Search Results

EmbryoScope+ consists of the following devices with the following indications for use:

The EmbryoScope+ incubator provides an environment with controlled temperature and gas concentrations (CO2 and O2) for the development of embryos at or near body temperature. Use of the EmbryoScope+ incubator is limited to five days (120 hr) covering the time from post insemination to day five of development.

The EmbryoSlide+ culture dish is intended for preparing, storing, and transferring human embryos. The EmbryoSlide+ culture dish must be used together with the EmbryoScope+ incubator.

The Embryo Viewer software is intended for displaying, storing, and transferring images generated by the EmbryoScope+ incubator. This software includes a user annotation for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo Viewer software does not control any hardware components in the EmbryoScope+ incubator.

The ES Server software is intended to store, archive and transfer data. In addition, this software includes functions for managing models and performing calculations based on image data and embryo development parameters.

The EmbryoScope+ incubator, EmbryoViewer software, and ES Server software must be used together to export embryo images from the EmbryoScope+ incubator. The EmbryoViewer software must be used together to analyze the embryo images.

EmbryoScope+ consists of the following devices: EmbryoScope+ incubator, EmbryoSlide+ culture dish, EmbryoViewer software, and ES Server software.

The EmbryoScope+ incubator is a bench top embryo incubator with a time-lapse imaging function. It provides temperature control, and time-lapse microscopy at multiple focal planes. This device can hold up to 15 culture dishes (EmbryoSlide+ culture dish) in the incubation chamber. The culture dishes are placed on the dish holder in the EmbryoScope+ incubator. The holder provides direct heat transfer to the EmbryoSlide+ culture dish. The built-in microscope consists of an LED illumination unit and an inverted microscope/camera unit. During image acquisition, each culture dish located on the culture dish holder is rotated to the microscopy system and individual image stacks are acquired from all individual embryos in each culture dish.

The EmbryoSlide+ culture dish is a radiation-sterilized polystyrene culture dish containing two separate reservoirs. Each reservoir has eight culture well is used to culture one embryo. Therefore, a total of 16 embryos can be cultured on one dish. Each dish includes four special wells that are only used for rinsing and handling the embryos either before or after incubation. An adhesive barcode label printed from the EmbryoViewer software is used to mark each dish. The barcode label contains two different 2D data matrices that provide information on the patient ID, treatment ID, and insemination time). The EmbryoSlide+ culture dish has a sterility assurance level of 10° and a shelf-life of four years. This device is subject to mouse embryo assay (MEA) and endotoxin testing before lot release.

The EmbryoViewer software is used for displaying, comparing, storing, and transferring images generated by the EmbryoScope+ incubator. The data that can be viewed using this software includes embryo images, incubation details, alarms, log files and other instrument parameters. This software also includes a user annotation for capturing information on embryo development parameters as well as a user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection. The EmbryoViewer software neither controls any hardware components in the EmbryoScope+ incubator nor performs any diagnostics.

The ES Server software allows users to update and view common data. The server acts as the central unit, which stores data and controls the data flow to and from the connected devices. The server can be connected to multiple EmbryoScope+ incubators and computers with the EmbryoViewer software installed.

The provided text does not contain information about a "study that proves the device meets the acceptance criteria" in the format of a clinical trial or a specific comparative effectiveness study with human readers and AI assistance. Instead, it describes non-clinical performance testing conducted to support the substantial equivalence of the EmbryoScope+ device to its predicate devices.

The acceptance criteria are generally implied by the design specifications and testing standards mentioned.

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

1. Table of Acceptance Criteria and the Reported Device Performance

The text doesn't explicitly present a direct "acceptance criteria" vs. "reported performance" table for all aspects. However, it lists performance specifications for the EmbryoScope+ incubator and the results of various non-clinical tests.

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

The document describes non-clinical bench testing. For the Mouse Embryo Assay (MEA), the sample size is implicitly "one-cell mouse embryos" without a specific number. The data provenance is not mentioned (e.g., country of origin). The testing seems to be experimental/prospective in nature, rather than retrospective use of human patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. The document describes non-clinical performance and engineering testing (electrical safety, EMC, software V&V, bench performance, sterilization, package integrity, endotoxin, mouse embryo assay). These do not involve human experts establishing ground truth for a diagnostic AI system.

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

Not applicable, as this is non-clinical performance testing, not a clinical study requiring adjudication of expert interpretations.

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 is mentioned. The device, EmbryoScope+, includes software (EmbryoViewer) with "user-defined modeling function, which allows the user to combine annotated information on embryo development parameters to aid in embryo selection." However, the text details non-clinical testing for substantial equivalence, not a clinical study on human reader performance with or without AI assistance.

