Deploy FastAPI teeth detection API

README.md

@@ -1,11 +0,0 @@
----
-title: Teeth Detection Api
-emoji: 👀
-colorFrom: red
-colorTo: blue
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,1325 @@
+
+# from fastapi import FastAPI, File, Path
+# from fastapi.middleware.cors import CORSMiddleware
+# import uvicorn
+# import numpy as np
+# from io import BytesIO
+# from PIL import Image
+# import tensorflow as tf
+# from tensorflow.keras.applications.efficientnet import preprocess_input  # type: ignore
+# import uuid
+# from fastapi import File, UploadFile, Query, HTTPException
+# from fastapi.responses import JSONResponse
+# import time
+
+# # HuggingFace
+# from transformers import pipeline
+# import torch
+# import json
+# import os
+# from pathlib import Path  
+# from datetime import datetime
+
+# BASE_DIR = Path(__file__).parent
+# KNOWLEDGE_BASE_PATH = BASE_DIR / "knowledge_base" / "clinical_rules.json"
+
+
+
+# # ============================================================
+# # CONFIGURATION
+# # ============================================================
+# IMAGE_SIZE = 224
+
+# # Local TensorFlow models
+# BINARY_MODEL_PATH = r"D:\Colab-python\teethDises\new\api\models\model_2.keras"
+# DISEASE_MODEL_PATH = r"D:\Colab-python\teethDises\new\api\models\LAST_model_efficent.h5"
+
+# # BINARY_MODEL_PATH = "./model_2.keras"
+# # DISEASE_MODEL_PATH = "./LAST_model_efficent.h5"
+
+# import os
+# BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+# MODELS_DIR = os.path.join(BASE_DIR, "models")
+# BINARY_MODEL_PATH = os.path.join(MODELS_DIR, "model_2.keras")
+# DISEASE_MODEL_PATH = os.path.join(MODELS_DIR, "LAST_model_efficent.h5")
+
+# print(os.path.exists(BINARY_MODEL_PATH))
+# print(os.path.isfile(BINARY_MODEL_PATH))
+
+
+# # HuggingFace Teeth Health Model
+# HF_TEETH_HEALTH_MODEL = "steven123/Check_GoodBad_Teeth"
+
+# DEVICE = 0 if torch.cuda.is_available() else -1
+
+# BINARY_CLASSES = ["not_teath", "teath"]
+# TEETH_HEALTH_CLASSES = ["Good Teeth", "Bad Teeth"]
+
+# DISEASE_CLASSES = [
+#     "Calculus",
+#     "Dental Caries",
+#     "Gingivitis",
+#     "Mouth Ulcer",
+#     "Tooth Discoloration",
+#     "Hypodontia"
+# ]
+
+
+# # ============================================================
+# # LOAD KNOWLEDGE BASE
+# # ============================================================
+# def load_knowledge_base():
+#     """تحميل قاعدة المعرفة من ملف JSON"""
+#     try:
+#         with open(KNOWLEDGE_BASE_PATH, 'r', encoding='utf-8') as f:
+#             return json.load(f)
+#     except FileNotFoundError:
+#         print(f"⚠️ Warning: Knowledge base file not found at {KNOWLEDGE_BASE_PATH}")
+#         return {"diseases": {}, "general_rules": {}}
+
+# knowledge_base_data = load_knowledge_base()
+# diseases_db = knowledge_base_data.get("diseases", {})
+# general_rules = knowledge_base_data.get("general_rules", {})
+
+
+
+# # ============================================================
+# # APPLICATION INITIALIZATION
+# # ============================================================
+# app = FastAPI(
+#     title="Integrated Teeth Detection System",
+#     description="Binary Detection → Teeth Health → Disease Classification",
+#     version="1.2.0"
+# )
+
+# app.add_middleware(
+#     CORSMiddleware,
+#     allow_origins=["*"],
+#     allow_credentials=True,
+#     allow_methods=["*"],
+#     allow_headers=["*"],
+# )
+
+# import os
+# print("exists:", os.path.exists(BINARY_MODEL_PATH))
+# print("isfile:", os.path.isfile(BINARY_MODEL_PATH))
+
+# # ============================================================
+# # # MODEL LOADING
+# # ============================================================
+# print("[INFO] Loading TensorFlow models...")
+# BINARY_MODEL = tf.keras.models.load_model(BINARY_MODEL_PATH)
+# DISEASE_MODEL = tf.keras.models.load_model(DISEASE_MODEL_PATH)
+
+# print("[INFO] Loading HuggingFace Teeth Health model...")
+# TEETH_HEALTH_MODEL = pipeline(
+#     "image-classification",
+#     model=HF_TEETH_HEALTH_MODEL,
+#     device=DEVICE
+# )
+
+# print("[INFO] All models loaded successfully")
+
+# # ============================================================
+# # IMAGE PREPROCESSING
+# # ============================================================
+# def load_image(image_bytes: bytes) -> Image.Image:
+#     return Image.open(BytesIO(image_bytes)).convert("RGB")
+
+# def preprocess_for_binary(image_bytes: bytes) -> np.ndarray:
+#     image = load_image(image_bytes)
+#     image = image.resize((IMAGE_SIZE, IMAGE_SIZE))
+#     image = np.array(image).astype(np.float32) 
+#     return image
+
+# def preprocess_for_disease(image_bytes: bytes) -> np.ndarray:
+#     image = load_image(image_bytes)
+#     image = image.resize((IMAGE_SIZE, IMAGE_SIZE))
+#     image = np.array(image).astype(np.float32)
+#     image = preprocess_input(image)
+#     return image
+    
+# def assess_urgency(result):
+#     return {
+#         "level": result.get("urgency_level", "low"),
+#         "message": result.get("urgency_message", "")
+#     }
+# def combine_advice(result):
+#     combined = []
+#     seen = set()
+
+#     for advice in result.get("personalized_home_care", []):
+#         if advice not in seen:
+#             combined.append(advice)
+#             seen.add(advice)
+
+#     return combined[:4]
+
+
+# #===========================================================
+# # RECOMMENDATION ENGINE
+# # ============================================================
+# def add_unique_advice(advice_list, target_list):
+#     """
+#     Adds advice to target_list if not already present (prevents exact duplicates)
+#     """
+#     if not advice_list:
+#         return
+#     for advice in advice_list:
+#         if advice and advice not in target_list:
+#             target_list.append(advice)
+# #============================================================'
+# #  Advanced weighted recommendation
+# #============================================================
+# def get_weighted_recommendations(top_predictions, age: int, pain_level: int, bleeding: bool):
+#     result = {
+#         "timestamp": datetime.now().isoformat(),
+#         "primary_condition": None,
+#         "overall_risk_score": 0.0,
+#         "risk_category": "Early Stage",
+#         "clinical_overview": [],
+#         "priority_treatment_plan": [],
+#         "supportive_treatments": [],
+#         "personalized_home_care": {"essential": [], "recommended": [], "avoid": []},
+#         "follow_up_recommendation": [],
