It is intended for use for endoscopy and endoscopic surgery within the thoracic and abdominal cavities including female reproductive organs. Not suitable for use for observation and treatment of the heart and must not contact the heart or its vicinity.

The SIRIUS Endoscope System as a robotic endoscope consists of Video Processor, Laparoscope Handle, Laparoscope Head and Joystick. The SIRIUS Endoscope System is developed for minimal invasive surgery application.

The SIRIUS Endoscope System is a fully integrated compact 3D laparoscopic camera system with a flexible tip that can change its viewing direction. The Laparoscope Head is made of biocompatible materials. The articulated tip has three degrees of freedom enabling C and S shaped bending. The insertion section is 10 mm diameter and 342 mm working length. Stereo camera with 1080 high-definition resolution. It has 90 degrees field of view, 10-100 mm depth of view.

The SIRIUS Endoscope System is to be used only under the supervision of a trained surgeon and professional clinical staff with trained use of the device.

The device is intended for use in Hospital operating theatres only.

This 510(k) clearance letter focuses on establishing substantial equivalence to a predicate device, rather than proving the device meets new acceptance criteria through a specific study design typically seen for AI/ML devices or novel technologies. The "acceptance criteria" here are implicitly linked to the performance of the predicate device and relevant international standards.

Therefore, many of the specific details you requested regarding acceptance criteria and study design (like sample size for test sets, number of experts for ground truth, MRMC studies, standalone performance, training sets) are not present in this type of document because the submission is not presenting evidence of novel diagnostic or assistive AI performance. It's a submission for a new model of an endoscope system, demonstrating it performs as safely and effectively as a previously cleared version.

However, I can extract information related to product performance and testing where available, and explain why other details are absent based on the nature of this 510(k) submission.

Analysis of Acceptance Criteria and Device Performance for SIRIUS Endoscope System (K250939)

The SIRIUS Endoscope System (PR-SI-1230) received 510(k) clearance based on its substantial equivalence to a predicate device (K221642: SIRIUS Endoscope System). The "acceptance criteria" in this context are not defined as specific performance metrics for a novel AI algorithm, but rather as meeting the safety, effectiveness, and performance standards expected of an endoscope system, particularly in comparison to its predicate. The studies provided focus on verifying that the new model performs comparably to the predicate and adheres to relevant industry standards.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a substantial equivalence submission for an updated hardware device (endoscope system) rather than a novel AI diagnostic, the acceptance criteria are primarily aligned with regulatory standards, predicate device performance, and international product standards. There are no specific AI performance metrics like sensitivity, specificity, or AUC mentioned.

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

This document does not describe a clinical "test set" in the context of an AI/ML or diagnostic performance study. The "tests" mentioned are primarily bench tests, engineering validations, and usability evaluations, not clinical studies involving patient data or images. Therefore, details like data provenance or a specific test set sample size for diagnostic performance are not provided. The comparisons are against the predicate device's design and adherence to recognized performance standards.

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

Not applicable. This submission is about the physical endoscope system, not an AI diagnostic algorithm requiring expert ground truth for image interpretation or diagnosis. The "ground truth" for the performance section refers to engineering specifications and compliance with international standards.

4. Adjudication Method for the Test Set

Not applicable, as there's no diagnostic test set requiring human adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC study was not conducted or reported. This type of study is typically done for AI algorithms that assist or augment human reading of medical images to demonstrate improvement in reader performance. The SIRIUS Endoscope System is a hardware device for visualization and surgery, not an AI-powered diagnostic tool in that sense.

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

Not applicable. There is no standalone algorithm being evaluated for performance independent of human operation for diagnostic purposes. The "software" referred to in the document relates to the device's operational software, not an AI for image analysis.

7. The Type of Ground Truth Used

The "ground truth" for this submission is based on:

• International Standards: e.g., ISO 10993 series for biocompatibility, ISO 11135 for sterility, IEC 60601 series for electrical safety/EMC, IEC 62471 for light source safety, ISO 8600 series for endoscope performance, and ANSI/AAMI IEC 62366-1 for usability.
• Engineering Specifications: The design and function of the device itself are validated against its own specifications and those of the predicate.
• Predicate Device Performance: The primary "ground truth" for substantial equivalence is that the new device performs "as well as the legally marketed predicate device."

