Search Results

This medical device is intended to segment Cardiac chambers as anatomical structures on contrast or non-contrast MR scans of adult patients that undergo Cardiac MR procedures. The algorithm is not specific to any gender or ethnic group or clinical conditions.

The TeraRecon Cardiac.Chambers.MR algorithm is comprised of two components:

1. The TeraRecon Cardiac.Chambers.MR for Cine-ax
2. The TeraRecon Cardiac.Chambers.MR De-ax

1: The TeraRecon Cardiac.Chambers.MR for Cine-ax
The TeraReconCardiac.Chambers.MR algorithm for Cine-ax is an image processing software device that can be deployed as a containerized application (e.g.,Docker container).

The TeraRecon Cardiac.Chambers.MR algorithm for Cine-ax automatically detects and identifies the heart location and derives left ventricular (LV) and right ventricular (RV) myocardium segmentation on DICOM-compliant cardiovascular MR images of different cardiac imaging sequences.

The TeraRecon Cardiac.Chambers.MR for Cine-ax algorithm performs a segmentation (or tracing) around the epicardial border as well as the endocardial border wall. For the RV the algorithm segments the endocardial border wall.

2: The TeraRecon Cardiac.Chambers.MR for De-ax
The TeraReconCardiac.Chambers.MR algorithm for De-ax is an image processing software device that can be deployed as a containerized application (e.g.,Docker container).

The TeraRecon Cardiac.Chambers.MR algorithm for De-ax automatically detects and identifies the heart location and derives left ventricular (LV) myocardium segmentation on DICOM-compliant cardiovascular MR images of different cardiac imaging sequences.

The TeraRecon Cardiac.Chambers.MR for De-ax algorithm performs a segmentation (or tracing) around the epicardial border as well as the endocardial border wall.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by the reported performance relative to a threshold (DICE score). While specific thresholds aren't explicitly stated as "acceptance criteria," the text confirms the device passed these criteria. We infer the thresholds from the reported mean DICE scores that met the acceptance criteria.

Notes on Acceptance Criteria:

• The document states: "The results of the Cine-ax algorithm showed the LV Myocardium mean DICE scores for were within the acceptance criteria at 0.82 (0.81,0.83)... The results indicated the LV Chambers mean DICE Scores were within the acceptance criteria and were at or greater than 0.90 (0.89, 0.91)... and the mean DICE Score for RV Chamber was 0.84 (0.82, 0.85) and thus within the 95% confidence interval and passing the DICE limit score." This implies the lower bound of the 95% CI or a value just below the reported mean was the threshold. For simplicity and clarity, I've listed the lower bound of the reported 95% CI where available as the inferred minimum acceptance criterion, or the stated passing value.
• For the De-ax algorithm, it states: "The results of the De-ax algorithm showed the LV myocardium mean DICE scores were within the acceptance criteria at 0.79 (0.75, 0.83), and the LV Chamber mean DICE scores were within the acceptance criteria at 0.88 (0.84, 0.92)." This implies the lower bound of the 95% CI was the threshold.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size (Test Set): 100 adult patients (50 for the Cine-ax algorithm, 50 for the De-ax algorithm).
• Data Provenance: Retrospective cohort study.
  • 82% of studies came from the United States.
  • 18% of studies came from Europe.
  • Data was collected from different sites than the training data.
  • Included data from three MR equipment manufacturers: GE, Philips, or Siemens (covering 74% of US scanners).

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

• Number of Experts: At least one (referred to as "a board certified radiologist").
• Qualifications: A board-certified radiologist practicing in the United States with experience in reviewing cMR (cardiac MR) studies.

4. Adjudication Method for the Test Set

• The document states: "All collected datasets were reviewed by a board certified radiologist practicing in the United States with experience in reviewing cMR studies. The radiologists evaluated whether each cMR scan met the inclusion/exclusion criteria, and if the study did not meet the inclusion exclusion criteria then the study was replaced."
• This suggests a single-reader read for inclusion/exclusion criteria, followed by implicit establishment of ground truth by this single expert (or group of experts if "radiologists" implied more than one but written singular elsewhere). An explicit adjudication method (e.g., 2+1, 3+1) for the actual segmentation ground truth is not detailed, implying either a single expert's consensus or a pre-established "ground truth" that the single radiologist reviewed for study suitability. The sentence "The next phase of the study was to collect and compare the TeraRecon Cardiac.Chambers.MR cine-ax algorithm output to the created ground truth as described below" further suggests either a pre-existing ground truth or one established by the single reviewing radiologist, but not a multi-reader adjudication process for the segmentation itself.

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

• No, the provided text does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The study focused on the standalone performance of the algorithm against established ground truth.

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

• Yes, a standalone study was performed. The study compared the "TeraRecon Cardiac.Chambers.MR [algorithm] output to the created ground truth." This indicates an evaluation of the algorithm's performance without direct human interaction or assistance during the segmentation process.

7. The Type of Ground Truth Used

• The ground truth was established by expert review ("All collected datasets were reviewed by a board certified radiologist practicing in the United States with experience in reviewing cMR studies"). The ground truth itself consisted of segmented cardiac chambers (LV Myocardium, LV Chamber, RV Chamber, LV only myocardium and chamber for de-ax) against which the algorithm's DICE scores were calculated. While "expert consensus" is often multi-reader, the text describes a single expert reviewing the dataset for suitability and implying their role in the "created ground truth." Pathology or outcomes data were not mentioned as ground truth sources.

8. The Sample Size for the Training Set

• The sample size for the training set is not specified in the provided text. The document only states: "It is ensured that patient data received for training of the algorithm is from different sites than the validation data utilized for this study."

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

• The method for establishing ground truth for the training set is not specified in the provided text. It only mentions that the training data came from different sites than the validation data.

Ask a specific question about this device