OPTARI: An open-source software framework for clinical translation of optoacoustic imaging

Moritz Schillinger; Maximilian Bader; Adrian Buehler; Felix Wachter; Ferdinand Knieling; Vasilis Ntziachristos; Katharina Breininger

cs.SEOct 23, 2026

OPTARI: An open-source software framework for clinical translation of optoacoustic imaging

Authors: Moritz Schillinger, Maximilian Bader, Adrian Buehler, Felix Wachter, Ferdinand Knieling, Vasilis Ntziachristos, Katharina Breininger

Organizations: Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany · Chair of Biological Imaging, Central Institute for Translational Cancer Research (TranslaTUM), School of Medicine and Health & School of Computation, Information and Technology, Technical University of Munich, Munich, Germany · Institute of Biological and Medical Imaging, Bioengineering Center, Helmholtz Zentrum München, Neuherberg, Germany · Department of Vascular Surgery, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany ·

Abstract

Combined optoacoustic (OptA) and ultrasound imaging is a promising modality across a wide range of pathologies. Its use in clinical research, however, is limited by a lack of analysis software accessible to users without programming expertise. Existing tools are either script-based engineering frameworks or proprietary vendor applications. We present OPTARI, an open-source graphical software application to facilitate large-scale clinical optoacoustic-ultrasound (OPUS) studies. OPTARI builds on the napari image viewer and the PATATO toolkit for OptA data processing. It supports native vendor and open HDF5 data formats, aligns with the IPASC standard, and is distributed as a standalone executable. Features include region-of-interest annotation, reconstruction, chromophore unmixing, deep-learning-based tissue segmentation, and temporal and spectral analysis modules. OPTARI offers a combination of features for clinical study analysis that none of the compared tools provide. The automated tissue segmentation produced results comparable to expert labeling for muscle tissue, and batch processing reduced analysis time from minutes to under one second per scan. The tool is used in ongoing clinical OPUS studies. OPTARI connects engineering frameworks with medical research and provides an open-source basis for reproducible and standardized analysis in clinical OptA imaging studies.

Figures & tables

	Requirement	Description
R1	Easy Deployment	Installation and execution require no command-line interaction or script execution. Distribution as a standalone executable that runs without administrative privileges, so it can be deployed in restricted hospital IT environments.
R2	Graphical Interface	Provide a click-based GUI ( GUI ) for intuitive navigation, paired with keyboard shortcuts to speed up repetitive workflows.
R3	Study Navigation	Support analysis across multiple subjects and scans, easy switching between scans, and fast scrolling through temporal and spectral layers.
R4	Objective Processing	Replace subjective parameter selection with deterministic procedures as much as reasonably possible, and allow easy sharing of parameters and configurations.
R5	Documentation	Provide feature documentation and step-by-step guides for common clinical study workflows.
R6	Interoperability	Read and write both vendor-native and open data formats, and keep the underlying code accessible and documented so that custom modules or data formats can be integrated.

Table 1: System requirements for OPTARI.

Figure 1: Main viewer window of OPTARI. (1) Scan Browser for study navigation. (2) Sliders for temporal and spectral scrolling. (3) Layer List , showing image data and annotations. (4) Metadata viewer. (5) Live Analysis table, showing dynamic updates of ROI data. (6) Saved Analysis table to collect data across scans.

Figure 2: Selection of processing and analysis widgets in OPTARI. (7) Segmentation module to automatically place an ROI in the target tissue. (8) ROI Library for loading and saving ROI presets. (9) Temporal Analysis module to plot signal intensity changes over time. (10) Spectral Analysis module to visualize signal magnitude across wavelengths. (11) Reconstruction module for BP - and deep-learning-based image reconstruction. (12) Unmixing module for spectral unmixing of chromophore concentrations.

Figure 3: Overview of the modular software architecture and selected components of OPTARI: UI Layer (dock widgets), Control Layer (central OptariController and specialized task modules), Utilities Layer, and External Layer.