+#         "requires_dentist": False,
+#         "urgency_level": "low",
+#         "urgency_message": ""
+#     }
+
+#     if not top_predictions:
+#         return result
+
+#     severity_scale = {"high": 3, "medium": 2, "moderate":2, "mild": 1, "low": 1,"structural": 2}
+#     urgency_scale = {"high": 3, "medium": 2, "low": 1}
+#     confidence_rules = general_rules.get("confidence_weighting", {})
+
+#     filtered_predictions = [p for p in top_predictions if p.get("confidence", 0) > 0.05]
+#     if not filtered_predictions:
+#         return result
+
+#     total_conf = sum(p["confidence"] for p in filtered_predictions)
+#     total_risk_score = 0
+#     detected_conditions = []
+
+#     for pred in filtered_predictions:
+#         disease = pred["class"]
+#         confidence = pred["confidence"]
+#         weight = confidence / total_conf if total_conf > 0 else 0
+
+#         if disease not in diseases_db:
+#             continue
+
+#         detected_conditions.append(disease)
+#         disease_info = diseases_db[disease]
+#         base = disease_info.get("base_info", {})
+#         treatments = disease_info.get("treatment_options", {}).get("primary", [])
+#         home_advice = disease_info.get("home_advice", {})
+
+#         # 🔹 Severity & urgency
+#         severity = base.get("severity", "low")
+#         urgency = base.get("urgency", "low")
+#         severity_value = severity_scale.get(severity, 1)
+#         urgency_value = urgency_scale.get(urgency, 1)
+        
+#         # --- Symptom-based adjustment (Improved Clinical Logic) ---
+#         bleeding_factor = 1 if bleeding else 0
+#         disease_category = base.get("category", "")
+
+#         # Option 1: Direct multiplier (pain_level 0-10)
+#         if disease_category in ["tooth_decay", "inflammatory"]:
+#              severity_value += pain_level * 0.3   
+#              urgency_value += pain_level * 0.3
+#         elif disease_category in ["soft_tissue", "mineral_deposit","developmental","aesthetic"]:
+#              severity_value += pain_level * 0.1   
+#              urgency_value += pain_level * 0.1 
+
+#         # Bleeding impact
+#         if disease_category in ["inflammatory", "tooth_decay"]:
+#             urgency_value += bleeding_factor * 1.5
+#         elif disease_category in ["soft_tissue", "mineral_deposit","developmental","aesthetic"]:
+#             urgency_value += bleeding_factor * 0.4  
+
+#         # Age sensitivity
+#         if age < 12 or age > 65:
+#             urgency_value += 0.5
+
+#         # حساب عامل الثقة بناءً على confidence
+#         if confidence >= 0.8:
+#             confidence_factor = 1.0  
+#         elif confidence >= 0.5:
+#             confidence_factor = confidence_rules.get("medium", 0.5)
+#         else:
+#             confidence_factor = confidence_rules.get("low", 0.2)
+        
+
+
+#         disease_risk = ((severity_value * 0.6 + urgency_value * 0.4) * weight * confidence_factor)
+#         total_risk_score += disease_risk
+
+#         # Treatment level
+#         if severity == "high":
+#             treatment_level = "aggressive"
+#         elif severity in ["medium", "structural"]:
+#             treatment_level = "moderate"
+#         else:
+#             treatment_level = "conservative"
+
+#         # Clinical overview
+#         result["clinical_overview"].append({
+#             "condition": disease,
+#             "confidence_percent": round(confidence * 100, 2),
+#             "impact_weight": round(weight, 3),
+#             "severity": severity,
+#             "urgency": urgency,
+#             "treatment_level": treatment_level
+#         })
+
+#         # Treatment plans
+#         if treatment_level == "aggressive":
+#             for t in treatments:
+#                 add_unique_advice([t], result["priority_treatment_plan"])
+#         elif treatment_level == "moderate":
+#             for t in treatments[:1]:
+#                 add_unique_advice([t], result["supportive_treatments"])
+
+#         # --- Home care advice (Compact & Professional) ---
+#         essential_advice = home_advice.get("essential", [])[:2]
+#         recommended_advice = home_advice.get("recommended", [])[:2]
+#         avoid_advice = home_advice.get("avoid", [])[:2]
+
+#         add_unique_advice(essential_advice, result["personalized_home_care"]["essential"])
+#         add_unique_advice(recommended_advice, result["personalized_home_care"]["recommended"])
+#         add_unique_advice(avoid_advice, result["personalized_home_care"]["avoid"])
+
+#         # Build-up advice
+#         build_up = disease_info.get("build_up_recommendation", {})
+#         if build_up.get("applicable", False):
+#             conditions = build_up.get("conditions", {})
+#             for cond in conditions.values():
+#                 if confidence >= cond.get("confidence_threshold", 0.3):
+#                     materials = ", ".join(cond.get("materials", []))
+#                     reason = cond.get("reason", "")
+#                     advice_text = f"Consider build-up using {materials} ({reason})"
+#                     add_unique_advice([advice_text], result["personalized_home_care"]["recommended"])
+
+#         # Dentist requirement
+#         if base.get("requires_dentist", False):
+#             result["requires_dentist"] = True
+
+#         # Follow up
+#         follow_up = disease_info.get("follow_up")
+#         if follow_up:
+#             add_unique_advice([follow_up], result["follow_up_recommendation"])
+
+#     # Normalize risk
+#     normalized_risk = min(total_risk_score, 5)
+#     result["overall_risk_score"] = round(normalized_risk, 2)
+
+#     # Risk Category
+#     if normalized_risk >= 4:
+#         result["risk_category"] = "Critical"
+#     elif normalized_risk >= 3:
+#         result["risk_category"] = "Advanced"
+#     elif normalized_risk >= 2:
+#         result["risk_category"] = "Progressive"
+#     else:
+#         result["risk_category"] = "Early Stage"
+
+#     # Urgency
+#     if normalized_risk >= 3.5:
+#         result["urgency_level"] = "high"
+#         result["urgency_message"] = "Immediate dental consultation required (within 24-48 hours)."
+#     elif normalized_risk >= 2.0:
+#         result["urgency_level"] = "medium"
+#         result["urgency_message"] = "Dental appointment recommended within 1-4 weeks."
+#     else:
+#         result["urgency_level"] = "low"
+#         result["urgency_message"] = "Maintain oral hygiene and monitor symptoms."
