Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models

1. 1Pre-training a large language model on a general domain
2. 2Mid-training the model on a clinical domain to adapt to radiology report summarization
3. 3Fine-tuning the model on a specific radiology report dataset
4. 4Evaluating the model's performance on a test dataset to measure improvement

Data scientists and AI engineers on a healthcare team can benefit from this research to develop more accurate summarization models, improving physician productivity and patient care

💡 Mid-training of LLMs on a clinical domain can improve summarization performance over traditional pre-training and fine-tuning methods

📊 Mid-training LLMs improves radiology report summarization #AIinHealthcare