The study, led by Mingwu Jin, professor of physics at UT Arlington, focuses on computed tomography angiography, or CTA, an advanced imaging test that noninvasively assesses coronary artery disease, the world’s leading cause of death. CTA combines a CT scan with iodine contrast dye injected into a patient’s vein to create detailed three-dimensional images of blood vessels and surrounding tissues throughout the body. Beyond the heart, doctors rely on the technique to detect aneurysms, narrowed or damaged vessels, blood clots, tumors, and a range of other conditions, which is precisely why reducing its radiation footprint could benefit so many people.

The project is funded by a three-year, $579,745 grant from the National Heart, Lung, and Blood Institute, part of the National Institutes of Health. It is titled Deep leaRning-bAsed reConstruction, or DRAC, for Multi-Phase Cardiac CT Angiography. The work targets a specific and increasingly important imaging protocol known as multi-phase coronary CTA, which captures images at multiple points during the heartbeat. By sampling the cardiac cycle repeatedly, the technique gives doctors far more information and helps reduce the blurring caused by the heart’s constant motion. The drawback is unavoidable physics: collecting images across multiple phases exposes patients to more radiation than a single-phase scan.

Lowering the radiation dose in medical imaging has been vigorously pursued due to imaging prevalence and the potential cancer risk of ionizing radiation, Jin explained. Although notable progress has been made by developing advanced reconstruction methods, the dose reduction potential is far from its limit. That statement captures the central tension of modern radiology: the same X-ray photons that produce exquisitely detailed images of the heart also carry a small but cumulative risk, and every reduction in dose must be earned without sacrificing the information clinicians need to make life-or-death decisions.

To understand how the UT Arlington team plans to earn that reduction, it helps to know what happens inside a CT scanner. The raw data collected during a scan are not images at all but measurements of X-ray attenuation from many angles. Reconstruction methods transform those measurements into the cross-sectional pictures doctors can interpret. One advanced approach is model-based iterative reconstruction, known as MBIR, an algorithm designed to generate high-quality cross-sectional images while potentially using less radiation. Rather than applying simple filtered back-projection, MBIR builds a mathematical model of the imaging process itself and iteratively refines the image until it best explains the measured data, suppressing noise in the process.

A second pillar of the project is 4D reconstruction, which adds the dimension of time to standard three-dimensional imaging. In cardiac imaging, this technique can capture clear views of fast-moving heart valves and coronary arteries while reducing motion artifacts, the ghostly streaks and blurs that arise when the heart moves between X-ray projections. By explicitly modeling motion over the cardiac cycle, 4D methods allow scanners to gather less data per phase while still producing images that look as though they were frozen at a single instant of the heartbeat.

Jin said that recent breakthroughs in deep learning provide an unprecedented opportunity to substantially lower radiation doses by combining MBIR with information learned from a large database of high-quality multi-phase coronary CTA images. The resulting 4D DRAC method would reconstruct a patient’s images using not only data from that individual scan, but also information learned from a much larger collection of images. In practical terms, the neural network acts as a kind of learned prior: it has seen what healthy and diseased coronary arteries look like in full-dose, high-quality scans, and it uses that statistical knowledge to fill in the details that a low-dose scan alone cannot resolve. This is the same broad principle that has revolutionized image denoising, super-resolution, and medical image synthesis across radiology, now aimed at one of the most technically demanding reconstruction problems in the field.

To test the hypothesis, Jin and his team will pursue three interlocking aims. First, they will build a synthetic patient library using computational human models based on retrospectively collected multi-phase coronary CTA data from real patients. Synthetic data allow the researchers to know the ground truth exactly, which is essential for training and validating deep-learning algorithms without exposing additional patients to scans. Second, they will develop three-dimensional and four-dimensional deep-learning methods that combine CT imaging physics with features learned from the high-quality patient data, ensuring the network respects the actual mathematics of X-ray attenuation rather than hallucinating plausible-looking anatomy. Third, they will determine the lowest radiation dose that can be used without compromising diagnostic accuracy, evaluating that accuracy with a computer model designed to mimic how a radiologist assesses an image, then validating the results through a small-scale study involving human observers.

The Mayo Clinic in Rochester, Minnesota, will provide multi-phase coronary CTA patient data for the study, giving the UT Arlington team access to clinically realistic images acquired on state-of-the-art scanners. That partnership matters because deep-learning reconstruction methods live or die by the diversity and quality of their training data; a network trained only on idealized images may fail when confronted with the variability of real patients, from differing heart rates and body habitus to calcium deposits and stents that scatter X-rays in complicated ways. By anchoring the synthetic library in retrospectively collected clinical data, the project aims to bridge the gap between algorithmic promise and bedside reality.

