Search Results

The SCHOELLY Oxygen Saturation Imaging (OSI) Camera System (consisting of Camera Control Unit and Camera Head) is used for endoscopic observation, diagnosis, treatment, and image recording. It is intended to process signals transmitted from a fiberoptic endoscope that is connected to the Camera Head.

This product may be used on all patients requiring endoscopic examination using SCHOELLY Laparoscopes and FUJIFILM's light source BL-7000X together with monitor, recorder and various peripheral devices. BLI (Blue Light Imaging) and LCI (Linked Color Imaging) are adjunctive tools which can be used to supplement white light endoscopy. BLI and LCI are not intended to replace histopathological sampling as a means of diagnosis.

The SCHOELLY OSI Camera System is further intended for use as an adjunctive monitor of the hemoglobin oxygen saturation of blood in superficial tissue of the endoscopic observation image area in pattents at risk for ischemic states. The prospective clinical value of measurements made with OSI has not been demonstrated in disease states.

The proposed SCHOELLY Oxygen Saturation Imaging (OSI) Camera System is comprised of the SCHOELLY OSI Camera Control Unit (CCU) and the SCHOELLY OSI Camera Head (CH). It is intended for real-time endoscopic imaging and may be used on all patients requiring endoscopic examination.

The proposed device is for use with SCHOELLY Laparoscopes - mounted to the SCHOELLY OSI CH, or a videoscope connected to the SCHOELLY OSI CCU, an endoscopic light source and light guide and optional further light guide accessories. Further optional accessories to complete the endoscopic system include a monitor, an image recorder and further peripheral input devices (keyboard, mouse, foot pedal, etc.).

The proposed SCHOELLY OSI Camera System is suitable for real-time endoscopic visible imaging (white light imaging, WLI) as well as for real-time visualization of tissue oxygen saturation (StO2) levels during minimally invasive surgery (oxygen saturation imaging, OSI).

The document provided does not contain a study proving the device meets specific acceptance criteria based on human-in-the-loop performance, nor does it detail a multi-reader multi-case (MRMC) study or standalone algorithm performance with clearly defined acceptance criteria and adjudicated ground truth as typically found in AI/ML device submissions.

Instead, the document is a 510(k) Premarket Notification from the U.S. Food and Drug Administration (FDA) for the SCHOELLY Oxygen Saturation Imaging (OSI) Camera System. This type of submission primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than fulfilling pre-defined performance acceptance criteria for an AI/ML algorithm.

Therefore, many of the requested details, such as sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, and effect sizes in MRMC studies, are not explicitly present in the provided text in the context of an AI/ML performance study.

However, I can extract information related to the device's technical and non-clinical performance and substantial equivalence:

Acceptance Criteria and Reported Device Performance (based on Non-Clinical Performance Testing):

The document details non-clinical performance testing and a comparison to a predicate device. While not presented as a formal "acceptance criteria table" for an AI/ML model, the comparison to the predicate device and the successful completion of specified tests serve as the basis for demonstrating equivalence.

• Sterilization: Successfully passed sterilization validations according to instructions in the user manual, compliant with ANSI/AAMI ST98:2022 and ISO 14937:2009. |
  | Software Documentation | - Software documentation provided for a Basic Documentation Level per FDA Guidance (June 2023).
• Software lifecycle, documentation, and validation managed in accordance with IEC 62304:2006 + A1:2016. |
  | Electrical Safety and EMC Testing | - Assessed for conformity and complied with IEC 60601-1:2005+AM1:2012, IEC 60601-1-2:2014, IEC 60601-1-2:2020, and IEC 60601-2-18:2009. |
  | Imaging Mode Performance (WLI, BLI, LCI) | - Accurately reproduced reference artifacts for image sharpness, depth of field, signal-to-noise ratio, temporal noise, color reproduction, dynamic range, and distortion.
• Produced images with similar intensity, color, and contrast compared to the primary predicate device in in-vivo animal and human oral cavity/hand testing. |
  | OSI Performance (Oxygen Saturation Imaging) | - Accuracy: Measurements of oxygen saturation were similar to those produced by the primary predicate device when compared to a reference device (Spectros T-Stat™ 303 Microvascular Tissue Oximeter) on a tissue phantom with controlled oxygen levels.
• Effect of Variables: OSI testing included measurements regarding the effect of distance, angle, orientation, temperature, and duration.
• 2D Variation: Measurement of two-dimensional StO2 variation was performed.
• Image Similarity: Produced similar images of tissue oxygenation compared to the primary predicate device in human oral cavity/hand and in-vivo animal (intestines and stomach) testing. |

