Researchers at Ben-Gurion University of the Negev have developed a method called DISCOVER, which reverse engineers AI decisions by breaking down medical images into clinically significant components. This approach enhances understanding of AI's decision-making processes, crucial for applications in biology and medicine. The findings were published in Nature Communications, highlighting the importance of interpretability in AI models.
The DISCOVER method was tested in collaboration with the Israeli startup AIVF, focusing on in-vitro fertilization (IVF) embryos. The researchers demonstrated that AI could predict embryo quality with human-like accuracy, while also revealing new indicators of embryo quality, such as blastocyst density. This technology has the potential to improve embryo selection in fertility treatments and can be applied to various medical imaging domains.
• DISCOVER method enhances AI interpretability in medical imaging.
• AI predicts embryo quality with human-like accuracy in IVF.
This method is crucial for AI applications in recognizing patterns in complex datasets, such as medical images.
In this context, generative AI is used to create synthetic images of embryos to understand AI decision-making.
This is essential for clinical applications where understanding AI's rationale can influence treatment decisions.
The university's research team developed the DISCOVER method to enhance AI's interpretability in medical imaging.
AIVF collaborated with researchers to apply the DISCOVER method in assessing embryo quality during IVF.
McKnight's Senior Living 15month
ophthalmologytimes 13month
Isomorphic Labs, the AI drug discovery platform that was spun out of Google's DeepMind in 2021, has raised external capital for the first time. The $600
How to level up your teaching with AI. Discover how to use clones and GPTs in your classroom—personalized AI teaching is the future.
Trump's Third Term? AI already knows how this can be done. A study shows how OpenAI, Grok, DeepSeek & Google outline ways to dismantle U.S. democracy.
Sam Altman today revealed that OpenAI will release an open weight artificial intelligence model in the coming months. "We are excited to release a powerful new open-weight language model with reasoning in the coming months," Altman wrote on X.