+
+#     # Multi-disease interaction
+#     if "Calculus" in detected_conditions and "Gingivitis" in detected_conditions:
+#         result["clinical_overview"].append({
+#             "condition": "Clinical Interaction",
+#             "note": "Dental calculus may be contributing to gingival inflammation.",
+#             "impact_weight": 0
+#         })
+
+#     # Sort overview
+#     result["clinical_overview"] = sorted(result["clinical_overview"], key=lambda x: x.get("impact_weight", 0), reverse=True)
+
+#     # Primary condition
+#     if result["clinical_overview"]:
+#         result["primary_condition"] = result["clinical_overview"][0]["condition"]
+
+#     return result
+
+# # ============================================================
+# # PREDICTION FUNCTIONS
+# # ============================================================
+# def predict_teeth(image: np.ndarray, threshold: float = 0.5) -> dict:
+#     image = np.expand_dims(image, axis=0)
+#     score = BINARY_MODEL.predict(image, verbose=0)[0][0]
+
+#     is_teeth = score >= threshold
+#     confidence = score if is_teeth else 1 - score
+
+#     return {
+#         "is_teeth": bool(is_teeth),
+#         "class": BINARY_CLASSES[1] if is_teeth else BINARY_CLASSES[0],
+#         "confidence": float(confidence),
+#         "raw_score": float(score),
+#         "threshold": threshold
+#     }
+
+# def predict_teeth_health(image_bytes: bytes) -> dict:
+#     image = load_image(image_bytes)
+#     outputs = TEETH_HEALTH_MODEL(image)
+
+#     top = outputs[0]
+
+#     return {
+#         "predicted_class": top["label"],
+#         "confidence": float(top["score"]),
+#         "all_predictions": outputs
+#     }
+
+# def predict_disease(image: np.ndarray) -> dict:
+#     image = np.expand_dims(image, axis=0)
+#     predictions = DISEASE_MODEL.predict(image, verbose=0)[0]
+
+#     top_index = np.argmax(predictions)
+#     confidence = predictions[top_index]
+
+#     top_predictions = sorted(
+#         [
+#             {
+#                 "class": DISEASE_CLASSES[i],
+#                 "confidence": float(predictions[i])
+#             }
+#             for i in range(len(DISEASE_CLASSES))
+#         ],
+#         key=lambda x: x["confidence"],
+#         reverse=True
+#     )[:3]
+
+#     return {
+#         "predicted_class": DISEASE_CLASSES[top_index],
+#         "confidence": float(confidence),
+#         "top_predictions": top_predictions
+#     }
+
+# # ============================================================
+# # MAIN PIPELINE
+# # ============================================================
+# def teeth_diagnosis_pipeline(image_bytes: bytes, threshold: float = 0.5) -> dict:
+#     # 1️⃣ Binary detection
+#     binary_image = preprocess_for_binary(image_bytes)
+#     binary_result = predict_teeth(binary_image, threshold)
+
+#     if not binary_result["is_teeth"]:
+#         return {
+#             "status": "rejected",
+#             "binary_result": binary_result,
+#             "message": "Image does not contain teeth"
+#         }
+
+#     # 2️⃣ Teeth Health
+#     health_result = predict_teeth_health(image_bytes)
+
+#     label = str(health_result.get("predicted_class", "")).lower()
+#     confidence = health_result.get("confidence", 0)
+
+#     if label == "good teeth" and confidence >= 0.84:
+#         disease_result = {
+#             "message": "Teeth are healthy and free of diseases",
+#             "predicted_class": None,
+#             "top_predictions": []
+#         }
+#     else:
+#         disease_image = preprocess_for_disease(image_bytes)
+#         disease_result = predict_disease(disease_image)
+
+#     return {
+#         "status": "success",
+#         "binary_result": binary_result,
+#         "teeth_health_result": health_result,
+#         "disease_result": disease_result
+#     }
+
+# # ============================================================
+# # API ENDPOINTS
+# # ============================================================
+# @app.get("/")
+# def root():
+#     return {
+#         "system": "Integrated Teeth Detection & Diagnosis API",
+#         "pipeline": [
+#             "Teeth Detection",
+#             "Teeth Health Classification",
+#             "Disease Classification"
+#         ]
+#     }
+
+# @app.post("/predict")
+# async def predict(file: UploadFile = File(...), threshold: float = 0.5):
+#     image_bytes = await file.read()
+#     result = teeth_diagnosis_pipeline(image_bytes, threshold)
+#     result["filename"] = file.filename
+#     return result
+
+# @app.post("/detect-teeth")
+# async def detect_teeth(
+#     file: UploadFile = File(...),
+# ):
+#     """
+#     Detect whether the image contains teeth or not
+#     """
+
+#     request_id = str(uuid.uuid4())
+
+#     try:
+#         image_bytes = await file.read()
+
+#         image = preprocess_for_binary(image_bytes)
+#         binary_result = predict_teeth(image)
+
+#         return {
+#             "status": "success",
+#             "request_id": request_id,
+#             "filename": file.filename,
+#             "is_teeth": binary_result["is_teeth"],
+#             "predicted_class": binary_result["class"],
+#             "confidence": binary_result["confidence"],
+#             "raw_score": binary_result["raw_score"],
+#         }
+
+#     except Exception:
+#         raise HTTPException(
+#             status_code=500,
+#             detail=f"Internal server error | request_id: {request_id}"
+#         )
+
+# @app.post("/check-teeth-health")
+# async def check_teeth_health(file: UploadFile = File(...)):
+#     image_bytes = await file.read()
+#     return predict_teeth_health(image_bytes)
+
+
+# @app.post("/advanced-recommendations")
+# async def advanced_recommendations(
+#     file: UploadFile = File(...),
+#     threshold: float = Query(0.5, ge=0.0, le=1.0),
+#     age: int = Query(18, ge=0, le=120),
+#     pain_level: int = Query(0, ge=0, le=10),
+#     bleeding: bool = False,
+# ):
+#     request_id = str(uuid.uuid4())
+
+#     try:
+#         image_bytes = await file.read()
+#         diagnosis = teeth_diagnosis_pipeline(image_bytes, threshold)
+
+#         if diagnosis.get("status") != "success":
+#             raise HTTPException(status_code=422, detail="Diagnosis failed.")
