Researchers developed PRTS, a deep learning model that infers single-cell spatial transcriptomics from standard H&E-stained tissue images.
Key Details
- 1PRTS stands for Pathology-driven Reconstruction of Transcriptomic States.
- 2It predicts an expression matrix for 1,820 genes at single-cell resolution from H&E images.
- 3The method provides 27x higher resolution than traditional spatial transcriptomics spot technologies.
- 4Validated on mouse brain, human lung cancer, and breast cancer datasets.
- 5PRTS identified 21 cell subtypes and matched key gene expression patterns to ground truth.
- 6Potential applications include diagnostics, cancer subtyping, and drug discovery.
Why It Matters
PRTS could enable cost-effective, scalable spatial transcriptomics directly from routinely collected pathology slides, advancing both research and diagnostics where gene expression mapping was previously prohibitively expensive or impractical.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.