Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline | |
| from transformers import AutoModelForSequenceClassification | |
| from PIL import Image | |
| import pytesseract | |
| import pdfplumber | |
| import torch | |
| # Load BART for zero-shot classification and Bio_ClinicalBERT for text summarization | |
| def load_models(): | |
| # Bio_ClinicalBERT for text summarization | |
| tokenizer_bert = AutoTokenizer.from_pretrained("emilyalsentzer/Bio_ClinicalBERT") | |
| model_bert = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn") | |
| summarizer = pipeline("summarization", model=model_bert, tokenizer=tokenizer_bert, device=0 if torch.cuda.is_available() else -1) | |
| # BART model for zero-shot classification | |
| classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli", device=0 if torch.cuda.is_available() else -1) | |
| return summarizer, classifier | |
| summarizer, classifier = load_models() | |
| # OCR for Image using Tesseract | |
| def extract_text_from_image(image): | |
| return pytesseract.image_to_string(image) | |
| # Extract text from PDF using pdfplumber | |
| def extract_text_from_pdf(pdf_file): | |
| text = "" | |
| with pdfplumber.open(pdf_file) as pdf: | |
| for page in pdf.pages: | |
| text += page.extract_text() or "" | |
| return text | |
| # Analyze and interpret the medical report | |
| def analyze_medical_text(text): | |
| # Summarize the extracted text using ClinicalBERT | |
| summarized_text = summarizer(text, max_length=100, min_length=30, do_sample=False)[0]['summary_text'] | |
| # Use BART for classification insights | |
| interpretation = classifier( | |
| summarized_text, | |
| candidate_labels=["normal", "abnormal", "urgent", "needs follow-up", "critical condition"], | |
| multi_label=True | |
| ) | |
| recommendations = classifier( | |
| summarized_text, | |
| candidate_labels=["medication", "dietary change", "exercise", "follow-up with a doctor", "lifestyle change"], | |
| multi_label=True | |
| ) | |
| return { | |
| "summary": summarized_text, | |
| "interpretation": interpretation['labels'], | |
| "recommendations": recommendations['labels'] | |
| } | |
| # Streamlit UI | |
| st.title("Medical Lab Report Analyzer with ClinicalBERT and BART") | |
| st.write("Upload your medical lab report (PDF/Image) to get a summary and actionable insights.") | |
| uploaded_file = st.file_uploader("Choose a PDF/Image file", type=["pdf", "png", "jpg", "jpeg"]) | |
| if uploaded_file: | |
| file_type = uploaded_file.type | |
| # Extract text based on file type | |
| if file_type == "application/pdf": | |
| with st.spinner("Extracting text from PDF..."): | |
| extracted_text = extract_text_from_pdf(uploaded_file) | |
| else: | |
| with st.spinner("Extracting text from Image..."): | |
| image = Image.open(uploaded_file) | |
| extracted_text = extract_text_from_image(image) | |
| # Analyze the extracted text | |
| if extracted_text.strip(): | |
| with st.spinner("Analyzing report using ClinicalBERT..."): | |
| result = analyze_medical_text(extracted_text) | |
| # Display the results | |
| st.subheader("Summary of the Report") | |
| st.write(result['summary']) | |
| st.subheader("Interpretation of Results") | |
| for label in result['interpretation']: | |
| st.write(f"- {label.capitalize()}") | |
| st.subheader("Actionable Recommendations") | |
| for rec in result['recommendations']: | |
| st.write(f"- {rec.capitalize()}") | |
| else: | |
| st.error("No text could be extracted. Please try with a different file.") | |