(385 days)
The CSMC Cardiac Suite is intended to enable an automated display, review, and quantification of Nuclear Medicine Cardiology medical images and datasets. CSMC Cardiac Suite may be used in multiple settings including the hospital, clinic, doctors office, or remotely. The results provided should be reviewed by qualified healthcare professionals (e.g., radiologists, cardiologists, or general nuclear medicine physicians) trained in the use of medical imaging devices.
The Cedars-Sinai Cardiac Suite is a stand-alone software solution for Cardiac SPECT and PET imaging processing and review. Cedars-Sinai Cardiac Suite minimum system requirements include a computer with at least 1GB RAM, 50MB hard disk space for software installation, a display resolution at least 1024x768 with 16-bit color, a network adapter, a mouse (or other pointer device; trackpad, trackball, etc.) and one of the following operating systems: Windows XP Professional. Windows Vista Professional. Windows 7 Professional. The Cedars-Sinai Cardiac Suite operates on camera independent reconstructed SPECT and/or PET image files. CSMC Cardiac Suite will be marketed as a comprehensive application suite that includes QGS (Quantitative Gated SPECT), QPS (Quantitative Perfusion SPECT) and CSImport applications. This allows automatic processing and review of quantitative and qualitative information generated by nuclear medicine studies. Purchasable Options consist of Quantitative Blood Pool SPECT (QBS), QARG (for reporting purposes), Fusion (SPECT/CT/CTA and/or PET/CT/CTA), Motion Correction (MOCO) and QPET. QPET also includes viability quantification and two additional databases (rubidium and ammonia) for processing PET studies.
Acceptance Criteria and Device Performance Study for Cedars-Sinai Cardiac Suite (K100714)
The Cedars-Sinai Cardiac Suite is a stand-alone software solution for Cardiac SPECT and PET imaging processing and review, including applications such as QGS, QPS, QBS, QARG, CSImport, MoCo, and QPET. The device's substantial equivalence to predicate devices (AutoQUANT® Plus and Cedars-Sinai BPGS and MoCo Software Programs) was demonstrated through performance testing.
1. Acceptance Criteria and Reported Device Performance
The core of the performance testing revolved around demonstrating that the algorithms in the CSMC Cardiac Suite operate identically to those in the predicate devices.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Functional Equivalence: Each software application functions as per its specifications. | QPS Verification: 1211 tests passed, 0 failed. |
| QGS Verification: 1211 tests passed, 0 failed. | |
| QBS Verification: 632 tests passed, 0 failed. | |
| QARG Verification: 1161 tests passed, 0 failed. | |
| CSImport Verification: 111 tests passed, 2 failed (These two failures are likely acceptable as the overall submission was cleared). | |
| MOCO Verification: 23 tests passed, 0 failed. | |
| Installation Verification: 82 tests passed, 0 failed. | |
| Regression Tests: 912 tests passed, 0 failed (across multiple daily runs). | |
| Algorithmic Equivalence: All algorithms (with the exception of two new ones: "Quality Score" and "RV algorithm") produce the same results as previous versions of the software (predicate devices). | A set of 16 studies had their algorithm results compared to those of the predicate device. These comparisons were included in regression tests, which consistently passed (912 tests passed, 0 failed). This implies identical results for the algorithms common to both the device and its predicates. |
| New Algorithms Functionality: The two new algorithms ("Quality Score" and "RV algorithm") are integrated and perform as expected as part of the updated QPS / QGS. | The document states that the updated version of QPS and QGS includes an improved contouring algorithm based on a quality score and RV (right ventricle) extraction and analysis. The comprehensive nature of the functional and regression tests (which passed) suggests these new features are functional and integrated correctly. |
2. Sample Size and Data Provenance
- Test Set Sample Size: 16 studies were used for direct comparison of algorithm results between the device and its predicate. Beyond this, thousands of tests were conducted for functional and regression testing, but the specific number of unique patient cases for these tests is not explicitly stated.
- Data Provenance: The document does not specify the country of origin of the data. It also does not explicitly state whether the data was retrospective or prospective, but given the nature of comparing to predicate device results, it's highly likely to be retrospective data that was previously processed by the predicate devices.
3. Number of Experts and Qualifications for Ground Truth
The document does not indicate the involvement of experts for establishing ground truth for the test set in the context of clinical interpretation or diagnosis. The focus was on the performance of the algorithms themselves compared to predicate device results, not against a human-derived clinical ground truth for a diagnostic outcome.
4. Adjudication Method
Not applicable. The study focused on algorithmic equivalence to predicate devices, not on a diagnostic outcome requiring expert adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or performed. The study aimed to demonstrate that the device's algorithms operate identically to previously cleared predicate devices.
6. Standalone Performance Study
Yes, a standalone (algorithm only without human-in-the-loop performance) study was effectively done. The performance testing section directly addresses the functionality and output of the software's algorithms, comparing them to predicate device outputs. The statement, "With the exception of two new algorithms ("Quality Score" and "RV algorithm") all algorithms operate identically (i.e. produce the same results) as with previous versions of the software (referenced in predicate devices)", indicates a standalone evaluation of the algorithmic output.
7. Type of Ground Truth Used
The ground truth used for the algorithmic equivalence testing was the results generated by the predicate devices (AutoQUANT® Plus and Cedars-Sinai BPGS/MoCo Software Programs). For the functional verification tests (QPS, QGS, etc.), the ground truth was the expected output or behavior defined by the software's specifications.
8. Sample Size for the Training Set
The document does not provide any information regarding a "training set" or its sample size. This suggests that the device was not developed using traditional machine learning supervised training paradigms that require distinct training sets, or at least, such details were not considered relevant for this 510(k) submission focused on substantial equivalence to existing devices. The new algorithms ("Quality Score" and "RV algorithm") are mentioned, but their development methodology (including if they involved new training) is not detailed.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as no training set information is provided or implied in the document.
§ 892.1200 Emission computed tomography system.
(a)
Identification. An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.(b)
Classification. Class II.