Kentucky-Open-Science
/

NP-GIANT

@@ -7,6 +7,7 @@ tags:
 - neuropathology
 - image-classification
 - university-of-kentucky
 license: apache-2.0
 datasets:
 - BDSA-neuropathology
@@ -28,7 +29,7 @@ This model is a Vision Transformer adapted for neuropathology tasks, developed u
 ## Model Details
 * **Model Type:** Vision Transformer (ViT) for neuropathology.
-* **Developed by:** Center for Applied Artificial Intelligence (CAAI)
 * **Model Date:** 10/2025
 * **Base Model Architecture:** Dinov2-with-registers-giant (https://huggingface.co/facebook/dinov2-with-registers-giant)
 * **Input:** Image (224x224).
@@ -52,8 +53,8 @@ This model is intended for research purposes in the field of neuropathology.
 * **Dataset(s):** The model was trained on data from the University of Kentucky.
     * **Name/Identifier:** UK Alzheimer's Disease Center Neuropathology Whole Slide Image Cohort [BDSA TEST v1.0]
-    * **Source:** [UK-ADRC Neuropathology Lab at the University of Kentucky University of Kentucky](https://neuropathlab.createuky.net/)
-    * **Description:** The dataset contained 57 hole slide images (WSIs) of human post-mortem brain tissue sections. Sections were stained with Hematoxylin and Eosin (H&E).
     * **Preprocessing:** WSIs were tiled into non-overlapping 224x224 pixel patches at multiple magnification levels (40x, 10x, 2.5x, and 1.25x). For each magnification level, a maximum of 1000 tiles per annotation label were extracted to ensure balanced representation across pathological features.
     * **Annotation :** "Regions of interest (ROIs) for Gray Matter, White Matter, Leptomeninges, Exclude and Superficial Cortex were annotated. Annotations completed by Allison Neltner using a [web-based tool](https://github.com/pitt-bdsa/webapps) developed my Thomas Pearce, MD (UMPC).

 - neuropathology
 - image-classification
 - university-of-kentucky
+- emory-university
 license: apache-2.0
 datasets:
 - BDSA-neuropathology
 ## Model Details
 * **Model Type:** Vision Transformer (ViT) for neuropathology.
+* **Developed by:** [Center for Applied Artificial Intelligence (CAAI)](https://caai.ai.uky.edu/) and [Gutman Lab](https://winshipcancer.emory.edu/profiles/gutman-david.php)
 * **Model Date:** 10/2025
 * **Base Model Architecture:** Dinov2-with-registers-giant (https://huggingface.co/facebook/dinov2-with-registers-giant)
 * **Input:** Image (224x224).
 * **Dataset(s):** The model was trained on data from the University of Kentucky.
     * **Name/Identifier:** UK Alzheimer's Disease Center Neuropathology Whole Slide Image Cohort [BDSA TEST v1.0]
+    * **Source:** Gutman Lab and [UK-ADRC Neuropathology Lab at the University of Kentucky University of Kentucky](https://neuropathlab.createuky.net/)
+    * **Description:** The dataset contained 57 whole slide images (WSIs) of human post-mortem brain tissue sections from UK-ADRC and N patches from the Gutman Lab.  Sections were stained with Hematoxylin and Eosin (H&E).
     * **Preprocessing:** WSIs were tiled into non-overlapping 224x224 pixel patches at multiple magnification levels (40x, 10x, 2.5x, and 1.25x). For each magnification level, a maximum of 1000 tiles per annotation label were extracted to ensure balanced representation across pathological features.
     * **Annotation :** "Regions of interest (ROIs) for Gray Matter, White Matter, Leptomeninges, Exclude and Superficial Cortex were annotated. Annotations completed by Allison Neltner using a [web-based tool](https://github.com/pitt-bdsa/webapps) developed my Thomas Pearce, MD (UMPC).