Researchers have developed a self-learning software able to identify vascular changes in patients with peripheral arterial disease (PAD)


Researchers at the University and the University Hospital of Bonn have developed a method that could be used to diagnose atherosclerosis. Using self-learning software, they were able to identify vascular changes in patients with peripheral arterial disease (PAD), often at an early stage.

Although these early stages do not yet cause symptoms, they are nevertheless already associated with increased mortality. The algorithm used photos from an organ not normally associated with PAD: the eye. The results have now been published in the journal Scientific Reports.

The fundus of the eye is very well supplied with blood. It has to be, so that the more than 100 million photoreceptors in the retina and the nerve cells connected to them can do their work. At the same time, the arteries and veins can be observed and photographed through the pupil without much effort.

It may be possible to detect early signs of atherosclerosis (hardening of the arteries) with such an examination in the future. In this case, chronic remodeling processes lead to narrowing of the vessels and hardening of the affected arteries. It is the main cause of heart attacks and strokes, the most frequent causes of death in western industrialized nations, as well as peripheral arterial disease (PAD).

More than four million people in this country suffer from PAD. “Because it usually does not cause any symptoms in the first few years, the diagnosis is often only made when secondary damage has already occurred,” explains Dr. Nadjib Schahab, head of the angiology section and one of the authors of the study.

“The consequences can be dramatic. In the long term, progressive circulatory problems in the legs and arms may even result in amputation. In addition, the risk of a fatal heart attack or stroke is significantly increased—even in the early stages of the disease.”

Early diagnosis is therefore very important in order to be able to treat those affected in time. The interdisciplinary project of the Department of Informatics at the University of Bonn and the Department of Ophthalmology and the Heart Center of the University Hospital Bonn starts exactly there.

“We photographed 97 eyes of women and men who suffered from PAD,” explains Dr. Maximilian Wintergerst from the University Eye Hospital in Bonn. “In more than half of them, the disease was still at a stage where it did not cause any symptoms.” In addition, the team took camera images of the background of 34 eyes of healthy control subjects.

Eye provides clues to insidious vascular disease
The algorithm pays particular attention to the large retinal vessels when detecting peripheral arterial disease. This is shown by the bright red areas in the image, which were particularly important for the classification. Credit: DOI: 10.1038/s41598-022-05169-z

Neural network detects early vascular changes

They then used the images to feed a convolutional neural network (CNN). This is software that is modeled on the human brain in the way it works. If such a CNN is trained with photos whose content is known to the computer, it can later recognize the content of unknown photos. For this to work with sufficient certainty, however, one normally needs several tens of thousands of training photos—far more than were available in the study.

“We therefore first carried out a pre-training with another disease that attacks the vessels in the eye,” explains Prof. Dr. Thomas Schultz from the Bonn-Aachen International Center for Information Technology (b-it) and the Institute for Computer Science II at the University of Bonn. To do this, the researchers used a dataset of more than 80,000 additional photos.

“In a sense, the algorithm learns from them what to pay particular attention to,” says Schultz, who is also a member of the Transdisciplinary Research Areas “Modeling” and “Life and Health” at the University of Bonn. “We therefore also speak of transfer learning.”

The CNN trained in this way was able to diagnose with remarkable accuracy whether the eye photos came from a PAD patient or a healthy person. “A good 80 percent of all affected individuals were correctly identified, if we took into account 20 percent false positives—that is, healthy individuals whom the algorithm incorrectly classified as sick,” Schultz explains. “That’s amazing, because even for trained ophthalmologists, PAD can’t be detected from fundus images.”

In further analyses, the researchers were able to show that the neural network pays particular attention to the large vessels in the back of the eye during its assessment. For the best possible result, however, the method needed digital images with a sufficiently high resolution. “Many CNNs work with very low-resolution photos,” Schultz says.

“That is sufficient to detect major changes. For our PAD classification, on the other hand, we need a resolution at which details of the vascular structures remain discernible.”

The researchers hope to further improve the performance of their method in the future. To do so, they plan to cooperate with ophthalmology and vascular medicine centers worldwide that will provide them with additional fundus images of affected individuals. The long-term goal is to develop a simple, rapid and reliable diagnostic method that does not require concomitant procedures such as the administration of eye drops.

