Stanford AI Tool Predicts Cancer Gene Activity from Biopsy Images, Potentially Revolutionizing Cancer Diagnosis

3 Sources

Stanford Medicine researchers have developed an AI-powered tool called SEQUOIA that can predict gene activity in cancer cells using only biopsy images, potentially speeding up diagnosis and treatment decisions while reducing costs.

News article

Stanford Researchers Develop AI Tool to Predict Cancer Gene Activity

Stanford Medicine researchers have developed an innovative artificial intelligence (AI) tool that could revolutionize cancer diagnosis and treatment planning. The computational program, named SEQUOIA (slide-based expression quantification using linearized attention), can predict the activity of thousands of genes within tumor cells based solely on standard microscopy images of biopsy samples 1.

How SEQUOIA Works

SEQUOIA was developed using data from 7,584 cancer biopsies across 16 different cancer types. The AI model analyzes thin sections of tumor biopsies prepared with hematoxylin and eosin staining, a standard method for visualizing cancer cells 2.

By integrating this data with transcriptomic information and images from thousands of healthy cells, SEQUOIA can predict the expression patterns of more than 15,000 different genes from the stained images. For some cancer types, the AI-predicted gene activity showed over 80% correlation with actual gene activity data 3.

Potential Impact on Cancer Diagnosis and Treatment

Traditional methods of determining genomic changes driving tumor growth require genetic sequencing of RNA isolated from the tumor, a process that can take weeks and cost thousands of dollars. SEQUOIA could potentially bypass this need, offering several advantages:

  1. Speed: The AI tool can quickly identify gene signatures in patients' tumors, accelerating clinical decision-making.
  2. Cost-effectiveness: By reducing the need for expensive genetic sequencing, SEQUOIA could save the healthcare system significant amounts of money.
  3. Comprehensive analysis: The tool can predict the activation of large genomic programs, which is often more clinically relevant than individual gene expression.

Promising Results in Breast Cancer

To test SEQUOIA's clinical utility, the researchers focused on breast cancer, a well-studied cancer type with established gene signatures correlated to treatment responses and patient outcomes 1.

The team demonstrated that SEQUOIA could provide genomic risk scores comparable to the FDA-approved MammaPrint test, which analyzes 70 breast-cancer-related genes. Patients identified as high-risk by SEQUOIA showed worse outcomes, including higher rates of cancer recurrence and shorter time before recurrence 2.

Future Prospects and Limitations

While SEQUOIA shows great promise, it is not yet ready for clinical use. The tool needs to undergo clinical trials and receive FDA approval before it can be used to guide treatment decisions. However, the research team, led by Olivier Gevaert, PhD, a professor of biomedical data science at Stanford, is continually improving the algorithm and exploring its potential applications 3.

The development of SEQUOIA represents a significant step forward in the integration of AI and genomics in cancer research and treatment. As the tool continues to evolve, it could potentially be applied to all cancer types, offering a new source of valuable data for oncologists and researchers alike.

Explore today's top stories

Apple Considers Partnering with Anthropic or OpenAI to Enhance Siri's AI Capabilities

Apple is reportedly exploring the possibility of using AI models from Anthropic or OpenAI to power a new version of Siri, potentially sidelining its in-house technology in a major strategic shift.

TechCrunch logoTom's Hardware logoBloomberg Business logo

11 Sources

Technology

4 hrs ago

Apple Considers Partnering with Anthropic or OpenAI to

Baidu's Open-Source Ernie AI: A Game-Changer in the Global AI Race

Baidu, China's tech giant, is set to open-source its Ernie AI model, potentially disrupting the global AI market and intensifying competition with Western rivals like OpenAI and Anthropic.

CNBC logoSiliconANGLE logoDataconomy logo

4 Sources

Technology

20 hrs ago

Baidu's Open-Source Ernie AI: A Game-Changer in the Global

Microsoft's AI Diagnostic Tool Outperforms Human Doctors in Complex Medical Cases

Microsoft unveils an AI-powered diagnostic system that demonstrates superior accuracy and cost-effectiveness compared to human physicians in diagnosing complex medical conditions.

Wired logoFinancial Times News logoGeekWire logo

6 Sources

Technology

12 hrs ago

Microsoft's AI Diagnostic Tool Outperforms Human Doctors in

Google Unveils Comprehensive AI Integration in Education with Gemini and NotebookLM

Google announces a major expansion of AI tools in education, including Gemini for Education and NotebookLM for under-18 users, aiming to transform classroom experiences while addressing concerns about AI in learning environments.

TechCrunch logoThe Verge logoAndroid Police logo

7 Sources

Technology

4 hrs ago

Google Unveils Comprehensive AI Integration in Education

Apple's Ambitious Roadmap: Seven New XR Devices Planned for 2027 and Beyond

Apple is reportedly developing seven new extended reality (XR) devices, including upgraded Vision Pro headsets and smart glasses, set to launch from 2027 onwards, signaling a major push into the wearable tech market.

CNET logoThe Verge logoTom's Guide logo

10 Sources

Technology

20 hrs ago

Apple's Ambitious Roadmap: Seven New XR Devices Planned for
TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

Β© 2025 Triveous Technologies Private Limited
Twitter logo
Instagram logo
LinkedIn logo