moudy93/radiology-summarization-t5-lora

Model Card for Model ID

Model Details

Model Description

• Developed by: MAHAMAT YOUSSOUF
• Funded by [optional]: Self-funded / Personal project
• Shared by [optional]: [More Information Needed]
• Model type: Transformer-based Text-to-Text model (T5-base fine-tuned for summarization)
• Language(s) (NLP): English
• License: Apache 2.0
• Finetuned from model [optional]: t5-base

Model Sources [optional]

• Repository: https://huggingface.co/moudy93/radiology-summarization-t5-lora
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

Summarization of radiology reports (e.g., converting long findings into concise clinical summaries)

Assisting healthcare NLP pipelines for report abstraction

Educational use for NLP model fine-tuning demonstrations

Downstream Use [optional]

Integration into clinical decision support systems (non-diagnostic support only)

Use in Retrieval-Augmented Generation (RAG) pipelines for medical QA

Preprocessing step for structured medical data extraction

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

The model inherits biases from the training dataset (radiology reports may reflect demographic or institutional bias)

Limited generalization outside radiology domain

May generate hallucinated or incomplete summaries

Not suitable for real-world clinical decision-making without expert oversight

Performance depends heavily on input formatting and report style

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. -Validate outputs with domain experts before use in healthcare contexts

-Avoid using outputs as standalone medical advice

-Monitor for hallucinations and factual inconsistencies

-Fine-tune further if adapting to different medical datasets

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import T5Tokenizer, T5ForConditionalGeneration

model_name = "https://huggingface.co/moudy93/radiology-summarization-t5-lora"

tokenizer = T5Tokenizer.from_pretrained(model_name) model = T5ForConditionalGeneration.from_pretrained(model_name)

input_text = "summarize: The lungs are clear. No focal consolidation, pleural effusion, or pneumothorax."

inputs = tokenizer(input_text, return_tensors="pt", truncation=True) outputs = model.generate(**inputs, max_length=64)

summary = tokenizer.decode(outputs[0], skip_special_tokens=True) print(summary)

Training Details

Training Data

"NLMCXR_reports" / "ecgen-radiology" Training Data

Dataset: Radiology report dataset (NLMCXR_reports/ecgen-radiology dataset)

Size: ~3995 samples

Input: Full radiology findings

Target: Corresponding summaries/impressions

Training Procedure

Preprocessing [optional]

Removed XML/HTML tags and special characters

Normalized whitespace and lowercased text

Added task prefix: "summarize:"

Tokenization using T5 tokenizer with truncation and padding

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

Held-out validation/test split from the same dataset 10%

Factors

-Input length variability

-Clinical terminology complexity

-Report structure differences

Metrics

ROUGE-1

ROUGE-2

ROUGE-L

Results

ROUGE-1: ~0.56

ROUGE-2: 0.46

ROUGE-L: 0.56

[More Information Needed]

Results

[More Information Needed]

Summary

-The model performs well on structured radiology reports

-Struggles with rare conditions or highly unstructured text

-Generates concise and readable summaries in most cases

Technical Specifications

Model Architecture and Objective

Encoder-decoder Transformer (T5)

Objective: Sequence-to-sequence text generation (summarization)

Compute Infrastructure

Single GPU training environment

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

-Python3

-PyTorch

-Hugging Face Transformers

-Datasets library

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

• PEFT 0.19.1