8. The Sample Size for the Training Set

Not applicable. This document does not describe an AI/ML algorithm that requires a training set.

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

Not applicable, as there is no training set for an AI/ML algorithm mentioned.

Summary of Study Type:

The submission focuses on design verification and validation testing to demonstrate that the new SIRIUS Endoscope System (PR-SI-1230) is safe, effective, and performs as well as its predicate. This includes ensuring compliance with a wide array of international standards (ISO, IEC, ANSI/AAMI) for medical device manufacturing, biocompatibility, electrical safety, sterility, and basic endoscope performance. The differences from the predicate (e.g., working length, joystick design, locking mechanism) were specifically verified through engineering and usability tests to ensure they did not negatively impact safety or effectiveness.

Ask a specific question about this device

The i-Cut system is indicated for morcellating and extracting tissue in laparoscopic, gynecologic surgical procedures.

The i-Cut is a single use laparoscopic power morcellator. It is provided sterile.

The i-Cut consists of a rotating cutting tube with a trocar that provides protection against the cutting blade when locked in the "CLOSED" position. The device comes with an obturator for placement into the patient's body and a locking clip that keeps the trocar in the "closed" position during insertion. The activation button must be pressed to cut tissue.

The lumen of the device is designed for use with a standard grasper or Tenaculum forceps with a diameter between 10 to 14 mm. The i-Cut is designed to be used with surgical instruments of diameters between 10 to 14 mm. The lumen is fitted with a silicone valve to prevent gas loss during use of the device.

The i-Cut is electrically operated by a DC Motor which is powered by a 24V AC/DC mains adapter. The non-sterile i-Cut Power Supply with power cord is supplied separately to power the device.

This 510(k) clearance letter pertains to the i-Cut, a single-use laparoscopic power morcellator. The provided text details regulatory information, device description, indications for use, and non-clinical performance testing. However, it does not include information about clinical studies with human participants, acceptance criteria tables, sample sizes for test sets (in the context of clinical performance), expert ground truth establishment, or multi-reader multi-case (MRMC) comparative effectiveness studies.

The document primarily focuses on non-clinical bench testing to demonstrate substantial equivalence to a predicate device (LiNA eXcise, K101458). Therefore, I cannot address most of the requested points related to clinical study acceptance criteria and performance as this information is not present in the provided text.

Here's an analysis of what can be extracted from the provided text, and where gaps exist:

Preamble:

The provided 510(k) clearance letter for the i-Cut device focuses on demonstrating substantial equivalence through non-clinical performance testing (bench testing) rather than clinical trials with human participants. Therefore, many of the requested details pertaining to clinical study design, human reader performance, and expert consensus for ground truth are not present in this document. The "acceptance criteria" and "device performance" discussed here apply to the bench testing conducted, not clinical outcomes in human subjects.

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

Based on the provided non-clinical performance testing section, we can infer some "acceptance criteria" as implied by the successful completion of each test. The "reported device performance" is generally stated as "passed" or "met requirements." No numerical data for specific criteria are provided beyond the stated specifications (e.g., cutting rate, speed).

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

• Sample Size: The document does not specify the sample sizes (e.g., number of devices, number of tests) for each of the non-clinical performance tests. It only states that the tests were performed and passed.
• Data Provenance: The data provenance is from non-clinical bench testing conducted by the manufacturer, A.M.I. Agency for Medical Innovations GmbH. The country of origin of the manufacturer is Austria. This data is inherently prospective as it involves new testing for the device's clearance.

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

Not applicable. This was a non-clinical bench testing study. "Ground truth" in this context pertains to engineering specifications and performance metrics rather than clinical diagnoses established by medical experts. Usability testing involved "surgeons of different experience with laparoscopic morcellators," but it was to assess device compatibility and integrity, not to establish a clinical ground truth for a diagnostic AI.

