The retina, the thin layer of light-sensitive tissue lining the back of the eye, is the only place in the human body where blood vessels can be observed directly and non-invasively. This unique window makes retinal vessel imaging enormously valuable clinically. Changes in the width, curvature, branching pattern, and density of these vessels are early fingerprints of systemic and ocular conditions, including diabetic retinopathy, hypertensive retinopathy, and glaucoma, all of which can progress silently for years before a patient notices any loss of vision. Because early detection is the single most effective defense against permanent visual impairment, ophthalmologists have long sought automated systems capable of measuring the vasculature accurately and consistently. The manual tracing of vessels, however, is tedious, time-consuming, and subject to significant variability between different human experts, a problem the research team set out to eliminate.

The new study, led by Guanghui Song of Ningbo Tech University together with Binhua He of Zhejiang Sci-Tech University and Yan Nie of Ningbo University, focuses on a particularly challenging type of retinal imaging: fluorescein angiography, or FA. In this procedure, a fluorescent dye is injected into the bloodstream, and as it circulates through the retina, a specialized camera captures sequences of images in which the vessels glow brightly against a dark background. FA offers a dynamic, high-contrast view of blood flow that standard color fundus photography cannot match, revealing leakage, non-perfusion areas, and vascular abnormalities that would otherwise remain hidden. Yet the very characteristics that make FA so informative also make it difficult for automated analysis. Images are often affected by uneven illumination, background fluorescence, noise, and wide variation in vessel calibers, from thick major arcades down to capillaries only a pixel or two across.

To cope with this complexity, the researchers turned to multiscale analysis, a strategy rooted in the mathematics of wavelets. Wavelet transforms decompose a signal or image into components at different scales and resolutions, much as a musical equalizer separates sound into bass, midrange, and treble. The stationary wavelet transform in particular is translation-invariant, meaning it does not shift its representation when the input shifts, a property that makes it well suited to detecting structures of different sizes without introducing artifacts. By applying this transform to the angiographic images, the team generated a set of feature maps that emphasized vessels at each characteristic width. Fine capillaries standing out at fine scales, while large vessels emerged at coarser ones. This preprocessing step effectively converts the raw image into a richer representation in which vessel-like structures are amplified and background clutter suppressed.

These multiscale features then feed into a fully complex multiscale neural network, an architecture designed so that its internal processing parallels the scale hierarchy established by the wavelet stage. The core design principle is adaptation to two sources of variability that plague retinal image analysis: the enormous range of vessel widths and the constantly changing orientation of vessels as they sweep across the curved surface of the retina. Because the network receives explicit scale-decomposed inputs, it can assign different weights to different scales depending on context, learning to interpret a faint thin structure as a capillary rather than noise, and to distinguish a thick vessel from an illumination artifact. The complex-valued formulation of the network adds another dimension of representational power, allowing phase information carried by the wavelet coefficients to be exploited rather than discarded, which helps the model respond to the directionality of vascular structures.

Training such a network on relatively limited sets of expert-annotated medical images is a notorious bottleneck in medical artificial intelligence. Overfitting, in which a model memorizes the quirks of its training data rather than learning generalizable patterns, is a constant danger. The team addressed this with a deliberate data augmentation strategy: rotation operations were applied at least once across the layers during the training phase. In effect, the network was repeatedly confronted with the same vascular anatomy presented at different orientations, forcing it to learn features that are genuinely rotation-tolerant rather than tied to the particular angle at which vessels happened to appear in the training images. This echoes a broader theme in modern deep learning research, where equivariance to geometric transformations is prized precisely because biological structures, like retinal vessels, can appear at arbitrary orientations in any given scan.

The performance of the resulting system was evaluated on three different datasets, and in each case the proposed method delivered better results than the current state-of-the-art techniques it was compared against. This cross-dataset consistency matters greatly, because many published segmentation algorithms perform impressively on the specific dataset they were tuned to but degrade sharply when confronted with images from a different camera, a different patient population, or a different imaging protocol. Robustness across datasets is therefore one of the most honest indicators of whether a method has genuine clinical potential or is merely exploiting statistical idiosyncrasies of one benchmark.

