News | Cardiac Imaging | November 16, 2023

Using Deep Learning to Process Raw Photoacoustic Channel Data and Guide Cardiac Interventions

The model automatically pinpoints the location of cardiac catheters in photoacoustic images, paving the way for safer cardiac procedures 

The model automatically pinpoints the location of cardiac catheters in photoacoustic images, paving the way for safer cardiac procedures

A photoacoustic approach to guiding cardiac catheters involves short laser pulses delivered using an optical fiber attached to a catheter, while a special signal transducer picks up the ensuing ultrasound waves generated within the heart. Experiments with live swine demonstrate the potential of combining deep neural networks with photoacoustic imaging. Such models can help robotic arms carefully control the position of cardiac catheters during cardiac interventions. Image courtesy of Gubbi et al., doi 10.1117/1.JBO.29.S1.S11505 


November 16, 2023 — Cardiovascular diseases rank among the top causes of death across the world, and cardiac interventions are similarly very common. For example, cardiac catheter ablation procedures, which are used to treat arrythmias, number in several tens of thousands per year in the US alone. In these procedures, surgeons insert a thin, flexible tube called a catheter into the femoral vein in the leg and navigate their way up to the heart, where the problematic tissue is destroyed using cold or focused radiation. 

Even though cardiac catheter-based procedures are considered minimally invasive, the position of the catheter tip must be carefully monitored and controlled to prevent damage to the heart. In most cases, surgeons rely on fluoroscopy to localize and guide the catheter tip. However, this approach exposes both the patient and the medical staff to ionizing radiation, which can lead to problems such as increased risk of cancer or birth defects.  

An alternative method to guide cardiac catheters involves photoacoustic imaging. In this approach, short laser pulses are delivered using an optical fiber attached to the catheter while a special signal transducer picks up the ensuing ultrasound waves generated within the heart. Photoacoustic images generated this way can be used to guide robotic arms manipulating the cardiac catheter to enhance precision and minimize risks. However, the algorithms used to automatically detect photoacoustic sources in these images, which are located close to the catheter tip, are susceptible to errors such as reflection artifacts. 

A research team led by Muyinatu A. Lediju Bell, the John C. Malone Associate Professor in the Whiting School of Engineering at Johns Hopkins University, USA, has been working toward a solution to this issue. As reported in a new study published in the Journal of Biomedical Optics, they have developed a new approach for cardiac catheter localization through photoacoustic imaging by leveraging machine learning. 

The researchers proposed using a deep convolutional neural network (CNN) to pinpoint the position of cardiac catheter tips in photoacoustic images. However, deep neural networks need to be trained on very large datasets to perform correctly, which would require hours of manual image acquisition and annotation. To circumvent this problem, the team turned to simulated data. “We trained the network with simulated channel data frames which we formatted to accommodate the field of view of the photoacoustic transducer, including multiple noise levels, signal amplitudes, and sound speeds, to ensure robustness against channel noise, target amplitude, and sound speed differences,” said Bell. To make the CNN more robust, the training dataset also included simulated images with artifacts. 

The researchers introduced an additional processing step called “histogram matching” to further enhance the performance of the model. Herein, they automatically modified acquired images so that they looked similar to the simulated images used to train the CNN. 

Through ex vivo and in vivo experiments on excised swine hearts and live swine, respectively, the team demonstrated the impressive performance of their deep learning-based approach. The positional errors for the catheter tip were remarkably small; most of them were even smaller than the resolution of the photoacoustic signal transducer. The network achieved Euclidean errors of 1.02 ± 0.84 mm for target depths of 20–100 mm. Furthermore, it exhibited great performance metrics, with precision, recall, and F1 scores as high as 100%. “Our results demonstrate the potential of the proposed method to identify photoacoustic sources in future interventional cardiology and cardiac electrophysiology applications, with the broader potential to replace fluoroscopy during these procedures,” said Bell, satisfied with the outcomes. 

Overall, this study can pave the way for safer cardiac interventions that require catheters, helping doctors and patients alike in the fight against heart diseases. 

For more information: https://spie.org/ 


Related Content

News | Cardiac Imaging

Cleerly, a leader in cardiovascular imaging, today announced the promotions of two key executives to expanded leadership ...

Home July 02, 2025
Home
News | Cardiac Imaging

June 25, 2025 — Royal Philips and Methodist Hospitals recently announced the healthcare provider’s strategic investment ...

Home June 25, 2025
Home
News | Cardiac Imaging

June 12, 2025 — GE HealthCare has announced the combination of GE HealthCare’s proprietary features and algorithms with ...

Home June 12, 2025
Home
News | Cardiac Imaging

April 1, 2025 — UltraSight recently announced the presentation at the American College of Cardiology (ACC) Annual ...

Home April 15, 2025
Home
News | Cardiac Imaging

April 3, 2025 — Tower Health and Siemens Healthineers recently announced a 10-year agreement focused on equipment ...

Home April 04, 2025
Home
News | Cardiac Imaging

Pfizer has awarded $80,000 to Rutgers Robert Wood Johnson Medical School (RWJMS) to fund an Amyloidosis Fellowship at ...

Home December 19, 2024
Home
News | Cardiac Imaging

Dec. 11, 2024 — Genetesis, Inc. has launched the CardioFlux Membership program. CardioFlux Membership is designed to be ...

Home December 18, 2024
Home
News | Cardiac Imaging

Nov. 13, 2024 – A recent study has demonstrated the value of the single-exposure dual-energy X-ray detector in advancing ...

Home November 13, 2024
Home
News | Cardiac Imaging

Oct. 15, 2024 — Four of the seven Medicare Administrative Contractors (MACs) have released final local coverage ...

Home October 16, 2024
Home
News | Cardiac Imaging

Oct. 15, 2024 – Elucid has announced that four of the seven Medicare Administrative Contractors (MACs) will extend ...

Home October 15, 2024
Home
Subscribe Now