Upload 3 files

app.py

@@ -0,0 +1,174 @@
+# app.py
+
+import gradio as gr
+import torch
+from PIL import Image
+import numpy as np
+import json
+from huggingface_hub import hf_hub_download
+
+# Import necessary model libraries
+import segmentation_models_pytorch as smp
+import timm
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+from torchvision import transforms
+
+# --- 1. SETUP: Download and Load all models and data ---
+
+print("--> Initializing application and downloading models...")
+DEVICE = "cpu"
+
+# --- Download and Load Segmentation Model (UNet) ---
+try:
+    SEG_REPO_ID = "sheikh987/unet-isic2018"
+    SEG_MODEL_FILENAME = "unet_full_data_best_model.pth"
+    print(f"--> Downloading segmentation model from: {SEG_REPO_ID}")
+    seg_model_path = hf_hub_download(repo_id=SEG_REPO_ID, filename=SEG_MODEL_FILENAME)
+    
+    segmentation_model = smp.Unet(encoder_name="resnet34", encoder_weights=None, in_channels=3, classes=1).to(DEVICE)
+    segmentation_model.load_state_dict(torch.load(seg_model_path, map_location=DEVICE))
+    segmentation_model.eval()
+    print("    Segmentation model loaded successfully.")
+
+except Exception as e:
+    print(f"!!! ERROR loading segmentation model: {e}")
+    raise gr.Error("Failed to load the segmentation model. Check repository name and file paths.")
+
+
+# --- Download and Load Classification Model (EfficientNet) ---
+try:
+    CLASS_REPO_ID = "sheikh987/efficientnet-isic-classifier"
+    CLASS_MODEL_FILENAME = "efficientnet_isic_classifier_best.pth"
+    print(f"--> Downloading classification model from: {CLASS_REPO_ID}")
+    class_model_path = hf_hub_download(repo_id=CLASS_REPO_ID, filename=CLASS_MODEL_FILENAME)
+
+    NUM_CLASSES = 7
+    classification_model = timm.create_model('efficientnet_b3', pretrained=False, num_classes=NUM_CLASSES).to(DEVICE)
+    classification_model.load_state_dict(torch.load(class_model_path, map_location=DEVICE))
+    classification_model.eval()
+    print("    Classification model loaded successfully.")
+
+except Exception as e:
+    print(f"!!! ERROR loading classification model: {e}")
+    raise gr.Error("Failed to load the classification model. Check repository name and file paths.")
+
+
+# --- Load Knowledge Base and Labels ---
+try:
+    with open('knowledge_base.json', 'r') as f:
+        knowledge_base = json.load(f)
+    print("--> Knowledge base loaded.")
+except FileNotFoundError:
+    raise gr.Error("knowledge_base.json not found. Make sure it has been uploaded to the Space.")
+
+idx_to_class_abbr = {0: 'MEL', 1: 'NV', 2: 'BCC', 3: 'AKIEC', 4: 'BKL', 5: 'DF', 6: 'VASC'}
+
+# --- Define Image Transforms ---
+transform_segment = A.Compose([
+    A.Resize(height=256, width=256),
+    A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], max_pixel_value=255.0),
+    ToTensorV2(),
+])
+transform_classify = transforms.Compose([
+    transforms.Resize((300, 300)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+
+print("\n--> Application ready to accept requests.")
+
+
+# --- 2. DEFINE THE FULL PIPELINE FUNCTION (UPDATED) ---
+
+def full_pipeline(input_image):
+    if input_image is None:
+        return None, None, "Please upload an image."
+
+    image_np = np.array(input_image.convert("RGB"))
+
+    # STAGE 1: SEGMENTATION
+    augmented_seg = transform_segment(image=image_np)
+    seg_input_tensor = augmented_seg['image'].unsqueeze(0).to(DEVICE)
+    with torch.no_grad():
+        seg_logits = segmentation_model(seg_input_tensor)
+    seg_mask = (torch.sigmoid(seg_logits) > 0.5).float().squeeze().cpu().numpy()
+    
+    if seg_mask.sum() < 200:
