logo
#

Latest news with #TechnologyandResearch

AI-powered model to predict liver cancer recurrence
AI-powered model to predict liver cancer recurrence

Arab Times

time6 days ago

  • Health
  • Arab Times

AI-powered model to predict liver cancer recurrence

SINGAPORE, July 22, (Xinhua): Singaporean researchers have developed an artificial intelligence-powered scoring system capable of predicting the recurrence of liver cancer, according to a press release from the Agency for Science, Technology and Research on Monday. Developed by scientists from the Institute of Molecular and Cell Biology (IMCB) under the agency in collaboration with the Singapore General Hospital, the system can forecast the recurrence of hepatocellular carcinoma, the most common type of liver cancer, with approximately 82 percent accuracy. The system works by analyzing the spatial distribution of natural killer immune cells and five key genes within liver tumor tissues. "In Singapore, up to 70 percent of liver cancer patients experience recurrence within five years," said Principal Investigator Joe Yeong from the IMCB, noting that this system empowers clinicians to intervene as early as possible. Researchers validated the system using tissue samples from 231 patients across five hospitals. It is now accessible via a free web portal for research purposes, with plans underway to integrate it into standard clinical workflows.

Scientists develop AI system that can predict liver cancer recurrence
Scientists develop AI system that can predict liver cancer recurrence

Business Standard

time6 days ago

  • Health
  • Business Standard

Scientists develop AI system that can predict liver cancer recurrence

In a major medical breakthrough, scientists in Singapore have developed an AI-powered diagnostic tool capable of accurately predicting the recurrence of liver cancer — specifically hepatocellular carcinoma (HCC), one of the deadliest cancers globally. The Tumour Immune Microenvironment Spatial (TIMES) score, an innovative diagnostic system, has been developed through a joint effort by researchers at the Agency for Science, Technology and Research (A*STAR)'s Institute of Molecular and Cell Biology (IMCB) and Singapore General Hospital (SGH), according to a press release from SGH. The TIMES model, which was recently featured on the cover of the renowned journal Nature, is being seen as a game-changer in personalised cancer diagnostics and early intervention. What is hepatocellular carcinoma? Hepatocellular carcinoma (HCC) is the most common type of liver cancer, often linked to chronic liver diseases such as cirrhosis. It remains the third leading cause of cancer-related deaths worldwide, and recurrence rates are alarmingly high. In Singapore alone, around 70 per cent of liver cancer patients experience a relapse within five years of treatment, making early detection of the recurrence vital for improving survival rates. How the TIMES system works The TIMES score uses advanced machine learning and spatial biology to assess the likelihood of liver cancer returning after surgery. By integrating multiplex immunofluorescence imaging, spatial transcriptomics, and proteomics data, the model uses the XGBoost machine learning algorithm to detect molecular patterns within tumour tissue—patterns that traditional diagnostic methods cannot identify. Specifically, it evaluates the distribution of natural killer (NK) cells and the expression of five key genes inside the tumour microenvironment. This combination allows the AI to determine a patient's risk of recurrence with approximately 82 per cent accuracy, outperforming existing clinical tools. Potential of the TIMES system Early and accurate prediction of relapse means that doctors can tailor follow-ups and treatment plans more effectively. This would increase the chances of long-term survival. According to Dr Joe Yeong, Principal Investigator at A*STAR IMCB and SGH's Department of Anatomical Pathology, the TIMES system represents a big leap in the ability to anticipate cancer relapse and initiate timely intervention. The study also identified a biomarker called SPON2, produced by NK cells. SPON2 has been found to be associated with the risk of recurrence. Studies have further revealed that SPON2 and NK cells enhance anti-tumour activity by improving migration towards cancer cells and activating CD8 and T-cells. This finding could also pave the way for improved AI-guided immunotherapy. Denise Goh, co-first author and senior research officer at A*STAR IMCB, explained, 'TIMES turns standard pathology slides into predictive diagnostic tools. Not only does the AI algorithm improve prognostic precision, but it also enables clinicians to revise treatment and monitoring plans proactively — potentially saving lives.' Validated and ready for wider use The TIMES model was tested using tumour samples from 231 patients across five hospitals, demonstrating its reliability across diverse datasets. To encourage global collaboration, the team has also launched a free online portal that allows medical professionals to upload tissue images and get AI-generated recurrence risk assessments. The underlying software framework has been patented, and further validation trials are scheduled at SGH and the National Cancer Centre Singapore later this year. The research team is currently working with diagnostic partners to standardise the system and transform it into a clinically approved diagnostic kit for routine hospital use. SGH, Singapore's largest tertiary healthcare institution and a globally recognised academic medical centre, played a key role in this project and will continue to support its clinical rollout. If successful, the TIMES score could become a key breakthrough for future cancer care.

