Handling Irrelevant Uploads in Flask Application for Bone Fracture Detection

Question

I'm developing a Flask application for bone fracture detection, where users can upload X-ray images, and the application predicts whether a bone fracture is present or not. However, I'm facing an issue with handling irrelevant uploads, such as images of body parts other than elbows, hands, and shoulders.

Here's an overview of my Flask application code:

Flask app code

import os
from flask import Flask, request, jsonify
from werkzeug.utils import secure_filename
from predictions import predict
from flask_cors import CORS

app = Flask(__name__)
CORS(app)  # Enable CORS for all routes
app.config['UPLOAD_FOLDER'] = 'uploads'
app.config['ALLOWED_EXTENSIONS'] = {'png', 'jpg', 'jpeg'}

def allowed_file(filename):
    return '.' in filename and filename.rsplit('.', 1)[1].lower() in app.config['ALLOWED_EXTENSIONS']

@app.route('/predict', methods=['POST'])
def predict_bone_fracture():
    if 'file' not in request.files:
        return jsonify({'error': 'No file part'})

    file = request.files['file']

    if file.filename == '':
        return jsonify({'error': 'No selected file'})

    if file and allowed_file(file.filename):
        filename = secure_filename(file.filename)
        filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
        file.save(filepath)

        # Perform prediction using the predict function from predictions.py
        bone_type_result = predict(filepath)
        result = predict(filepath, bone_type_result)

        # You can customize the response based on your requirements
        return jsonify({'bone_type': bone_type_result, 'result': result})

    return jsonify({'error': 'Invalid file format'})

if __name__ == "__main__":
    app.run()

The predict_bone_fracture() function receives the uploaded image, saves it to a specified folder, and then performs predictions using a predict() function from an external module (predictions.py). If the uploaded file is not an image or has an unsupported format, it returns an error response.

My main concern is how to handle cases where users upload images that do not correspond to the specified body parts (i.e., elbows, hands, shoulders). For example, if a user uploads an image of an eye instead of a bone, the application should reject the upload and provide an appropriate error message.

I believe I need to incorporate a mechanism to detect the relevant body parts in the uploaded images and verify if they match the expected body parts for prediction (i.e., elbows, hands, shoulders). However, I'm unsure about the best approach to implement this.

Could you please provide suggestions or ideas on how to address this issue? Specifically, I'm looking for guidance on:

Implementing a mechanism to detect relevant body parts in the uploaded images. Checking if the detected body parts match the expected body parts for prediction. Providing appropriate error handling and messages for irrelevant uploads. Any insights or code examples would be greatly appreciated. Thank you!