🔬 What if a special camera could detect cancer just by analyzing your urine— even telling you which organ is affected? A Japanese startup is turning space satellite technology into a revolutionary cancer screening tool, using a camera that sees 141 colors invisible to the human eye. Here's how "color AI" could change everything we know about cancer diagnosis.
Cancer: Humanity's Most Persistent Enemy
Cancer remains the leading cause of death in Japan, where one in two people will develop cancer in their lifetime. Among the deadliest forms, pancreatic cancer is particularly devastating—with a five-year survival rate of just 7–13%. Because the pancreas is a "silent organ," tumors often go undetected until it's too late.
Yet early detection dramatically changes outcomes. For colorectal cancer caught while still localized, the five-year survival rate exceeds 90%. But once it has spread to distant organs, that number plummets below 20%. The message is clear: in the fight against cancer, finding it early is everything.
The Problem with Current Cancer Diagnosis
Today, the definitive way to diagnose cancer is through pathological examination—a doctor examines tissue samples under a microscope, assessing cell shapes to determine whether they're malignant. While this method is the gold standard, it comes with significant limitations.
First, it's highly subjective. Diagnoses depend heavily on the individual pathologist's experience, and different doctors can reach different conclusions from the same sample. Second, there's a severe global shortage of pathologists. Japan has roughly 2,600 certified pathology specialists—far fewer than needed. In countries like Cambodia, the number drops to fewer than ten. Third, the process is slow, often taking weeks for results to come back, adding anxiety and delaying treatment.
From Space Satellites to Cancer Screening
Enter Milk. Inc., a Japanese deep-tech startup founded in 2019 that's tackling these challenges with an unexpected tool: a camera originally designed for outer space.
The "hyperspectral camera" was initially developed for mounting on satellites, where it could identify mineral deposits on Earth's surface by analyzing reflected light across hundreds of wavelengths. While a standard camera captures images using just three colors (red, green, and blue—mimicking human vision), a hyperspectral camera captures 141 distinct color channels simultaneously. That's 47 times more color information than our eyes can perceive, spanning from ultraviolet to near-infrared wavelengths.
The camera's original developer was Professor Shin Satori, a former JAXA (Japan Aerospace Exploration Agency) engineer who worked on ion engines for asteroid exploration missions. The technology was even featured on Japan's lunar orbiter "Kaguya."
Milk.'s CEO, Daiki Nakaya, hails from Ehime Prefecture. After studying physics in America, he became fascinated with applying this space technology to medicine. His driving question: "Can we decode cancer through the lens of physics?" In 2015, he began researching cancer cell analysis using hyperspectral cameras, teaching himself AI and machine learning along the way.
Detecting Cancer by "Color"
So how can a camera spot cancer cells? The key lies in spectral signatures—unique patterns of how materials absorb and reflect light at different wavelengths.
Every substance has a distinct "light fingerprint." While cancer cells and healthy cells may look identical under a standard microscope, analyzing them across 141 wavelengths reveals subtle but measurable differences in their spectral patterns. Milk.'s proprietary "Color AI" analyzes these microscopic color variations to identify cancerous cells with remarkable precision.
Through collaborative research with Kitasato University and other medical institutions, Milk. has achieved striking results: 98% accuracy in identifying pancreatic cancer, 98.7% accuracy in distinguishing four stages of colorectal disease (from ulcerative colitis through mild and severe dysplasia to cancer), and 95.2% accuracy in classifying four types of ovarian cancer.
The pancreatic cancer result is particularly noteworthy, as this type of cancer has long been considered one of the hardest to detect early using conventional methods.
A Future Where Urine Tests Can Find Cancer
Perhaps the most groundbreaking application is using this technology for non-invasive cancer screening through urine analysis. It's known that cancer-derived components exist in blood, sputum, and urine. By combining the hyperspectral camera with Color AI, Milk. has demonstrated the potential to determine not only whether cancer is present, but even which organ is affected—all from a simple urine sample.