Singapore researchers develop AI-based model to predict liver cancer recurrence
Singapore researchers develop AI-based model to predict liver cancer recurrence

United News of India

time7 days ago

  • Health
  • United News of India

Singapore researchers develop AI-based model to predict liver cancer recurrence

Singapore, July 21 (UNI) Singaporean researchers have developed an artificial intelligence-powered scoring system capable of predicting the recurrence of liver cancer, according to a press release from the Agency for Science, Technology and Research on Monday. Developed by scientists from the Institute of Molecular and Cell Biology (IMCB) under the agency in collaboration with the Singapore General Hospital, the system can forecast the recurrence of hepatocellular carcinoma, the most common type of liver cancer, with approximately 82 per cent accuracy. The system works by analyzing the spatial distribution of natural killer immune cells and five key genes within liver tumor tissues. "In Singapore, up to 70 per cent of liver cancer patients experience recurrence within five years," said Principal Investigator Joe Yeong from the IMCB, noting that this system empowers clinicians to intervene as early as possible. Researchers validated the system using tissue samples from 231 patients across five hospitals. It is now accessible via a free web portal for research purposes, with plans underway to integrate it into standard clinical workflows. Further validation studies are scheduled to begin later this year. UNI XINHUA AKT PRS

Singlish-savvy national AI chatbot can check in on seniors, intercept scam calls
Singlish-savvy national AI chatbot can check in on seniors, intercept scam calls

