AWS Certified Machine Learning – Specialty — Question 104

A medical imaging company wants to train a computer vision model to detect areas of concern on patients' CT scans. The company has a large collection of unlabeled CT scans that are linked to each patient and stored in an Amazon S3 bucket. The scans must be accessible to authorized users only. A machine learning engineer needs to build a labeling pipeline.
Which set of steps should the engineer take to build the labeling pipeline with the LEAST effort?

Answer options

• A. Create a workforce with AWS Identity and Access Management (IAM). Build a labeling tool on Amazon EC2 Queue images for labeling by using Amazon Simple Queue Service (Amazon SQS). Write the labeling instructions.
• B. Create an Amazon Mechanical Turk workforce and manifest file. Create a labeling job by using the built-in image classification task type in Amazon SageMaker Ground Truth. Write the labeling instructions.
• C. Create a private workforce and manifest file. Create a labeling job by using the built-in bounding box task type in Amazon SageMaker Ground Truth. Write the labeling instructions.
• D. Create a workforce with Amazon Cognito. Build a labeling web application with AWS Amplify. Build a labeling workflow backend using AWS Lambda. Write the labeling instructions.

Correct answer: C

Explanation

The correct answer is C because creating a private workforce and using Amazon SageMaker Ground Truth with the built-in bounding box task type is specifically designed for labeling tasks like those required for CT scans. Options A and D involve more complex setups that require additional resources and development work, while option B is less suitable because it focuses on image classification rather than the bounding box task that is more appropriate for identifying areas of concern in medical images.