mao1207 commited on
Commit
08a10c0
·
verified ·
1 Parent(s): 05592eb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -5
README.md CHANGED
@@ -1,13 +1,11 @@
1
  ---
2
  license: mit
3
- ---
4
- Certainly! Below is a modified version of the text you provided, structured to serve as a model card for the "BioMed-VITAL" model. This format typically includes sections that outline the model's purpose, data used for training, and performance metrics:
5
-
6
- ---
7
 
8
  #### Overview
9
  BioMed-VITAL is a multimodal foundation model specifically tuned for biomedical applications. It leverages visual and textual data to improve understanding and reasoning within the biomedical domain.
10
 
 
 
11
  #### Model Training
12
  The training of BioMed-VITAL involved two key stages, both incorporating clinician preferences to ensure the relevance and quality of the training data:
13
 
@@ -19,4 +17,14 @@ The training of BioMed-VITAL involved two key stages, both incorporating clinici
19
  The effectiveness of BioMed-VITAL was demonstrated through significant improvements in two key areas:
20
 
21
  - **Open Visual Chat:** The model showed a relative improvement of 18.5%, indicating enhanced capabilities in engaging in visual dialogues pertinent to biomedical contexts.
22
- - **Medical Visual Question Answering (VQA):** BioMed-VITAL achieved a win rate of up to 81.73% in this domain, showcasing its superior performance in interpreting and responding to complex medical imagery and queries.
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
 
 
 
 
3
 
4
  #### Overview
5
  BioMed-VITAL is a multimodal foundation model specifically tuned for biomedical applications. It leverages visual and textual data to improve understanding and reasoning within the biomedical domain.
6
 
7
+ ![Biomed-VITAL Framework Overview](https://raw.githubusercontent.com/BioMed-VITAL/BioMed-VITAL.github.io/main/images/updated_instruction_data_framework_00.png)
8
+
9
  #### Model Training
10
  The training of BioMed-VITAL involved two key stages, both incorporating clinician preferences to ensure the relevance and quality of the training data:
11
 
 
17
  The effectiveness of BioMed-VITAL was demonstrated through significant improvements in two key areas:
18
 
19
  - **Open Visual Chat:** The model showed a relative improvement of 18.5%, indicating enhanced capabilities in engaging in visual dialogues pertinent to biomedical contexts.
20
+ - **Medical Visual Question Answering (VQA):** BioMed-VITAL achieved a win rate of up to 81.73% in this domain, showcasing its superior performance in interpreting and responding to complex medical imagery and queries.
21
+
22
+ ## Case Study
23
+ ### Biomedical Visual Instruction-Following Example
24
+ ![](https://raw.githubusercontent.com/BioMed-VITAL/BioMed-VITAL.github.io/main/images/case_update2_00.png)
25
+ ### Biomedical VQA Benchmark
26
+ ![](https://raw.githubusercontent.com/BioMed-VITAL/BioMed-VITAL.github.io/main/images/case5_updated_00.png)
27
+ ### Clinician Annotation Examples
28
+ ![](https://raw.githubusercontent.com/BioMed-VITAL/BioMed-VITAL.github.io/main/images/appendixH_00.png)
29
+
30
+ For more information, access to the dataset, and to contribute, please visit our [GitHub repository](https://github.com/yourrepo/biomed-vital).