AI reads MRIs to predict brain tumor genetics — no biopsy needed

Kari Jaaskelainen

06 Nov 2025 — 1 min read

What if AI could read routine MRI scans and predict a brain tumor’s genetics — no biopsy? This study pairs computational imaging with large language models (LLMs) to zero-shot predict IDH mutation status in gliomas.

Multi-parametric MRI plus tumor segmentation become interpretable visual attributes and quantitative features.
Those features are serialized into a standardized JSON and sent as a prompt — no model fine-tuning.
Tested on six public datasets (N=1,427): strong, balanced performance across varied cohorts, even without manual annotations.
GPT-5 outperformed GPT-4o for context-driven phenotype interpretation.
Volumetric features mattered most; subtype-specific imaging markers and clinical info added value.

Why it matters: toward precise, non-invasive tumor genotyping and faster, safer decisions in neuro-oncology. Preprint: http://arxiv.org/abs/2511.03376v1 Code: https://github.com/ATPLab-LUMS/CIM-LLM

Paper: http://arxiv.org/abs/2511.03376v1

Register: https://www.AiFeta.com

AI MedicalImaging NeuroOncology MRI Radiogenomics LLM BrainTumor IDH Healthcare OpenScience

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)