OCT functions by directing light into the eye and interpreting the backscattered photons to construct images of internal structures like the retina and choroid. But the journey of photons through tissue is fraught with challenges. When light encounters complex biological matrices, it scatters unpredictably, producing signals that blend with those carrying useful information. This phenomenon, known scientifically as “optical crosstalk,” causes image blur and loss of contrast, making it difficult to discern fine detail that could be critical for early disease detection. Optical crosstalk is essentially a breakdown of coherence within the returning light, as photons from a single spatial point arrive dispersed across multiple detector pixels. For ophthalmologists and patients alike, this translates to potentially missed or delayed diagnosis of conditions where subtle changes herald disease onset.

The breakthrough reported by Professor Maciej Wojtkowski and his team from the International Centre for Translational Eye Research (ICTER) introduces STOC-T, an innovative approach that goes beyond conventional image enhancement techniques. Unlike software filters applied post-hoc to clean up images, STOC-T reforms the optics of data collection itself—imposing controlled, repetitive phase modulations onto the illuminating light during scanning. By employing distinct spatial phase masks that alter the wavefront of the illuminating beam, the system captures a series of images, each with a differently patterned illumination. Scattered photons, which respond chaotically to these phase shifts, become decorrelated and diminish upon averaging multiple frames. Conversely, photons faithfully reflecting true tissue architecture maintain coherent behavior, thus strengthening their visibility in the final reconstructed image.

This methodology can be likened to differentiating a single voice in a bustling crowd. Just as a consistent voice can be isolated amid random background chatter using adaptive recording strategies, STOC-T distinguishes meaningful optical signals from noise in real-time. This preemptive discrimination obviates the need for computational post-processing to “clean” images after data acquisition, which historically cannot fully recover information lost to scattering. Defensive design of the imaging process ensures that interfering signals are suppressed from the outset, preserving delicate cellular-level details of the retina and choroid that are indispensable for early diagnosis.

STOC-T’s performance has been rigorously tested both in laboratory settings and on living tissue. In one compelling demonstration, a standard imaging target obscured by a highly scattering artificial medium and even by rat skin rendered virtually invisible under conventional OCT. Upon integrating STOC-T’s phase modulation technique, the obscured structural features resurfaced with remarkable clarity. This experiment underscores the scale of the optical crosstalk problem and the potency of STOC-T, since the objects remained physically present but were previously hidden by noise.

The true clinical significance comes from STOC-T’s application to human retinal imaging, where it achieves a lateral resolution near five micrometers—a scale sufficiently fine to resolve individual photoreceptors and ganglion cells as well as intricate vasculature within the choroid. This extraordinary level of detail enables prospective monitoring of microscopic disease processes with an acuity far surpassing existing OCT methods. Additionally, STOC-T provides new insights through optoretinography (ORG), capturing functional responses of photoreceptors to flickering light stimuli at frequencies up to 45 Hz. These functional measurements resemble electrophysiological studies conducted via invasive patch-clamp techniques, suggesting that STOC-T could non-invasively monitor cellular function—a significant leap for early detection of retinal dysfunction before structural damage occurs.

The potential clinical impact of this technology cannot be overstated. Visual impairment affects more than 2.2 billion individuals worldwide, with over a billion cases attributable to conditions amenable to early diagnosis and intervention. Diseases such as glaucoma, diabetic retinopathy, and age-related macular degeneration often become irreversibly severe due to delayed detection. STOC-T’s capacity to enhance diagnostic accuracy at the cellular and functional levels augments the ophthalmologist’s ability to initiate timely therapies, potentially halting or reversing vision loss before clinical symptoms manifest.

Despite these promises, STOC-T remains an experimental technique, currently limited by technical demands. The system requires cutting-edge hardware, including a high-speed CMOS camera capable of capturing quarter-million frames per second and a tunable near-infrared laser source spanning 800 to 870 nanometers in wavelength. The immense data volume generated—exceeding 8.5 gigabytes per acquisition—also presents significant computational challenges for real-time processing and analysis. These hurdles explain why STOC-T is not yet in widespread clinical use, although ongoing advances in photonic hardware and data science are likely to mitigate these barriers.

Looking forward, the research team envisions enhancing the system’s flexibility using multimode optical fibers for phase modulation. Such fibers, with diameters around 50 micrometers and lengths extending to hundreds of meters, support hundreds of propagation modes. They offer the theoretical potential to reduce optical crosstalk noise by a factor approaching 30 without complex electronic controls, simplifying implementation while preserving image quality improvements.

