Search Results

EVIS EUS ENDOSCOPIC ULTRASOUND CENTER OLYMPUS EU-ME3 is intended to be used with Olympus ultrasound endoscopes and Olympus ultrasound probes to observe real-time ultrasound images and is indicated for use within the gastrointestinal (GI) tract, biliary and pancreatic ducts and surrounding organs, intraluminal ultrasound for airways, tracheobronchial tree, trans-rectal, trans-urethral, and trans-esophageal (non-cardiac).

The EVIS EUS ENDOSCOPIC ULTRASOUND CENTER OLYMPUS EU-ME3 system (including KEYBOARD MAJ-2380), when combined with compatible ultrasound video scopes or ultrasound probes, makes an endoscopic ultrasound imaging system that can acquire and display and record real-time ultrasound images of the target tissue or organs. It supplies the driving voltage to the ultrasound transducers to generate ultrasound waves. Using these transducers, the Subject system can display endoscopic and ultrasound images to provide measurements and calculations of distance, area, circumference, time, blood velocity, strain ratio, strain histogram and shear wave speed of the targeted areas. It also allows the storage and retrieval of images for reviewing and printing. The Subject system enables the user to print and record images to an external recording device. Additionally, the Subject system enables the user to record movies to internal memory. The accessories submitted for clearance with the EU-ME3 that may be purchased separately include three (3) Software Options, which unlock software that is pre-installed on the EU-ME3 (for Contrast Harmonic Echo [MAJ-2381], Elastography [MAJ-2382] and Shear Wave Quantification [MAJ-2383]).

The provided FDA 510(k) summary (K243502 for the OLYMPUS EU-ME3) does not contain the detailed information necessary to answer all the questions regarding acceptance criteria and a study proving the device meets those criteria, particularly concerning AI/software performance in a clinical context.

This document describes a premarket notification for a medical imaging device that primarily focuses on hardware and basic software functionalities of an endoscopic ultrasound system, rather than an AI/ML-driven device that requires performance metrics against a defined ground truth.

Specifically, the document states: "No clinical data were collected to support performance of the Subject device." This explicitly indicates that no clinical study, whether involving human readers, standalone AI, or comparative effectiveness, was performed or presented in this submission to establish performance against acceptance criteria for an AI/ML component.

Therefore, the following points can be directly addressed based on the provided text, while others cannot.

Acceptance Criteria and Device Performance Study Analysis (Based on Provided Document K243502)

The provided document describes the Olympus EU-ME3 (EVIS EUS Endoscopic Ultrasound Center), an ultrasound imaging system. The 510(k) submission primarily focuses on demonstrating substantial equivalence to a predicate device (OLYMPUS EU-ME2 Premier Plus, K203128) based on technological characteristics and non-clinical performance data, not a study of an AI/ML algorithm's clinical performance.

Therefore, it is crucial to note that the document explicitly states: "No clinical data were collected to support performance of the Subject device." This means there is no clinical study described within this submission that proves the device meets specific performance acceptance criteria for an AI-driven functionality.

The "acceptance criteria" discussed in this document are primarily related to non-clinical bench testing, safety, electrical compatibility, and compliance with regulatory standards for an ultrasound imaging system.

1. A table of acceptance criteria and the reported device performance

Based on the "SUMMARY OF NON-CLINICAL PERFORMANCE DATA" section (Page 8), the following non-clinical tests were completed and demonstrated compliance, implying these are the "acceptance criteria" for the non-AI/ML aspects of the device demonstrated in this submission:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not applicable / Not provided. The document explicitly states "No clinical data were collected to support performance of the Subject device." The testing described is non-clinical bench testing, not a clinical study involving a test set of patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable / Not provided. Since no clinical data or clinical study was conducted for performance evaluation in this submission, there was no need for experts to establish ground truth for a clinical test set.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable / Not provided. No clinical test set.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No. The document explicitly states, "No clinical data were collected to support performance of the Subject device." Therefore, no MRMC study, especially one involving AI assistance, was conducted.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• No. The document describes a full ultrasound imaging system. While it mentions features like "Elastography and Shear Wave Speed Measurement (Shear Wave Quantification)" and "Strain Ratio/Strain Histogram," these are described as modes or measurement functions of the imaging device itself, rather than a separate AI algorithm that performs standalone analysis and requires independent performance validation. The submission focuses on the inherent physical and software capabilities of the ultrasound machine for these measurements.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Not applicable for clinical performance. For the non-clinical bench testing, the "ground truth" would be the known physical properties of the phantoms or test objects used (e.g., known distances, known material properties for elasticity measurements).

8. The sample size for the training set

• Not applicable. This submission does not describe an AI/ML algorithm that requires a training set. The device is an ultrasound imaging system with various modes and measurement capabilities.

9. How the ground truth for the training set was established

• Not applicable. No training set was involved as this is not an AI/ML device submission requiring such.

Ask a specific question about this device