(202 days)
The AutoChamber software is an opportunistic AI-powered quantitative imaging tool that measures and reports cardiac chambers volumes comprising left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), and left ventricular wall (LVW) from non-contrast chest CT scans including coronary artery calcium (CAC) scans and lung CT scans. AutoChamber is not intended to rule out the risk of a cardiovascular disease, and the results should not be used for any purpose other than to enable physicians to investigate patients that AutoChamber shows signs of enlarged heart (cardiomegaly), enlarged cardiac chambers, and left ventricular hypertrophy (LVH) whose conditions are otherwise missed by human eyes in non-contrast chest CT scans. AutoChamber similarly measures and reports LA, LV, RA, RV, and LVW in contrast-enhanced coronary CT angiography (CCTA) scans. Additionally, AutoChamber measures and reports cardiothoracic ratio (CTR) in both contrast and non-contrast CT scans where the entire thoracic cavity is in the axial field of view. AutoChamber quantitative imaging measurements are adjusted by body surface area (BSA) and are reported both in cubic centimeter volume (cc) and percentiles by gender using reference data from 5830 people who participated in the Multi-Ethnic Study of Atherosclerosis (MESA). AutoChamber should not be ordered as a standalone CT scan but instead should be used as an opportunistic add-on to existing and new CT scans of the chest, such as CAC and lung CT scans, as well as CCTA scans.
Using AutoChamber quantitative imaging measurements and their clinical evaluation, healthcare providers can investigate asymptomatic patients who are unaware of their risk of heart failure, atrial fibrillation, stroke and other life-threatening conditions associated with enlarged cardiac chambers, and LVH that may warrant additional risk-assessment or follow-up. AutoChamber quantitative imaging measurements are to be reviewed by radiologists or other medical professionals and should only be used by healthcare providers in conjunction with clinical evaluation.
The AutoChamber Software is an opportunistic AI-powered quantitative imaging tool that provides an estimate of cardiac volume, cardiac chambers volumes and left ventricular (LV) mass from non-contrast chest CT scans as well as contrast-enhanced chest CT scans. In addition to cardiac chambers volume and LV mass, AutoChamber measures and reports cardiothoracic ratio (CTR).
AutoChamber Software reads a CT scan (in DICOM format) and extracts scan specific information like acquisition time, pixel size and scanner type. The AutoChamber Software uses an AI trained model to identify cardiac chambers in the field of view and measure the volume of each chamber including left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), and LV wall (LVW). AutoChamber calculates the volume of each chamber as well as the corresponding total volume of all cardiac chambers and, if the field of view contains the entire width of the thoracic cavity in the axial view, it calculates and reports cardiothoracic ratio (CTR).
AutoChamber calculates the volume of each chamber based upon the volume of each pixel multiplied by the number of pixels in the region of interest per slice, multiplied by the number of slices included in each chamber's segmentation. The total volume per chamber is reported in cubic centimeters (CC). In addition to reporting the measured volume in CC per chamber report shows volumes adjusted by body surface area (BSA) and corresponding percentiles using reference data from 5830 people who participated in the Multi-Ethnic Study of Atherosclerosis (MESA). The default cut-off value for further investigations is the 75th percentile but it is optional and subject to provider's judgement.
AutoChamber does not provide a numerical individualized risk score/prediction or categorial assessment for whether an individual patient will develop cardiovascular disease over a specified period of their percentile(s).
AutoChamber is a post-processing quantitative imaging software that works on existing and new CT scans. The AutoChamber Software is a software module installed by trained personnel only. The AutoChamber Software is executed via a parent software which provides the necessary input and visualizes the output data. The software itself does not offer user controls or access. The user cannot change or edit the segmentation or results of the device. The user must accept or reject the region where the cardiac chamber volume measurement is done. If rejected, the user must retry with a new series of images or conduct an alternate method to measure cardiac chamber volume. The expert's review solely pertains to the region of interest being properly located.
Software passes if the healthcare provider sees the cardiac chamber volumes and left ventricular mass highlighted by AutoChamber are correctly placed on the cardiac region based upon expert knowledge. Software fails if the healthcare provider sees the cardiac chamber volumes and left ventricular mass highlighted by AutoChamber are incorrectly placed outside of the cardiac anatomy. Software fails if the healthcare provider sees that the quality of the CT scan is compromised by image artifacts, motion, or excessive noise.
Based on the provided text, here's a description of the acceptance criteria and the study proving the device meets them:
Acceptance Criteria and Device Performance
The document does not explicitly state a table of quantitative acceptance criteria for the performance of the AutoChamber software (e.g., a specific mean absolute error for volume measurements or a target F1-score for segmentation). Instead, the software validation section states: "Software Verification and Validation testing was completed to demonstrate the safety and effectiveness of the device. Testing demonstrates the AutoChamber Software meets all its functional requirements and performance specifications."