Professor Wojtkowski emphasizes that STOC-T represents a transformative conceptual advance rather than a final product. The roadmap to widespread application involves optimizing speed, minimizing data volume, refining phase encoding strategies, and automating image reconstruction workflows. The foundational principle—shaping the acquisition process to preempt noise contamination—opens avenues not only for ophthalmology but also for diverse biomedical imaging fields where light scattering impairs image fidelity. This innovation exemplifies how deep physical understanding combined with technical ingenuity can reshape diagnostic imaging, making previously invisible biological details accessible and advancing patient care.

In summary, STOC-T addresses a critical bottleneck in OCT imaging by employing spatio-temporal phase modulation to separate meaningful tissue signals from scattered noise at the data collection stage. This technique enhances resolution, contrast, and functional imaging capability, holding significant promise for earlier and more accurate diagnosis of a broad spectrum of vision-threatening diseases. Although currently laboratory-bound due to technical demands, STOC-T’s theoretical and experimental foundations herald a new era in optical imaging, where noise is never blindly accepted but actively prevented from degrading our view of living tissue.

Subject of Research: Human tissue samples

Article Title: Spatio-temporal optical coherence imaging and tomography for in vivo applications

News Publication Date: 25-May-2026

Web References: DOI: 10.1117/1.JBO.31.11.113504

Image Credits: Optica

Keywords

Optical coherence tomography, STOC-T, ophthalmology, retinal imaging, optical crosstalk, phase modulation, optoretinography, photoreceptors, biomedical optics, imaging noise reduction, high-resolution microscopy, optical imaging innovations

OCT imaging excels in revealing detailed retinal morphology, but conventional computational models often treat these volumetric datasets as collections of isolated two-dimensional slices or neglect inter-slice contextual information. This piecemeal approach can lead to information loss and insufficient exploitation of the intrinsic three-dimensional continuity of OCT volumes. Additionally, retinal diagnostics commonly rely on multiple complementary imaging modalities beyond OCT, including fundus autofluorescence (FAF) and infrared retinal imaging (IR), which provide diverse functional and structural perspectives. Until recently, integrating these diverse yet interrelated imaging sources into unified analytical frameworks has been an unfulfilled frontier, constraining the ability to generate holistic and accurate diagnostic models.

In a groundbreaking breakthrough reported in Nature Biomedical Engineering, Liu et al. introduce OCTCube-M, a pioneering three-dimensional multi-modal foundation model designed to capitalise on the full spatial information contained within OCT volumes while seamlessly integrating additional retinal imaging modalities. This innovative framework signifies a paradigm shift in retinal image analysis by harnessing a multi-modal contrastive learning technique dubbed COEP, optimized to align and synergize 3D OCT data with two-dimensional en face (EF) images and other imaging formats. Through this approach, the authors address critical gaps in current retinal imaging analytics, laying the foundation for robust automated systems with unprecedented diagnostic and prognostic capabilities.

The architecture of OCTCube-M is centered around three distinct model variants that build upon one another’s complexity and data inputs. OCTCube represents the foundational uni-modal model, pretrained on an extensive cohort of 26,605 volumetric OCT scans comprising approximately 1.62 million individual 2D slices. This vast amount of training data enables the model to learn rich multi-scale spatial features that underpin the structural heterogeneity of healthy and diseased retinas. Moving beyond single-modality analysis, OCTCube-IR incorporates paired infrared retinal images, leveraging 26,685 matched OCT-IR pairs to refine cross-modality representations and facilitate integrated interpretation. Finally, OCTCube-EF further expands the framework with tri-modal learning by including over 400,000 2D en face retinal images alongside more than 4 million OCT slices, targeting complex prognostic applications such as quantifying the growth rate of geographic atrophy.

One of the crowning achievements of OCTCube is its consistent state-of-the-art performance across eight major retinal diseases, including diabetic retinopathy, age-related macular degeneration (AMD), and retinal vein occlusion, among others. The model’s 3D native learning approach preserves spatial continuity across slices, enabling it to detect subtle pathologies that often elude 2D slice-based methods. More significantly, OCTCube demonstrates extraordinary generalization capabilities, proving robust when deployed across different clinical cohorts, imaging devices, and even disparate imaging modalities. Such robustness is critical for real-world clinical applicability, ensuring that AI-driven diagnostic tools maintain reliability beyond controlled training environments.

The OCTCube-IR model capitalizes on the synergy between OCT’s detailed volumetric data and IR imaging’s enhanced visualization of retinal vasculature and pigmentation. By jointly analyzing these modalities, OCTCube-IR can perform accurate cross-modal retrieval, enabling seamless matching of patient data even when one modality is missing or imperfect. This integration enhances diagnostic confidence and opens pathways for novel clinical workflows that leverage multi-dimensional imaging data. Moreover, the combined analysis paves the way for detecting mixed phenotypes and subtle disease markers that are better characterized when viewed through multiple optical lenses.

