Learn how we helped a clinical imaging intelligence company implement a solution to de-identify PHI and CT scans that comply with HIPAA rules and build a foundational MLOps infrastructure to support scalable machine learning in life sciences.
From notebooks to frictionless production: learn how to make your ML models update themselves every week (or earlier). Complete an MLOps + DevOps integration on AWS with practical architecture, detailed steps, and a real case in which a Startup transformed its entire process.
Explore how we helped a healthcare organization build an AI system that significantly enhanced cancer diagnostics.
A clinical imaging intelligence company is accelerating the approval and adoption of life-saving therapies to patients through an AI-powered digital biomarker solution. With proprietary imaging biomarkers for precise quantitative endpoints and a trial imaging management solution, the company's solution is helping biopharma sponsors save millions in drug development costs.
The client needed to enhance their platform with a robust solution for de-identifying protected health information (PHI) from Computed Tomography (CT) scans to comply with HIPAA safe harbor rules. While they had an existing process for metadata de-identification, they lacked a solution for removing sensitive information embedded within medical images themselves.
Additionally, the client wanted to establish foundational MLOps infrastructure to enable their data scientists to effectively develop, deploy, and manage machine learning models at scale for their life sciences applications.
Caylent designed and implemented a comprehensive AWS-based solution with two main components:
A scalable workflow was created to process clinical imaging data while ensuring compliance with HIPAA safe harbor rules:
To support the client's machine learning initiatives in clinical imaging analysis:
SageMaker Studio Environment: Configured with Jupyter notebooks, EFS volumes, and security policies
End-to-End MLOps Pipelines:
Containerization: SageMaker-native containerization for Python models
Governance: Resource tagging, AWS CloudWatch, AWS EventBridge, and AWS SageMaker Governance
The implementation delivered significant benefits to the client's life sciences operations:
The solution specifically addressed the unique requirements of life sciences data processing, including handling single-channel grayscale medical images with intensity values of 0-10,000, secondary captures, videos, and annotations - all while maintaining strict compliance with healthcare data privacy regulations.
By implementing this solution, the client strengthened their position as a leader in clinical imaging intelligence, further enhancing their ability to accelerate the development and approval of life-saving therapies.
Leveraging our accelerators and technical experience
Browse GenAI Offerings
Caylent Industries
Accelerate medical innovation and improve patient outcomes and experience with a secure and resilient global cloud infrastructure on AWS.
Caylent Services
Apply artificial intelligence (AI) to your data to automate business processes and predict outcomes. Gain a competitive edge in your industry and make more informed decisions.
Caylent Team