Search Results

Imbio IQ-UIP is a computer-aided software indicated for use in passively notifying specialists associated with interstitial lung disease (ILD) centers of radiological findings suggestive of radiological usual interstitial pneumonia (UIP) in non-contrast, chest CT scans of adults. Imbio IQ-UIP uses an artificial intelligence algorithm to analyze images and identify positive findings on a worklist application separate from and in parallel to the standard of care radiological image interpretation. Identification of positive findings include summary reports with a clinical guideline reference for the definition of UIP pattern that are meant for informational purposes only. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

The results of Imbio IQ-UIP are used to notify specialists at an ILD center of radiological findings that may be consistent with UIP. These specialists are qualified clinicians experienced in evaluating chest CTs for ILD. Input images originate from within the same hospital network associated with the ILD center. The results of Imbio IQ-UIP are intended to be used in conjunction with additional patient information and based on the user's professional judgment, to assist with the review of medical images. Notified clinicians are responsible for viewing full image series and making final clinical determinations.

Imbio IQ-UIP is a computer-aided software indicated for use in notifying specialists associated with Interstitial Lung Disease (ILD) Centers of radiological findings suggestive of radiological Usual Interstitial Pneumonia (UIP) in non-contrast, chest CT scans of adults.

Imbio IQ-UIP uses an artificial intelligence algorithm to analyze images and identify positive findings on a worklist application separate from and in parallel to the standard of care radiological image interpretation. Identification of positive findings include summary reports with a clinical guideline reference for the definition of UIP pattern that are meant for informational purposes only. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

The development of the deep learning inference model utilized anonymized, multi-center, retrospective, volumetric chest CT scans from several different, private and public data sources including multiple hospitals, clinical imaging centers, and imaging databases. Chest CT datasets were identified where each dataset represented an individual subject and acquisition. Data was subdivided into "bins" between the two stages of model development roughly 80%:20%: 1) model training and validation (i.e., hyper-parameter tuning) and 2) model testing (i.e. performance assessment). Site independence was maintained for several of the databases with clinical location data labels by randomly assigning each clinic location an integer value between 1 and 1000. Then, increasing from the lowest to highest random integer value, all data sets from a specific clinic location were assigned to the training bin until 80% of the total number of datasets from a database had been assigned to the training bin. The remaining were assigned to the testing bin. The testing data set was locked and quarantined from the datasets used in the device's model training and validation.

The results of Imbio IQ-UIP are intended to be used in conjunction with other patient information and based on the user's professional judgment, to assist with the review of medical images. Notified clinicians are responsible for viewing full image series and making final clinical determinations.

This document details the acceptance criteria and the study that proves the device (Imbio IQ-UIP) meets these criteria, based on the provided FDA 510(k) summary.

Device Name: Imbio IQ-UIP
Intended Use: Computer-aided software indicated for passively notifying specialists associated with interstitial lung disease (ILD) centers of radiological findings suggestive of radiological usual interstitial pneumonia (UIP) in non-contrast, chest CT scans of adults. It uses an AI algorithm to analyze images and identify positive findings on a worklist application, separate from and in parallel to standard-of-care radiological image interpretation. The device does not alter the original medical image and is not intended to be used as a diagnostic device.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated as quantitative thresholds in the provided document. However, the study focuses on evaluating the device's performance metrics (AUC ROC, PPV, Specificity, Sensitivity) in identifying radiological UIP patterns. The "acceptance" is implied by the reported performance figures that demonstrate the device's ability to meet its intended purpose of identifying findings "suggestive of radiological usual interstitial pneumonia."

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

• Sample Size for Test Set: 804 individual patient images.
• Data Provenance: Anonymized, multi-center, retrospective, volumetric chest CT scans from several different, private and public data sources including multiple hospitals, clinical imaging centers, and imaging databases. The country of origin is not explicitly stated but can be inferred to be primarily the United States given the use of U.S. board-certified radiologists for ground truthing.

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

• Number of Experts: Five experts (referred to as "truthers").
• Qualifications of Experts:
  • U.S. board-certified radiologists.
  • Practicing within the United States.
  • Minimum of 5+ years experience evaluating chest CTs for ILDs.
  • Clinical familiarity with using the ATS/ERS/JRS/ALAT diagnostic categories for UIP pattern.
  • None involved in the development of the algorithm/device, ensuring independence.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method (e.g., 2+1, 3+1). It only mentions that five experts "performed ground truthing" of the performance datasets. Therefore, the specific method for resolving disagreements or arriving at a consensus ground truth amongst the five experts is not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

The provided information does not indicate that an MRMC comparative effectiveness study was done to compare human readers with AI assistance vs. without AI assistance. The study focuses on a standalone performance assessment of the AI algorithm.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, a standalone performance assessment was done. The reported performance metrics (AUC ROC, PPV, Specificity, Sensitivity) are from the device's independent analysis of images, without human intervention during the assessment. The document explicitly calls this "standalone performance assessment."

7. The Type of Ground Truth Used

The ground truth used was expert consensus based on the evaluation by five U.S. board-certified radiologists with specific experience in ILD and UIP pattern diagnosis using established clinical guidelines (ATS/ERS/JRS/ALAT diagnostic categories).