If this technology reaches clinical use, it could eliminate the need for expensive CT and MRI machines, remove radiation exposure concerns, and make cancer screening as simple as providing a urine sample. In Japan, where cancer screening participation rates remain stubbornly low, the sheer convenience could be transformative.
The Road to Commercialization
Milk. is currently developing a product called "ANSWER for Pathology"—a pathology diagnosis support system. It uses a "Hyper Slide Scanner" equipped with hyperspectral cameras to photograph cell samples, which the Color AI then analyzes to generate instant diagnostic reports. The company has already photographed approximately 10,000 clinical cases and is collaborating with five medical institutions to build datasets for pancreatic and bile duct cancers.
The company's trajectory has been impressive. In 2021, it won the top prize in the Medical & Healthcare category at the "Mirai 2021" pitch event hosted by Sumitomo Mitsui Banking Corporation. In 2022, it was selected for the Tokyo Metropolitan Government's Advanced Medical Device Acceleration Project (AMDAP), securing access to up to approximately $40 million in grants and expert support. In 2025, Milk. gained widespread attention when it received a unanimous $670,000 investment from four investors—including tech entrepreneur Takafumi Horie—on NewsPicks' popular show "Make Money Survive."
Beyond healthcare, hyperspectral camera technology has applications in food freshness assessment, infrastructure inspection, and agricultural monitoring. Milk.'s mission is nothing less than "a world free from the suffering of disease."
A Global Race with a Japanese Edge
Hyperspectral imaging for cancer detection is an active research field worldwide. At the University of Texas at Dallas, researchers have developed a micro-imaging device small enough for endoscope integration, with visions of smartphone-based self-scanning. Teams in Taiwan and India are also combining deep learning with hyperspectral techniques.
What sets Milk. apart is its unique combination of JAXA-derived space camera heritage, 141-channel color resolution, and Japan's unparalleled expertise in endoscopic technology. Japan holds nearly 100% of the global endoscope market share, giving it a significant advantage in merging optical and medical technologies.
Cancer is a challenge every country faces. If this Japanese-born technology reaches practical application, it could fundamentally change how we fight cancer worldwide. How does your country approach early cancer detection? Would you take a simple urine test if it could screen for cancer? We'd love to hear your thoughts.
References
- https://milk-med.com/
- https://amdap.metro.tokyo.lg.jp/interview_milk_med.html
- https://prtimes.jp/main/html/rd/p/000000014.000076265.html
- https://www.tv-tokyo.co.jp/broad_tvtokyo/program/detail/202601/27984_202601311030.html
- https://news.utdallas.edu/health-medicine/advanced-micro-imaging-device-cancer-detection-2025/
Reactions in Japan
As someone who lost my mother to pancreatic cancer, just hearing about 98% detection accuracy brings me to tears. I can't help thinking—if only this technology had existed back then. I sincerely hope it reaches practical use soon.
Lab-level accuracy and real-world clinical performance are completely different things. The media is overhyping this when the product isn't even on the market yet. The regulatory approval process for medical devices takes years.
Space technology being repurposed for medicine is incredibly romantic. The idea that Kaguya's camera could save lives on Earth is the ideal form of spinoff tech. Guess JAXA's budget wasn't a waste after all.
Getting Horie to invest means they've succeeded at PR, but will it actually become a product? Japanese startups have a pattern of going under due to funding issues.
If urine tests can detect cancer, could they be included in school health checkups? Kids cry less than with blood draws, which would be a relief as a parent. I wish a culture of early detection could take root from childhood.
As a pathologist, honestly, my hope of being freed from the pressure of 'missing something' outweighs any fear of AI taking my job. I welcome it as a support tool—though final decisions should remain with humans.
Entrusting the future of medicine to a 20-person startup feels precarious. Unless a major medical device manufacturer acquires or partners with them, it probably won't scale.