+
+#         top_predictions = diagnosis["disease_result"].get("top_predictions", [])
+
+#         if not top_predictions:
+#             return JSONResponse(
+#                 status_code=200,
+#                 content={
+#                     "status": "no_disease_detected",
+#                     "request_id": request_id,
+#                     "summary": {
+#                         "primary_condition": None,
+#                         "confidence": 0,
+#                         "confidence_level": "none",
+#                         "overall_risk_score": 0,
+#                         "risk_category": "Low",
+#                         "urgency_level": "low",
+#                         "requires_dentist": False
+#                     },
+#                     "general_advice": [
+#                         "Continue regular dental checkups",
+#                         "Maintain good oral hygiene"
+#                     ]
+#                 }
+#             )
+
+#         advanced_recs = get_weighted_recommendations(
+#             top_predictions, age=age, pain_level=pain_level, bleeding=bleeding
+#         )
+
+#         primary_conf = diagnosis["disease_result"]["confidence"]
+#         if primary_conf >= 0.9:
+#             confidence_level = "very_high"
+#         elif primary_conf >= 0.7:
+#             confidence_level = "high"
+#         elif primary_conf >= 0.5:
+#             confidence_level = "medium"
+#         else:
+#             confidence_level = "low"
+
+#         return {
+#             "status": "success",
+#             "request_id": request_id,
+#             "filename": file.filename,
+#             "summary": {
+#                 "primary_condition": diagnosis["disease_result"]["predicted_class"],
+#                 "confidence": primary_conf,
+#                 "confidence_level": confidence_level,
+#                 "overall_risk_score": advanced_recs.get("overall_risk_score"),
+#                 "risk_category": advanced_recs.get("risk_category"),
+#                 "urgency_level": advanced_recs.get("urgency_level"),
+#                 "requires_dentist": advanced_recs.get("requires_dentist"),
+#                 "show_emergency_banner": advanced_recs.get("urgency_level") == "high"
+#             },
+#             "diagnosis": {"top_predictions": top_predictions},
+#             "recommendations": {
+#                 "clinical_overview": advanced_recs.get("clinical_overview"),
+#                 "priority_treatment": advanced_recs.get("priority_treatment_plan"),
+#                 "supportive_treatment": advanced_recs.get("supportive_treatments"),
+#                 "home_care": advanced_recs.get("personalized_home_care"),
+#                 "follow_up": advanced_recs.get("follow_up_recommendation"),
+#                 "urgency_message": advanced_recs.get("urgency_message")
+#             }
+#         }
+
+#     except Exception as e:
+#         raise HTTPException(status_code=500, detail=f"Internal server error | request_id: {request_id}")    
+    
+
+
+# # ============================================================
+# # SERVER START
+# # ============================================================
+# if __name__ == "__main__":
+#     print("=" * 70)
+#     print("Integrated Teeth Detection & Disease Classification System")
+#     print("Server running at: http://localhost:8000")
+#     print("API Docs: http://localhost:8000/docs")
+#     print("=" * 70)
+
+#     uvicorn.run(app, host="0.0.0.0", port=8000)
+
+
+
+
+from fastapi import FastAPI, File, Path
+from fastapi.middleware.cors import CORSMiddleware
+import uvicorn
+import numpy as np
+from io import BytesIO
+from PIL import Image
+import tensorflow as tf
+from tensorflow.keras.applications.efficientnet import preprocess_input  # type: ignore
+import uuid
+from fastapi import File, UploadFile, Query, HTTPException
+from fastapi.responses import JSONResponse
+import time
+import pyheif
+
+
+
+# HuggingFace
+from transformers import pipeline
+import torch
+import json
+import os
+from pathlib import Path  
+from datetime import datetime
+
+
+
+
+# ============================================================
+# CONFIGURATION
+# ============================================================
+IMAGE_SIZE = 224
+
+BINARY_MODEL_PATH = "./model_2.keras"
+DISEASE_MODEL_PATH = "./LAST_model_efficent.h5"
+
+
+print(os.path.exists(BINARY_MODEL_PATH))
+print(os.path.isfile(BINARY_MODEL_PATH))
+
+BASE_DIR = Path(__file__).parent
+KNOWLEDGE_BASE_PATH = BASE_DIR / "knowledge_base" / "clinical_rules.json"
+
+
+# HuggingFace Teeth Health Model
+HF_TEETH_HEALTH_MODEL = "steven123/Check_GoodBad_Teeth"
+
+DEVICE = 0 if torch.cuda.is_available() else -1
+
+BINARY_CLASSES = ["not_teath", "teath"]
+TEETH_HEALTH_CLASSES = ["Good Teeth", "Bad Teeth"]
+
+DISEASE_CLASSES = [
+    "Calculus",
+    "Dental Caries",
+    "Gingivitis",
+    "Mouth Ulcer",
+    "Tooth Discoloration",
+    "Hypodontia"
+]
+
+
+# ============================================================
+# LOAD KNOWLEDGE BASE
+# ============================================================
+def load_knowledge_base():
+    """تحميل قاعدة المعرفة من ملف JSON"""
+    try:
+        with open(KNOWLEDGE_BASE_PATH, 'r', encoding='utf-8') as f:
+            return json.load(f)
+    except FileNotFoundError:
+        print(f"⚠️ Warning: Knowledge base file not found at {KNOWLEDGE_BASE_PATH}")
+        return {"diseases": {}, "general_rules": {}}
+
+knowledge_base_data = load_knowledge_base()
+diseases_db = knowledge_base_data.get("diseases", {})
+general_rules = knowledge_base_data.get("general_rules", {})
+
+
+
+# ============================================================
+# APPLICATION INITIALIZATION
+# ============================================================
+app = FastAPI(
+    title="Integrated Teeth Detection System",
+    description="Binary Detection → Teeth Health → Disease Classification",
+    version="1.2.0"
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+print("exists:", os.path.exists(BINARY_MODEL_PATH))
+print("isfile:", os.path.isfile(BINARY_MODEL_PATH))
+
+# ============================================================
+# # MODEL LOADING
+# ============================================================
+print("[INFO] Loading TensorFlow models...")
+BINARY_MODEL = tf.keras.models.load_model(BINARY_MODEL_PATH)
+DISEASE_MODEL = tf.keras.models.load_model(DISEASE_MODEL_PATH)
+
+print("[INFO] Loading HuggingFace Teeth Health model...")
+TEETH_HEALTH_MODEL = pipeline(
+    "image-classification",
+    model=HF_TEETH_HEALTH_MODEL,
+    device=DEVICE
+)
+
+print("[INFO] All models loaded successfully")
+
+# ============================================================
+# IMAGE PREPROCESSING
+# ============================================================
+def load_image(image_bytes: bytes) -> Image.Image:
+    """
+    Load any image and convert to RGB.
+    Supports HEIC/HEIF and standard formats (JPEG, PNG, etc.).