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

Not applicable. This was a non-clinical bench testing study. Adjudication methods are typically used in clinical studies where multiple human readers interpret data to establish a consensus ground truth.

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

Not applicable. No MRMC comparative effectiveness study was performed or described. The clearance is based on substantial equivalence demonstrated through non-clinical bench testing. The device is a physical surgical tool, not an AI.

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

Not applicable. This device is a physical surgical tool and does not employ a standalone algorithm for diagnostic or interpretative purposes.

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

For non-clinical bench testing, the "ground truth" is defined by engineering specifications, regulatory standards (e.g., ISO, ASTM, IEC), and predefined pass/fail criteria for device performance (e.g., measuring force, checking for wear, verifying electrical safety compliance). There is no "expert consensus" or "pathology" in the medical sense for these tests.

8. The sample size for the training set

Not applicable. This device is a mechanical/electrical surgical tool, not an AI/ML algorithm that requires a training set.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device

The KARL STORZ suction and irrigation system (consisting of handle and suction/irrigation tubes, cannulae or needles) is intended for use by qualified surgeons to provide suction and/or irrigation function to help flush or remove blood, fluids, and tissue debris from the operation site during general, gynecologic, urologic, and thoracic laparoscopic surgical procedures.

The devices in the KARL STORZ Suction and Irrigation System are manually operated, reusable surgical devices consisting of handle, suction/irrigation tubes, cannulae or needles. The handle is intended to be used in combination with suction/irrigation cannulae and tubing and controls the suction and irrigation. Enabled by the handle with stop cock valve, the regulation of the irrigated quantity of fluids via the tubes, or rather the quantity of aspirated fluid (e.g., blood, fluids, and tissue debris) into or out of the patient is performed. Cannula and needle: Enabled by the pointed distal end, both puncture and injection/extraction cannulae and needles, perform puncturing of target organs or tissues and injecting fluids into operating site i.e. extracting blood or fluids from them. The prerequisite for suction is either a vacuum powered suction wall apparatus or a pump, which serve as impulse for the suction. The proximal end of the tube set is connected to the vacuum or pump. Either a pump is required as impulse for irrigation or the natural force of gravity, i.e., by positioning the flush bag at the appropriate height.

The provided document is an FDA 510(k) Premarket Notification for medical devices, specifically KARL STORZ suction and irrigation systems. This type of submission focuses on demonstrating substantial equivalence to legally marketed predicate devices, primarily through non-clinical performance data and does not typically include studies involving artificial intelligence (AI) or machine learning (ML) components, nor does it present "acceptance criteria" and "device performance" in the context of an AI/ML model's diagnostic or predictive capabilities.

Therefore, the requested information regarding AI/ML-related acceptance criteria and study details (such as sample sizes for test and training sets, expert adjudication methods, MRMC studies, standalone performance, ground truth establishment, etc.) cannot be extracted from this document, as it is not relevant to the type of device and submission described.

The document focuses on:

• Device Description: Manually operated, reusable surgical devices (handle, suction/irrigation tubes, cannulae, needles).
• Intended Use: Suction and/or irrigation to flush or remove blood, fluids, and tissue debris during laparoscopic surgical procedures.
• Basis for Substantial Equivalence: Comparison to predicate KARL STORZ devices (K945059 and K951190) based on technological characteristics and non-clinical performance data.
• Non-Clinical Performance Data Provided:
  • Biocompatibility testing: Compliance with ISO 10993.
  • Reprocessing Validation: Compliance with standards like ANSI/AAMI/ISO 14937, 11138-3, 11607-1, 11737-1, 17664, 17665-1 regarding cleaning and sterilization.
  • Bench Top Performance Testing: Leak Test, Flow Incoming Test, Flow Outgoing Test.

The document explicitly states: "Clinical testing was not required to demonstrate the substantial equivalence to the predicate device. Non-clinical bench testing was sufficient to assess safety and effectiveness and to establish the substantial equivalence of the modifications."

In summary, this document does not contain information about an AI/ML device or its associated performance studies.