If the 4D DRAC methods succeed, the implications could extend well beyond the coronary arteries. Jin said the project could substantially lower the radiation dose needed for multi-phase coronary CTA, potentially improving its use in detecting the narrowing of coronary arteries and monitoring the progression of high-risk plaque, the unstable lesions most likely to trigger heart attacks. He noted that the methods could also be applied to other dynamic CT scans, which use a series of images to track changes over time, from perfusion studies of the brain to oncology follow-ups. And because the approach couples physics-based reconstruction with learned priors, it inherits the interpretability advantages of MBIR while gaining the pattern-recognition power of modern AI, a combination many researchers see as the most credible path to routine ultra-low-dose imaging.

The award also reflects the collaborative and educational dimension of the research. Graduate students Noor Rasel and Darnisha Langlais will work with Jin on the project, and the grant will allow him to hire undergraduate students in the summers, giving them hands-on opportunities to apply AI techniques to medical imaging. This award reflects the high quality of Dr. Jin’s research and the strength of his proposed ideas, said Alex Weiss, professor of physics and former department chair. I know a great deal of work goes into preparing a successful proposal of this kind. This is a significant achievement for Dr. Jin and a major benefit to our department. For the millions of patients who will undergo cardiac CT in the coming years, the hope is that the project’s most lasting contribution will be images just as sharp, diagnoses just as certain, and doses substantially smaller.

Subject of Research: AI-based low-dose reconstruction for multi-phase cardiac CT angiography

Article Title: UT Arlington study aims to cut radiation in heart scans

Article References: UT Arlington study aims to cut radiation in heart scans. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: cardiac CT angiography, radiation dose reduction, deep learning, image reconstruction, coronary artery disease, University of Texas at Arlington, NIH funding, 4D reconstruction, model-based iterative reconstruction, medical imaging, machine learning, cardiovascular imaging

The research, led by Mengyuan Jing, Haoxiang Lu, and Qing Liu with colleagues at Lanzhou University Second Hospital, the Guangdong Cardiovascular Institute, and partner institutions, set out to build an explainable machine learning model that could predict functional improvement after ablation in patients with atrial fibrillation combined with heart failure. Rather than relying on a single measurement, the team fused three complementary streams of information: the geometry of the left atrium and pulmonary veins as seen on cardiac CT angiography, quantitative radiomics features extracted from the left atrial wall, and a handful of routine clinical variables. The result was a combined model, dubbed COMB, that achieved an area under the receiver operating characteristic curve of 0.866 in the training set, 0.803 in the validation set, and 0.845 in an independent testing set drawn from other hospitals.

Those numbers deserve unpacking, because the area under the curve, or AUC, is the workhorse metric for judging how well a model separates patients who will improve from those who will not. A value of 0.5 would mean the model performs no better than a coin flip, while 1.0 would indicate perfect discrimination. Scores consistently above 0.80 across three separate patient cohorts, including an external test set the model had never encountered during development, represent solid, clinically meaningful performance. Equally important is how the team arrived at that performance. Patients from the primary institution were randomly divided into training and validation sets in a seven-to-three ratio, while two other organizations contributed entirely separate testing cohorts, a design that guards against the model simply memorizing the quirks of one hospital’s scanner or patient population.

The technical heart of the study lies in what the researchers chose to measure. Cardiac CT angiography, already a routine part of pre-ablation planning because it maps the pulmonary veins before catheter insertion, provides exquisitely detailed three-dimensional images of the left atrium, the chamber where fibrillation typically originates. From these images the team extracted morphological features describing the shape of the left atrium and the pulmonary veins, capturing subtle geometric signatures such as chamber distortion and remodeling that a human reader might overlook. In parallel, they applied radiomics, a computational approach that converts medical images into hundreds of quantitative descriptors of texture, intensity, and spatial pattern, to the left atrial wall itself, the thin muscular sleeve where ablation lesions are created and where fibrotic change often determines whether the procedure succeeds.

From this high-dimensional feature space, the researchers distilled two focused models. Two shape features and three left atrial wall radiomics features survived rigorous screening and were used to construct what they called the Shape model and the Wall model, respectively. Each model produced a continuous score, the Shape_score and the Wall_score, which quantified how strongly a given patient’s cardiac anatomy resembled that of patients who went on to improve. These scores were then integrated with the clinical variables that proved most informative, namely gender, hyperlipidemia, blood urea level, and the type of atrial fibrillation, to yield the final combined model. The parsimony is striking: out of the vast number of features that could have been included, the final predictor rests on just a handful of imaging and clinical inputs, all obtainable from examinations and blood tests that are already standard practice.