+    """
+    try:
+        # جرب نقرأ الصورة كـ HEIC/HEIF
+        heif_file = pyheif.read_heif(image_bytes)
+        image = Image.frombytes(
+            heif_file.mode, 
+            heif_file.size, 
+            heif_file.data, 
+            "raw", 
+            heif_file.mode, 
+            heif_file.stride
+        )
+        return image.convert("RGB")
+
+    except pyheif.error.HeifError:
+        # لو مش HEIC/HEIF، افتحها كـ JPEG/PNG عادي
+        try:
+            return Image.open(BytesIO(image_bytes)).convert("RGB")
+        except Exception as e:
+            raise HTTPException(status_code=422, detail=f"Invalid or corrupted image: {str(e)}")
+        
+def preprocess_for_binary(image_bytes: bytes) -> np.ndarray:
+    image = load_image(image_bytes)
+    image = image.resize((IMAGE_SIZE, IMAGE_SIZE))
+    image = np.array(image).astype(np.float32) 
+    return image
+
+def preprocess_for_disease(image_bytes: bytes) -> np.ndarray:
+    image = load_image(image_bytes)
+    image = image.resize((IMAGE_SIZE, IMAGE_SIZE))
+    image = np.array(image).astype(np.float32)
+    image = preprocess_input(image)
+    return image
+    
+def assess_urgency(result):
+    return {
+        "level": result.get("urgency_level", "low"),
+        "message": result.get("urgency_message", "")
+    }
+def combine_advice(result):
+    combined = []
+    seen = set()
+
+    for advice in result.get("personalized_home_care", []):
+        if advice not in seen:
+            combined.append(advice)
+            seen.add(advice)
+
+    return combined[:4]
+
+
+#===========================================================
+# RECOMMENDATION ENGINE
+# ============================================================
+def add_unique_advice(advice_list, target_list):
+    """
+    Adds advice to target_list if not already present (prevents exact duplicates)
+    """
+    if not advice_list:
+        return
+    for advice in advice_list:
+        if advice and advice not in target_list:
+            target_list.append(advice)
+#============================================================'
+#  Advanced weighted recommendation
+#============================================================
+def get_weighted_recommendations(top_predictions, age: int, pain_level: int, bleeding: bool):
+    result = {
+        "timestamp": datetime.now().isoformat(),
+        "primary_condition": None,
+        "overall_risk_score": 0.0,
+        "risk_category": "Early Stage",
+        "clinical_overview": [],
+        "priority_treatment_plan": [],
+        "supportive_treatments": [],
+        "personalized_home_care": {"essential": [], "recommended": [], "avoid": []},
+        "follow_up_recommendation": [],
+        "requires_dentist": False,
+        "urgency_level": "low",
+        "urgency_message": ""
+    }
+
+    if not top_predictions:
+        return result
+
+    severity_scale = {"high": 3, "medium": 2, "moderate":2, "mild": 1, "low": 1,"structural": 2}
+    urgency_scale = {"high": 3, "medium": 2, "low": 1}
+    confidence_rules = general_rules.get("confidence_weighting", {})
+
+    filtered_predictions = [p for p in top_predictions if p.get("confidence", 0) > 0.05]
+    if not filtered_predictions:
+        return result
+
+    total_conf = sum(p["confidence"] for p in filtered_predictions)
+    total_risk_score = 0
+    detected_conditions = []
+
+    for pred in filtered_predictions:
+        disease = pred["class"]
+        confidence = pred["confidence"]
+        weight = confidence / total_conf if total_conf > 0 else 0
+
+        if disease not in diseases_db:
+            continue
+
+        detected_conditions.append(disease)
+        disease_info = diseases_db[disease]
+        base = disease_info.get("base_info", {})
+        treatments = disease_info.get("treatment_options", {}).get("primary", [])
+        home_advice = disease_info.get("home_advice", {})
+
+        # 🔹 Severity & urgency
+        severity = base.get("severity", "low")
+        urgency = base.get("urgency", "low")
+        severity_value = severity_scale.get(severity, 1)
+        urgency_value = urgency_scale.get(urgency, 1)
+        
+        # --- Symptom-based adjustment (Improved Clinical Logic) ---
+        bleeding_factor = 1 if bleeding else 0
+        disease_category = base.get("category", "")
+
+        # Option 1: Direct multiplier (pain_level 0-10)
+        if disease_category in ["tooth_decay", "inflammatory"]:
+             severity_value += pain_level * 0.3   
+             urgency_value += pain_level * 0.3
+        elif disease_category in ["soft_tissue", "mineral_deposit","developmental","aesthetic"]:
+             severity_value += pain_level * 0.1   
+             urgency_value += pain_level * 0.1 
+
+        # Bleeding impact
+        if disease_category in ["inflammatory", "tooth_decay"]:
+            urgency_value += bleeding_factor * 1.5
+        elif disease_category in ["soft_tissue", "mineral_deposit","developmental","aesthetic"]:
+            urgency_value += bleeding_factor * 0.4  
+
+        # Age sensitivity
+        if age < 12 or age > 65:
+            urgency_value += 0.5
+
+        # حساب عامل الثقة بناءً على confidence
+        if confidence >= 0.8:
+            confidence_factor = 1.0  
+        elif confidence >= 0.5:
+            confidence_factor = confidence_rules.get("medium", 0.5)
+        else:
+            confidence_factor = confidence_rules.get("low", 0.2)
+        
+
+
+        disease_risk = ((severity_value * 0.6 + urgency_value * 0.4) * weight * confidence_factor)
+        total_risk_score += disease_risk
+
+        # Treatment level
+        if severity == "high":
+            treatment_level = "aggressive"
+        elif severity in ["medium", "structural"]:
+            treatment_level = "moderate"
+        else:
+            treatment_level = "conservative"
+
+        # Clinical overview
+        result["clinical_overview"].append({
+            "condition": disease,
+            "confidence_percent": round(confidence * 100, 2),
+            "impact_weight": round(weight, 3),
+            "severity": severity,
+            "urgency": urgency,
+            "treatment_level": treatment_level
+        })
+
+        # Treatment plans
+        if treatment_level == "aggressive":
+            for t in treatments:
+                add_unique_advice([t], result["priority_treatment_plan"])
+        elif treatment_level == "moderate":
+            for t in treatments[:1]:
+                add_unique_advice([t], result["supportive_treatments"])
+
+        # --- Home care advice (Compact & Professional) ---
+        essential_advice = home_advice.get("essential", [])[:2]
+        recommended_advice = home_advice.get("recommended", [])[:2]
+        avoid_advice = home_advice.get("avoid", [])[:2]
+
+        add_unique_advice(essential_advice, result["personalized_home_care"]["essential"])
+        add_unique_advice(recommended_advice, result["personalized_home_care"]["recommended"])
+        add_unique_advice(avoid_advice, result["personalized_home_care"]["avoid"])
+
+        # Build-up advice
+        build_up = disease_info.get("build_up_recommendation", {})
+        if build_up.get("applicable", False):
+            conditions = build_up.get("conditions", {})
+            for cond in conditions.values():
+                if confidence >= cond.get("confidence_threshold", 0.3):
+                    materials = ", ".join(cond.get("materials", []))
+                    reason = cond.get("reason", "")
+                    advice_text = f"Consider build-up using {materials} ({reason})"
+                    add_unique_advice([advice_text], result["personalized_home_care"]["recommended"])
+
+        # Dentist requirement
+        if base.get("requires_dentist", False):
+            result["requires_dentist"] = True
+
+        # Follow up
+        follow_up = disease_info.get("follow_up")
+        if follow_up:
+            add_unique_advice([follow_up], result["follow_up_recommendation"])
+
+    # Normalize risk
+    normalized_risk = min(total_risk_score, 5)
+    result["overall_risk_score"] = round(normalized_risk, 2)
+
+    # Risk Category
+    if normalized_risk >= 4:
+        result["risk_category"] = "Critical"
+    elif normalized_risk >= 3:
+        result["risk_category"] = "Advanced"
+    elif normalized_risk >= 2:
+        result["risk_category"] = "Progressive"
+    else:
+        result["risk_category"] = "Early Stage"
+
+    # Urgency
+    if normalized_risk >= 3.5:
+        result["urgency_level"] = "high"
+        result["urgency_message"] = "Immediate dental consultation required (within 24-48 hours)."