Regarding the other specific requirements for AI/ML performance studies:

1. Sample size used for the test set and the data provenance:

   • The document mentions "images of the human oral cavity and hand" and "intestines and stomach images from an in-vivo animal study."
   • It does not specify the exact number of images, patients, or animals used for these comparative tests.
   • The provenance is implied to be both human (oral cavity and hand) and animal (intestines and stomach), likely from a clinical or laboratory setting for in-vivo testing, but the country of origin is not specified, nor is whether the data was retrospective or prospective.

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

   • The document does not mention the use of experts to establish "ground truth" for the imaging comparisons in the sense of independent clinical review. The comparisons are stated as being directly between the SCHOELLY device's output and the predicate device's output, and against reference artifacts/tissue phantoms for quantitative measures.
   • For the oxygen saturation accuracy, the "reference device" (Spectros T-Stat™ 303 Microvascular Tissue Oximeter) serves as a quantitative reference for the tissue phantom, but this is a device-to-device comparison, not expert-adjudicated ground truth.

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

   • Not applicable as no expert adjudication process is described for establishing ground truth for an AI/ML model's output. The performance relies on instrumental comparisons and visual similarity to a predicate.

4. 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 study is mentioned. The device's primary function is imaging and visualization, including adjunctive oxygen saturation monitoring, not necessarily an AI-driven diagnostic aid for human readers. Therefore, an MRMC study demonstrating human reader improvement with AI assistance is not described.

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

   • The document implies a "standalone" technical performance evaluation for the imaging capabilities and oxygen saturation measurements, where the device's output is compared directly to reference standards or the predicate device. However, this is for the device's imaging capabilities (hardware and embedded algorithms for image processing), not an independent AI algorithm producing a standalone diagnostic output.

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

   • For imaging characteristics (sharpness, color reproduction, etc.), "reference artifacts" were used.
   • For oxygen saturation accuracy, a "tissue phantom with controlled oxygen levels" and a "reference device" (Spectros T-Stat™ 303 Microvascular Tissue Oximeter) were used.
   • For visual comparisons (intensity, color, contrast, tissue oxygenation), the predicate device's output and in-vivo human/animal images served as the comparison basis, not a an independent "ground truth" established by expert consensus, histology, or outcomes. The substantial equivalence relies on the similarity to the predicate device's output.

7. The sample size for the training set:

   • Not applicable. This is a 510(k) submission for an imaging system, not explicitly an AI/ML device that requires a distinct "training set" for model development as typically understood in AI/ML validation studies. The "algorithms" mentioned are for image processing (BLI, LCI, OSI modes) and are inherent to the camera system, not necessarily a separate AI/ML model trained on a large dataset.

8. How the ground truth for the training set was established:

   • Not applicable for the same reason as above. If the device incorporates learned algorithms, the details of their training and validation are not provided in this 510(k) summary, which focuses on demonstrating substantial equivalence rather than detailing AI/ML model development.

In summary: The provided text is a 510(k) summary demonstrating substantial equivalence for an endoscopic camera system. It highlights non-clinical performance testing comparing the device's output to a predicate device and established technical standards, rather than an AI/ML performance study with a distinct test set, ground truth experts, and reader studies.

Ask a specific question about this device

Processor VP-7000:
The VP-7000 unit is used for endoscopic observation, diagnosis, treatment, and image recording. It is intended to process electronic signals transmitted from a video endoscope (a video camera in an endoscope).

This product may be used on all patients requiring endoscopic examination and when using a Fujinon/FUJIFILM medical endoscope and light source together with montor, recorder and various peripheral devices. BLI (Blue Light Imaging), LCI (Linked Color Imaging) and FICE (Flexible spectral-Imaging Color Enhancement) are adjunctive tools for gastrointestinal endoscopic examination which can be used to supplement Fujifilm white light endoscopy. BLI, LCI and FICE are not intended to replace histopathological sampling as a means of diagnosis.

The Image Processing Unit EX-0 is an optional module intended for use as an adjunctive monitor of the hemoglobin oxygen saturation of blood in superficial tissue of the endoscopic observation image area in patients at risk for ischemic states.

This product may be used on all patients requiring endoscopic examination when using a Fujinon/FUJIFILM medical endoscope, video processor and light source together with monitor, recorder and various peripheral devices.

