Keeping up appearances: the radiographic evolution of cardiovascular implantable electronic devices

Multimodality imaging in patients with implantable loop recorders: Tips and tricks

An implantable loop recorder (ILR) is a leadless rectangular device used for prolonged electrocardiographic monitoring for up to 3 years. This miniaturized device, inserted subcutaneously, allows clinicians to investigate possible cardiac rhythm disturbances in patients suffering from recurrent unexplained syncope. As the age of the population increases rapidly and the number of ILR patients amplifies, the clinical significance of ILRs is undeniable. Although radioopaque and easily seen on plain chest radiographs and other imaging modalities, ILRs may represent a challenge for clinicians and radiologists to recognize their classic appearance and differentiate them from numerous other cardiac devices. This article aims to summarize current literature on ILRs, their basic function, types, and indications for implantation, but most of all, it aims to familiarize clinicians and radiologists with common imaging features of these devices, safety issues, and artifact-reducing methods. Specifically, this review discusses the typical appearance of ILRs on major diagnostic imaging modalities, including chest X-ray, mammography, ultrasonography, computed tomography, and magnetic resonance imaging (MRI). Furthermore, optimization strategies to mitigate image artifacts and safety issues regarding MRI are discussed.

Australian radiographers' awareness of cardiac implantable electronic devices (CIEDs) in mammographic imaging

INTRODUCTION

Women presenting for mammography occasionally have pacemakers or other cardiac-implantable electronic devices (CIEDs) in situ. This research investigates Australian radiographers' awareness of CIEDs in the diagnostic and screening settings.

METHODS

A survey of radiographers with mammography experience in Australia was conducted using SurveyMonkey™. Respondents were asked if they could confidently identify images of devices and whether they had imaged them mammographically. A Chi-squared test of independence was used to compare the association between demographics and CIED awareness. A value of p < 0.05 was deemed statistically significant.

RESULTS

There were 220 valid responses. All CIED types had been imaged. Most respondents had imaged a pacemaker (94.5%) and implantable cardioverter-defibrillator (ICD) (85.6%), compared to the three different implantable loop recorders (ILRs) (ILR-1: 63.4%; ILR-2: 14.1%; and IRL-3: 26.9% and the emerging subcutaneous ICDs (S-ICDs) (11.9%). Most respondents felt confident identifying the pacemaker (95%) and the ICD (86.1%). Only 19.4% of respondents could confidently identify the emerging S-ICD.

CONCLUSION

A lack of awareness of new and emerging devices may impact approaches to imaging and present significant risk to patients. The lack of studies comprehensively describing devices and their mammographic appearance to support radiographers' knowledge and awareness highlights an urgent need to progress research in this area.

IMPLICATIONS FOR PRACTICE

As a part of continuing professional development, radiographers performing mammography must ensure they remain up to date with current and emerging technology, including CIEDs. This study has identified a lack of awareness of the different types of CIEDs currently being implanted and imaged, which may translate to unsafe imaging practices. There is an urgent need for further education to bridge this knowledge gap and ensure the safety of practice in imaging women with CIEDs.

FOOTLINE

Mammography: CIED Imaging.

Pre-deployment assessment of an AI model to assist radiologists in chest X-ray detection and identification of lead-less implanted electronic devices for pre-MRI safety screening: realized implementation needs and proposed operational solutions

Purpose

Chest X-ray (CXR) use in pre-MRI safety screening, such as for lead-less implanted electronic device (LLIED) recognition, is common. To assist CXR interpretation, we "pre-deployed" an artificial intelligence (AI) model to assess (1) accuracies in LLIED-type (and consequently safety-level) identification, (2) safety implications of LLIED nondetections or misidentifications, (3) infrastructural or workflow requirements, and (4) demands related to model adaptation to real-world conditions.

Approach

A two-tier cascading methodology for LLIED detection/localization and identification on a frontal CXR was applied to evaluate the performance of the original nine-class AI model. With the unexpected early appearance of LLIED types during simulated real-world trialing, retraining of a newer 12-class version preceded retrialing. A zero footprint (ZF) graphical user interface (GUI)/viewer with DICOM-based output was developed for inference-result display and adjudication, supporting end-user engagement and model continuous learning and/or modernization.

Results

During model testing or trialing using both the nine-class and 12-class models, robust detection/localization was consistently 100%, with mAP 0.99 from fivefold cross-validation. Safety-level categorization was high during both testing ( AUC ≥ 0.98 and ≥ 0.99 , respectively) and trialing (accuracy 98% and 97%, respectively). LLIED-type identifications by the two models during testing (1) were 98.9% and 99.5% overall correct and (2) consistently showed AUC ≥ 0.92 (1.00 for 8/9 and 9/12 LLIED-types, respectively). Pre-deployment trialing of both models demonstrated overall type-identification accuracies of 94.5% and 95%, respectively. Of the small number of misidentifications, none involved MRI-stringently conditional or MRI-unsafe types of LLIEDs. Optimized ZF GUI/viewer operations led to greater user-friendliness for radiologist engagement.

Conclusions

Our LLIED-related AI methodology supports (1) 100% detection sensitivity, (2) high identification (including MRI-safety) accuracy, and (3) future model deployment with facilitated inference-result display and adjudication for ongoing model adaptation to future real-world experiences.