CT imaging data of more than 40,000 people, of which 6 were early-stage, and all received surgical treatment.

The DAMO Academy PANDA model research team registered contrast-enhanced CT images from more than 2,000 pancreatic cancer patients onto non-contrast CT, enabling the model to learn to identify subtle pancreatic lesions in lower-resolution images.

The model's sensitivity for identifying pancreatic cancer patients reached 92.9%, with specificity of 99.9%, about 34% higher sensitivity than experienced radiologists.

Contrast-enhanced CT requires injection of contrast agent and is relatively expensive, making it unsuitable for large-scale population screening; non-contrast CT is the most common imaging method in outpatient settings. If "opportunistic screening" for cancer can be completed in these readily available images, it means no additional examination burden needs to be placed on patients, and any ordinary visit or physical examination could become an opportunity window for detecting early cancer.

DAMO Academy's multi-cancer early screening AI technology has begun global promotion, covering 9 countries and regions worldwide and serving more than 20 million people.

At the same time, DAMO Academy is also advancing the goal of "one scan, multiple screenings," meaning that through a single non-contrast CT, AI can not only identify pancreatic cancer but also simultaneously complete screening for liver cancer, esophageal cancer, gastric cancer, colorectal cancer, and even emergencies such as aortic syndrome.

Following pancreatic cancer, DAMO Academy's released colorectal cancer screening AI model DAMO COCA accurately identified 5 missed colorectal cancer cases from non-contrast CT images of 27,000 people, with sensitivity reaching 86.6% and specificity reaching 99.8%.

Doctors are irreplaceable in experiential judgment and clinical decision-making, but human eyes have fatigue blind spots, attention is drawn by the chief complaint, and when facing hundreds of detail-dense imaging slices, there is always the possibility of omission.

Recently, a research team from Massachusetts General Hospital, Harvard University, published a study in The Lancet Digital Health, using an ordinary photo to predict the mortality risk of a cancer patient. Although the model's predictions are not completely accurate, those patients with higher mortality risk did indeed have a higher probability of death.

The logic of FaceAge is built on the concept of "biological age." At the same age of 60, some people look 52, while others look 71, because of differences in lifestyle, disease history, and genetics.

Researcher Mak pointed out that people who smoke often look older than their actual age; the same is true for heavy drinkers.

The researchers trained an algorithm to analyze and process 40 million ordinary face images without a given specific task. They then adjusted the model so that it could analyze face images in two different ways: one for estimating a person's physiological age, and one for predicting the survival probability of cancer patients.

Whether the person in the photo is frowning or smiling, whether they are wearing makeup, and under what lighting conditions, none of these affect the age prediction.

In terms of mortality risk prediction, in a test group of 3,820 cancer patients, more than half of those in the group with the highest mortality risk scores died within just 90 days after the photo was taken.

Researchers also found in the genetic data of lung cancer patients that FaceAge scores were negatively correlated with a gene called CDK6. CDK6 is an important participant in cell cycle regulation and is associated with the progression of multiple cancers. A model trained on facial photos had, to some extent, captured signals at the genetic level.

Sophont's CEO shared another case on social media, involving osteosarcoma.

Their model Holon-S1 analyzed the patient's pathology slides. This model had not undergone specialized training for osteosarcoma, but it extracted key biological information from the slide images: the patient's fibroblast-related genes showed overexpression.

This phenomenon had previously been discovered by the patient's medical team through advanced molecular testing, and the corresponding therapeutic target had already been identified.

New questions

In their paper, the FaceAge researchers specifically mentioned a direction that worries them: such a tool may be helpful to clinicians, but it may also be highly attractive to life insurance companies or employers, who might try to use it to assess an individual's risk level.

In addition, the "visual features of aging" learned by the model may not apply to all skin colors and facial structures. If the model systematically overestimates biological age for certain ethnic groups, this error will replicate and amplify existing inequality in an extremely hidden way, and those misjudged may not even know what happened.

A previous study found that some commercial models used to predict patients' medical needs systematically underestimated the needs of Black patients, because the models used historical medical spending as a proxy for health status, while historically Black patients received fewer medical resources for the same condition.

The researchers emphasized that before FaceAge enters clinical use, it needs to be tested in more diverse populations to identify and eliminate potential errors.

How to handle these new questions is much harder than training a model.

"Special statement: The above content (including videos, pictures, and audio if any) is uploaded and published by users of "Dafeng Hao," a self-media platform under Phoenix Net. This platform only provides information storage space services.

Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."