CW
SCIENTIFIC LEADERSHIP
Prof. Dr. med. Cleo-Aron Weis, M.Sc.
Scientific SupervisorScientific supervision and strategic oversight of DPARS; Head of Computational Pathology Heidelberg.
Digital pathology infrastructure
From scanner output to structured pathology data.
DPARS is a modular orchestration platform designed to connect heterogeneous whole-slide imaging workflows with metadata intelligence, quality control, standards-based conversion, delivery and retention-aware archival.
One coordinated platform
A modular journey for every whole-slide image.
DPARS separates responsibilities into observable services so each step can evolve independently while preserving provenance across the workflow.
Digital Pathology Workflow
DPARS closes the operational gap.
Inspired by the DPARS presentation: heterogeneous scanner output enters a controlled, traceable processing layer before clinical delivery. The workflow below stays inside a horizontally scrollable frame on smaller screens.
INPUT
Scanners
SVS · NDPI · TIFF · other WSI formats
→
01
Format handling
Routes heterogeneous scanner output into the appropriate DPARS path.
→
02
BabelShark
Reads label and file metadata, resolves identity and standardizes naming.
→
03
Quality Control
Evaluates focus, sharpness and image-quality signals before downstream processing.
→
04 · WHEN NEEDED
WSI-Forge
Creates a normalized full-resolution WSI derivative for supported routing scenarios.
→
05
Dicomizer
Creates standards-oriented DICOM WSI output with validation.
→
06
Uploader
Tracks delivery state, retries and transfer toward PACS.
→
CLINICAL DESTINATION
PACS / WSI
Managed access for the diagnostic workflow.
Dagsterorchestration · runs · recovery
PostgreSQLstate · lineage · traceability
Dashboardmonitoring · review · operations
Wall-Eretention · archival lifecycle
Service constellation
Specialized services. Shared lineage.
⌁
Metadata intelligence
Multi-route metadata extraction combines fast paths with deeper barcode and OCR strategies when needed.
BABELSHARK →◫
Quality gates
Image-quality metrics create explicit checkpoints before downstream conversion and delivery.
QC →◇
Interoperability
Format-aware normalization and DICOM conversion reduce dependence on a single scanner ecosystem.
WSI-FORGE + DICOMIZER →↗
Controlled delivery
Transfer state, retries, durations and failures remain observable rather than disappearing into a black box.
UPLOADER →◌
Archival lifecycle
Long-term storage policy is separated from the clinical processing path and governed by validation-first rules.
WALL-E →◎
Orchestration & audit
Database-backed lineage and orchestration provide a coherent operational view across independently evolving modules.
DPARS CORE →Architecture principle
Processing and archival are intentionally separated.
Full-resolution derivatives support active processing. Reduced-resolution archival derivatives belong to a separate lifecycle and never re-enter the processing pipeline.
Active processing path
Scanner → metadata/routing → quality gate → normalization when required → DICOM conversion → controlled delivery.
Long-term archival path
Database-driven retention eligibility → reduced-resolution OME-TIFF derivative → independent validation → future cleanup eligibility under fail-closed safety rules.
Follow a slide
One WSI. One traceable journey.
A conceptual walkthrough of how DPARS turns heterogeneous scanner output into an observable, standards-oriented digital pathology workflow.
01 · INGESTScannerWSI enters the controlled workflow.
02 · UNDERSTANDBabelSharkIdentity, label metadata and routing.
03 · VERIFYQuality ControlImage-quality metrics and gate.
04 · NORMALIZEWSI-ForgeFull-resolution derivative when required.
05 · STANDARDIZEDicomizerDICOM WSI representation.
06 · DELIVERUploaderTraceable delivery and state.
DPARS Team
Leadership and ownership, in one view.
Scientific leadership and project responsibilities are shown together—without turning the team into a ranking.
SA
PROJECT & TECHNICAL LEADERSHIP
Shahram Aliyari, M.Sc.
Project Lead & Coordinator · Platform ArchitectureOverall project coordination, platform architecture, cross-service integration, orchestration and data-lineage design; responsibility for BabelShark, WSI-Forge and Wall-E.
BT
SERVICE OWNERSHIP
Balamurugan Thirukonda S. B.
Quality ControlResponsible for the DPARS Quality Control service and its operational integration.
ML
SERVICE OWNERSHIP
Maximilian Legnar, M.Sc.
Dicomizer · UploaderResponsible for DICOM conversion and the downstream upload service.
Institutional affiliation/titles and DPARS project responsibilities are intentionally separated. Portrait blocks are ready for approved public profile photographs.
Why DPARS
Built for heterogeneous digital pathology.
DPARS focuses on the operational gap between scanner output and downstream clinical or research systems: identity, metadata, quality, interoperability, traceability and lifecycle management. The architecture is modular so individual services can be tested, replaced and extended without collapsing the workflow into one monolithic application.