The prospective clinical value of measurements made with OXEI has not been demonstrated in disease states.

Light Source BL-7000X:
The BL-700X Light Source is used for endoscopic observation, diagnosis, treatment, and image recording, It is intended to provide illumination to an endoscope. The light source also functions as a pump to supply air through the endoscope while inside the body to assist in obtaining clear visualization to facilitate diagnostic examination.

This product may be used on all patients requiring endoscopic examination and when using a Fujinon/FUJIFILM medical endoscope and video processor together with monitor, recorder and various peripheral devices.

Processor VP-7000 relays the image from the endoscope to a video monitor. Projection can be either analog or digital at the user's preference. VP-7000 also incorporates internal digital storage capacity. VP-7000 controls the light projected to the body cavity. VP-7000 provides for optional structural enhancement through user modes FICE (Flexible spectral-Imaging Color Enhancement), BLI (Blue Light Imaging), BLI-brt (Blue Light Imaging-Bright) and LCI (Linked Color Imaging) at the user's option. Spectral and structural enhancements are achieved through proprietary software. The device is AC operated at a power setting of 120V/60Hz, 0.8A. VP-7000 is housed in a steel-polycarbonate case measuring 390x485x110mm. Optional Image Processing Unit EX-0 receives image data from the VP-7000, and displays an OXEI image on a LCD monitor. The OXEI image is a color-coded digital image showing tissue oxygen saturation (StO2). EX-0 incorporates an internal digital storage capacity. The device is AC-operated at a power setting of 120V/60Hz, 1.0A. EX-0 is housed in a steel-polycarbonate case measuring 320x165x340 mm.

The Fujifilm endoscopes employ fiber bundles to transmit light from Light Source BL-7000X and subsequently to the body cavity. BL-7000X employs five LED lamps. Brightness control is performed by the user. The device is AC operated at a power setting of 120V / 60Hz 1.2A. BL-7000X is housed in a steel polycarbonate case measuring 395x485x155mm.

Processor VP-7000, Light Source BL-7000X, and Image Processing Unit EX-0 are used as a system in conjunction with a compatible video laparoscope or endoscope for visualization of tissue oxygen saturation (StO2) levels.

The provided document describes the Fujifilm Processor VP-7000, Light Source BL-7000X, and Image Processing Unit EX-0. The Image Processing Unit EX-0 is an optional module intended for use as an adjunctive monitor of hemoglobin oxygen saturation of blood in superficial tissue of the endoscopic observation image area in patients at risk for ischemic states.

Based on the provided information, the acceptance criteria and the study proving the device meets them can be summarized as follows:

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

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

• Bench Testing: 7 different blood-based phantoms. Data provenance is not explicitly stated but implies laboratory (benchtop) testing.
• Animal Testing:
  • Study 1 (Laparoscopic): Number of animals not specified, but involved "a visualization study."
  • Study 2 (Endoscopic): 4 female Göttingen minipigs.
  • Study 3 (Open Surgery): 3 swine.
• Data Provenance (Animal Studies): Live animal studies, likely conducted in a controlled laboratory environment. No specific country of origin is mentioned for the animal studies, but the entire submission is to the U.S. FDA. The details provided (e.g., "female Göttingen minipigs at 11 months of age") suggest prospective data collection.

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

• Bench Testing: A "dissolved oxygen meter" was used as the "gold standard" for StO2 measurements. This is an objective measurement tool, not human experts.
• Animal Testing: The document does not specify the use of human experts to establish ground truth for the StO2 measurements. The reference device (T-Stat 303 Microvascular Tissue Oximeter) served as a comparator, and the study focused on the comparability of the subject device's measurements to the reference device and, implicitly, to the physiological changes induced (e.g., decreased arterial oxygen saturation).

4. Adjudication method for the test set:

Not applicable. The ground truth for StO2 measurement was established by an objective "gold standard" (dissolved oxygen meter in bench testing) or by comparison to a legally marketed predicate/reference device and physiological changes in animal models. No human adjudication is mentioned for the StO2 measurements.

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, an MRMC comparative effectiveness study was not done. The device (Image Processing Unit EX-0) acts as an "adjunctive monitor" of StO2. The studies described focus on the device's ability to measure StO2 accurately and comparably to a reference device, not on improving human reader performance in interpreting images with AI assistance versus without it. This device itself is an "adjunctive tool," not specifically an AI assisting human interpretation of images for diagnosis, but rather providing a quantifiable physiological parameter (StO2).

