Update app.py

app.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 import streamlit as st
 import google.generativeai as genai
 import os
@@ -17,7 +18,7 @@ st.markdown(
     """
     ### Welcome to the AI Clinical Support Demonstrator
     This application demonstrates how Generative AI (Google Gemini) can be guided to assist with analyzing clinical information.
-    - **Agentic Text Analysis:** Simulates a structured reasoning process on clinical text to identify key findings, suggest considerations, and note information gaps.
+    - **Agentic Text Analysis:** Simulates a structured reasoning process on clinical text.
     - **Medical Image Analysis:** Provides descriptive observations of potential anomalies in medical images.
 
     **Crucially, this tool is for demonstration purposes ONLY. It does NOT provide medical advice or diagnosis.**
@@ -43,11 +44,10 @@ else:
     st.error("⚠️ Gemini API Key not found. Please configure `GEMINI_API_KEY` in Streamlit secrets or environment variables.", icon="🔑")
     st.stop()
 
-# Initialize models
+# Initialize models using Session State for persistence across reruns
 TEXT_MODEL_NAME = 'gemini-1.5-pro-latest' # For agentic text reasoning
-VISION_MODEL_NAME = 'gemini-1.5-flash'   # For image analysis
+VISION_MODEL_NAME = 'gemini-1.5-flash'   # For image analysis (or 'gemini-pro-vision')
 
-# Use session state to initialize models only once
 if 'models_initialized' not in st.session_state:
     st.session_state.models_initialized = False
     st.session_state.text_model = None
@@ -58,20 +58,17 @@ if genai_client_configured and not st.session_state.models_initialized:
         st.session_state.text_model = genai.GenerativeModel(TEXT_MODEL_NAME)
         st.session_state.vision_model = genai.GenerativeModel(VISION_MODEL_NAME)
         st.session_state.models_initialized = True
-        # Display success message subtly in sidebar perhaps, or remove if too noisy
-        # st.sidebar.success("AI Models Ready.", icon="✅")
     except Exception as e:
         st.error(f"Fatal Error: Failed to initialize Gemini models. Text: {TEXT_MODEL_NAME}, Vision: {VISION_MODEL_NAME}. Details: {e}", icon="💥")
         st.stop()
 elif not genai_client_configured:
-    # Should have stopped already, but defensive check
     st.error("AI Models could not be initialized due to configuration issues.", icon="🚫")
     st.stop()
 
 
 # --- Core AI Interaction Functions ---
 
-# Refined AGENTIC prompt for Text Analysis with formatting request
+# AGENTIC prompt for Text Analysis (Remains the same as previous good version)
 AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE = """
 **Simulated Clinical Reasoning Agent Task:**
 
@@ -83,26 +80,26 @@ AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE = """
 
 **Simulated Agentic Steps (Perform sequentially):**
 
-1.  **Information Extraction & Structuring:**
+1.  **## 1. Information Extraction & Structuring:**
     *   Key Demographics (Age, Sex if provided).
     *   Primary Symptoms/Signs.
     *   Relevant Medical History.
     *   Pertinent Negatives (if mentioned).
 
-2.  **Differential Considerations Generation:**
+2.  **## 2. Differential Considerations Generation:**
     *   Based *only* on Step 1, list **potential differential considerations** (possible conditions).
     *   **Use cautious language:** "could be consistent with," "warrants consideration," "less likely but possible." **AVOID definitive statements.**
     *   Briefly justify each consideration based on findings.
 
-3.  **Information Gap Analysis:**
+3.  **## 3. Information Gap Analysis:**
     *   Identify critical missing information (e.g., lab results, imaging, exam specifics, duration/onset).
 
-4.  **Suggested Next Steps for Investigation (for Clinician):**
+4.  **## 4. Suggested Next Steps for Investigation (for Clinician):**
     *   Propose logical next steps a **healthcare professional might consider**.
     *   Categorize (e.g., Further History, Exam Points, Labs, Imaging).
     *   Frame as *suggestions* (e.g., "Consider ordering...", "Assessment of X may be informative").
 