Straits Times

time28-05-2025

  • Straits Times

Singlish-savvy national AI chatbot can check in on seniors, intercept scam calls

Meralion is available for the public to install for free to adapt for their uses. PHOTO: LIANHE ZAOBAO SINGAPORE – A rtificial intelligence agents trained to speak in English, local mother-tongue languages and even Singlish may soon be deployed to call elderly patients or seniors to check in on how them are doing, or in anti-scam centres to intercept suspicious calls. 'I've been told (the chatbot) can also handle non-verbal cues such as the speaker's volume, emotion, tone,' said Digital Development and Information Minister Josephine Teo, unveiling the chatbot on May 28 at the Asia Tech x Singapore conference. Called Meralion (short for Multimodal Empathetic Reasoning and Learning in One Network), the chatbot can understand at least eight regional languages such as English, Mandarin, Tamil, Malay, Thai and Singlish - Singapore's unique take on English which fuses regional languages. Meralion, which is developed by A*Star ( Agency for Science, Technology and Research), is available for the public to install for free to adapt for their uses. Its developers are also in talks with a social service agency to deploy the chatbot, and are refining the program for use in scam detection. For instance, Meralion can help social workers ring seniors to remind them to take their medication. The AI program, which works autonomously, can also check in on the seniors' well-being, analysing their tone and dialogue for signs of sadness or anger that might require closer attention from human staff members. The chatbot will generate a summary of the call, detailing the senior's needs and well-being. Meralion's development is part of a $70 million initiative funded by the National Research Foundation and the Infocomm Media Development Authority (IMDA), which aims to build large language models tailored for the region. The fund has also backed AI Singapore's Sea-Lion (South-east Asian Languages in One Network) model, which is trained on at least 11 major languages used in the region. The Meralion chatbot fills a gap for locally-attuned language models as most current AI systems are trained largely on Western data, said Dr Lawrence Wee, director of business and ecosystems at IMDA's BizTech Group. As a result, chatbots like ChatGPT and Google Gemini that dominate the fast-growing AI field can often stumble over local dialects, communication styles and nuances, so deploying them here often requires extensive retraining on regional data. Meralion, trained on the national speech corpus, understands when multiple languages are spoken in the same sentence, reflecting how people in the region naturally communicate . Meralion can also detect emotional tone to enable more empathetic interactions with the chatbot, said IMDA and A*Star. They added that Meralion is being trained to understand Chinese dialects in future updates. Mrs Teo, who is Minister-in-Charge of Smart Nation and Cybersecurity, said that the Meralion chatbot can serve the needs of more than 450 million people in the region who use these languages. In a demonstration on May 26, the media was shown how Meralion can be deployed in eldercare and anti-scam efforts. The social services AI bot asked the caller how he was feeling and understood his Singlish reply, which included a lament on his early start to the day: 'I wake up at 6 and make my kopi-o ' (local black coffee). The bot responded in Singlish: 'Aiyo h , so sayang... Hope your kopi-o helped. Have you eaten? Remember to take care of yourself, okay?' For more severe concerns such as body aches, the bot can give basic advice, such as to rest or ice bruises. Urgent cases can be flagged directly to social workers, depending on how the program is implemented. Dr Wee said Meralion's developers are in talks with a social service agency, which it did not identify, to deploy the AI chatbot for eldercare . In a separate demo nstration , Meralion was used to screen likely scam calls to prevent scammers from reaching victims over the phone. If a call seems suspicious, Meralion answers, identifies itself as an AI assistant and asks the caller to state their purpose. The bot assesses the purpose of the call before deciding whether to let the call through or to block it. Meralion can also block calls made by bots, often used by scammers to target victims en masse. It is yet to be see n how potential clients will implement the technology. Telcos might employ it to screen suspicious calls before they reach users who opt in for the security service, or as an app to filter calls , said Mr Lam Pang Ngean, business development director at Axion IT Solutions, which is working with A*Star bring Meralion to potential clients. An earlier version of Meralion has been downloaded more than 90,000 times by start-ups , research labs and academics, among other users, since it was rolled out as an open-source tool in December 2024. 'Furthermore, (Meralion's latest version) understands sentences containing a mix of languages, which is common in multi-cultural societies,' said Mrs Teo, speaking to several hundred tech policymakers, researchers and industry guests in attendance at Capella in Sentosa. 'It's very unusual for us to complete a whole sentence using just one language,' she said, adding that there were more than 1,200 languages and dialects in South-east Asia. Meralion follows the footsteps of Sea-Lion, another large language model designed to reflect local cultures. The open-source Sea-Lion software has been installed more than 200,000 times, said Mrs Teo, adding that the interest in a regionally attuned model indicated a demand for a new AI program capable of understanding speech, text and other modes of communication. Organised by IMDA, the ATxSG conference is expected to host 3,500 attendees from around the world who will attend panels and discussions on AI governance and innovation in the technology sector between May 27 and 29. Executives from major tech companies like OpenAI, Microsoft and Google are also scheduled to attend panel discussions that address pressing issues in tech. Mrs Teo announced the Meralion Consortium, which launches with 12 member organisations including DBS Bank, the Ministry of Health and ST Engineering, to with Meralion's developers to refine the AI model so that they can be used by member companies and their sectors. The consortium will focus on multilingual customer support, analysing speech and text for emotional cues to support wellbeing and care and to improve AI's decision-making ability by factoring cultural contexts. The members include Microsoft, which is working with A*Star on how Meralion can be woven into its suite of office tools. SPH Media, which runs The Straits Times, is also exploring ways to use Meralion to support AI apps in user experience and customer service tools, said chief operating officer Loh Yuh Yiing. Join ST's WhatsApp Channel and get the latest news and must-reads.

Singapore chipmakers unfazed by tariff threat, see AI and talent hunt as bigger challenges
Singapore chipmakers unfazed by tariff threat, see AI and talent hunt as bigger challenges

Straits Times

time26-05-2025

  • Business
  • Straits Times

Singapore chipmakers unfazed by tariff threat, see AI and talent hunt as bigger challenges

