Researchers combined micro-CT imaging and deep learning to detect subtle disease-induced changes in coral skeletons with high accuracy.
Key Details
- 1Florida Atlantic University researchers used micro-CT imaging to generate detailed 3D reconstructions of coral skeletons.
- 2Deep learning, specifically U-Net family convolutional neural networks, was applied to segment and analyze skeletal features.
- 3The top-performing model (Attention U-Net) achieved more than 98% accuracy while reducing processing time to 7 hours.
- 4Study revealed disease-driven changes in porosity, density, and thickness of coral skeletons, providing new quantitative insights.
- 5The research opens the possibility of applying similar imaging-AI workflows to other biological, engineered, or geological samples.
Why It Matters
This work demonstrates the power of combining advanced 3D imaging with AI for high-throughput, non-destructive analysis of complex biological structures, a methodology that could be directly translated to radiology and imaging biomarker research. It also underscores how imaging AI can improve disease assessment and guide conservation or clinical strategies.
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.