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

Yes, the performance testing of the StO2 measurement function appears to be a standalone evaluation of the device's capability to measure and display StO2 levels. The bench testing directly compared the device's output to a gold standard, and the animal studies evaluated the device's measurements against a reference device's measurements and induced physiological states. The language suggests the device outputs StO2 values or color-coded images autonomously, without direct human intervention in the measurement process itself, though a human interprets the displayed information.

7. The type of ground truth used:

• Bench Testing: Dissolved oxygen meter (objective measurement, considered a "gold standard").
• Animal Testing:
  • Comparison to a legally marketed reference device (T-Stat 303 Microvascular Tissue Oximeter).
  • Induced physiological states (e.g., decreasing arterial oxygen saturation (SpO2) to simulate ischemic states). These physiological changes and the measurements from the reference device serve as the de-facto ground truth for evaluating the subject device's performance in a living system.

8. The sample size for the training set:

Not applicable. The document describes performance testing for a 510(k) submission, which focuses on demonstrating substantial equivalence to a predicate device. This typically involves verification and validation testing, not the development and training of an AI algorithm from a training set. The Image Processing Unit EX-0 processes existing endoscopic image data to display StO2; it is not presented as a machine learning or AI-driven diagnostic tool that requires a training set in the conventional sense.

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

Not applicable, as no training set is described for this device in the provided document.

Ask a specific question about this device

The Spectros T-Stat™ 2.0 Microvascular Tissue Oximeter is intended for use as an adjunct monitor of the localized hemoglobin oxygen saturation of blood in the microvascular tissue spaces (StO2%) in infants, children, or adults at risk for reduced-flow and no-flow ischemic states.

The prospective clinical value of measurements made with the T-Stat™ Oximeter has not been demonstrated in disease states. The T-Stat™ Oximeter should not be used as the sole basis for diagnosis or therapy.

The Spectros T-Stat™ 2.0 Microvascular Tissue Oximeter is a broadband, multiwavelength, Visible Light Spectroscopy (VLS) monitoring system for measuring the saturation of hemoglobin with oxygen in the microvascular tissue spaces (StO2%).

The complete system consists of a disposable sensor probe connected to a software-driven electronic monitor. Data collection, analysis, and display functions are provided by the monitor. Illumination of the tissue is provided by a visible light source in the sensor probe placed near, on, or into the target tissue to be studied. Reflected light is captured and returned to the monitor via a detachable connection at the monitor end of the patient probe. StO2% is estimated using differential optical diffuse reflectance spectroscopy and fitting for background scattering over a range of reflected visible wavelengths.

The provided text does not contain detailed information about specific acceptance criteria or a comprehensive study report for the T-Stat 2.0 Microvascular Tissue Oximeter. Instead, it focuses on the device's substantial equivalence to a predicate device (T-Stat 303™ Microvascular Tissue Oximeter) based on design modifications and re-verification of existing standards.

Therefore, I cannot provide a detailed answer to all parts of your request. However, I can extract what is available regarding testing and validation:

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics for the T-Stat 2.0. The test summary mentions compliance verification with international standards and re-verification of functional requirements.

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 does not specify a "test set" in the context of patient data or clinical samples. The testing described is primarily engineering and software validation. Therefore, information about sample size for a clinical test set and data provenance is not available.

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)

This information is not provided as the document does not describe a clinical study where ground truth would be established by experts.

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

This information is not provided as the document does not describe a clinical study.

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 information is not provided. The T-Stat 2.0 is a tissue oximeter, not an AI-assisted diagnostic imaging device for human readers.

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

The T-Stat 2.0 provides StO2% measurements. The "functional continuity" re-verification suggests standalone performance relative to the predicate device's established functionality. However, detailed performance metrics for just the algorithm are not provided.

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

The document focuses on engineering and software validation against established standards and the functional requirements of the predicate device. It does not mention a "ground truth" in the clinical sense (e.g., pathology, outcomes data) for the T-Stat 2.0's performance validation. The predicate device's existing clearance would have relied on such ground truth for its initial establishment of effectiveness.

8. The sample size for the training set

The document does not mention a "training set" as it describes re-verification of a modified device, not the development of a new algorithm requiring a training set.

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

This information is not provided as there is no mention of a training set.

Ask a specific question about this device