Chip firms at the Semicon Southeast Asia 2025 last week were unanimous in their view that the industry will not be immune to a global economic slowdown. PHOTO: SEMI SINGAPORE - Singapore's semiconductor industry will continue to invest and innovate to address the growing demand for more efficient chips, despite threats of new trade barriers that can further disrupt its highly globalised supply chain. The more pressing challenges for chipmakers and companies in related businesses – both multinational and local – are the hunt for talent, and the race to innovate and stay competitive and relevant in the era of artificial intelligence. To be sure, chip firms at the three-day Semicon Southeast Asia 2025 in Singapore during May 20 - May 22 were unanimous in their view that despite its solid growth prospects, the industry will not be immune to a global economic slowdown induced by the current trade policy uncertainty and any new tariffs that would affect consumer demand for electronic goods. While making its supply chains more adaptable to geopolitical demand and supply vulnerabilities remain an uphill task, the industry has so far successfully weathered intensifying trade tensions and technology competition between the world's two largest economies – the United States and China since 2017. In the same period, global chip sales have increased at a record pace and are expected to cross the US$1 trillion (S$1.28 trillion) mark by early 2030s from around US$627 billion in 2024. More recently, chip revenues are getting an additional uplift from the fast-growing cloud capacity, with new data centres popping up worldwide to handle the immense computational and data storage demands of artificial intelligence (AI) applications. The industry, however, sees the AI opportunity as a challenge as well. Referring to AI, Mr Tim Breen, chief executive officer of chipmaker GlobalFoundries, said at the Semicon event: 'There is, of course, optimism across the board, but within that is a question – are we ready? Are we ready for that growth? 'If innovation takes five companies to make it happen, do we really know how to work together in groups globally in a world that is more fragmented?' As a step in deepening its innovation partnerships, GlobalFoundries, which has a chipmaking plant in Singapore, signed a pact on the sidelines of the event with the Agency for Science, Technology and Research (A*Star), the Republic's lead public sector research and development (R&D) agency. The collaboration will give the chipmaker access to A*Star's R&D facilities for development and support for workforce skills enhancement in advanced packaging – the most talked-about technology at the Semicon event. Advanced packaging – which involves combining multiple chips and components into a single package – has become a key priority for the industry. Since AI workloads need more computational speed, data storage capacity and high electricity consumption, the technology delivers processing units that not only excel in performance but are also energy efficient. Mr Breen believes that no company in the world can bring such complex semiconductor devices to market on their own. 'You need a whole host of innovation, you need a whole host of manufacturing partnerships to do that,' he said. Other company executives also echoed Mr Breen's view, saying chipmakers are deepening their collaboration with test and packaging companies, chip designers and equipment makers to address the AI imperative. Mr Andrew Goh, corporate vice-president and general manager for South - east Asia at Lam Research, which makes machines used in chip manufacturing, said his company is also deepening its partnerships with its customers, suppliers and other stakeholders in the ecosystem to help address both the supply chain and technological challenges. 'We are working with the governments, schools and universities to collaborate on the R&D and innovation that we can do locally,' Mr Goh told The Straits Times. The company has a network of plants across Asia, including one in Malaysia and two offices in Singapore , to manage its supply chain and customer support. He said Lam has ongoing engagements with the Republic's Nanyang Technological University and National University of Singapore to also help them maintain a talent pipeline, and develop and retain their workforce. Mr Goh said AI is not only changing the market for companies like Lam, with demand rising for machines for advanced packing and manufacturing of advanced chips, it is also having an impact internally. AI is being increasingly used to boost factory floor efficiency of chipmakers and equipment makers like Lam, which also means increasing demand for talent. 'Maintaining a talent pipeline has become a pressing challenge for the industry, not only in Singapore but in other countries and regions as well,' Mr Goh said. The Semicon event also had a dedicated space for career exploration fair that hosted several career talks. Ms Michelle Phua, director of operations management at chip equipment maker Applied Materials, said the industry has broadened the scope of talent from engineering graduates and diploma holders to professionals in related fields such as software development. Singapore universities and polytechnics offer several programmes focused on areas like integrated circuit design, manufacturing and operations. In recent years, they have also launched short courses for graduates and mid-career professions under the umbrella of the SkillsFuture scheme – a joint initiative of the Ministry of Trade and Industry and Government Technology Agency of Singapore (GovTech). Still, developing a sustainable talent pipeline is seen as a problem not only by large multinational firms such as GlobalFoundries, Lam Research and Applied Materials but also by small and medium-sized enterprises (SMEs). Mr Kenneth Lee, CEO of Global Tech Solutions – which provides refurbishment, installations and field service support to chipmakers – said graduates do not see chip manufacturing as less glamorous. 'We put in a lot of effort, like participating in career events and going to educational institutions to introduce ourselves and the industry,' he said. Still, many company executives appreciated the Government's effort to boost talent supply, and recognised the importance of working closely with universities and polytechnics to encourage more of their graduates to join the industry. Join ST's Telegram channel and get the latest breaking news delivered to you.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store