-5.  **Mandatory Disclaimer:** Conclude with: "This AI-generated analysis is for informational support only. It is **NOT** a diagnosis and cannot replace the judgment of a qualified healthcare professional."
+5.  **## 5. Mandatory Disclaimer:** Conclude with: "This AI-generated analysis is for informational support only. It is **NOT** a diagnosis and cannot replace the judgment of a qualified healthcare professional."
 
 **Input Clinical Information:**
 ---
@@ -112,21 +109,46 @@ AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE = """
 **Agentic Analysis:**
 """
 
-# Refined prompt for Image Analysis with formatting request
+# REFINED prompt for Image Analysis - More explicit instructions based on good example
 IMAGE_ANALYSIS_PROMPT_TEMPLATE = """
 **Medical Image Analysis Request:**
 
-**Context:** Analyze the provided medical image. User may provide additional context or questions.
+**Context:** Analyze the provided medical image objectively based *only* on visual information. User may provide additional context or questions.
 
-**Output Format:** Please structure your response using Markdown headings for each step (e.g., `## 1. Visible Structures`).
+**Output Format:** Structure your response precisely using the following Markdown headings. Be factual and descriptive.
 
 **Task:**
 
-1.  **Describe Visible Structures:** Briefly describe main anatomical structures.
-2.  **Identify Potential Anomalies:** Point out areas that *appear* abnormal or deviate from typical presentation (e.g., "potential opacity," "altered signal intensity," "possible asymmetry"). Use cautious, descriptive language. **This is not a definitive finding.**
-3.  **Correlate with User Prompt (if provided):** Address specific user questions based *only* on visual information. State if the image cannot answer the question.
-4.  **Limitations:** State that image quality, view, lack of clinical context, and the AI's nature limit analysis.
-5.  **Mandatory Disclaimer:** Explicitly state this is AI visual analysis, not radiological interpretation or diagnosis, requiring review by a qualified professional with clinical context.
+1.  **## 1. Visible Structures:**
+    *   Identify the likely imaging modality and view (e.g., PA Chest Radiograph, Axial CT slice of the abdomen).
+    *   Briefly list the main anatomical structures clearly visible (e.g., ribs, heart silhouette, lung fields, diaphragm).
+
+2.  **## 2. Identify Potential Anomalies / Key Findings:**
+    *   Carefully examine the image for any areas that *appear* abnormal or deviate significantly from typical presentation.
+    *   **Use extremely cautious, descriptive language.** Describe *what* you see (e.g., "area of increased opacity," "region of lucency," "asymmetry observed in X," "potential contour abnormality," "patchy distribution").
+    *   **Specify location accurately** using standard anatomical terms (e.g., "right lower lung zone," "left hilum," "hepatic flexure region").
+    *   **Crucially, AVOID interpretive or diagnostic terms** (DO NOT use words like "pneumonia," "tumor," "fracture," "infection," "inflammation"). Stick strictly to visual observation.
+    *   If relevant and clearly discernible, mention the **absence** of certain major expected abnormalities (pertinent negatives, e.g., "No obvious large pneumothorax identified," "Bowel gas pattern appears unremarkable in visualized areas").
+    *   Compare sides if applicable and relevant differences are seen (e.g., "Left lung field demonstrates greater transparency compared to the right").
+
+3.  **## 3. Correlate with User Prompt (if provided):**
+    *   Address specific user questions based *strictly* on the visual information identifiable in the image.
+    *   If the image cannot visually answer the question (e.g., requires clinical context, different view), state that clearly.
+    *   If no user prompt was provided, state "N/A".
+
+4.  **## 4. Limitations of this AI Analysis:**
+    *   **Explicitly list the following limitations inherent to this analysis:**
+        *   Dependency on the **quality, resolution, and potential artifacts** of the provided image.
+        *   Analysis is restricted to the **single view/slice(s)** provided; other areas are not assessed.
+        *   **Complete lack of clinical context:** Patient history, symptoms, physical exam findings, and laboratory results are unknown and not considered.
+        *   **Absence of prior imaging studies:** Comparisons over time are not possible, which is often crucial for interpretation.
+        *   The AI functions purely on **visual pattern recognition**; it does not perform clinical reasoning or differential diagnosis.
+
+5.  **## 5. Mandatory Disclaimer:**
+    *   State clearly: This is an AI-generated visual analysis intended for informational and demonstration purposes **ONLY**.
+    *   It is **NOT** a radiological interpretation or medical diagnosis.
+    *   It **CANNOT** substitute for a comprehensive evaluation and interpretation by a qualified radiologist or physician integrating full clinical information.
+    *   Any potential observations noted herein **MUST** be correlated with clinical findings and reviewed/confirmed by qualified healthcare professionals.
 
