Cloud Tiering is Coming of Age for Clinical Files

Healthcare organizations today are storing petabytes of medical imaging data—labs, X-rays, MRIs, CT scans and more—a number that is expanding with no end in sight. To make matters worse, due to regulations, healthcare providers typically must retain medical imaging files for several years; they may even have an enterprise-wide policy of not deleting data ever.

Aside from compliance requirements, clinical researchers may need access to the data indefinitely while clinicians require collaboration and file sharing across a patient’s continuum of care. This presents a conundrum from both an economic and IT management perspective.

Internal storage for large image files is expensive—costing millions a year for some organizations on Porsche-grade NAS devices.

The data must be secured, replicated and backed up. Meanwhile, in most cases, imaging data is rarely accessed after a few days.

To get more flexibility and cost savings, healthcare organizations are increasing their investments in cloud data storage. In a recent webinar sponsored by the Society for Imaging Informatics in Medicine (SIIM), storage architects from two large healthcare systems discussed strategies for tiering and migrating images to the cloud.

Such decisions can be rife with politics and long-standing institutional perspectives. Health systems are generally risk-averse—they are handling sensitive patient information after all—and tolerance for downtime is usually quite low.

Read the Whitepaper: How to Manage Medical Imaging Data Growth Costs

Cloud Tiering in Healthcare for Dear Life

Healthcare professionals depend upon accurate, timely data to make the best decisions; the loss of important patient data can have dire consequences. Keeping these large files safe and readily available could be a matter of life or death for a patient with a serious illness.

One of the storage managers interviewed in the SIIM webinar noted that a TCO study projected savings of 65% from moving pathology images that are 90 days or older from the on-premises HCI and NAS arrays to a third tier on Google Cloud Object Storage. That’s compelling evidence to consider a new unstructured data management strategy.

In this particular case, the organization is scanning 1TB of pathology slides per day; they remain on the Tier 1 HCI storage for three days, after which they are moved to the Tier 2 NAS device. Using Komprise, the post-90 day old slides are automatically tiered to Google Cloud storage, and once there, move between two tiers based on age.

“The Komprise transparent move technology (TMT) hides the location from technicians,” the storage manager said. “They don’t even notice it’s coming from the cloud.”

Since these older images stored in the cloud are accessed so rarely, the cloud egress fees to bring them back to the on-premises digital pathology solution have been minimal. Komprise pulls the slides back to the Tier 2 storage for rehydration and afterward they are deleted since there’s a copy in the cloud.

Using Komprise for Medical Imaging Cloud Tiering and Cloud Data Management

Medical imaging systems use high-performance NAS devices to store medical images. This ensures fast access to files for the medical staff. However, such high-end storage is expensive and the images are generally not used after patient diagnosis. Komprise provides a tightly integrated solution with NAS devices to automatically move older images (e.g. images over 90 days old) to the cloud based on policy for significantly cheaper storage and without affecting user experience. Komprise is in use by large hospitals throughout the nation.

Paving the Way for Medical Image Longevity

As high-value unstructured data like medical images exceed the limits of on-premises storage, the options are becoming increasingly limited within static budgets. Healthcare organizations need to craft a long-term plan with simple execution for cloud data management. Consider this comment from the SIIM webinar speaker:

“Because we’re keeping slides indefinitely, the amount of storage that would be required to house that much data indefinitely (600k slides annually, 1TB a day) would be prohibitively expensive. We had to come up with a new solution for Tier 3, which is the archived data.”

Sound familiar? Learn more about Komprise Intelligent Data Management for health and life sciences.

Read the blog post: Healthcare and Unstructured Data Management

FAQs: Medical Imaging, Cloud Tiering, and AI-Ready Data

Why is medical imaging data such a challenge for healthcare organizations today?

Healthcare organizations are generating petabytes of unstructured data from imaging systems such as PACS, digital pathology, and radiology. These files must often be retained for years or even indefinitely, driving massive storage, backup, and compliance costs.

At the same time, most imaging data is rarely accessed after initial diagnosis, yet it remains on expensive primary storage. This creates a growing gap between data growth and IT budgets.

As AI adoption increases, this challenge intensifies because imaging data is also one of the most valuable inputs for clinical AI, making it essential to manage both cost and accessibility.

How does unstructured data management improve AI outcomes in healthcare?

AI models rely on high-quality, relevant datasets. Without proper unstructured data management, healthcare organizations risk:

• ingesting duplicate or low-value images
• increasing AI processing and storage costs
• reducing model accuracy due to noisy data
• exposing sensitive patient data

A metadata-driven approach enables organizations to:

• identify the most relevant imaging datasets
• enrich metadata for search and retrieval
• filter out unnecessary data before AI ingestion

This ensures AI systems are trained and operated on trusted, high-value clinical data, improving both accuracy and outcomes.

How does Komprise help manage medical imaging data growth and costs?

Komprise enables healthcare IT teams to analyze, classify, and automatically tier unstructured data based on usage and value.

For medical imaging, this means:

• transparently moving older, inactive images to lower-cost cloud storage
• freeing up expensive primary NAS capacity
• maintaining seamless access for clinicians and researchers
• enabling cloud-native access for AI and analytics

Organizations can reduce storage costs by up to 70% while extending the life of existing infrastructure and supporting AI initiatives. Learn more about Komprise for Hospitals and Healthcare.

What does the NewYork-Presbyterian case study show about AI data ingestion?

The NewYork-Presbyterian Hospital case study highlights how intelligent data management directly impacts AI success.

Using Komprise Intelligent AI Ingest with cloud storage and AI tools, the organization:

• reduced cloud storage costs by 96%
• reduced data footprint from 1PB to ~33TB through intelligent data curation
• achieved 10x faster AI data ingestion
• delivered curated, high-value datasets to AI systems instead of bulk data

The key insight: AI performance improves when you ingest less, but better data faster.

Why is intelligent tiering critical for AI-driven healthcare environments?

Intelligent tiering is not just about cost savings. It is foundational to scalable AI.

By automatically placing data on the right storage tier based on usage and value, organizations can:

• reduce infrastructure costs across storage, backup, and cloud
• ensure high-value data remains accessible for AI and clinical workflows
• minimize unnecessary data movement and duplication
• enable direct access to cloud-based AI services

Komprise takes this further by combining Transparent Move Technology for intelligent tiering with:

• global metadata visibility
• automated data workflows
• AI-ready data ingestion

This creates a continuous pipeline of curated, governed data for AI, rather than a static archive.