+    elif normalized_risk >= 2.0:
+        result["urgency_level"] = "medium"
+        result["urgency_message"] = "Dental appointment recommended within 1-4 weeks."
+    else:
+        result["urgency_level"] = "low"
+        result["urgency_message"] = "Maintain oral hygiene and monitor symptoms."
+
+    # Multi-disease interaction
+    if "Calculus" in detected_conditions and "Gingivitis" in detected_conditions:
+        result["clinical_overview"].append({
+            "condition": "Clinical Interaction",
+            "note": "Dental calculus may be contributing to gingival inflammation.",
+            "impact_weight": 0
+        })
+
+    # Sort overview
+    result["clinical_overview"] = sorted(result["clinical_overview"], key=lambda x: x.get("impact_weight", 0), reverse=True)
+
+    # Primary condition
+    if result["clinical_overview"]:
+        result["primary_condition"] = result["clinical_overview"][0]["condition"]
+
+    return result
+
+# ============================================================
+# PREDICTION FUNCTIONS
+# ============================================================
+def predict_teeth(image: np.ndarray, threshold: float = 0.5) -> dict:
+    image = np.expand_dims(image, axis=0)
+    score = BINARY_MODEL.predict(image, verbose=0)[0][0]
+
+    is_teeth = score >= threshold
+    confidence = score if is_teeth else 1 - score
+
+    return {
+        "is_teeth": bool(is_teeth),
+        "class": BINARY_CLASSES[1] if is_teeth else BINARY_CLASSES[0],
+        "confidence": float(confidence),
+        "raw_score": float(score),
+        "threshold": threshold
+    }
+
+def predict_teeth_health(image_bytes: bytes) -> dict:
+    image = load_image(image_bytes)
+    outputs = TEETH_HEALTH_MODEL(image)
+
+    top = outputs[0]
+
+    return {
+        "predicted_class": top["label"],
+        "confidence": float(top["score"]),
+        "all_predictions": outputs
+    }
+
+def predict_disease(image: np.ndarray) -> dict:
+    image = np.expand_dims(image, axis=0)
+    predictions = DISEASE_MODEL.predict(image, verbose=0)[0]
+
+    top_index = np.argmax(predictions)
+    confidence = predictions[top_index]
+
+    top_predictions = sorted(
+        [
+            {
+                "class": DISEASE_CLASSES[i],
+                "confidence": float(predictions[i])
+            }
+            for i in range(len(DISEASE_CLASSES))
+        ],
+        key=lambda x: x["confidence"],
+        reverse=True
+    )[:3]
+
+    return {
+        "predicted_class": DISEASE_CLASSES[top_index],
+        "confidence": float(confidence),
+        "top_predictions": top_predictions
+    }
+
+# ============================================================
+# MAIN PIPELINE
+# ============================================================
+def teeth_diagnosis_pipeline(image_bytes: bytes, threshold: float = 0.5) -> dict:
+    # 1️⃣ Binary detection
+    binary_image = preprocess_for_binary(image_bytes)
+    binary_result = predict_teeth(binary_image, threshold)
+
+    if not binary_result["is_teeth"]:
+        return {
+            "status": "rejected",
+            "binary_result": binary_result,
+            "message": "Image does not contain teeth"
+        }
+
+    # 2️⃣ Teeth Health
+    health_result = predict_teeth_health(image_bytes)
+
+    label = str(health_result.get("predicted_class", "")).lower()
+    confidence = health_result.get("confidence", 0)
+
+    if label == "good teeth" and confidence >= 0.84:
+        disease_result = {
+            "message": "Teeth are healthy and free of diseases",
+            "predicted_class": None,
+            "top_predictions": []
+        }
+    else:
+        disease_image = preprocess_for_disease(image_bytes)
+        disease_result = predict_disease(disease_image)
+
+    return {
+        "status": "success",
+        "binary_result": binary_result,
+        "teeth_health_result": health_result,
+        "disease_result": disease_result
+    }
+
+# ============================================================
+# API ENDPOINTS
+# ============================================================
+@app.get("/")
+def root():
+    return {
+        "system": "Integrated Teeth Detection & Diagnosis API",
+        "pipeline": [
+            "Teeth Detection",
+            "Teeth Health Classification",
+            "Disease Classification"
+        ]
+    }
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...), threshold: float = 0.5):
+    image_bytes = await file.read()
+    result = teeth_diagnosis_pipeline(image_bytes, threshold)
+    result["filename"] = file.filename
+    return result
+
+@app.post("/detect-teeth")
+async def detect_teeth(
+    file: UploadFile = File(...),
+):
+    """
+    Detect whether the image contains teeth or not
+    """
+
+    request_id = str(uuid.uuid4())
+
+    try:
+        image_bytes = await file.read()
+
+        image = preprocess_for_binary(image_bytes)
+        binary_result = predict_teeth(image)
+
+        return {
+            "status": "success",
+            "request_id": request_id,
+            "filename": file.filename,
+            "is_teeth": binary_result["is_teeth"],
+            "predicted_class": binary_result["class"],
+            "confidence": binary_result["confidence"],
+            "raw_score": binary_result["raw_score"],
+        }
+
+    except Exception:
+        raise HTTPException(
+            status_code=500,
+            detail=f"Internal server error | request_id: {request_id}"
+        )
+
+@app.post("/check-teeth-health")
+async def check_teeth_health(file: UploadFile = File(...)):
+    image_bytes = await file.read()
+    return predict_teeth_health(image_bytes)
+
+
+@app.post("/advanced-recommendations")
+async def advanced_recommendations(
+    file: UploadFile = File(...),
+    threshold: float = Query(0.5, ge=0.0, le=1.0),
+    age: int = Query(18, ge=0, le=120),
+    pain_level: int = Query(0, ge=0, le=10),
+    bleeding: bool = False,
+):
+    request_id = str(uuid.uuid4())
+
+    try:
+        image_bytes = await file.read()
+        diagnosis = teeth_diagnosis_pipeline(image_bytes, threshold)
+
+        if diagnosis.get("status") != "success":
+            raise HTTPException(status_code=422, detail="Diagnosis failed.")
