(87 days)
The CalScoR Software is intended to be used with the Rapidia software by a trained physician for the review and analysis of CT images as an aid in cardiac analysis.
CalScoR is a Windows-compatible software program that runs with the previously cleared Rapidia Software (K012290). The Rapidia Software is a fast, practical, and accurate tool for 3D (three dimensional) and 2D (two dimensional) viewing and manipulation of CT and MRI images using the most advanced graphics-rendering technology.
CalScoR can specify the location of calcium in images, calculate the calcium score based on Agaston's method display the percentile of the score with the graph, and issue reports.
Here's a summary of the acceptance criteria and study details for the 3DMed Co., Ltd. CalScoR software, based on the provided text:
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Scores obtained from CalScoR and predicate device (AccuScore) are similar. Linear regression slope = 1, intercept = 0. | Linear regression demonstrated the scores were similar, with a calculated slope of 1 and intercept of 0. |
| Scores obtained from CalScoR and predicate device (AccuScore) are essentially identical. | F-test resulted in an F-value of 13742853.39, showing the two scores are identical within 0.0001 (0.01%) error level. |
| CalScoR performs all functions according to the functional requirements specified in the Software Requirements Specifications. | Testing demonstrated that the CalScoR performs all functions according to the functional requirements. |
Study Information
- Sample size used for the test set and the data provenance: Not explicitly stated. The document mentions "Tests were performed to compare the accuracy," but does not specify the number of cases or the origin of the data.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as the comparison was against a predicate device's output, not expert-established ground truth.
- Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable, as the comparison was against a predicate device's output.
- If a multi-reader, multi-case (MRMC) comparative effectiveness study was done: No, an MRMC study was not done. The study focused on comparing the algorithm's output to a predicate device's output.
- If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Yes, the testing compared the CalScoR software's output directly to the predicate device's output, indicating a standalone algorithm comparison.
- The type of ground truth used (expert consensus, pathology, outcomes data, etc.): The "ground truth" for this study was the output of a legally marketed predicate device, AccuScore/Accuview Software (K990241), which also calculates calcium scores based on Agaston's method.
- The sample size for the training set: Not applicable. The document does not describe a machine learning model that would require a distinct training set. The device's algorithm for calculating calcium score is stated to be based on Agaston's method.
- How the ground truth for the training set was established: Not applicable.
Overall, the study focused on demonstrating substantial equivalence to a predicate device by comparing the outputs of the two software programs using statistical methods (linear regression and F-test), rather than directly validating against clinical outcomes or a human expert standard.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).