Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
highlights:2025:foramslice [2025/12/02 06:36] – Didier Barradas Bautistahighlights:2025:foramslice [2025/12/02 06:38] (current) – Didier Barradas Bautista
Line 42: Line 42:
  
 ===== Research Breakthrough ===== ===== Research Breakthrough =====
-<WRAP hi>+<WRAP>
 Foraminifera are microscopic organisms whose fossilized shells provide insight into the history of Earth's climate. Our **ForamDeepSlice** framework uses deep learning to automatically classify 12 foraminifera species from micro-CT scans with unprecedented accuracy. Foraminifera are microscopic organisms whose fossilized shells provide insight into the history of Earth's climate. Our **ForamDeepSlice** framework uses deep learning to automatically classify 12 foraminifera species from micro-CT scans with unprecedented accuracy.
   * 📊 Tested on 97 specimens representing 27 species, ForamDeepSlice achieved **95.6%** accuracy and **99.6%** top-3 accuracy across 109,617 2D slices.   * 📊 Tested on 97 specimens representing 27 species, ForamDeepSlice achieved **95.6%** accuracy and **99.6%** top-3 accuracy across 109,617 2D slices.
Line 56: Line 56:
 </WRAP> </WRAP>
 <WRAP center> <WRAP center>
-{{:wiki:highlights:2025:foram_pipeline.png?1000}}+{{:wiki:highlights:2025:foramdeepslice_workflow_v1.jpg?1000}}
 </WRAP> </WRAP>
  
 <fs 18>**🎯 KVL's Contribution**</fs> <fs 18>**🎯 KVL's Contribution**</fs>
-<color #000000>KVL's visualization scientists **Abdelghafour Halimi**, **Didier Barradas-Bautista**, and **Ronell Sicat** contributed significantly to the development of the ForamDeepSlice framework through:+KVL's visualization scientists **Abdelghafour Halimi**, **Didier Barradas-Bautista**, and **Ronell Sicat** contributed significantly to the development of the ForamDeepSlice framework through:
  
   * Design and implementation of PatchEnsemble strategy for improved classification accuracy   * Design and implementation of PatchEnsemble strategy for improved classification accuracy
Line 68: Line 68:
   * Optimization of preprocessing pipeline and data augmentation strategies   * Optimization of preprocessing pipeline and data augmentation strategies
   * Public release of the ForamDeepSlice framework for scientific community use   * Public release of the ForamDeepSlice framework for scientific community use
-</color>+
  
 </WRAP> /* end column */ </WRAP> /* end column */