Requirement / Feature	iLabs	PATATO	MITK-PAI	PATLAB	ImageJ/Fiji	OPTARI
R1: Easy Deployment
– Standalone executable	$+$	$-$	$+$	$-$	$+$	$+$
– No admin rights required	$+$	$\circ$	$\circ$	$-$	$+$	$+$
R2: Graphical Interface
– GUI -driven analysis	$+$	$\circ$	$+$	$\circ$	$+$	$+$
– Keyboard shortcuts	$-$	$-$	$\circ$	$-$	$+$	$+$

Table 2: Feature comparison of OPTARI against existing software tools used in clinical OptA imaging. Evaluation criteria correspond to the requirements (R1–R6) defined in Section 2 . Assessment based on the software versions and documentation available in September 2026.

Figure 4: Automated batch-mode analysis applied to one representative scan (13 wavelengths, $\lambda$ ). Each panel reports two configuration choices for its step. Times are reported as mean $\pm$ standard deviation over 100 repetitions, measured on a standard laptop (Intel Core i7-1255U, 1.7 GHz, 16 GB RAM). HDF5 data are loaded lazily, so the read cost may fall into the following steps. The default configuration (HDF5 loading, BP , two-chromophore LU , single-class segmentation, single-frame extraction) took 0.93 $\pm$ 0.03 s in total.

Photoacoustic Tomography

See all 10 papers

AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis
Mar 19, 2026Ufaq Khan, L. D. M. S. Sai Teja, Ayuba Shakiru +4Medical Image Analysis Ultrasound Imaging
MBZUAI, Abu Dhabi, UAE · NIT Silchar, India · Birmingham City University, UK
Representation learning from OCT images
May 4, 2026Hedi Tabia, Désiré Sidibé, Nawres Khlifa +6Medical Imaging Medical Imaging Foundation Models
IBISC Univ. Evry Université Paris-Saclay · University of Tunis El Manar · ESIEE Paris - Université Gustave Eiffel +2
OCTN: Neural OCT Representations for Robot-Guided Precision Intervention
Sep 6, 2026Ravi Prakash, Ryan P. McNabb, Patrick J. Codd +1Optical Coherence Tomography Implicit Neural Representations
Duke University, Durham, NC 27705 USA · Arizona State University, Phoenix, AZ 85287 USA

Mar 19, 2026J/K move · Enter open · S save

AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis

Ufaq Khan, L. D. M. S. Sai Teja, Ayuba Shakiru, Mai A. Shaaban+3

MBZUAI, Abu Dhabi, UAE · NIT Silchar, India · Birmingham City University, UK

Medical Image Analysis Ultrasound Imaging Multi-Task Learning

Open paper AskPDF arXiv

Ultrasound images vary widely across scanners, operators, and anatomical targets, which often causes models trained in one setting to generalize poorly to new hospitals and clinical conditions. The Foundation Model Challenge for Ultrasound Image Analysis (FMC-UIA) reflects this difficulty by requiring a single model to handle multiple tasks, including segmentation, detection, classification, and landmark regression across diverse organs and datasets. We propose a unified multi-task framework based on a transformer visual encoder from the Qwen3-VL family. Intermediate token features are projected into spatial feature maps and fused using a lightweight multi-scale feature pyramid, enabling both pixel-level predictions and global reasoning within a shared representation. Each task is handled by a small task-specific prediction head, while training uses task-aware sampling and selective loss balancing to manage heterogeneous supervision and reduce task imbalance. Our method is designed to be simple to optimize and adaptable across a wide range of ultrasound analysis tasks. The performance improved from 67% to 85% on the validation set and achieved an average score of 81.84% on the official test set across all tasks. The code is publicly available at: https://github.com/saitejalekkala33/FMCUIA-ISBI.git

Abstract

Photoacoustic Tomography

Explore similar work

AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis

Representation learning from OCT images

OCTN: Neural OCT Representations for Robot-Guided Precision Intervention