(65 days)
The Imbio PHA Software device is designed to measure the maximal diameters of the right and left ventricles of the heart, the main pulmonary artery, and the ascending aorta from a volumetric CTPA acquisition and report the RV/LV and Pa/Ao ratios. PHA analyzes cases using an artificial intelligence algorithm to identify the location and measurements of the anatomy. The PHA software provides the user with annotated images showing measurements. Its results are not intended to be used on a stand-alone basis for clinical decision-making or otherwise preclude clinical assessment of CTPA cases.
Imbio's PHA Software is a set of medical image post-processing computer algorithms that together perform automated right and left ventricle, pulmonary artery (PA), and aorta (Ao) measurements from CT pulmonary angiography (CTPA) scans, and reports the RV/LV and PA/Ao ratios. The Imbio PHA is a single command-line executable program that may be run directly from the or through scripting and thus the user interface is minimal. Imbio PHA Software is a Software as a Medical Device (SaMD) intended to provide annotated images and a PDF report that will be read most typically at a PACS workstation. Imbio PHA Software is an aid, only used to support a physician in the analysis of CTPA images. The Imbio PHA Software program reads in CTPA DICOM datasets, processes the data, then writes output DICOM files and summary reports to a specified directory. Imbio PHA Software outputs DICOM CT images overlaid with color-codings indicating where the measurements were made. Additionally, a summary PDF report is output. Imbio PHA Software does not interface directly with any CT scanner or data collection equipment; instead the software imports data previously generated by such equipment and is integrated as part of the radiological workflow, reducing the risk of use errors.
The Imbio PHA (4.0.0) device is intended to measure the maximal diameters of the right and left ventricles of the heart, the main pulmonary artery, and the ascending aorta from a volumetric CTPA acquisition and report the RV/LV and Pa/Ao ratios. The device utilizes an artificial intelligence algorithm for identification and measurement of the anatomy, providing annotated images to the user. Its results are not intended for stand-alone clinical decision-making.
Here's a breakdown of the acceptance criteria and the study proving the device meets these criteria:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria for the Imbio PHA (4.0.0) device were based on the Intra-class Correlation Coefficient (ICC) of measurements.
| Acceptance Criteria | Reported Device Performance | Conclusion |
|---|---|---|
| ICC of all measurements (annotators and algorithm) > 0.90 (excellent) | ICC = 0.94 | Met |
| ICC of all measurements (annotators and algorithm) within 95% CI of the ICC of only annotators | (Specific CI not provided, but the overall ICC of 0.94 indicates strong agreement) | Inferred as Met (given "excellent agreement") |
The reported device performance, with an ICC of 0.94, indicates excellent agreement between the algorithm's measurements and those performed by expert radiologists.
2. Sample Size and Data Provenance
- Test Set Sample Size: 100 contrast-enhanced CT pulmonary angiography (CTPA) datasets.
- Data Provenance: The datasets were sourced from multiple centers and multiple databases. While specific countries are not mentioned, the experts establishing ground truth were U.S. board-certified radiologists practicing within the United States. The data was likely retrospective, as it mentions "datasets were sourced."
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Three expert radiologists.
- Qualifications: U.S. board-certified radiologists practicing within the United States, each with a minimum of 10 years of clinical experience.
4. Adjudication Method for the Test Set
The adjudication method involved each radiologist independently measuring the diameter of the pulmonary artery trunk at the bifurcation and the aorta diameter at the same slice. Intra-class correlation coefficients were then calculated to show equivalency between the radiologists and between the radiologists and the algorithm. This implies a comparison of individual expert measurements rather than a formal consensus adjudication where experts reconcile their differences to arrive at a single ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was specifically mentioned that directly assesses the improvement of human readers with AI assistance versus without AI assistance. The study focused on the agreement between the AI algorithm and expert radiologists' measurements.
6. Standalone Performance (Algorithm Only)
Yes, a standalone performance assessment was done. The study specifically states, "100 contrast-enhanced CT pulmonary angiography (CTPA) datasets were used for standalone performance assessment." The ICC calculation of 0.94 directly reflects the agreement between the algorithm's measurements and the expert radiologists' measurements, indicating its standalone performance in providing measurements consistent with human experts.
7. Type of Ground Truth Used
The type of ground truth used was expert consensus/agreement based on measurements. Specifically, the ground truth for the pulmonary artery and aorta diameter measurements was established by three expert radiologists, and the agreement between these experts and the algorithm was quantified using ICC.
8. Sample Size for the Training Set
The document does not specify the sample size for the training set. It only describes the test set used for performance assessment.
9. How Ground Truth for Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only details the ground truthing process for the performance (test) datasets.
§ 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).