TLDR: Scientists in Singapore have developed an AI-powered scoring system, the Tumour Immune Microenvironment Spatial (TIMES) score, to predict the recurrence of hepatocellular carcinoma (HCC), the most common form of liver cancer. Featured in ‘Nature’, this innovation achieves approximately 82% accuracy by analyzing the spatial distribution of natural killer cells and five specific genes within tumor tissues, offering a significant advancement in patient care.
Singaporean researchers have achieved a significant breakthrough in cancer diagnostics with the development of an artificial intelligence (AI)-powered scoring system designed to predict the recurrence of hepatocellular carcinoma (HCC), the most prevalent form of liver cancer. Named the Tumour Immune Microenvironment Spatial (TIMES) score, this innovative system was developed by scientists from A*STAR’s Institute of Molecular and Cell Biology (IMCB) and Singapore General Hospital (SGH). The groundbreaking study was featured as the cover story in the April 15, 2025, issue of the prestigious scientific journal ‘Nature’.
The TIMES score operates by meticulously analyzing the precise spatial distribution of immune cells, specifically natural killer (NK) cells, and five key genes within liver tumor tissues. Unlike traditional methods that merely count cell presence, the AI system examines their exact location and interaction relative to cancer cells. Dr. Joe Yeong, a principal investigator at both A*STAR IMCB and SGH’s anatomical pathology department, explained, ‘Instead of just counting how many NK cells are present, we analyse exactly where they are positioned relative to the cancer cells. By understanding how NK cells are distributed and how they interact with cancer cells – for example, whether they are close enough to attack the cancer effectively – we can predict the likelihood of cancer returning after surgery.’ Dr. Yeong also serves as the Director of ImmunoPathology at the SingHealth Duke-NUS Pathology Academic Clinical Programme.
This AI-driven approach allows TIMES to predict recurrence risk with approximately 82% accuracy, significantly outperforming existing clinical staging methods. This high accuracy is crucial, as up to 70% of liver cancer patients in Singapore experience recurrence within five years. An accurate prediction method enables doctors to identify high-risk patients much earlier, allowing for proactive and targeted treatment strategies.
Ms. Denise Goh, Senior Research Officer at A*STAR IMCB and co-first author of the study, highlighted the transformative potential of the system, stating, ‘The TIMES scoring system transforms routine tissue slides into powerful predictive tools. By identifying patients at higher risk of relapse, we can proactively alter treatment strategies and monitoring, potentially saving more lives.’ The study also identified a key biomarker, SPON2, expressed by NK cells, which showed a strong correlation with recurrence risk, with functional assays confirming that SPON2+ NK cells exhibit heightened anti-tumour activity.
Also Read:
- Artificial Intelligence Set to Drive Singapore’s Sustained 3% Annual GDP Growth
- AI’s Growing Role in Health Diagnosis: A Double-Edged Sword for Americans and Clinicians
The researchers validated the TIMES system using tissue samples from 231 patients across five hospitals. Looking ahead, the technology has been made accessible via a free web portal for research use, with plans to integrate TIMES into routine clinical workflows. Further validation studies are scheduled to begin later this year at SGH and the National Cancer Centre Singapore. Discussions are also underway with diagnostic partners to develop the system into a clinically approved diagnostic test kit, promising a future where this AI innovation can significantly enhance patient care and improve survival outcomes for liver cancer patients globally.