 **User's Additional Context/Question (if any):**
 ---
@@ -136,68 +158,76 @@ IMAGE_ANALYSIS_PROMPT_TEMPLATE = """
 **Image Analysis:**
 """
 
+# --- Backend Functions ---
+
 def run_agentic_text_analysis(text_input: str) -> Tuple[Optional[str], Optional[str]]:
     """Sends clinical text to the configured text model for simulated agentic analysis."""
     if not text_input or not text_input.strip():
         return None, "Input text cannot be empty."
     if not st.session_state.models_initialized or not st.session_state.text_model:
-         return None, "Text analysis model not initialized."
+         return None, "Text analysis model not initialized. Please refresh or check configuration."
 
     try:
         prompt = AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE.format(text_input=text_input)
-        response = st.session_state.text_model.generate_content(prompt)
+        response = st.session_state.text_model.generate_content(prompt) # Use model from session state
 
+        # Handle response variations
         if response.parts:
             return response.text, None
         elif response.prompt_feedback.block_reason:
-             return None, f"Analysis blocked by safety filters: {response.prompt_feedback.block_reason.name}. Review input."
+             return None, f"Analysis blocked by safety filters: {response.prompt_feedback.block_reason.name}. Please review or revise input."
         else:
              candidate = response.candidates[0] if response.candidates else None
              if candidate and candidate.finish_reason != "STOP":
-                 return None, f"Analysis stopped prematurely. Reason: {candidate.finish_reason.name}."
+                 # If stopped for reasons other than normal completion (e.g., length, safety)
+                 return None, f"Analysis stopped prematurely. Reason: {candidate.finish_reason.name}. Input might be too long or triggered other limits."
              else:
-                 return None, "Received an empty or unexpected response from the AI model."
+                 # General case for empty or unexpected response
+                 return None, "Received an empty or unexpected response from the AI model for text analysis."
 
     except Exception as e:
-        print(f"ERROR in run_agentic_text_analysis: {e}") # Basic server-side log
-        st.error("An error occurred during text analysis.", icon="🚨") # User-facing error
-        return None, "An internal error occurred during text analysis. Please try again later."
+        print(f"ERROR in run_agentic_text_analysis: {e}") # Log for server/dev console
+        st.error("An error occurred during text analysis.", icon="🚨") # User-facing generic error
+        return None, "An internal error occurred during text analysis. Please try again later or contact support if the issue persists."
 
 def analyze_medical_image(image_file: Any, user_prompt: str = "") -> Tuple[Optional[str], Optional[str]]:
-    """Sends a medical image to the configured vision model for analysis."""
+    """Sends a medical image to the configured vision model for analysis using the refined prompt."""
     if not image_file:
         return None, "Image file cannot be empty."
     if not st.session_state.models_initialized or not st.session_state.vision_model:
-         return None, "Image analysis model not initialized."
+         return None, "Image analysis model not initialized. Please refresh or check configuration."
 
     try:
         try:
+            # Open and prepare the image
             image = Image.open(image_file)
-            # Convert to RGB ensure compatibility, common requirement for vision models
             if image.mode != 'RGB':
-                 image = image.convert('RGB')
+                 image = image.convert('RGB') # Ensure RGB format
         except Exception as img_e:
-             return None, f"Error opening or processing the uploaded image file: {img_e}"
+             return None, f"Error opening or processing the uploaded image file: {img_e}. Please ensure it's a valid image."
 
