Class 3 Cancer Risk Assessment Software
MFDS KOREA
World's best performing hepatocellular carcinoma onset and recurrence prediction software
Setting a new standard for liver cancer risk prediction.
Hepatocellular carcinoma onset risk assessment
software for patients with chronic hepatitis B
World-class
liver cancer risk prediction accuracy
Proven accuracy at clinically applicable levels
DeepFore achieved a C-index of 0.89 (95% CI 0.87–0.90),
demonstrating substantially higher performance than
previously published global hepatocellular carcinoma (HCC) prediction models.
Performance comparison: DeepFore vs. existing models
Source: Shin, Hyunjae, et al. "AI model using CT-based imaging biomarkers to predict hepatocellular carcinoma in patients with chronic hepatitis B." Journal of Hepatology 82.6 (2025): 1080-1088.
DeepFore's globally recognized technology
Knowing your risk level
is the start of liver cancer management
Why is predicting liver cancer risk important?
but early detection improves the 5-year survival rate significantly to 59.8%.
When the disease progresses to liver cancer, annual treatment costs increase to KRW 42.44 million, and in cases requiring liver transplant, it reaches KRW 155.8 million annually. (*Source: White Paper on Liver Diseases in Korea, Korean Association for the Study of the Liver)
Thus, liver cancer is a disease that places a significant economic burden not only on patients but also on families and society as a whole.
The risk group is clear, but individual risk levels vary significantly.
Therefore, it is essential to predict and prepare for not only initial onset but also recurrence.
Beyond diagnosis that sees only the present,
liver cancer management through future-risk prediction
More efficient
chronic hepatitis B patient management with DeepFore
Existing process
workflow
AI-powered precision prediction for
optimal liver cancer management for every patient
DeepFore analyzes clinical information and CT imaging data to precisely categorize patients into 4 groups: high-risk, intermediate-risk, low-risk and minimal-risk.
This helps clinicians set tailored management and monitoring strategies for each patient, supporting faster and more accurate patient-centered personalized treatment planning.