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

While the EmbryoViewer software includes "user-defined modeling function" to "aid in embryo selection," the substantial equivalence argument relies on comparing the entire system (incubator, software, dish) to predicate devices through non-clinical performance metrics. There is no specific mention of a standalone algorithm performance study without human involvement, particularly relating to "embryo selection" capability. The software primarily displays, stores, transfers images, and allows for user annotation and user-defined modeling, implying human-in-the-loop use. It explicitly states, "The EmbryoViewer software neither controls any hardware components in the EmbryoScope+ incubator nor performs any diagnostics."

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

For the non-clinical tests described:

• EmbryoSlide+ Culture Dish (MEA): The "ground truth" for the MEA test was defined by the biological outcome: "percent of embryos developed to the expanded blastocyst stage within 96 hours." This is an objective biological endpoint.
• Other non-clinical tests (electrical safety, EMC, metrology, etc.): Ground truth is established by adherence to engineering specifications, recognized standards (e.g., IEC, EN, ASTM, ISO, USP, ANSI/AAMI), and design specifications.

8. The sample size for the training set

Not applicable. The document does not describe a machine learning model that requires a training set in the conventional sense. The "user-defined modeling function" in the EmbryoViewer software suggests that users define their own criteria based on embryo development parameters, rather than the device itself being trained on a large dataset.

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

Not applicable, as no machine learning training set is described.

Ask a specific question about this device

To provide an environment with controlled temperature, CO2 (and other gases) for the development of embryos. This model has an integrated inverted microscope and imaging system for embryo viewing. Device use is limited to five days (120 hr) covering the time from post-fertilization to day 5 of development.

The EmbryoScope™ - (Version D) is an embryo incubator, which performs a series of unattended measurements including time-lapse microscopy at multiple planes and logging of incubation conditions on individual embryos during their development. The device has a build-in microscope within a red light source. Separate processing units control the incubation environment and the data acquisition to ensure safe and reliable operation. The Device allows incubation of up to 72 individual embryos in six sterile disposable EmbryoSlides™ each with capacity for 12 embryos.

The provided document describes a 510(k) submission for a change in the indication for use of the EmbryoScope™ - (Version D) device. Therefore, the "acceptance criteria" discussed are related to demonstrating that the device remains safe and effective for the extended use duration, rather than performance metrics of an AI model.

Here's an analysis based on the information provided, framed to address the requested categories for a device rather than an AI:

1. Table of Acceptance Criteria and the Reported Device Performance

The acceptance criteria are implied by the need to demonstrate that extending the incubation period from 3 days to 5 days does not alter the safety and effectiveness of the device, specifically relating to ongoing pregnancies and adverse effects. The study aimed to show "non-inferiority" or "no significant difference" in relevant clinical outcomes.

2. Sample size used for the test set and the data provenance

The document states: "Clinical data showed that the EmbryoScope™ - (Version D) performs according to the intended use of the device. No significant difference was found between the rates of ongoing pregnancies in the EmbryoScope™ -- (Version D) with 5 days of incubation compared to three days of incubation. No adverse effects of image acquisition were observed."

• Sample Size: Not explicitly stated. The phrase "Clinical data" suggests a study was performed, but the number of embryos, patients, or cycles included in this "clinical data" is not provided.
• Data Provenance: Not explicitly stated (e.g., country of origin, specific clinics).
• Retrospective/Prospective: Not explicitly stated. However, "Clinical data showed..." implies an analysis of collected data, which could be either. The comparison to "three days of incubation" suggests either a prospective comparative trial or a retrospective analysis comparing cohorts.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This section is not applicable in the context of this device and submission. The "ground truth" here is objective clinical outcomes (ongoing pregnancies, observed adverse events), not a subjective assessment requiring expert consensus on image interpretation or similar tasks that an AI might perform.

4. Adjudication method for the test set

This section is not applicable. The "test set" here refers to clinical data for human fertility outcomes, not a set of items requiring human adjudication (like medical images).

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

This section is not applicable. The EmbryoScope™ is an IVF incubator with an imaging system; it is not an AI-powered diagnostic device for which human reader performance would be assessed with or without AI assistance.

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

This section is not applicable. The device is an incubator and imaging system, not a standalone algorithm. Its "performance" is its ability to maintain a suitable environment and acquire images effectively, ultimately supported by clinical outcomes.