+
+        top_predictions = diagnosis["disease_result"].get("top_predictions", [])
+
+        if not top_predictions:
+            return JSONResponse(
+                status_code=200,
+                content={
+                    "status": "no_disease_detected",
+                    "request_id": request_id,
+                    "summary": {
+                        "primary_condition": None,
+                        "confidence": 0,
+                        "confidence_level": "none",
+                        "overall_risk_score": 0,
+                        "risk_category": "Low",
+                        "urgency_level": "low",
+                        "requires_dentist": False
+                    },
+                    "general_advice": [
+                        "Continue regular dental checkups",
+                        "Maintain good oral hygiene"
+                    ]
+                }
+            )
+
+        advanced_recs = get_weighted_recommendations(
+            top_predictions, age=age, pain_level=pain_level, bleeding=bleeding
+        )
+
+        primary_conf = diagnosis["disease_result"]["confidence"]
+        if primary_conf >= 0.9:
+            confidence_level = "very_high"
+        elif primary_conf >= 0.7:
+            confidence_level = "high"
+        elif primary_conf >= 0.5:
+            confidence_level = "medium"
+        else:
+            confidence_level = "low"
+
+        return {
+            "status": "success",
+            "request_id": request_id,
+            "filename": file.filename,
+            "summary": {
+                "primary_condition": diagnosis["disease_result"]["predicted_class"],
+                "confidence": primary_conf,
+                "confidence_level": confidence_level,
+                "overall_risk_score": advanced_recs.get("overall_risk_score"),
+                "risk_category": advanced_recs.get("risk_category"),
+                "urgency_level": advanced_recs.get("urgency_level"),
+                "requires_dentist": advanced_recs.get("requires_dentist"),
+                "show_emergency_banner": advanced_recs.get("urgency_level") == "high"
+            },
+            "diagnosis": {"top_predictions": top_predictions},
+            "recommendations": {
+                "clinical_overview": advanced_recs.get("clinical_overview"),
+                "priority_treatment": advanced_recs.get("priority_treatment_plan"),
+                "supportive_treatment": advanced_recs.get("supportive_treatments"),
+                "home_care": advanced_recs.get("personalized_home_care"),
+                "follow_up": advanced_recs.get("follow_up_recommendation"),
+                "urgency_message": advanced_recs.get("urgency_message")
+            }
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Internal server error | request_id: {request_id}")    
+    
+
+
+# ============================================================
+# SERVER START
+# ============================================================
+if __name__ == "__main__":
+    print("=" * 70)
+    print("Integrated Teeth Detection & Disease Classification System")
+    print("Server running at: http://localhost:8000")
+    print("API Docs: http://localhost:8000/docs")
+    print("=" * 70)
+
+    uvicorn.run(app, host="0.0.0.0", port=7860)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

knowledge_base/clinical_rules.json

@@ -0,0 +1,331 @@
+{
+  "diseases": {
+    "Calculus": {
+      "base_info": {
+        "severity": "moderate",
+        "urgency": "medium",
+        "requires_dentist": true,
+        "category": "mineral_deposit"
+      },
+      "treatment_options": {
+        "primary": [
+          "Professional scaling and polishing",
+          "Deep cleaning procedure"
+        ],
+        "alternative": ["Antibacterial mouthwash", "Professional prophylaxis"],
+        "contraindications": ["Bleeding disorders", "Recent oral surgery"]
+      },
+      "home_advice": {
+        "essential": [
+          "Brush twice daily with tartar-control toothpaste",
+          "Floss daily to prevent buildup between teeth",
+          "Use electric toothbrush for better plaque removal"
+        ],
+        "recommended": [
+          "Use water flosser for hard-to-reach areas",
+          "Salt water rinses twice weekly"
+        ],
+        "avoid": [
+          "Tobacco products",
+          "Excessive coffee/tea (can stain calculus)"
+        ]
+      },
+      "build_up_recommendation": {
+        "applicable": false,
+        "reason": "Calculus requires removal, not build-up",
+        "alternative": "Professional cleaning"
+      },
+      "follow_up": "Professional cleaning every 6 months or sooner if prone to buildup"
+    },
+
+    "Dental Caries": {
+      "base_info": {
+        "severity": "high",
+        "urgency": "high",
+        "requires_dentist": true,
+        "category": "tooth_decay"
+      },
+      "treatment_options": {
+        "primary": ["Dental filling", "Root canal if advanced"],
+        "alternative": [
+          "Silver diamine fluoride",
+          "Hall technique (for children)"
+        ],
+        "contraindications": ["Severe pulpitis", "Vertical root fracture"]
+      },
+      "home_advice": {
+        "essential": [
+          "Avoid sugary foods and drinks between meals",
+          "Use fluoride toothpaste with 1350-1500ppm fluoride",
+          "Brush for 2 minutes twice daily"
+        ],
+        "recommended": [
+          "Use fluoride mouthwash before bed",
+          "Chew sugar-free gum after meals"
+        ],
+        "avoid": [
+          "Sticky candies and dried fruits",
+          "Carbonated drinks",
+          "Frequent snacking"
+        ]
+      },
+      "build_up_recommendation": {
+        "applicable": true,
+        "conditions": {
+          "early_caries": {
+            "confidence_threshold": 0.3,
+            "materials": ["Composite resin", "Glass ionomer"],
+            "reason": "Early caries can be treated with conservative build-up"
+          },
+          "immature_tooth": {
+            "confidence_threshold": 0.2,
+            "materials": ["Composite resin", "Component"],
+            "reason": "Immature teeth benefit from build-up to protect pulp"
+          },
+          "erupting_tooth": {
+            "confidence_threshold": 0.15,
+            "materials": ["Glass ionomer", "Composite"],
+            "reason": "Erupting teeth require build-up to guide proper development"
+          }
+        },
+        "contraindications": ["Deep caries near pulp", "Active infection"]
+      },
+      "follow_up": "Return in 6 months or sooner if pain develops"
+    },
+
+    "Hypodontia": {
+      "base_info": {
+        "severity": "structural",
+        "urgency": "medium",
+        "requires_dentist": true,
+        "category": "developmental"
+      },
+      "treatment_options": {
+        "primary": [
+          "Orthodontic evaluation",
+          "Space management",
+          "Build-up restoration for developing teeth"
+        ],
+        "alternative": [
+          "Dental implants (adults)",
+          "Resin-bonded bridge",
+          "Removable partial denture"
+        ],
+        "multidisciplinary": ["Orthodontist", "Pedodontist", "Prosthodontist"]