Ask a specific question about this device

Camera System: The Camera System is indicated for use in general laparoscopy, ear endoscopy, ear endoscopy, sinuscopy, and plastic surgery whenever a laparoscope/ endoscope/ arthroscope is indicated for use. A few examples of the more common endoscope surgeries are Laparoscopic cholecystectomy, Laparoscopic hernia repair, Laparoscopic appendectomy, Laparoscopic pelvic lymph node detection, Laparoscopically assisted hysterectomy, Laparoscopic and thorascopic anterior spinal fusion, Anterior cruciate ligament reconstruction, Knee arthroscopy, Decompression fixation, Wedge resection, Lung biopsy, Pleural biopsy, Dorsal sympathectomy, Pleurodesis, Internal mammary artery dissection for coronary artery bypass grafting where endoscopic visualization is indicated and Examination of the evacuated cardiac chamber during performance of valve replacement. The users of the Camera System are general surgeons, gynecologists, cardiac surgeons, plastic surgeons, orthopedic surgeons, ENT surgeons and urologists.

NIR FI Light Source: The NIR FI Light Source and NIR FI Light Guide are indicated for use to provide real-time endoscopic visible and nearinfrared fluorescence imaging. The NIR FI Light Source and NIR FI Light Guide enable surgeons to perform minimally invasive surgery using standard endoscope visual light as well as visual assessment of vessels, blood flow and related tissue perfusion, and at least one of the major extra-hepatic bile duct, common bile duct and common hepatic duct), using near-infrared imaging.

Fluorescence imaging of biliary ducts with the NIR FI Light Source and NIR FI Light Guide is intended for use with standard-of-care white light and, when indicated, intraoperative cholangiography. The devices are not intended for standalone use for biliary duct visualization.

The individual components of the subject device, SCHOELL Y's NIR FI System, form a system to provide real-time endoscopic visible imaging (wight light imaging, WLI) and near-infrared (NIR) illumination and imaging (fluorescence imaging, FI) using indocyanine green (ICG):

• Camera System suitable for processing and recordings visible light images as well as NIR images. The Camera System consists of a Camera Control Unit (CCU) and a Camera Head for connection to a fiberoptic scope;
• . Light Source and Light Guide for use with a fiberoptic scope for emitting light within the visible spectrum as well as in the NIR spectrum to cause fluorescence;
• . Fiberoptic Laparoscope suitable for visible light and NIR light illumination and imaging;

The imaging agent (ICG) is not provided by SCHOELLY as part of the subject system.

The submitted information does not contain a study that proves the device meets the acceptance criteria in the format requested. The document primarily focuses on establishing substantial equivalence to a predicate device for regulatory clearance. It describes general performance testing conducted, but not in the context of specific acceptance criteria and detailed study results as typically found in clinical trials or dedicated performance studies for AI/ML devices.

However, based on the provided text, I can extract information related to the device and the types of testing performed to support its regulatory clearance.

Here's an attempt to structure the available information, noting where specific details (like acceptance criteria, sample sizes, ground truth establishment, or expert involvement for performance scores) are not explicitly present in the provided document:

Device Name: Near-Infrared (NIR) Fluorescence Imaging (FI) System: Camera System (Camera Control Unit, Camera Head to be coupled to a fiberoptic scope), NIR FI Light Source

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for device performance (e.g., specific sensitivity, specificity, accuracy targets). Instead, it relies on demonstrating compliance with recognized standards and substantial equivalence to a predicate device.

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

The document does not specify a "test set" in the context of evaluating a dataset for AI performance. The performance data mentioned refers to engineering and quality system validation tests. No information is provided regarding the origin (country, retrospective/prospective) of specific data sets used for validating imaging performance beyond general statements about "non-clinical performance test data."

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

Not applicable based on the provided text. The document does not describe a study involving expert readers establishing ground truth for a test set to assess AI performance. The focus is on the device's technical specifications and safety/effectiveness in a comparative context to a predicate device.

