DICOM Whole Slide Imaging (WSI) is a specification that extends the DICOM standard to accommodate the unique data characteristics of digital pathology. It defines a dual-layer storage model: a low-resolution overview image for rapid navigation and a high-resolution, tiled pyramid representation of the entire glass slide. This structure enables efficient streaming and pan-and-zoom viewing of massive, multi-gigabyte images without requiring the entire file to be loaded into memory.
Glossary
DICOM Whole Slide Imaging

What is DICOM Whole Slide Imaging?
DICOM Whole Slide Imaging (WSI) is a standard supplement to the DICOM protocol that defines a data structure and metadata framework for the storage, retrieval, and viewing of gigapixel digital pathology images within existing Picture Archiving and Communication Systems (PACS).
By encoding pathology images as a native DICOM SOP Class, WSI enables the convergence of radiology and pathology workflows on a single VNA or PACS infrastructure. This integration leverages existing DICOMweb services like WADO-RS for efficient, HTTP-based retrieval of specific image tiles, eliminating departmental data silos and allowing for the unified management of a patient's complete diagnostic imaging record.
Core Characteristics of DICOM WSI
DICOM Whole Slide Imaging (WSI) extends the DICOM standard to manage gigapixel digital pathology images, enabling their storage, retrieval, and viewing within standard PACS infrastructure.
Multi-Resolution Pyramid Structure
A DICOM WSI file stores the image as a pyramidal data structure, not a single flat image. This pyramid contains multiple downsampled versions of the original slide, from the highest resolution base layer to a low-resolution thumbnail. This enables efficient progressive streaming, where a viewer requests only the resolution and spatial region needed for the current zoom level, avoiding the need to transfer the entire gigapixel file over a network.
Tiled Organization for Sparse Access
Each layer of the pyramid is subdivided into a regular grid of rectangular tiles, typically 256x256 or 512x512 pixels. This tiling is the core mechanism for sparse data access. A viewing client can use the DICOMweb WADO-RS service to fetch only the specific tiles that fall within the current viewport, rather than downloading the entire image. This HTTP-based tile retrieval is fundamental to the responsive pan-and-zoom experience in digital pathology.
Dual-Personality SOP Classes
DICOM WSI introduces VL Whole Slide Microscopy Image Storage SOP Classes. These are unique because they are 'dual-personality' objects. They contain both traditional DICOM patient and study metadata in a standard header and the pixel data pyramid. This allows a PACS to index and manage a WSI file like any other DICOM image while specialized viewers can interpret the pyramid for navigation. The primary SOP Class UID is 1.2.840.10008.5.1.4.1.1.77.1.6.
Companion Segmentation Objects
WSI is often analyzed by AI to produce tissue maps. The DICOM Segmentation SOP Class is used to store these results as a companion object. A segmentation object references the source WSI instance and encodes binary or fractional maps (e.g., tumor regions) as a tiled, multi-resolution pyramid. This maintains the spatial alignment between the original image and the AI-generated overlay, allowing them to be viewed in perfect registration within a PACS viewer.
Concatenation for Unlimited Size
A single gigapixel WSI can exceed the 4 GB limit of a classic DICOM file. To handle this, the standard uses DICOM Concatenation. The image is split across multiple DICOM instances (parts) that share a single SOP Instance UID. The Concatenation UID (0020,9161) and In-concatenation Number (0020,9162) tags link these parts together, allowing a reader to reassemble the complete dataset seamlessly. This ensures even the largest slides remain compliant.
Optical Path and Z-Stack Encoding
WSI supports advanced microscopy techniques. The Optical Path Sequence (0048,0105) describes the illumination, filter, and objective lens used to acquire the image, which is critical for fluorescence or multispectral imaging. Furthermore, the standard can encode Z-stacks—multiple focal planes at the same XY position—by using the Dimension Organization module, allowing pathologists to focus through the depth of a tissue sample directly within a DICOM-compliant viewer.
Frequently Asked Questions
Essential questions about the DICOM supplement that brings gigapixel digital pathology into the radiology workflow, enabling standard PACS infrastructure to manage microscopy data.
DICOM Whole Slide Imaging (WSI) is a supplement to the DICOM standard that defines how gigapixel digital pathology images are stored, transmitted, and managed using the same infrastructure as radiology. Unlike a standard DICOM CT or MR image, which is a single frame or a small stack of frames, a WSI object represents a multi-resolution pyramid of images. The core difference lies in the data structure: WSI uses a tiled pyramidal organization where the full-resolution baseline layer is divided into thousands of individual square tiles, and multiple downsampled layers are generated to enable smooth zooming and panning. This is defined in the VL Whole Slide Microscopy Image Storage SOP Class. Standard DICOM relies on a single pixel matrix per frame; WSI introduces the concept of a Total Pixel Matrix and a Tiled Organization, allowing a viewer to request only the specific tiles needed for the current viewport, rather than downloading the entire multi-gigabyte file. This enables the use of DICOMweb protocols like WADO-RS for efficient, HTTP-based streaming of pathology data directly into a standard PACS workstation.
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.

Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.

Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
Related Terms
Understanding DICOM Whole Slide Imaging requires familiarity with the specific DICOM objects, protocols, and infrastructure components that enable gigapixel pathology in a standard PACS environment.

About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us