+      },
+      "home_advice": {
+        "essential": [
+          "Maintain excellent oral hygiene around missing areas",
+          "Regular dental checkups every 6 months",
+          "Keep adjacent teeth clean to prevent shifting"
+        ],
+        "recommended": [
+          "Consider orthodontic consultation",
+          "Use fluoridated toothpaste for remaining teeth"
+        ],
+        "age_specific": {
+          "child_6_12": [
+            "Space maintainers may be needed",
+            "Monitor eruption of permanent teeth",
+            "Avoid hard foods on adjacent teeth"
+          ],
+          "teen_13_18": [
+            "Discuss orthodontic options",
+            "Consider temporary build-up",
+            "Plan for future implants"
+          ],
+          "adult_19_plus": [
+            "Evaluate for implants or bridges",
+            "Consider bone grafting if implant planned",
+            "Regular assessment of adjacent teeth"
+          ]
+        }
+      },
+      "build_up_recommendation": {
+        "applicable": true,
+        "priority": "high_for_developing",
+        "age_ranges": [
+          {
+            "min": 6,
+            "max": 12,
+            "priority": "essential",
+            "reason": "Primary/transitional dentition needs build-up for space maintenance",
+            "materials": ["Composite build-up", "Space maintainer"]
+          },
+          {
+            "min": 13,
+            "max": 18,
+            "priority": "recommended",
+            "reason": "Build-up recommended until growth complete",
+            "materials": ["Composite", "Temporary build-up"]
+          },
+          {
+            "min": 19,
+            "max": 100,
+            "priority": "consider",
+            "reason": "Build-up temporary solution, fixed restoration preferred",
+            "materials": ["Composite", "Temporary until definitive treatment"]
+          }
+        ],
+        "clinical_notes": "For erupting/developing teeth, build-up is ALWAYS preferred over fixed restoration"
+      },
+      "follow_up": "Every 6 months with radiographic monitoring of adjacent teeth"
+    },
+
+    "Gingivitis": {
+      "base_info": {
+        "severity": "mild",
+        "urgency": "low",
+        "requires_dentist": false,
+        "category": "inflammatory"
+      },
+      "treatment_options": {
+        "primary": [
+          "Improved oral hygiene",
+          "Professional cleaning if persistent"
+        ],
+        "alternative": [
+          "Antiseptic mouthwash",
+          "Chlorhexidine gel (short term)"
+        ],
+        "contraindications": ["Allergy to mouthwash ingredients"]
+      },
+      "home_advice": {
+        "essential": [
+          "Brush twice daily with soft-bristled toothbrush",
+          "Floss daily - this is crucial for gum health",
+          "Use gentle circular motions, not aggressive scrubbing"
+        ],
+        "recommended": [
+          "Use antiseptic mouthwash (alcohol-free preferred)",
+          "Salt water rinses (1 tsp salt in warm water) twice daily"
+        ],
+        "avoid": [
+          "Hard toothbrushes",
+          "Aggressive brushing that causes bleeding",
+          "Tobacco products"
+        ]
+      },
+      "build_up_recommendation": {
+        "applicable": false,
+        "reason": "Gingivitis affects gums, not tooth structure"
+      },
+      "follow_up": "Improvement expected in 2 weeks; see dentist if persists"
+    },
+
+    "Tooth Discoloration": {
+      "base_info": {
+        "severity": "mild",
+        "urgency": "low",
+        "requires_dentist": false,
+        "category": "aesthetic"
+      },
+      "treatment_options": {
+        "primary": ["Professional cleaning", "Whitening treatments"],
+        "alternative": [
+          "Composite veneers",
+          "Porcelain veneers",
+          "Microabrasion"
+        ],
+        "contraindications": ["Pregnancy", "Severe sensitivity", "Caries"]
+      },
+      "home_advice": {
+        "essential": [
+          "Reduce consumption of staining foods (coffee, tea, red wine)",
+          "Rinse with water after consuming staining substances",
+          "Use whitening toothpaste with mild abrasives"
+        ],
+        "recommended": [
+          "Consider professional whitening for better results",
+          "Maintain excellent oral hygiene"
+        ],
+        "avoid": [
+          "Smoking and tobacco products",
+          "Excessive acidic foods that erode enamel",
+          "Overuse of whitening products"
+        ]
+      },
+      "build_up_recommendation": {
+        "applicable": true,
+        "conditions": {
+          "severe_discoloration": {
+            "confidence_threshold": 0.6,
+            "materials": ["Composite veneer", "Porcelain veneer"],
+            "reason": "Severe discoloration may require build-up/veneer"
+          },
+          "structural_damage": {
+            "confidence_threshold": 0.4,
+            "materials": ["Composite build-up"],
+            "reason": "Build-up can restore both structure and color"
+          }
+        }
+      },
+      "follow_up": "As desired for cosmetic improvement"
+    },
+
+    "Mouth Ulcer": {
+      "base_info": {
+        "severity": "mild",
+        "urgency": "low",
+        "requires_dentist": false,
+        "category": "soft_tissue"
+      },
+      "treatment_options": {
+        "primary": ["Topical analgesics", "Avoid irritants"],
+        "alternative": [
+          "Prescription mouthwash",
+          "Corticosteroid gel (severe)"
+        ],
+        "contraindications": ["Immunosuppression", "Infection"]
+      },
+      "home_advice": {
+        "essential": [
+          "Salt water rinses (1 tsp salt in warm water) 3-4 times daily",
+          "Avoid spicy, acidic, or rough foods",
+          "Use soft toothbrush carefully around ulcer"
+        ],
+        "recommended": [
+          "Apply topical gel for pain",
+          "Rinse with alcohol-free mouthwash"
+        ],
+        "avoid": [
+          "Hot foods and beverages",
+          "Citrus fruits and juices",
+          "Crunchy foods (chips, nuts)"
+        ]
+      },
+      "build_up_recommendation": {
+        "applicable": false,
+        "reason": "Ulcers are soft tissue condition"
+      },
+      "follow_up": "Should heal within 7-14 days; see dentist if persists beyond 3 weeks"
+    }
+  },
+
+  "general_rules": {
+    "confidence_weighting": {
+      "high": 0.8,
+      "medium": 0.5,
+      "low": 0.2
+    },
+    "treatment_urgency": {
+      "high": "See dentist within 24-48 hours",
+      "medium": "Schedule appointment within 2 weeks",
+      "low": "Monitor and schedule routine checkup"
+    },
+    "build_up_indications": [
+      "Developing dentition (age < 18)",
+      "Partially erupted teeth",
+      "Minimal to moderate tooth structure loss",
+      "Temporary restoration needed",
+      "Economic considerations"
+    ],
+    "fixed_indications": [
+      "Fully developed dentition (age ≥ 18)",
+      "Extensive tooth structure loss",
+      "Complete root formation",
+      "Long-term definitive solution needed",
+      "Aesthetic demands in anterior teeth"
+    ]
+  }
+}