+        return None, None, "Analysis Failed: No lesion could be clearly identified."
+
+    # STAGE 2: CROP and CLASSIFY
+    rows = np.any(seg_mask, axis=1)
+    cols = np.any(seg_mask, axis=0)
+    rmin, rmax = np.where(rows)[0][[0, -1]]
+    cmin, cmax = np.where(cols)[0][[0, -1]]
+    
+    padding = 15
+    rmin, rmax = max(0, rmin - padding), min(image_np.shape[0], rmax + padding)
+    cmin, cmax = max(0, cmin - padding), min(image_np.shape[1], cmax + padding)
+
+    cropped_image_pil = Image.fromarray(image_np[rmin:rmax, cmin:cmax])
+
+    class_input_tensor = transform_classify(cropped_image_pil).unsqueeze(0).to(DEVICE)
+    with torch.no_grad():
+        class_logits = classification_model(class_input_tensor)
+        probabilities = torch.nn.functional.softmax(class_logits, dim=1)
+    
+    confidence, predicted_idx = torch.max(probabilities, 1)
+    confidence_percent = confidence.item() * 100
+    
+    # SAFETY NET
+    CONFIDENCE_THRESHOLD = 75.0
+    if confidence_percent < CONFIDENCE_THRESHOLD:
+        inconclusive_text = (
+            f"**Analysis Inconclusive**\n\n"
+            f"The AI model's confidence ({confidence_percent:.2f}%) is below the required threshold of {CONFIDENCE_THRESHOLD}%.\n\n"
+            "This can happen if the image is blurry, has poor lighting, or shows a condition the model was not trained on.\n\n"
+            "**--- IMPORTANT DISCLAIMER ---**\n"
+            "This is NOT a diagnosis. Please consult a qualified dermatologist for an accurate assessment."
+        )
+        mask_display = Image.fromarray((seg_mask * 255).astype(np.uint8))
+        return mask_display, cropped_image_pil, inconclusive_text
+
+    # --- STAGE 3: LOOKUP and FORMAT (UPDATED) ---
+    predicted_abbr = idx_to_class_abbr[predicted_idx.item()]
+    info = knowledge_base.get(predicted_abbr, {})
+    
+    # Format the 'causes' and 'treatments' lists into clean, bulleted strings
+    causes_list = info.get('causes', ['Specific causes not listed.'])
+    causes_text = "\n".join([f"• {c}" for c in causes_list])
+
+    treatments_list = info.get('common_treatments', ['No specific treatments listed.'])
+    treatments_text = "\n".join([f"• {t}" for t in treatments_list])
+
+    # Build the final output text using all the information
+    info_text = (
+        f"**Predicted Condition:** {info.get('full_name', 'N/A')} ({predicted_abbr})\n"
+        f"**Confidence:** {confidence_percent:.2f}%\n\n"
+        f"**Description:**\n{info.get('description', 'No description available.')}\n\n"
+        f"**Common Causes:**\n{causes_text}\n\n"
+        f"**Common Treatments:**\n{treatments_text}\n\n"
+        f"**--- IMPORTANT DISCLAIMER ---**\n{info.get('disclaimer', '')}"
+    )
+    
+    mask_display = Image.fromarray((seg_mask * 255).astype(np.uint8))
+    
+    return mask_display, cropped_image_pil, info_text
+
+
+# --- 3. CREATE AND LAUNCH THE GRADIO INTERFACE ---
+iface = gr.Interface(
+    fn=full_pipeline,
+    inputs=gr.Image(type="pil", label="Upload Skin Image"),
+    outputs=[
+        gr.Image(type="pil", label="Segmentation Mask"),
+        gr.Image(type="pil", label="Cropped Lesion"),
+        gr.Markdown(label="Analysis Result")
+    ],
+    title="AI Skin Lesion Analyzer",
+    description="This tool performs a two-stage analysis on a skin lesion image. **Stage 1:** A UNet model segments the lesion. **Stage 2:** An EfficientNet model classifies the segmented lesion. \n\n**DISCLAIMER:** This is an educational tool and is NOT a substitute for professional medical advice. Always consult a qualified dermatologist for any health concerns.",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()