OCTCube-EF represents the zenith of multi-modal integration by combining volumetric OCT with en face imaging to tackle the demanding challenge of predicting geographic atrophy progression—a key vision-threatening feature of advanced AMD. Trained on an unparalleled dataset pool derived from six multicenter clinical trials spanning 23 countries, OCTCube-EF excels in quantifying and forecasting disease progression rates across diverse patient populations. This capability holds promise for personalized medicine, enabling clinicians to tailor interventions and monitor therapeutic efficacy more precisely in clinical trial contexts and routine care.

The development of OCTCube-M vividly illustrates the transformative power of contrastive learning-based multimodal fusion strategies in medical imaging. By learning aligned feature representations across divergent data types, COEP facilitates a common embedding space that respects individual modality strengths while enabling cross-talk and integrated reasoning. This technical advancement not only improves performance metrics but also enhances interpretability—a crucial factor in gaining clinical trust as it aids ophthalmologists in correlating AI insights with known pathophysiological bases seen across modalities.

Furthermore, the sheer scale and diversity of the training data underpinning OCTCube-M constitute one of the largest and most comprehensive retinal imaging repositories ever assembled. This extensive dataset diversity undergirds the models’ generalizability and resilience to variations introduced by demographic, device, or protocol differences, thus catalyzing the translation of research prototypes into clinically deployable tools. The foundation model philosophy embodied here—emphasizing pretraining on vast heterogeneous datasets before fine-tuning—mirrors successful strategies in natural language processing and computer vision, marking a pivotal step in ophthalmic AI.

In addition to its clinical implications, OCTCube-M sets elevated standards for future research in retinal imaging and computational ophthalmology. By demonstrating effective strategies for integrating volumetric and planar imaging data, it invites the exploration of other combinations of retinal image modalities, such as fluorescein angiography or adaptive optics scanning laser ophthalmoscopy. Moreover, the multi-modal contrastive learning framework is broadly applicable beyond ophthalmology, suggesting pathways to revolutionize imaging diagnostics across medical specialties reliant on heterogeneous imaging data.

The potential impact of OCTCube-M extends beyond diagnostic accuracy to inform clinical decision-making, patient stratification, and trial design. The ability to accurately predict disease progression trajectories empowers clinicians and researchers with actionable insights to optimize treatment plans and evaluate novel therapies more efficiently. In geographic atrophy, for example, objective biomarkers derived from OCTCube-EF could accelerate the development of disease-modifying drugs by providing reliable surrogate endpoints, thus addressing a critical unmet need in retinal therapeutics.

As the technology matures, real-world integration of OCTCube-M into clinical workflows will require careful consideration of usability, interoperability, and regulatory compliance. Its modular design allows adaptability across different health systems and imaging platforms, but challenges remain in standardizing input data formats and ensuring patient privacy during large-scale model deployment. Collaborative efforts among clinicians, engineers, and regulatory agencies will be essential in overcoming these hurdles and translating technological promise into routine practice.

In conclusion, the introduction of OCTCube-M marks a monumental leap in retinal imaging analytics through its innovative 3D multi-modal learning paradigm. By fully harnessing the rich structural details of OCT alongside complementary imaging modalities, it achieves a holistic view of retinal pathology that eclipses previous uni-modal approaches. This advance is poised to revolutionize how retinal diseases are diagnosed, monitored, and ultimately treated, heralding a new era of precision ophthalmology informed by sophisticated AI-driven insights.

Looking forward, the principles and frameworks established here will undoubtedly inspire future developments in multi-modal medical AI, driving innovation in complex disease understanding and management. OCTCube-M exemplifies the cutting edge of AI’s synergy with medical imaging, where deep learning models do not merely analyze pixels but serve as integral partners in unraveling human biology and improving patient outcomes in visionary new ways.

Subject of Research:
Three-dimensional multi-modal foundation models for integrated analysis of retinal imaging data, including optical coherence tomography, en face imaging, and infrared retinal imaging for diagnosis and prognosis of retinal diseases.

Article Title:
A three-dimensional multi-modal foundation model for optical coherence tomography.

Article References:
Liu, Z., Xu, H., Woicik, A. et al. A three-dimensional multi-modal foundation model for optical coherence tomography. Nat. Biomed. Eng (2026). https://doi.org/10.1038/s41551-026-01662-2

Image Credits:
AI Generated

DOI:
https://doi.org/10.1038/s41551-026-01662-2