Did you know hyperspectral cameras can also be used in agriculture? They can assess fruit sweetness and vegetable freshness in a single shot. It's fascinating that the same tech fighting cancer can also help reduce food waste.
I can't even imagine a world seen in 141 colors. We've just been assuming we 'see everything' with only three. It feels like we're witnessing the moment technology surpasses human limitations.
The PMDA (Japan's medical device regulatory agency) review is the biggest hurdle. Japan is conservative about medical device approval, so I just hope it doesn't end up being commercialized overseas first and then imported back to Japan.
I'm a Stage IV pancreatic cancer survivor. In my case, it was discovered by chance through back pain. If this technology becomes part of regular checkups, fewer people will have to rely on luck. That alone makes it worthwhile.
Cancer screening data is the ultimate personal information. Having AI analyze it means data governance must be questioned too. I hope security and privacy are designed in from the very beginning.
Watched the Breakthrough episode. Honestly, going from physics to self-taught AI to cancer research is an incredible career path. I thought Japan wasn't a place where unconventional researchers could thrive, but they clearly exist.
How far the testing cost can drop is key to widespread adoption. Current CT scans run about $100 per session. Urine-based testing has the potential to go lower, but the expensive hyperspectral camera itself is a bottleneck.
At small rural hospitals, there's often no pathologist, and we routinely wait weeks to send tissue to university hospitals. Same-day results from urine would transform regional healthcare. Rural areas need this tech the most.
Twenty years as a surgical oncologist. I've seen patient anxiety while waiting for pathology results countless times. A system that delivers real-time results isn't just a tech innovation—it's a patient care revolution.
In India, some regions have only one pathologist per 20,000+ people. If this camera becomes affordable, it could bridge healthcare gaps in developing nations. I have high hopes for Japanese technology.
Sweden has nationwide cancer screening programs, but pancreatic cancer isn't covered. If urine tests can detect it, this should be integrated into screening systems. Seems like a natural fit for Nordic healthcare models.
Interesting tech, but even at 98% accuracy, false positives and negatives remain an issue. The risk of subjecting healthy people to unnecessary follow-up exams due to false positives is always a point of debate in screening.
Over 4 million people are diagnosed with cancer in China annually. If this tech can be mass-produced, its impact on the Chinese market would be immense. Though Chinese companies are definitely racing to develop similar technology.
The UAE invests heavily in preventive healthcare. Painless, simple cancer screening could particularly help improve screening rates among women in Islamic cultures, where some face barriers to traditional examinations.
The approach of repurposing space tech for medicine reminds me of NASA spinoff technologies. But how well space camera tech scales on the ground is unknown. I'm curious about the cost structure.
In Brazilian public hospitals, it's not uncommon for cancer diagnosis results to take months. Same-day results from urine tests would revolutionize healthcare across Latin America. But I don't see a clear path to availability beyond developed nations.
As a German optical engineer, this is fascinating. In the optics field built by Zeiss and Leica, a Japanese startup is pushing new frontiers with hyperspectral technology. Competition drives technology forward.
Cervical cancer is a leading cause of death for women in South Africa. Access to advanced screening equipment is limited. If a handheld device is developed, it could be loaded onto mobile screening vans to serve communities.
Korea has relatively high cancer screening rates, but pancreatic cancer is still easily missed. Samsung Medical Center is researching similar AI diagnostics, but the hyperspectral camera angle is novel.
In Australia's vast territory, sending pathology samples to urban labs takes time. Diagnostic technology that can work in remote areas would be a genuine game-changer for outback medicine.
France offers free cancer screening under universal healthcare, but the number of covered tests is limited. Cost-effective new screening tech could accelerate discussions about expanding insurance coverage.
As a Japanese-Canadian, I'm proud to see innovation coming from Japan. Cancer wait times are a serious issue in Canada—it'd be wonderful if this technology were introduced to BC healthcare facilities.