Equally significant is the stability of the method. The researchers report that the framework produces consistent results across different training datasets and across inter-rater variability, the well-documented phenomenon in which two human experts annotating the same image disagree on fine details, particularly around the thinnest vessels and at branch points. A diagnostic tool that fluctuates depending on which annotator labeled its training data is of limited clinical value. The ability of the new method to absorb and transcend this human disagreement suggests it has learned a representation of vascular anatomy that is closer to the underlying biological reality than to the idiosyncrasies of any single annotation. As the authors note, this means the method can be practically used anywhere, a claim of portability that, if validated in prospective clinical studies, would be a meaningful advance for screening programs in settings where expert graders are scarce.

The clinical implications extend well beyond the technical achievement of drawing cleaner vessel maps. In diseases such as diabetic retinopathy, which affects a substantial fraction of the world’s growing diabetic population, the earliest signs of pathology are vascular: microaneurysms, capillary dropout, and changes in vessel tortuosity. Automated and accurate vessel segmentation is the foundational step upon which all such quantitative measurements depend. Fluorescein angiography is particularly central to assessing retinal perfusion, and recent work from other groups has explored using deep learning even to synthesize FA-like information from color fundus photographs. The present study complements that line of research by tackling the segmentation problem directly on authentic angiographic images, where the fluorescent signal provides a rich but noisy substrate for machine analysis.

The methodology also illustrates a persuasive middle path in medical AI design. Rather than relying solely on a generic convolutional architecture and hoping that enough data will teach it everything, the team built explicit domain knowledge into the pipeline. The choice of the stationary wavelet transform encodes decades of signal-processing understanding about how structures of varying scale can be separated, and the multiscale network architecture mirrors the physical fact that retinal vessels span a wide range of calibers. This hybrid of classical mathematics and modern deep learning, sometimes described as physics-informed or knowledge-guided machine learning, is increasingly seen as the most promising route to systems that are accurate, data-efficient, and trustworthy, the three qualities that regulators and clinicians alike demand from medical technology.

The work, which was partially supported by the Ningbo “Science and Technology Innovation Yongjiang 2035” key technology breakthrough plan project, arrives at a moment when the burden of retinal disease is rising worldwide. Diabetic retinopathy alone remains a leading cause of preventable blindness among working-age adults, and hypertension-related vascular changes in the retina are increasingly recognized as markers of broader cardiovascular risk. Screening programs that could deploy a stable, dataset-agnostic segmentation algorithm on angiographic images would multiply the reach of limited ophthalmological expertise, flagging patients who need urgent attention while sparing healthy individuals unnecessary interventions.

The authors caution, as with any new method, that broader clinical validation will be needed before deployment in routine care, and the study’s three-dataset evaluation, while encouraging, represents a step on a longer road toward regulatory approval and integration into hospital workflows. Nevertheless, the combination of superior performance, robustness across datasets, and stability against human annotation variability marks this framework as a notable contribution to the rapidly evolving field of retinal image analysis. If the promise holds, the humble wavelet, a mathematical tool first formalized more than a century ago in the work on orthogonal function systems, may find itself at the heart of software that safeguards the eyesight of millions.

Diabetic retinopathy (DR) arises from chronic hyperglycemia, which progressively damages retinal blood vessels, ultimately impairing vision. Despite the high global prevalence of diabetes, the molecular underpinnings of DR remain only partially understood, limiting therapeutic options and early intervention strategies. By constructing a comprehensive proteomic profile of retinal tissues affected by diabetes, researchers have now decoded complex protein expression patterns and signaling pathways that drive retinal degeneration, ballooning beyond traditional histological assessments.

This study integrated multiple advanced mass spectrometry platforms along with rigorous bioinformatics processing to capture the dynamic proteomic shifts occurring in diabetic retinopathy. The resulting atlas charts a vast array of protein alterations across different retinal cell types and disease stages, illuminating pathological mechanisms such as neuroinflammation, vascular dysfunction, and metabolic dysregulation. Importantly, this work emphasizes the heterogeneity of DR progression, revealing distinct protein signatures that correlate with varying disease severities.

One of the most revolutionary aspects of this proteome atlas is its potential to underpin personalized medicine in diabetic eye diseases. By characterizing individual molecular fingerprints, clinicians could one day predict patients’ risk of DR development or progression with unprecedented precision. This could inform tailored surveillance and therapeutic strategies, ensuring interventions are timely and biologically targeted, thereby diminishing the incidence of vision loss.

