A groundbreaking artificial intelligence tool called FastGlioma has been developed, enabling surgeons to detect residual cancerous brain tumours within 10 seconds during surgery. The innovation, detailed in a recent study in Nature, is seen as a significant advancement in neurosurgery, outperforming traditional tumour detection methods. Researchers from the University of Michigan and the University of California, San Francisco, led the study, highlighting its potential to improve surgical outcomes for patients with diffuse gliomas.

Todd Hollon, M.D., a neurosurgeon at the University of Michigan Health, described FastGlioma as a transformative diagnostic tool that provides a faster and more accurate method for identifying tumour remnants. He noted its ability to reduce reliance on current methods, such as intraoperative MRI or fluorescent imaging agents, which are often inaccessible or unsuitable for all tumour types.

Addressing Residual Tumours During Surgery

As per the study from Michigan Medicine – University of Michigan, residual tumours, which often resemble healthy brain tissue, are a common challenge in neurosurgery. Surgeons have traditionally struggled to differentiate between healthy brain and remaining cancerous tissue, leading to incomplete tumour removal. FastGlioma addresses this by combining high-resolution optical imaging with artificial intelligence to identify tumour infiltration rapidly and accurately.

In an international study, the model was tested on specimens from 220 patients with low- or high-grade diffuse gliomas. FastGlioma achieved an average accuracy of 92%, significantly outperforming conventional methods, which had a higher miss rate for high-risk tumour remnants. Co-senior author Shawn Hervey-Jumper, M.D., professor of neurosurgery at UCSF, emphasised its ability to enhance surgical precision while minimising the dependence on imaging agents or time-consuming procedures.

Future Applications in Cancer Surgery

FastGlioma is based on foundation models, a type of AI trained on vast datasets, allowing adaptation across various tasks. The model has shown potential for application in other cancers, including lung, prostate, and breast tumours, without requiring extensive retraining.

Aditya S. Pandey, M.D., chair of neurosurgery at the University of Michigan, affirmed its role in improving surgical outcomes globally, aligning with recommendations to integrate AI into cancer surgery. Researchers aim to expand its use to additional tumour types, potentially reshaping cancer treatment approaches worldwide.

A new artificial intelligence (AI) tool, Earth Copilot, has been introduced by NASA in collaboration with Microsoft to make Earth-related scientific data more accessible. Designed to summarise NASA’s extensive geospatial information, the AI-powered chatbot aims to simplify complex datasets and answer user queries with ease. By addressing questions like the environmental impact of events or changes in air quality, the tool seeks to bridge the gap between NASA’s vast database and users who may lack technical expertise.

Democratising Earth Science Data

The initiative is part of NASA’s effort to expand access to its data. According to Tyler Bryson, Corporate Vice President for Health and Public Sector Industries at Microsoft, many users struggle to utilise NASA’s database due to its technical nature. Extracting insights often requires specialised knowledge of geospatial analysis and data formats. By integrating AI into NASA’s data repository, Earth Copilot reduces the time needed to derive insights from scientific information, making the data more accessible in seconds.

Testing and Integration

Currently, Earth Copilot is in a testing phase, with NASA scientists and researchers evaluating its performance. Following this assessment, NASA plans to integrate the tool into its Visualisation, Exploration, and Data Analysis (VEDA) platform. VEDA already offers public access to some of NASA’s datasets, and Earth Copilot could enhance its usability for non-specialist users.

Potential Benefits

Earth Copilot is expected to transform how users interact with Earth science data by simplifying the process of analysis. The tool has been designed to answer complex questions, such as the effects of natural disasters or global events, using NASA’s comprehensive database. Its development aligns with the agency’s goal of enhancing public understanding of Earth’s systems and providing timely, accurate insights for decision-making.

While still limited to internal testing, Earth Copilot represents a promising step towards making Earth science data universally accessible.

A recent cosmic census has revealed an unexpected threefold rise in active black holes within dwarf galaxies, creating the most extensive database of intermediate-mass black holes recorded to date. This survey, conducted with the Dark Energy Spectroscopic Instrument (DESI) at the Mayall Telescope in Arizona, identified over 2,500 black holes in dwarf galaxies—more than triple the previously estimated number. Led by University of Utah astronomer Ragadeepika Pucha, the research team discovered that around 2 per cent of the nearly 115,000 surveyed dwarf galaxies contain black holes actively consuming matter. Previously, only 0.5 per cent of these galaxies were believed to host such black holes.

Unveiling Middleweight Black Holes in the Cosmos

The survey has also increased the number of intermediate-mass black hole candidates—those with masses between 100 and one million times that of the sun. With almost 300 new middleweight candidates identified, the known population has quadrupled from just 70. These findings are important for understanding black hole evolution, as middleweight black holes are seen as a bridge between stellar-mass black holes, formed from collapsing stars, and supermassive black holes, which are often found at the centres of larger galaxies. According to Pucha, this newly documented group of black holes offers clues into how early black holes may have evolved through gradual cosmic mergers.

Insights into Galaxy and Black Hole Co-Evolution

The unprecedented increase in detected black holes brings fresh opportunities to study the connection between galaxies and the black holes within them. As Dr Stéphanie Juneau from NOIRLab, a co-author of the study, remarks, the discovery raises fundamental questions about the evolution of galaxies and their black holes. It remains unclear whether galaxies formed first, subsequently creating black holes, or if black holes seeded galaxy growth.

Future of Cosmic Exploration with DESI

DESI’s findings open new chapters in understanding galactic evolution. Expected to release more detailed findings in 2025, the DESI project has already mapped 1.5 million galaxies, creating a vast 3D map that enables astronomers to probe dimmer galaxies that previously eluded detailed study. Astrophysicist Mallory Molina of Vanderbilt University, though not directly involved in the study, noted the transformative impact of the data, highlighting DESI’s ability to detect numerous black holes, even with basic observational tools, suggesting the potential for further discoveries.