Update app.py

app.py

@@ -3,29 +3,30 @@
 import gradio as gr
 from PIL import Image
 import torch
+import pandas as pd
 from transformers import AutoImageProcessor, AutoModelForImageClassification
 
-# Load model and processor
+# Load model
 model_name = "Anwarkh1/Skin_Cancer-Image_Classification"
 processor = AutoImageProcessor.from_pretrained(model_name)
 model = AutoModelForImageClassification.from_pretrained(model_name)
 label_map = model.config.id2label
 
-# Descriptions for each class
+# Skin condition descriptions (simple language)
 condition_info = {
-    "actinic keratoses": "Precancerous rough, scaly patches on sun-exposed skin.",
-    "basal cell carcinoma": "Common skin cancer, slow-growing and rarely spreads.",
-    "benign keratosis-like lesions": "Non-cancerous growths, may resemble warts or sun spots.",
-    "dermatofibroma": "Harmless small bumps often on legs, firm to the touch.",
-    "melanocytic nevi": "Common moles, generally benign unless changing in shape/size.",
-    "melanoma": "Serious skin cancer; early detection is critical.",
-    "vascular lesions": "Birthmarks or red/purple patches from abnormal blood vessels."
+    "actinic keratoses": "Dry, rough patch – sometimes early sign of skin cancer.",
+    "basal cell carcinoma": "Slow-growing skin cancer. Common but treatable.",
+    "benign keratosis-like lesions": "Non-cancerous growth. Like age spots or warts.",
+    "dermatofibroma": "Small, firm bump. Usually harmless.",
+    "melanocytic nevi": "Just a mole. Normal unless changing.",
+    "melanoma": "Dangerous skin cancer. Needs fast treatment.",
+    "vascular lesions": "Red or purple patches from blood vessels."
 }
 
-# Prediction logic
+# AI logic
 def classify_skin(image: Image.Image):
     if image is None:
-        return "Please upload or capture an image.", "", ""
+        return pd.DataFrame(), "Please upload or take a photo."
 
     image = image.convert("RGB")
     inputs = processor(images=image, return_tensors="pt")
@@ -35,33 +36,42 @@ def classify_skin(image: Image.Image):
     logits = outputs.logits
     probs = torch.nn.functional.softmax(logits, dim=1)[0]
 
-    # Prepare full result table
     threshold = 0.40
-    result_table = ""
-    summary = []
+    data = []
+    likely_conditions = []
+
     for idx, prob in enumerate(probs):
         label = label_map[idx]
-        confidence = prob.item()
-        status = "✅ Positive" if confidence > threshold else "❌ Negative"
-        desc = condition_info.get(label.lower(), "No description.")
-        result_table += f"**{label.capitalize()}**: {confidence * 100:.2f}% — {status}\n> {desc}\n\n"
-        if confidence > threshold:
-            summary.append(label.capitalize())
+        conf = prob.item()
+        status = "✅ Positive" if conf > threshold else "❌ Negative"
+        data.append({
+            "Condition": label.capitalize(),
+            "Confidence (%)": f"{conf*100:.2f}",
+            "Status": status,
+            "What it means": condition_info[label.lower()]
+        })
+        if conf > threshold:
+            likely_conditions.append(label.capitalize())
+
+    df = pd.DataFrame(data)
+    summary_text = (
+        "🧾 **Summary:** " +
+        (", ".join(likely_conditions) if likely_conditions else "No major concern seen by AI.") +
+        "\n\n📢 Please check with a real doctor for correct diagnosis."
+    )
 
-    final_summary = "🔍 **Likely Condition(s):** " + (", ".join(summary) if summary else "None detected above threshold.")
-    return result_table, final_summary, "⚠️ This tool is not a diagnosis. Always consult a certified dermatologist."
+    return df, summary_text
 
-# Gradio interface
+# Gradio Interface
 demo = gr.Interface(
     fn=classify_skin,
     inputs=gr.Image(type="pil", label="📷 Upload or Capture Skin Image"),
     outputs=[
-        gr.Markdown(label="🔬 Detailed Predictions"),
-        gr.Textbox(label="🧾 Summary"),
-        gr.Textbox(label="Disclaimer", max_lines=2)
+        gr.Dataframe(headers=["Condition", "Confidence (%)", "Status", "What it means"]),
+        gr.Markdown()
     ],
     title="AI Skin Condition Classifier",
-    description="Upload or take a photo of a skin condition to get predictions using a pre-trained AI model. Powered by Hugging Face Transformers."
+    description="Upload a photo of a skin issue. The AI will check 7 common conditions and suggest what looks likely. For support only — not a replacement for a real doctor."
 )
 
 if __name__ == "__main__":