8. The Sample Size for the Training Set

The document states that data was subdivided into "bins" for model development, with roughly 80% assigned to model training and validation (i.e., hyper-parameter tuning) and 20% for model testing (performance assessment). Since the test set was 804 images, the total number of unique datasets used for both training/validation and testing would be approximately 804 / 0.20 = 4020.
Therefore, the training set sample size would be approximately 3216 datasets (80% of 4020).

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

The document states that for model development, data was comprised of "anonymized, multi-center, retrospective, volumetric chest CT scans from several different, private and public data sources including multiple hospitals, clinical imaging centers, and imaging databases." It does not explicitly detail the method for establishing ground truth for the training set. However, given the nature of AI/ML model development for medical imaging, it is highly probable that the training data was also annotated or labeled by experts, or derived from clinical records/diagnoses that implicitly represent ground truth. The emphasis on independent "truthers" for the test set suggests a rigorous approach to testing, but the specifics of training data labeling are not provided in this summary.

Ask a specific question about this device

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.

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.

Ask a specific question about this device

Imbio CAC Software is intended for use as a non-invasive post-processing software to evaluate calcified plaques in the coronary arteries, which present a risk for coronary artery disease. Imbio CAC Software uses machine learning to analyze non-contrast thoracic CT images and outputs a summary report containing Agatston score, arterial age, and calcified lesion mass and volume metrics of the calcification burden for the whole heart and individual coronary artery level. Additionally, Imbio CAC Software outputs annotated images previewing the segmentation of calcifications for informational purposes only. Imbio CAC Software is limited to the quantification of detected possible calcifications in adult patients ≥ 29 years of age. It does not diagnose coronary artery disease. The device output will be available to the users as part of the standard DICOM viewing workflow. The Imbio CAC Software results are not intended to be used on a stand-alone basis for clinical decision-making or otherwise preclude clinical assessment of CT images.

The Imbio CAC Software is a set of medical image post-processing computer algorithms that together performs automated coronary artery calcification segmentation and reports a total Agatston score, calcified lesion mass and volume, and arterial age from thoracic computed tomography (CT) images. The Agatston score, calcified lesion mass and volume are reported both as a total and for each of the following individual coronary arteries: right coronary artery (RCA), left anterior descending (LAD), left circumflex (LCx). The Imbio CAC Software is a single command-line executable program that may be run directly from the command-line or through scripting and thus the user interface is minimal.

Imbio CAC Software is a Software and Medical Device (SaMD) intended to provide annotated DICOM-formatted images and a PDF report that will be read most typically at a PACS workstation. Imbio CAC Software is an aid only used to support a physician in the analysis of CT images.

The Imbio CAC Software program reads in thoracic CT DICOM datasets, processes the data, then writes output DICOM files and summary reports to a specified directory. Imbio CAC Software outputs DICOMs of the original input DICOM CT images overlaid with color-codings representing the coronary artery calcification segmentations. Additionally, a summary PDF report is output.

Imbio CAC 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.

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

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document only explicitly states one acceptance criterion related to quantitative performance.

2. Sample Size and Data Provenance for Test Set

• Sample Size: 500 anonymized chest CT series.
• Data Provenance: Retrospective and multi-center. The images were curated from "a variety of sources including large publically available databases and private imaging data brokers."
  • Patient Demographics:
    • Mean age: 64.3 years (SD: 10 years).
    • Age range: 29 years old to 90+.
    • Gender: 41.7% male, 42.5% female, 15.6% no gender information.
  • Scanner Manufacturers: GE Medical Systems (65.1%), Siemens (19.4%), Imatron (15.2%), and Philips (0.2%).
  • Acquisition Type: Equal split of ECG-gated and non-gated acquisitions.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: Not explicitly stated as "experts." Instead, "experienced 3D Image Post-Processing Technologists" were used. The number of technologists is not provided.
• Qualifications of Experts: "Experienced 3D Image Post-Processing Technologists." No specific years of experience or board certifications are mentioned.

4. Adjudication Method for Test Set

• The ground truth was established using an "FDA-cleared semi-automated CAC scoring software program." This implies a semi-automated process rather than a direct human expert adjudication method like 2+1 or 3+1. The technologists used this software to annotate the scans.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was mentioned or conducted. The study described is a standalone device performance assessment against a ground truth, not a comparison of human reader performance with and without AI assistance.

6. Standalone Performance Study

• Yes, a standalone (algorithm only without human-in-the-loop performance) study was conducted. The document states, "Non-clinical testing was conducted in the form of a retrospective, multi-center, standalone device performance assessment." The primary endpoint evaluated the Imbio CAC Software's agreement with the established ground truth.

7. Type of Ground Truth Used

• The ground truth was established by "experienced 3D Image Post-Processing Technologists using an FDA-cleared semi-automated CAC scoring software program." This can be categorized as a form of expert-assisted software output or "reference standard based on a previously cleared device." It is not explicitly stated to be pathology or outcomes data.

8. Sample Size for the Training Set

• The document does not provide information on the sample size for the training set. It only describes the test set used for performance validation.

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 describes the ground truth establishment for the test set. Given that the device uses machine learning, a training set with established ground truth would have been necessary for its development, but details are not included in this summary.

Ask a specific question about this device