Imbio RV/LV Software

Imbio, LLC • Radiology • 03/09/2021

510(k)IEC 62304 Class B

Device Purpose

The Imbio RV/LV Software utilizes an artificial intelligence algorithm to automatically segment and measure the maximal diameters of the right and left ventricles from volumetric CTPA images, subsequently reporting the RV/LV ratio. This medical image processing tool aims to enhance clinical assessment by providing quantitative data and annotated images, with studies demonstrating improved inter-radiologist agreement and accuracy compared to manual measurements.

Summary

The Imbio RV/LV Software is a medical image post-processing tool designed to analyze volumetric Computed Tomography Pulmonary Angiography (CTPA) acquisitions. Its primary function is to automatically measure the maximal diameters of the heart's right and left ventricles using an artificial intelligence algorithm. The software then calculates and reports the ratio of these diameters (RV/LV ratio). It processes DICOM CTPA image datasets and outputs annotated images displaying the ventricular measurements, along with a summary PDF report. The software operates via a command-line interface and is intended to be integrated into the radiological workflow, providing these outputs typically for review on a PACS workstation. It is important to note that the software's results are meant to support clinicians in their assessment of CTPA cases and are not intended for standalone use in clinical decision-making. Clinical performance of the Imbio RV/LV Software was evaluated through two reader studies using anonymized CTPA datasets. The first study aimed to demonstrate that the software's output report improved agreement among general radiologists when assessing RV/LV ratios. The second study focused on demonstrating the accuracy of the RV/LV diameter ratios calculated by the software in comparison to measurements made by radiologists. These studies support the software's role as an aid for physicians by providing automated, quantitative data from CTPA images to assist in the analysis of ventricular dimensions. The software does not directly interface with CT scanners but processes previously generated image files.

AI Regulatory Concerns

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

Keywords

RV/LV ratioCTPAArtificial IntelligenceImage SegmentationVentricle DiameterDICOMAutomated MeasurementRadiological Image ProcessingClinical Decision SupportReader Study

Device Metadata

Submission Number

K203256

Company

Imbio, LLC

Panel

Radiology

Product Code

N/A

Data Type

Images

Clinical Function

Assessment

AI Function

Analysis

AI Subclass

quantification/feature localization

Relevant Clinical Questions

Q1. How does the artificial intelligence algorithm handle anatomical variations or image artifacts in CTPA scans when segmenting the ventricles and determining maximal diameters?; What were the specific accuracy metrics (e.g., mean absolute difference, Bland-Altman limits of agreement) for the RV/LV diameter ratios generated by the software compared to radiologists' manual measurements in Reader Study-II?; What was the range of improvement in inter-reader agreement among general radiologists when using the RV/LV software, as demonstrated in Reader Study-I?; Are there known limitations or contraindications for using the Imbio RV/LV Software with specific patient populations (e.g., those with severe cardiac malformations, arrhythmias affecting image quality) or particular CTPA acquisition protocols?; How does the software's automated identification of the 'maximal diameter' of the ventricles account for potential variations in cardiac cycle phase if non-gated CTPA images are used, and how does this compare to manual clinical practice?

Risk Classification

ESL Analysis

IEC 62304 ClassB

FDA Device ClassII

FDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Authorized before §524B enforcement

Learn how Parasoft automates IEC 62304 compliance testing →

Cybersecurity Evidence

Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.

Cyber Score25/100

SBOM Evidence⚠ Not mentioned in summary

Cyber Risk Assessment✓ Detected in Summary

Postmarket Plan⚠ Not mentioned in summary

§524B ApplicableNo

Supply Chain BOM Evidence

Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.

SBOMSoftware Bill of Materials

- Not detected

ML-BOMMachine Learning Bill of Materials(algorithm, dataset)

✓ Detected

SaaSBOMSoftware-as-a-Service Bill of Materials

- Not detected

HBOMHardware Bill of Materials

- Not detected

CBOMCryptography Bill of Materials

- Not detected

VDR/VEXVulnerability Disclosure Report / Vulnerability Exploitability eXchange

- Not detected

OBOMOperations Bill of Materials

- Not detected

Analysis:

• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.

• Evidence of ML-BOM detected in AI-generated device summary.

• This device was authorized before §524B took effect. Cybersecurity evidence requirements were less prescriptive at the time.

• Postmarket cybersecurity monitoring plan not clearly documented in AI-generated device summary.

• Not detected in AI-generated device summary: SBOM, SaaSBOM, HBOM, CBOM, VDR/VEX, OBOM. These may be present in the full FDA submission.

Preparing a similar submission?

ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.

Assess Your Readiness →Or contact ESL directly