Models & Labs
PRISM2 Model Enhances Pathology Slide Interpretation
AI Newshigh confidence
Why it matters
- →PRISM2 integrates clinical dialogue with image analysis, enhancing diagnostic accuracy.
- →It outperforms existing clinical-grade products in cancer detection tasks.
- →The model represents a shift towards context-aware AI in medical diagnostics.
Paige and Microsoft have introduced PRISM2, a model that interprets pathology slides by combining image analysis with clinical dialogue. The model uses a perceiver-based encoder to process whole-slide images and generate diagnostic text, trained on a dataset of 2.3 million images and over 685,000 pathology reports. PRISM2 has demonstrated superior performance in cancer detection tasks compared to existing clinical-grade products. This development highlights a move towards more sophisticated AI tools in medical diagnostics, capable of providing context-rich interpretations rather than simple classifications.
Read originalThe story around this
TopicMicrosoft Advances Medical AICooling
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More in Models & Labs
Models & Labsother
llama.cpp b11193 adds Snapdragon Hexagon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm's Hexagon NPU on Linux arm64, a significant step for local inference on Snapdragon devices. It also updates CUDA builds to version 13.4 and introduces ROCm 10.0 binaries, keeping the project aligned with the latest NVIDIA and AMD driver ecosystems. KleidiAI on Apple Silicon is temporarily disabled in this build, likely due to stability checks rather than a feature rollback. For developers targeting edge AI or diverse GPU stacks, this update ensures broader compatibility without requiring custom compilation.
llama.cpp Releases
© Lev SelectorModels & Labsmodels
NVIDIA NVFP4 and SoL-Pi Token Efficiency
NVIDIA introduced the NVFP4 4-bit format and SoL-Pi technology, which uses 2x fewer tokens for improved efficiency.