What elevates the study beyond a typical prediction exercise is its commitment to explainability. Black-box algorithms have long been a stumbling block for clinical adoption, because physicians are understandably reluctant to act on a probability they cannot interrogate. The researchers addressed this by applying SHAP, or Shapley additive explanations, a technique borrowed from cooperative game theory that assigns each input feature a precise contribution to every individual prediction. In effect, SHAP reveals which factors pushed a particular patient’s predicted probability up or down, and by aggregating these contributions across the cohort, the team identified the features with the greatest impact on outcomes in both the Shape and Wall models. This transparency allows a cardiologist to see, for example, whether an unfavorable prediction stems from pronounced atrial remodeling, abnormal wall texture suggesting fibrosis, or a clinical factor such as persistent rather than paroxysmal fibrillation.

The clinical stakes of this kind of tool are considerable. Patients with atrial fibrillation and concomitant heart failure represent a particularly vulnerable group, and ablation in these individuals carries procedural risk, substantial cost, and a demanding recovery. If a model can reliably flag patients unlikely to experience functional improvement, clinicians could counsel them more honestly, weigh alternative management strategies such as optimized medical therapy, or reserve ablation for those with the greatest expected benefit. Conversely, identifying patients with a high predicted probability of improvement could support earlier referral and shared decision-making grounded in quantitative evidence rather than clinical intuition alone. Because the model’s inputs come from CT angiography and routine laboratory work, it could in principle be deployed without any additional testing beyond what pre-ablation workups already include.

The multicenter architecture of the study strengthens its claims in another important way. Models trained and tested within a single institution often flatter themselves, absorbing center-specific artifacts in scanner protocol, image reconstruction, and patient mix. By including 240 patients in the training set, 101 in the validation set, and 75 in external testing sets from two other organizations, the team demonstrated that the model’s discrimination held up across different hospitals and imaging environments. The ethics committees of all three participating institutions approved the retrospective study, and the requirement for individual informed consent was waived because of its retrospective design, with the work conducted in accordance with the Declaration of Helsinki.

The authors themselves are careful about the limits of what they have shown. The study was retrospective, meaning it looked backward at patients who had already undergone ablation rather than prospectively assigning the model to guide care in real time. The team explicitly states that further prospective evaluation is required before the model can be implemented clinically, a caveat that applies to nearly every prediction algorithm now emerging in cardiovascular medicine. Prospective validation would involve using the COMB model to generate predictions before ablation and then tracking whether those predictions match observed outcomes, ideally across diverse populations and healthcare systems. Questions about calibration, the agreement between predicted probabilities and actual event rates, and about how the model behaves in subgroups underrepresented in the data, would also need answers.

Even with those caveats, the study offers a compelling glimpse of where cardiac imaging and artificial intelligence are converging. The same CT scan obtained to map a patient’s pulmonary veins becomes, through shape analysis and radiomics, a quantitative portrait of atrial health, and machine learning converts that portrait, together with a few clinical facts, into an individualized forecast of recovery. The SHAP framework keeps the forecast auditable, showing clinicians exactly which anatomical and biological signals drove the conclusion. For the millions of patients whose fibrillation and heart failure travel together, and for the physicians deciding whether to offer them ablation, a tool that turns pre-procedural images into evidence-based expectations could reshape the conversation, replacing uncertainty with a number that both doctor and patient can understand, question, and trust.

Subject of Research: Explainable machine learning on cardiac CT angiography to predict functional improvement after atrial fibrillation ablation in patients with heart failure

Article Title: Explainable machine learning model based on cardiac CT angiography for predicting functional improvement after atrial fibrillation ablation: a multicenter study

Article References: Jing, M., Lu, H., Liu, Q., Jing, Y., Lei, F., Yang, X., Chen, G., Xi, H., Xin, W., Zhu, H., Sun, Q., Zhang, Y., Ren, J., Ren, W., Liu, Z., Wang, G., & Zhou, J. (2026). Explainable machine learning model based on cardiac CT angiography for predicting functional improvement after atrial fibrillation ablation: a multicenter study. BMC Medical Imaging. https://doi.org/10.1186/s12880-026-02822-1

Image Credits: AI Generated

DOI: 10.1186/s12880-026-02822-1

Keywords: atrial fibrillation, heart failure, catheter ablation, cardiac CT angiography, machine learning, radiomics, left atrium, SHAP explainability, predictive modeling, multicenter study, BMC Medical Imaging, cardiac imaging