Update README.md

README.md

@@ -11,6 +11,10 @@ pipeline_tag: summarization
 
 **Authored by**: Xin Tie, Muheon Shin, Ali Pirasteh, Nevein Ibrahim, Zachary Huemann, Sharon M. Castellino, Kara Kelly, John Garrett, Junjie Hu, Steve Y. Cho, Tyler J. Bradshaw
 
+## 📑 Model Description
+
+This is the fine-tuned BART model for summarizing findings in PET reports. 
+
 ## 📑 Abstract
 
 Purpose: To determine if fine-tuned large language models (LLMs) can generate accurate, personalized impressions for whole-body PET reports. 
@@ -35,7 +39,7 @@ findings_info =
 Description: PET CT WHOLE BODY
 Radiologist: James
 Findings: Head/Neck: xxx Chest: xxx Abdomen/Pelvis: xxx Extremities/Musculoskeletal: xxx
-Indication: The patient is a [AGE]-year old [SEX] with a history of xxx
+Indication: The patient is a 60-year old male with a history of xxx
 """
 
 inputs = tokenizer(findings_info.replace('\n', ' '), padding="max_length", truncation=True, max_length=1024, return_tensors="pt")
@@ -59,12 +63,11 @@ output_str = tokenizer.batch_decode(outputs, skip_special_tokens=True) # get the
 ### 📊 Performance Metrics
 
 For detailed evaluation results, please refer to our paper.
-- **ROUGE-1**: 1
-- **ROUGE-2**: 2
-- **ROUGE-L**: 3
-- **BLEU**: 4
-- **CHRF**: 5
-- **BERTScore**: 6
+- **ROUGE-1**: 51.9
+- **ROUGE-2**: 29.6
+- **ROUGE-L**: 38.6
+- **BLEU**: 22.6
+- **BERTScore**: 0.735
 
 ### 💡 Highlights
 
@@ -78,5 +81,5 @@ The models were trained on NVIDIA A100 GPUs.
 ---
 
 ## 📁 Additional Resources
-- **Finetuned from model:** [Facebook's BART Large) (https://huggingface.co/google/t5-v1_1-large)
+- **Finetuned from model:** [Facebook's BART Large) (https://huggingface.co/facebook/bart-large)
 - **Codebase for training and inference:** [GitHub Repository](https://github.com/xtie97/PET-Report-Summarization)