The closest the document comes to defining acceptance criteria is in the "Principles of Ops" section, describing conditions for software pass/fail from a user's perspective:
- Software passes if the healthcare provider sees the cardiac chamber volumes and left ventricular mass highlighted by AutoChamber are correctly placed on the cardiac region based upon expert knowledge.
- Software fails if the healthcare provider sees the cardiac chamber volumes and left ventricular mass highlighted by AutoChamber are incorrectly placed outside of the cardiac anatomy.
- Software fails if the healthcare provider sees that the quality of the CT scan is compromised by image artifacts, motion, or excessive noise.
- The only user interaction is to accept or reject the region where the cardiac chamber volume measurement is done, with rejection leading to a retry or alternate method. "The expert's review solely pertains to the region of interest being properly located."
Given this, the qualitative acceptance criteria appear to be centered on the correct anatomical localization of the measured cardiac chambers by the AI, as confirmed by expert review.
Reported Device Performance:
The document does not provide specific metrics (e.g., mean absolute error, Dice coefficient, accuracy, sensitivity, specificity) for the performance of the AutoChamber software against its ground truth. It only states that "AutoChamber results were compared with measurements previously made by cardiac MRI" and other CT scans. Therefore, a table of acceptance criteria vs. reported device performance cannot be fully constructed from the provided text, as the specific performance outcomes are not detailed, nor are the quantitative acceptance thresholds.
Study Details:
The clinical validation of the AutoChamber software was based on retrospective analyses.
-
Sample sizes used for the test set and data provenance:
- Study 1: 5003 cases where AutoChamber results from non-contrast cardiac CT scans were compared with measurements previously made by cardiac MRI.
- Study 2: 1433 patients with paired non-contrast and contrast-enhanced cardiac CT scans.
- Study 3: 171 patients who underwent both ECG-gated cardiac CT scan and non-gated full chest lung scan.
- Study 4: 131 cases where AutoChamber results were compared directly with a Reference device (K060937).
- Data Provenance: The reference data for percentiles is from 5830 people who participated in the Multi-Ethnic Study of Atherosclerosis (MESA). The specific country of origin for the test set data (the 5003, 1433, 171, and 131 cases) is not explicitly stated, but MESA is a US-based study. All studies were retrospective analyses of existing databases.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document implies that "expert knowledge" is used to confirm the correct placement of cardiac chamber volumes and LV mass. However, it does not specify the number of experts, their qualifications (e.g., specific board certifications, years of experience), or the process by which they established ground truth for the volumes themselves (e.g., manual segmentation by experts, or if the "cardiac MRI" measurements served as the primary ground truth, and if so, how those were established).
-
Adjudication method for the test set:
- The document does not specify a formal adjudication method (e.g., 2+1, 3+1 consensus) for the expert review or the establishment of ground truth for the test set. It mentions "The expert's review solely pertains to the region of interest being properly located," implying individual expert qualitative assessment of the AI's output, rather than a multi-reader consensus process for establishing the ground truth values themselves.
-
If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
- No, a multi-reader multi-case (MRMC) comparative effectiveness study designed to measure how much human readers improve with AI vs. without AI assistance is not described. The document states that the AI measurements were compared against existing data (e.g., MRI measurements, other CT scans). The AI is presented as a "post-processing quantitative imaging software" that helps physicians investigate patients and is to be reviewed by radiologists or medical professionals. This implies an assistive role, but a formal MRMC study demonstrating enhancement of human reader performance is not mentioned.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the clinical validation involved comparing the AutoChamber software's measurements directly with other established measurement methods (cardiac MRI, other CT scans, and a reference device). This indicates a standalone performance evaluation of the algorithm's output against a reference. The "Principles of Ops" section states, "The user cannot change or edit the segmentation or results of the device. The user must accept or reject the region where the cardiac chamber volume measurement is done." This suggests the algorithm performs autonomously, and its output is then presented for acceptance/rejection based on anatomical placement.
-
The type of ground truth used:
- The primary ground truth appears to be measurements previously made by cardiac MRI in one key study (5003 cases), and measurements from other CT scans or a cleared reference device (K060937) in other studies. The document does not explicitly state that these "measurements" were derived from pathology or clinical outcomes data, but rather from other imaging modalities considered reference standards (MRI) or other devices. The qualitative "expert knowledge" mentioned for passing/failing the software seems to be about the anatomical correctness of the AI's segmentation/placement rather than the true quantitative values themselves.
-
The sample size for the training set:
- The sample size for the training set is not specified in the provided text. It only mentions that the AutoChamber Software uses an "AI trained model."
-
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.
§ 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).