+        # Prepare the prompt using the refined template
         prompt_text = IMAGE_ANALYSIS_PROMPT_TEMPLATE.format(user_prompt=user_prompt if user_prompt else "N/A")
-        model_input = [prompt_text, image]
-        response = st.session_state.vision_model.generate_content(model_input)
+        model_input = [prompt_text, image] # Combine text prompt and image data
+
+        response = st.session_state.vision_model.generate_content(model_input) # Use model from session state
 
+        # Handle response variations
         if response.parts:
             return response.text, None
         elif response.prompt_feedback.block_reason:
-            return None, f"Image analysis blocked by safety filters: {response.prompt_feedback.block_reason.name}. This may relate to sensitive content policies."
+            return None, f"Image analysis blocked by safety filters: {response.prompt_feedback.block_reason.name}. This might relate to sensitive content policies regarding medical images."
         else:
              candidate = response.candidates[0] if response.candidates else None
              if candidate and candidate.finish_reason != "STOP":
-                 return None, f"Image analysis stopped prematurely. Reason: {candidate.finish_reason.name}."
+                 return None, f"Image analysis stopped prematurely. Reason: {candidate.finish_reason.name}. Input might be too complex or triggered other limits."
              else:
                  return None, "Received an empty or unexpected response from the AI model for image analysis."
 
     except Exception as e:
-        print(f"ERROR in analyze_medical_image: {e}") # Basic server-side log
-        st.error("An error occurred during image analysis.", icon="🖼️") # User-facing error
-        return None, "An internal error occurred during image analysis. Please try again later."
+        print(f"ERROR in analyze_medical_image: {e}") # Log for server/dev console
+        st.error("An error occurred during image analysis.", icon="🖼️") # User-facing generic error
+        return None, "An internal error occurred during image analysis. Please try again later or contact support if the issue persists."
 
 
 # --- Streamlit User Interface ---
@@ -208,7 +238,6 @@ def main():
     st.caption(f"Utilizing: Text Model ({TEXT_MODEL_NAME}), Vision Model ({VISION_MODEL_NAME})")
 
     # --- CRITICAL DISCLAIMER ---
-    # Positioned prominently after title/intro
     st.warning(
         """
         **🔴 IMPORTANT SAFETY & USE DISCLAIMER 🔴**
@@ -236,9 +265,10 @@ def main():
     # --- Main Area Layout (Input and Output Columns) ---
     col1, col2 = st.columns(2)
 
-    analysis_result = None # Initialize results variables for this run
+    analysis_result = None # Reset results variables for this run
     error_message = None
     output_header = "Analysis Results" # Default header
+    analyze_button_key = None # Initialize key variable
 
     # --- Column 1: Input Area ---
     with col1:
@@ -254,12 +284,12 @@ def main():
                 placeholder="Example: 68yo male, sudden SOB & pleuritic chest pain post-flight. HR 110, SpO2 92% RA. No known cardiac hx...",
                 key="text_input_area"
             )
-            analyze_button_key = "analyze_text_button"
+            analyze_button_key = "analyze_text_button" # Set key for this branch
             analyze_button_label = "▶️ Run Agentic Text Analysis"
 
             if st.button(analyze_button_label, key=analyze_button_key, type="primary"):
                 if text_input:
-                    with st.spinner("🧠 Simulating agentic reasoning..."):
+                    with st.spinner("🧠 Simulating agentic reasoning... Please wait."):
                         analysis_result, error_message = run_agentic_text_analysis(text_input)
                     output_header = "Simulated Agentic Analysis Output"
                 else:
@@ -278,7 +308,7 @@ def main():
                 placeholder="Example: 'Describe findings in the lung fields' or 'Any visible fractures?'",
                 key="image_prompt_input"
             )
-            analyze_button_key = "analyze_image_button"
+            analyze_button_key = "analyze_image_button" # Set key for this branch
             analyze_button_label = "🖼️ Analyze Medical Image"
 