The research team conducted extensive validation using patient-derived retinal samples, ensuring the translational relevance of their findings. They identified key proteins that serve as biomarkers for early-stage DR, proteins that control retinal vascular permeability, and molecules that regulate glial cell activation, all crucial players in the pathogenesis of diabetic retinopathy. The identification of such proteins also offers novel targets for pharmacological intervention, opening doors to drug development efforts grounded in robust molecular evidence.

The complexity of diabetic retinopathy, with its interplay between hyperglycemia-induced oxidative stress and immune system activation, is elegantly unraveled through this proteomic approach. Prior studies had hypothesized about the roles of these pathways, but the current atlas provides direct biochemical confirmation and quantification of involved protein networks. This level of insight was previously unattainable, marking a significant leap forward in basic and clinical diabetic retinopathy research.

Moreover, the data reveal how specific signaling cascades, such as those governing angiogenesis and extracellular matrix remodeling, are perturbed in diabetic eyes. These cascades are integral to retinal tissue homeostasis and their disruption contributes to the hallmark vascular lesions seen in DR. Targeting these molecular nodes may thus offer promising therapeutic avenues, as the atlas enables precise identification of vulnerable pathways that to date have been explored only cursorily.

The multi-dimensional characterization of the diabetic retina in this study also paves the way for integrating proteomic data with other “-omics” domains, such as genomics and metabolomics. Such holistic biological understanding could uncover further mechanistic nuances and systemic interactions that fuel diabetic retinopathy. Systems biology approaches leveraging this proteome atlas could thus illuminate disease trajectories and response to treatment over time.

Critically, this study addresses a long-standing challenge in diabetic retinopathy: the gap between clinical phenotyping and molecular causation. Historically, ophthalmologists have relied on fundoscopic imaging and clinical grading systems, which capture the visible manifestations but fail to reveal the molecular catalysts. By bridging this gap, the proteome atlas offers a molecular context to clinical findings, enabling a deeper comprehension of disease progression and therapeutic impact.

This research also highlights the potential of proteomic biomarkers to predict risk before overt clinical symptoms occur. Diabetic retinopathy typically advances silently, with retinal damage accruing invisibly until vision is compromised. Early identification using protein markers could revolutionize screening programs, allowing earlier intervention and possibly preventing irreversible damage.

Among the study’s most compelling findings is the elucidation of the role of mitochondrial dysfunction in retinal cells under diabetic stress. Proteins involved in energy metabolism and oxidative phosphorylation were markedly altered, suggesting impaired bioenergetics contributes significantly to retinal cell injury. This finding not only enriches our understanding of DR pathophysiology but also aligns with emerging evidence linking mitochondrial health to diabetic complications.

Additionally, the atlas points to inflammatory mediators as central orchestrators of retinal damage. Chronic low-grade inflammation in the diabetic milieu triggers a cascade of detrimental events, including leukostasis and microglial activation. By documenting altered abundance of inflammatory proteins, the study provides a molecular blueprint to design anti-inflammatory therapies that could halt or slow DR progression.

The creation of this proteome atlas was made possible by cutting-edge technologies such as high-resolution tandem mass spectrometry and sophisticated computational algorithms for proteome quantification. This exemplifies how technological innovation is propelling biomedical research into new frontiers, where vast datasets can be rendered into actionable clinical knowledge.

Furthermore, the atlas’s open-access framework invites global research collaboration, setting a new standard for data transparency and cross-disciplinary studies in diabetic retinopathy research. Sharing such detailed molecular maps encourages validation in diverse populations and fosters the collective advancement of targeted therapies.

In conclusion, this expansive proteomic exploration marks a milestone in diabetic retinopathy research. By unraveling the molecular fabric of the diseased retina, it unlocks unprecedented opportunities for early diagnosis, personalized treatment, and novel drug development. As diabetes continues its alarming worldwide rise, tools such as this proteome atlas stand to transform care paradigms and safeguard millions from vision loss, affirming the profound impact of molecular science on human health.

Subject of Research: Diabetic retinopathy, molecular mechanisms, proteomics, disease biomarker discovery, risk prediction

Article Title: Proteome atlas for mechanistic discovery and risk prediction of diabetic retinopathy

Article References:
Yang, S., Xin, Z., Xiong, R. et al. Proteome atlas for mechanistic discovery and risk prediction of diabetic retinopathy. Nat Commun 16, 9636 (2025). https://doi.org/10.1038/s41467-025-64634-1

Image Credits: AI Generated