Search Results

The Embryo Real-time Incubator (TLS301) is intended to provide an environment with controlled temperature and mixed gas (CO2 and other gases) for the development of embryos. The Embryo Real-time Incubator (TLS301) has an integrated camera and optics for imaging and viewing embryos during incubation, for a maximum time of 120 hours.

The Embryo Real-time Culture Dish (MC 2004) is intended for preparing, storing and transferring human embryos. It is intended to be used only with the Embryo Real-time Incubator (TLS301).

Embryo Realtime 2S Software and Embryo Realtime 3E Software accessories for the Embryo Real-time Incubator (TLS301).

The Embryo Realtime 2S Software is intended to store, archive and transfer data. In addition, the Embryo Realtime 2S Software includes functions for managing models and performing calculations based on image data and embryo development parameters.

Embryo Realtime 3E Software is intended for viewing and recording embryo development events from images captured using the Embryo Real-time Incubator (TLS301). Embryo Realtime 3E Software includes a user annotation for capturing information on embryo development parameters and a user-defined modeling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection.

Embryo Realtime 2S Software and Embryo Realtime 3E Software do not control any hardware components in the Embryo Real-time Incubator (TLS301). Embryo Realtime 2S Software and Embryo Realtime 3E Software are provided in different software package and must be used together.

The Embryo Real-time Incubator (TLS301) consists of the following components:

• Embryo Real-time Incubator, integrated with temperature control system, gas supply control system and time-lapse imaging system.
• Image capture software
• Workstation, composed of server and workstation software.
• Embryo Real-time Culture Dish (MC 2004)

The Embryo Real-time Incubator (TLS301) is a benchtop tri-gas (CO2, N2, and air) embryo incubator with a built-in microscope for time-lapse imaging intended to be used for the culture and monitoring of embryos used in Assisted Reproductive Technology (ART) procedures. It provides temperature control, gas control, and time-lapse imaging at multiple focal planes. The incubator chamber has the capacity to hold up to ten Embryo Real-time Culture Dishes (MC 2004). Each chamber contains a heating plate to maintain chamber temperatures. Gas (CO2, N2, and air) is mixed in a mixing chamber and passed through a HEPA/VOC filter prior to delivery to the incubation chamber. The built-in microscope consists of an illumination unit (red LED, 635 nm) and an inverted microscope/camera unit. The imaging system is mobile and is controlled through moving guide rail to automatically position the camera to the designated culture plate/well. The camera can acquire images in multiple focal planes. The time-lapse imaging system in the incubator along with the image capture software capture timelapse images of the embryos and transmit captured images to the computer for display and storage. The image capture software also reads the patient labels on the Embryo Real-time Culture Dish (MC 2004) and incorporates patient information into the imaging record.

The workstation includes a server and workstation software (Embryo Realtime 3E Software). It includes graphical user interface and receives and stores images. It also supports query, retrieval and display of the embryo images. The workstation software allows for manual annotation of the series of images obtained through time-lapse imaging into a user-defined model for the assessment of embryo's development. In addition, the server software (Embryo Realtime 2S Software), that does not include a graphical user interface, is designed to archive, transfer and store images of embryos from the time lapse incubator and performs user model management and calculations based on image data and user inputted embryo development parameters. The two software are used together.

The Embryo Real-time Culture Dish (MC 2004) is a single use, single-patient, polystyrene, radiation sterilized culture dish intended for preparing, storing, and transferring human embryos. It is intended to be used only with the Embryo Real-time Incubator (TLS301). It contains two types of wells for rinsing and handling the embryos before or after incubation and 16 wells for culturing the embryos during incubation. Each culture well is used to culture one embryo and a total of 16 embryos from a single patient can be cultured on one dish. The culture and rinsing wells have a volume of 30 µL and 50 µL, respectively. There is a central depression in the center of each culture well, where the embryo resides. The Embryo Real-time Culture Dishes (MC 2004) has a label area for unique identification of the culture dish.

The provided text pertains to the FDA 510(k) premarket notification for the "Embryo Real-time Incubator (TLS301)" and "Embryo Real-time Culture Dish (MC 2004)" and their associated software.

Based on the provided information, the acceptance criteria and study details are primarily focused on the non-clinical performance and substantial equivalence to a predicate device, rather than a clinical study evaluating diagnostic accuracy or reader performance with AI. The device does not appear to be an AI-based diagnostic tool in the typical sense, but rather an incubator with an integrated imaging system and software that aids in embryo selection.

Here's a breakdown of the requested information based on the document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes various performance tests and their acceptance criteria, predominantly for the hardware components (incubator, optics, culture dish) and basic software functionalities.

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

The document describes non-clinical bench testing.

• Sample Size: Not explicitly quantified for each specific test in terms of individual units. The "Mouse embryo assay (MEA)" involved embryos, but a specific number is not given.
• Data Provenance: The studies are described as "Non-clinical bench testing." There is no mention of human clinical data, retrospective or prospective studies, or country of origin for such data. The MEA, by its nature, would use animal (mouse) embryos.

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

This type of information is generally relevant for AI/diagnostic devices that require expert human labels for ground truth. The provided document describes non-clinical bench testing to verify hardware and software performance against specifications. As such, there is no mention of experts establishing a "ground truth" in the diagnostic sense, nor their qualifications. The closest would be implicit expertise in conducting the various standardized tests (e.g., electrical safety, sterility, MEA).

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set:

Not applicable. The tests described are objective non-clinical performance and safety tests, not subjective interpretations requiring adjudication among experts.

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 MRMC comparative effectiveness study was mentioned. The device's software (Embryo Realtime 3E Software) includes a "user-defined modeling function that allows the user to combine annotated information on embryo development parameters to aid in embryo selection." However, the document does not describe any study evaluating the comparative effectiveness or improvement in human reader performance (e.g., embryologists) with or without this AI assistance. The focus is on the software's functionality and validation rather than its clinical impact on human decision-making.

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

The document does not describe a standalone performance evaluation of the "user-defined modeling function" or any other algorithm. The software functions aid in embryo selection, implying a human-in-the-loop process. The "Embryo Realtime 2S Software... includes functions for managing models and performing calculations based on image data and embryo development parameters," but no standalone performance metrics are provided for these calculations.

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

For the specific tests mentioned:

• Hardware and Software Performance: Ground truth is defined by objective engineering specifications and scientific standards (e.g., temperature ranges, gas concentrations, electrical safety standards, image quality parameters, sterility levels, endotoxin limits, mouse embryo development rates).
• Mouse Embryo Assay (MEA): The "ground truth" for this test is the biological outcome of mouse embryo development to blastocyst (≥80% development in 96 hours), an accepted standard for assessing device biocompatibility.

8. The Sample Size for the Training Set:

The document does not describe any machine learning or AI model training. Therefore, there is no mention of a training set sample size. The software's "user-defined modeling function" suggests that users create or define models based on annotated information, rather than the device coming with a pre-trained model.

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

Not applicable, as no machine learning training set or associated ground truth establishment process is described.

Ask a specific question about this device