7. The type of ground truth used

The ground truth used for assessing the device's effectiveness was clinical outcomes data, specifically:

• Rates of ongoing pregnancies.
• Observation of adverse effects potentially related to image acquisition or the extended incubation period.

8. The sample size for the training set

This section is not applicable. The device is not an AI model that requires a training set in the conventional sense. The "training" for the device would be its engineering, design, and manufacturing processes, supported by non-clinical testing (electrical safety, EMC, environmental, operating performance) rather than a data training set.

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

This section is not applicable for the reasons stated above. The "ground truth" for the device's design and engineering is established through engineering principles, regulatory standards (e.g., IEC 60601-1), and extensive non-clinical testing to ensure hardware and software functionality, safety, and performance within specified environmental controls.

Ask a specific question about this device

To provide an environment with controlled temperature, CO2 (and other gases) for the development of embryos. This model has an integrated inverted microscope and imaging system for embryo viewing. Device use is limited to three days (72 hr) covering the time from post-fertilization to day 3 of development.

The EmbryoScope™ - (Version D) is an embryo incubator, which performs a series of unattended measurements including time-lapse microscopy at multiple planes and logging of incubation conditions on individual embryos during their development. The device has a build-in microscope within a red light source. Separate processing units control the incubation environment and the data acquisition to ensure safe and reliable operation. The Device allows incubation of up to 72 individual embryos in six sterile disposable EmbryoSlides™ each with capacity for 12 embryos.

Here's a breakdown of the acceptance criteria and study information for the EmbryoScope™ (Version D) and EmbryoSlide™ devices, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The documents describe the EmbryoScope™ (Version D) as an IVF incubator and the EmbryoSlide™ (FT-S-ES-D) as an IVF incubator accessory. The acceptance criteria primarily revolve around demonstrating substantial equivalence to predicate devices. This means the new devices perform as safely and effectively as existing legally marketed devices.

The "acceptance criteria" are not explicitly stated in numerical thresholds but are implied by the comparison to predicate devices and the clinical testing outcome. The "reported device performance" is the statement of equivalence and the finding of comparable outcomes.

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

The document mentions "Clinical data showed that the EmbryoScope TM - (Version D) performs according to the intended use of the device. No significant difference was found between the rates of ongoing pregnancies in a standard incubator and the EmbryoScope™ - (Version D)."

• Sample Size for Test Set: The exact sample size for the clinical study is not specified in the provided text.
• Data Provenance: The provenance (country of origin, retrospective/prospective) is not specified. It refers to "Clinical data," implying a human clinical study. Given the company's address in Denmark, it's possible the study was conducted there or in another European country. The context of a 510(k) submission to the FDA suggests the data must meet FDA's requirements for demonstrating safety and effectiveness.

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

The document does not specify the number of experts used to establish ground truth or their qualifications for the clinical study. The "ground truth" for the clinical study appears to be the "rates of ongoing pregnancies," which would typically be determined by medical professionals in an IVF setting.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method for the clinical study results. It simply states the finding of "no significant difference" in ongoing pregnancy rates.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• MRMC Study: No, an MRMC comparative effectiveness study was not performed or described in the provided text.
• Effect Size (Human Readers with/without AI): Not applicable, as this device (EmbryoScope) is an incubator and imaging system, not an AI-assisted diagnostic tool that aids human readers in interpretation. The "imaging system" is for embryo viewing, not AI-driven analysis for human interpretation.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Standalone Performance: Not applicable in the context of the primary function of these devices. The EmbryoScope™ is an incubator with an integrated imaging system for embryo viewing, and the EmbryoSlide™ is an accessory. There isn't an "algorithm" performing a diagnostic or interpretive function in a standalone capacity described in the documentation. The device's performance relates to maintaining a suitable environment for embryo development and enabling imaging, not making automated diagnoses.

7. The Type of Ground Truth Used

For the clinical study of the EmbryoScope™ (Version D), the type of ground truth used was outcomes data, specifically "rates of ongoing pregnancies."

For the EmbryoSlide™ (FT-S-ES-D), the ground truth for its biological compatibility was established through:

• Sterility testing (SAL 10-6)
• Non-pyrogenic testing by Limulus Amebocyte Lysate (LAL)
• Non-embryotoxic testing by the 1-cell mouse embryo assay (MEA)
• "Embryo survival rate" comparable to the predicate device.

8. The Sample Size for the Training Set

The document does not mention or imply any training set, as these devices are not described as employing machine learning or AI models that would require a dedicated training set. The "testing" referred to is for device performance, safety, and clinical outcomes.

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

Not applicable, as no training set is described for these devices.

Ask a specific question about this device