Search Results

Salix Central is a web-based software application that is intended to be used for viewing, post-processing, and analyzing cardiac computed tomography (CT) images acquired from a CT scanner in a Digital Imaging and Communications in Medicine (DICOM) Standard format.

This software provides tools that can be used for the qualitative and quantitative assessment of physician-identified coronary plaques and stenosis in coronary computed tomography angiography (CCTA) and to perform calcium scoring in non-contrast cardiac CT.

Salix Central is intended to complement standard care as an adjunctive tool and is not intended as a replacement to a medical professional's comprehensive diagnostic decision-making process. The software's semi-automated features are intended for an adult population and should only be used by qualified medical professionals experienced in examining and evaluating cardiac CT images.

Salix Central is a web-based software application, hosted on AWS cloud services, delivered using a SaaS model. The software provides interactive, post-processing tools for trained radiologists or cardiologists for viewing, and characterizing cardiac computed tomography (CT) image data obtained from a CT scanner. The physician-driven coronary analysis is used to review CT image data to prepare a standard coronary report that may include the presence and extent of physician-identified coronary plaques (i.e., atherosclerosis) and stenosis, and assessment of calcified plaque (calcium scoring). The Cardiac CT image data are physician-ordered and typically obtained from patients who underwent CCTA or CAC CT for evaluation of CAD or suspected CAD.

Here's a breakdown of the acceptance criteria and study details for Salix Central, based on the provided document:

Acceptance Criteria and Device Performance

Study Details

1. Sample Sizes Used for the Test Set and Data Provenance

• Total Unique Cases for Validation: 363 unique, de-identified cardiac CT studies.
• Specific Test Set Sizes:
  • Calcium Scoring: 302 non-contrast series.
  • Centerline Extraction and Vessel Labelling: 116 contrast-enhanced series.
  • Wall Segmentation (Lumen and Vessel Wall): 63 contrast-enhanced series.
• Data Provenance: Sourced from multiple unique centers in the USA. The data did not contribute to any training datasets for Salix Central algorithms. It included representation of multiple CT scanner manufacturers (Canon, GE, Philips, and Siemens). The study cohort included diverse demographics: 36% age 65+, 57% female, 67% White, 18% Black or African American, 13% Asian, and 19% Hispanic or Latino. The document indicates this was a retrospective evaluation as it refers to "sourced from" and "validation dataset consisted of" existing studies.

2. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Not explicitly stated as a specific number, but "board certified cardiologists with SCCT Level 3 certification (or equivalent experience)" were used. This implies multiple experts collaborated in establishing the ground truth, rather than a single individual.
• Qualifications of Experts: Board certified cardiologists with SCCT Level 3 certification (or equivalent experience).

3. Adjudication Method for the Test Set

• The document states that the ground truth "was independently established from the source clinical image interpretation" by qualified cardiologists. It does not explicitly describe an adjudication method (e.g., 2+1, 3+1) if there were discrepancies among experts, but rather implies a consensus or single, definitive reference standard decided upon by these experts.

4. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, the document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the ML-enabled algorithms against an established ground truth.

5. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

• Yes, the performance validation testing presented describes the standalone performance of the ML-enabled Salix Central outputs (calcium scoring, centerline extraction, vessel labelling, and lumen/vessel wall segmentation) against a reference ground truth. The results are reported as direct comparisons of the algorithm's output to the expert-established ground truth.

6. The Type of Ground Truth Used

• Expert Consensus/Manual Annotation: The ground truth was "established by board certified cardiologists with SCCT Level 3 certification (or equivalent experience) using manual annotation tools." This indicates an expert-derived ground truth based on manual interpretation and annotation of the images.

7. The Sample Size for the Training Set

• Training Dataset Size: 3835 unique patient cases.

8. How the Ground Truth for the Training Set was Established

• A "reference standard was created to train the machine (ML) enabled algorithms in Salix Central." While the specific methodology for ground truth establishment for the training set isn't detailed, it is implied that it was also based on creating a "reference standard" consistent with the clinical context as the validation set. Data for training was sampled from their database based on pre-defined exclusion criteria, ensuring no site was shared between training and validation cohorts.
• Data Provenance for Training Set: 6 unique sites from the USA, Canada, Australia, and Japan.

Ask a specific question about this device