knowledge_base.json

@@ -0,0 +1,101 @@
+{
+  "MEL": {
+    "full_name": "Melanoma (Cancerous)",
+    "description": "Melanoma is the most serious type of skin cancer. It develops in the cells (melanocytes) that produce melanin — the pigment that gives your skin its color. While less common than other skin cancers, melanoma is more dangerous because of its ability to spread to other organs more rapidly if not treated at an early stage.",
+    "causes": [
+      "Intense UV radiation exposure (sunburns), especially during childhood.",
+      "Use of tanning beds.",
+      "A family history of melanoma or having many moles."
+    ],
+    "common_treatments": [
+      "Surgical excision to remove the tumor and a margin of healthy skin.",
+      "Immunotherapy to boost the body's own immune system to fight cancer.",
+      "Targeted therapy drugs that focus on specific weaknesses in cancer cells.",
+      "Chemotherapy or radiation therapy in advanced cases."
+    ],
+    "disclaimer": "This is NOT a diagnosis. A potential melanoma detection requires urgent consultation with a qualified dermatologist for a biopsy and professional medical advice."
+  },
+  "NV": {
+    "full_name": "Melanocytic Nevus (Common Mole)",
+    "description": "A Melanocytic Nevus, commonly known as a mole, is a non-cancerous (benign) growth of pigment-producing cells (melanocytes). They are extremely common and most are harmless. However, it's important to monitor them for any changes in size, shape, or color, as this could be a sign of melanoma.",
+    "causes": [
+      "Largely determined by genetics.",
+      "Sun exposure, particularly during childhood, can increase the number of moles."
+    ],
+    "common_treatments": [
+      "No treatment is typically necessary for benign moles.",
+      "Monitoring for changes (Asymmetry, Border, Color, Diameter, Evolving).",
+      "Surgical removal if it is bothersome, for cosmetic reasons, or if it shows suspicious changes."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Always have new or changing moles checked by a qualified dermatologist."
+  },
+  "BCC": {
+    "full_name": "Basal Cell Carcinoma",
+    "description": "Basal Cell Carcinoma is the most common form of skin cancer. It is a slow-growing cancer that rarely spreads to other parts of the body. It often appears as a slightly transparent bump on sun-exposed skin, such as the head or neck. Early diagnosis and treatment are important.",
+    "causes": [
+      "Long-term, cumulative exposure to UV radiation from the sun.",
+      "Having fair skin that burns easily.",
+      "A history of severe sunburns."
+    ],
+    "common_treatments": [
+      "Surgical excision or Mohs surgery (a precise surgical technique).",
+      "Curettage and electrodesiccation (scraping and burning).",
+      "Topical medicated creams for very superficial cases."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Consult a qualified dermatologist for any health concerns."
+  },
+  "AKIEC": {
+    "full_name": "Actinic Keratosis (Pre-cancerous)",
+    "description": "Actinic Keratosis is a rough, scaly patch on the skin that develops from years of sun exposure. It is considered a pre-cancer because if left untreated, it can progress into a type of skin cancer called squamous cell carcinoma.",
+    "causes": [
+      "Frequent or intense exposure to UV rays from the sun or tanning beds.",
+      "Most common in fair-skinned, older individuals."
+    ],
+    "common_treatments": [
+      "Cryotherapy (freezing with liquid nitrogen).",
+      "Topical prescription creams or gels.",
+      "Photodynamic therapy (using a special light to activate a drug)."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Consult a qualified dermatologist for any health concerns."
+  },
+  "BKL": {
+    "full_name": "Benign Keratosis-like Lesions",
+    "description": "This is a general category for various non-cancerous (benign) skin growths, such as seborrheic keratosis ('pasted-on' growths) or solar lentigo (age spots/sun spots). These are very common and not cancerous.",
+    "causes": [
+      "Aging is a primary factor for seborrheic keratosis.",
+      "Genetics can play a role.",
+      "Sun exposure is the direct cause of solar lentigos (sun spots)."
+    ],
+    "common_treatments": [
+      "No treatment is medically necessary.",
+      "Can be removed for cosmetic reasons using methods like cryotherapy (freezing), scraping, or laser therapy."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Consult a qualified dermatologist for any health concerns."
+  },
+  "DF": {
+    "full_name": "Dermatofibroma",
+    "description": "A dermatofibroma is a common, benign (non-cancerous) lump that grows in the deeper layers of the skin. It often appears on the lower legs and feels like a hard button under the skin. It is typically harmless.",
+    "causes": [
+      "The exact cause is unknown.",
+      "Often appear after a minor skin injury like an insect bite or a shaving cut."
+    ],
+    "common_treatments": [
+      "No treatment is required unless it is causing symptoms like itching or pain.",
+      "Can be surgically excised if it is bothersome."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Consult a qualified dermatologist for any health concerns."
+  },
+  "VASC": {
+    "full_name": "Vascular Lesion",
+    "description": "A vascular lesion is a mark on the skin formed by blood vessels that have not formed correctly. This category includes benign conditions like cherry angiomas (small red dots), spider angiomas, or pyogenic granulomas. Most are harmless.",
+    "causes": [
+      "Genetics and aging are common factors for cherry angiomas.",
+      "Hormonal changes, such as during pregnancy, can cause spider angiomas."
+    ],
+    "common_treatments": [
+      "Most do not require treatment.",
+      "Can be removed for cosmetic reasons with laser therapy or electrocautery (a fine electric needle)."
+    ],
+    "disclaimer": "This is NOT a diagnosis. This AI tool is for informational purposes only. Consult a qualified dermatologist for any health concerns."
+  }
+}

requirements.txt

@@ -0,0 +1,8 @@
+torch
+torchvision
+segmentation-models-pytorch==0.3.3
+timm==0.9.2
+albumentations==1.3.1
+gradio==4.12.0
+Pillow
+numpy