             if image_file:
@@ -287,7 +317,7 @@ def main():
 
             if st.button(analyze_button_label, key=analyze_button_key, type="primary"):
                 if image_file:
-                    with st.spinner("👁️ Analyzing image..."):
+                    with st.spinner("👁️ Analyzing image... Please wait."):
                         analysis_result, error_message = analyze_medical_image(image_file, user_image_prompt)
                     output_header = "Medical Image Analysis Output"
                 else:
@@ -297,30 +327,33 @@ def main():
     with col2:
         st.header(output_header)
 
-        # Display results or errors if an analysis was attempted
-        # Check if button was pressed and corresponding result/error exists
-        button_pressed = st.session_state.get(analyze_button_key, False) if 'analyze_button_key' in locals() else False
+        # Determine if analysis was attempted in this run using the correct button key
+        button_pressed = st.session_state.get(analyze_button_key, False) if analyze_button_key else False
 
-        if button_pressed and (analysis_result or error_message):
-             if error_message:
+        if button_pressed:
+            # Only display results if the corresponding button was pressed AND generated output/error
+            if error_message:
                  st.error(f"Analysis Failed: {error_message}", icon="❌")
-             elif analysis_result:
-                 # Use st.markdown to render potential formatting from AI
-                 st.markdown(analysis_result)
-        elif not button_pressed :
+            elif analysis_result:
+                 # Use st.markdown to render potential formatting (like headings) from AI
+                 st.markdown(analysis_result, unsafe_allow_html=False) # Keep unsafe_allow_html=False for security
+            # No explicit 'else' needed here; if button pressed but no result/error, likely handled by input validation warning
+        else:
+            # Default placeholder message if no analysis attempted yet in this run
             st.info("Analysis results will appear here after providing input and clicking the corresponding analysis button.")
-        # Add a condition for button pressed but no input provided (already handled by st.warning in col1)
 
 
     # --- Sidebar Explanations ---
     st.sidebar.markdown("---")
     st.sidebar.header("About The Prompts")
     with st.sidebar.expander("View Agentic Text Prompt Structure", icon="📄"):
-        st.markdown(f"```plaintext\n{AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE.split('---')[0]} ... [Input Text] ...\n```")
+        # Show only the instructive part of the prompt template
+        st.code(AGENTIC_TEXT_ANALYSIS_PROMPT_TEMPLATE.split('---')[0] + "...", language='markdown')
         st.caption("Guides the AI through structured reasoning steps for text.")
     with st.sidebar.expander("View Image Analysis Prompt Structure", icon="🖼️"):
-        st.markdown(f"```plaintext\n{IMAGE_ANALYSIS_PROMPT_TEMPLATE.split('---')[0]} ... [User Prompt] ...\n```")
-        st.caption("Guides the AI to describe visual features and potential anomalies in images.")
+        # Show only the instructive part of the prompt template
+        st.code(IMAGE_ANALYSIS_PROMPT_TEMPLATE.split('---')[0] + "...", language='markdown')
+        st.caption("Guides the AI to provide cautious, descriptive visual observations for images.")
 
     st.sidebar.markdown("---")
     st.sidebar.error(
@@ -334,7 +367,7 @@ if __name__ == "__main__":
     if st.session_state.models_initialized:
         main()
     else:
-        # If models failed to initialize, errors would have been shown already.
-        # We might add a placeholder or further message here if needed.
-        st.info("Waiting for model initialization...") # Or check specific errors if needed
-        # The script might stop earlier if initialization fails critically.
+        # Errors during initialization should have been shown and stopped execution.
+        # This path might be reached if initialization is still pending in an async setup (not the case here)
+        # or if there was a non-fatal init issue not caught by st.stop().
+        st.info("Waiting for AI model initialization or resolving configuration issues...")