Nuclear and molecular imaging of PAD is an emerging field that provides numerous opportunities for physiological investigation into this traditionally underdiagnosed and undertreated disease. Recent studies have demonstrated that SPECT/CT perfusion imaging may enable the screening, diagnosis, and monitoring of responses to treatment (21, 22, 25), while PET/CT imaging may provide novel opportunities for molecular imaging of atherosclerosis and vascular inflammation (47), which to date, have remained relatively understudied in the setting of lower extremity PAD.

Additionally, these hybrid nuclear imaging approaches that utilize CT can offer simultaneous evaluation of calcium burden in the lower extremities that is not possible with conventional vascular imaging techniques (20). While nuclear imaging approaches in the setting of PAD remain exploratory in nature, these imaging techniques could potentially assist with screening for and diagnosis of regional perfusion abnormalities related to PAD and severity of PAD, which could subsequently assist clinicians by guiding targeted revascularization procedures or evaluating the response to revascularization.

Additionally, PET/CT imaging of arterial inflammation and active atherosclerosis may assist clinicians by detecting regions of active disease, thereby guiding endovascular therapy or monitoring of problematic lesions. Currently, hemodynamic tools such as ABI, TBI, and Doppler ultrasound are a mainstay of screening for PAD due to their relative efficiency and cost-effectiveness; however, perfusion imaging with nuclear techniques has proven to provide further physiological information beyond traditional hemodynamic assessment by detecting the specific anatomical region of underlying tissue ischemia, thus potentially setting the stage for their use during PAD diagnosis and treatment planning.

Collectively, nuclear imaging techniques advance the non-invasive evaluation of PAD beyond traditional means by offering quantitative regional analysis of vascular and muscle physiology, whereas traditional non-invasive vascular diagnostic tools have primarily focused on hemodynamic (e.g., ABI, TBI, ultrasound) or structural (e.g., angiography) assessments of the lower extremities. It’s important to note that while SPECT/CT and PET/CT imaging have demonstrated potential in PAD, the recent emergence of PET/MR imaging may also provide additional opportunities for partnering high-sensitivity molecular (PET) and high-resolution structural (MR) imaging in the setting of lower extremity PAD (38, 48).

Given the multifactorial nature of PAD-related complications, ongoing advancements in nuclear medicine and molecular imaging should facilitate development of novel imaging strategies that are capable of targeting the underlying pathophysiology associated with lower extremity PAD and enable serial monitoring of physiological responses to medical treatment.

Specifically, advancements with cadmium zinc telluride (CZT) SPECT systems and whole-body PET cameras may offer new approaches for quantifying absolute perfusion of lower extremity skeletal muscle beyond what has been previously accomplished with conventional 15O-water PET imaging.

Expanded application of 18F-FDG and 18F-NaF to the lower extremities, along with other developing radionuclides meant for atherosclerosis and thrombosis targeted imaging, could also allow for novel opportunities to investigate mechanisms associated with PAD disease progression and non-invasively detect occlusive peripheral thrombi (49–53).

Additionally, the use of multi-tracer imaging of different physiological processes in the lower extremities could theoretically be achieved with SPECT imaging of radionuclides that possess distinctly different gamma ray energy photopeaks, or with PET imaging by staggering injection times of short half-life radionuclides; however, the advantages and disadvantages associated with increased radiation exposure for patients receiving multiple radionuclide injections in a single imaging session would need to be carefully considered.

Beyond the various clinical investigations focused on nuclear imaging of PAD, a large number of pre-clinical studies have been published in recent years that also highlight ongoing developments in the field of molecular imaging that could possess translational potential for PAD patients.

These studies have utilized large and small animal models of atherosclerosis and hindlimb ischemia to validate novel SPECT- and PET-based approaches directed at perfusion (54) and angiogenesis targeted imaging (55–57), which continue to be the primary areas of pre-clinical PAD research. Overall, molecular imaging of lower extremity PAD remains a developing and exciting field of research that should provide novel insight into PAD pathophysiology and eventually expand the repertoire of non-invasive tests available to vascular medicine specialists.

reference link :

More information: Simon Mueller et al, Multiple instance learning detects peripheral arterial disease from high-resolution color fundus photography, Scientific Reports (2022). DOI: 10.1038/s41598-022-05169-z


Please enter your comment!
Please enter your name here

Questo sito usa Akismet per ridurre lo spam. Scopri come i tuoi dati vengono elaborati.