CardIQ Suite
K243672GE Medical Systems SCS · cleared 2025-06-18 · product code JAK · Radiology
Premarket evidence — what FDA accepted
source quote (p.4)
“CardIQ Suite is a non-invasive software application designed to provide an optimized application to analyze cardiovascular anatomy and pathology based on 2D or 3D CT cardiac non contrast and angiography DICOM data from acquisitions of the heart.”
source quote (p.11)
“The subject device has been updated to add another deep learning algorithm to segment non-contrasted heart exams. The new deep learning algorithm for heart segmentation of non-contrasted exams uses the same model as the previous existing heart segmentation algorithm for contrasted exams, however now the input is changed, and the model is trained and tested with the non-contrasted exams. In the subject device, a predefined HU threshold of -200 to 30 is applied to the ROI and is automatically generated on the segmented heart which provides the visualization of the heart fat estimate. Additionally, the Deep learning algorithm for coronary tracking in the subject device has been updated by retraining to a finer resolution for more precision and incorporates some post-processing steps to refine the centerline and tracking at vessel ostia, aorta, and vessel bifurcations. The lumen diameter quantification is calculated using a new non-deep learning algorithm and displayed as a lumen minimum diameter profile graph.”
source quote (p.11)
“The new deep learning algorithm for heart segmentation of non-contrasted exams uses the same model as the previous existing heart segmentation algorithm for contrasted exams, however now the input is changed, and the model is trained and tested with the non-contrasted exams. Additionally, the Deep learning algorithm for coronary tracking in the subject device has been updated by retraining to a finer resolution for more precision and incorporates some post-processing steps to refine the centerline and tracking at vessel ostia, aorta, and vessel bifurcations.”
Validation studies (4)
Bench
n=111 cases
endpoints: acceptance criteria of more than 90% of the exams that are successfully segmented
Bench
n=111 cases
endpoints: average Dice score is greater than or equal to 90%
Bench
n=94 cases
endpoints: mean absolute difference is lower than the mean voxel size, demonstrating sufficient agreement for lumen quantification
Bench
sample size not stated
endpoints: performance of these algorithms is enhanced when compared to the predicate device; met the defined acceptance criteria
Reported performance (1 observation)
source quote (p.14)
“For the New Heart Fat volume estimate algorithm (non-deep learning), the automated estimate of the volume of heart fat was deemed acceptable as the average Dice score is greater than or equal to 90% based on testing performed on 111 CT exams.”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (GE Medical Systems, LLC, initiated 2026-03-26): "GE HealthCare has become aware of a potential security vulnerability impacting AW Server deployed via Edison Health Link (EHL) based CT Smart Subscription used in conjunction with " Recalling firm matches this device's applicant.
first seen 2026-07-08 · recall res_event_number:98738
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (PHILIPS MEDICAL SYSTEMS, initiated 2026-03-07): "Philips has identified three software issues: 1. During a continuous CT (CCT) scan, there is the potential that the Gantry could remain at the current scan position after pressing" Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98588
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (Siemens Medical Solutions USA, Inc, initiated 2025-12-19): "To remove the software applications from certain CT systems as the applications have not received FDA 510(k) clearance." Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:98206
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (PHILIPS MEDICAL SYSTEMS, initiated 2025-09-25): "Issue 1: The potential for unintentional continued gantry/couch movement when a specific button series is used requiring use of manual stop. Issue 2. When performing a helical/Axia" Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:97699
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (Philips North America Llc, initiated 2025-05-29): "Devices with affected software may experience two unintended motion issues that may lead to contact between the Gantry or table with the operator or patient, along with additional " Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:97010
- recall_reason_pattern
Software/algorithm-related recall in product code JAK (, initiated 2025-05-23): "Due to a software bug the robotic arm may incorrectly guide the instrument compared to the planning defined by user." Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:96967
- …and 3 more.
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).