Search Results

Bunkerhill AAQ is a radiological image processing system software indicated for use in the analysis of CT exams with or without contrast, that include the L1 – L5 region of the abdominal aorta, in adults aged 22 and older.

The device is intended to assist appropriately trained medical specialists by providing the user with the maximum axial abdominal aortic diameter measurement of cases that include the abdominal aorta. Bunkerhill AAQ is indicated to evaluate normal and aneurysmal abdominal aortas and is not intended to evaluate post-operative aortas.

The Bunkerhill AAQ results are not intended to be used on a stand-alone basis for clinical decision-making or otherwise preclude clinical assessment of cases. These measurements are unofficial, are not final, and are subject to change after review by a qualified interpreting physician. For final clinically approved measurements, please refer to the official radiology report. Clinicians are responsible for viewing full images per the standard of care.

Bunkerhill AAQ is a software-only medical device that employs deep learning algorithms to provide automatic maximal abdominal aortic diameter measurements from axial CT scans of the abdomen/pelvis, with or without IV contrast.

Bunkerhill AAQ receives DICOM instances and processes them chronologically by running the algorithm on relevant series to measure the maximum abdominal aortic diameter. Following the AI processing, the output of the algorithm analysis is transferred to standard radiology image review and reporting software.

Bunkerhill AAQ produces a preview image annotated with the maximum axial diameter measurement. The diameter marking is not intended to be a final output, but serves the purpose of visualization and measurement. The original, unmarked series remains available in the PACS as well.

The preview image presents an unofficial and not final measurement, and the user is instructed to review the full image and any other clinical information before making a clinical decision. The image includes a disclaimer: "Not for diagnostic use. The measurement is unofficial, not final, and must be reviewed by a qualified interpreting physician".

Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) clearance letter for Bunkerhill Abdominal Aortic Quantification (AAQ):

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: 258 patients
• Data Provenance: Retrospective study. Data sourced from North Carolina, Alabama, the greater Washington D.C. area (all in the USA), and Sao Paulo, Brazil. This indicates a diverse geographical origin for the data.

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

• Number of Experts: 3
• Qualifications of Experts: U.S. Board Certified Radiologists. Specific experience level (e.g., 10 years) is not provided, but Board Certification implies a high level of expertise.

4. Adjudication Method for the Test Set

• The text states "a ground truth established by 3 U.S. Board Certified Radiologists." This implies a consensus-based approach among the three experts to establish the definitive ground truth reference. The specific adjudication method (e.g., majority vote, discussion to reach consensus) is not detailed, but the use of three experts suggests a robust process beyond a single reader.

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

• No, an MRMC comparative effectiveness study involving human readers with vs. without AI assistance was not reported. The study described is a standalone performance study of the algorithm against a defined ground truth.

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

• Yes, a standalone performance study was done. The text explicitly states, "The AAQ algorithm performance was validated in a stand-alone retrospective study for overall agreement of the device output compared to a ground truth established by 3 U.S. Board Certified Radiologists." The results (MAE, ΔICC, Bland-Altman limits) are all reflective of the algorithm's performance in isolation.

7. The Type of Ground Truth Used

• Expert Consensus. The ground truth was "established by 3 U.S. Board Certified Radiologists," indicating that their consensus measurements were considered the true values for comparison.

8. The Sample Size for the Training Set

• Not provided. The document only references the test set of 258 patients. Information regarding the training set size is not included in this excerpt.

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

• Not provided. Since the training set size itself is not mentioned, the method for establishing its ground truth is also absent from this document. It's common practice for similar methods (e.g., expert annotations) to be used for training data, but this specific excerpt doesn't confirm it.

Ask a specific question about this device