4. Adjudication Method for the Test Set

Not applicable. As no human expert evaluation of a test set for AI performance is described, no adjudication method is mentioned.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

No MRMC study is mentioned. The document primarily focuses on demonstrating substantial equivalence to a predicate device through technical comparisons and compliance with standards, rather than a study comparing human readers with and without AI assistance.

6. If a Standalone (Algorithm Only) Performance Study Was Done

The device described is a medical imaging system (hardware and integrated functionality for visible and NIR fluorescence imaging), not a standalone AI algorithm. Therefore, a standalone algorithm performance study as typically understood for AI/ML software is not applicable here. The "Non-Clinical Performance Testing" refers to the system as a whole.

7. The Type of Ground Truth Used

For the "Non-Clinical Performance Testing," the "ground truth" implicitly refers to the expected performance characteristics based on an existing predicate device and the design input requirements for endoscopic white light and near-infrared fluorescence imaging. The document does not specify an external "ground truth" like pathology, expert consensus on images, or outcomes data.

8. The Sample Size for the Training Set

Not applicable. The document does not describe the development or training of an AI algorithm with a training set. The device is an imaging system, not a machine learning model.

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

Not applicable. As there is no mention of a training set or AI algorithm training, the establishment of ground truth for such a set is not discussed.

Summary of Non-Inclusion:

The provided document is a 510(k) summary for a medical device (an imaging system) seeking clearance based on substantial equivalence. It is not a report on a clinical or performance study evaluating an AI/ML algorithm against specific performance metrics with independent test sets and expert ground truth. Therefore, many of the requested details, particularly those related to AI/ML study design (sample sizes for test/training sets, expert qualifications, ground truth establishment, MRMC studies), are not present in the given text. The "Performance Data" section details compliance with recognized safety, software, and reprocessing standards, and general non-clinical performance demonstrations for substantial equivalence.

Ask a specific question about this device

It is intended for use for endoscopy and endoscopic surgery within the thoracic and abdominal cavities including female reproductive organs. Not suitable for use for observation and treatment of the heart and must not contact the heart or its vicinity.

The SIRIUS Endoscope System as a robotic endoscope consists of Video Processor, Laparoscope Handle, Laparoscope Head and Joystick. The SIRIUS Endoscope System is developed for minimal invasive surgery application. The SIRIUS Endoscope System is a fully integrated compact 3D laparoscopic camera system with a flexible tip that can change its viewing direction. The Laparoscope Head is made of biocompatible materials. The articulated tip has three degrees of freedom enabling C and S shaped bending. The insertion is 10 mm diameter and 340 mm working length. Stereo camera with 1080 high-definition resolution. It has 120 degrees field of view, 10-100mm depth of view and bright light with 300 lumen.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text.

1. Table of Acceptance Criteria and Reported Device Performance

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 primarily describes bench testing and compliance to international standards. It does not specify "test sets" in the context of patient data or clinical trials with specific sample sizes. The data provenance is not mentioned beyond the manufacturer being in Hong Kong. The testing appears to be primarily laboratory-based (bench testing) rather than clinical studies using 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)

This information is not provided in the document. The document focuses on technical and regulatory compliance testing rather than expert-derived ground truth from clinical cases.

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

This information is not provided as the studies described are not clinical studies requiring adjudication of diagnostic outcomes.

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

There is no mention of an MRMC comparative effectiveness study, AI assistance, or human reader improvement. The device described is an endoscope system, not an AI-powered diagnostic tool.

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

There is no mention of an algorithm-only standalone performance study. The device is hardware (an endoscope system) with associated software, but not an AI algorithm performing diagnostic tasks independently.

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

For the performance testing, the "ground truth" is adherence to international standards (e.g., ISO 8600 series) and published specifications. For biocompatibility, sterility, electrical safety, etc., the ground truth is defined by the requirements of the respective international standards (e.g., ISO 10993, ISO 11135, IEC 60601, IEC 62471).

8. The sample size for the training set

This information is not applicable or not provided. The device is an endoscope system, and the testing described is not related to machine learning model training.

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

This information is not applicable or not provided for the same reasons as above.

Ask a specific question about this device

The SaberScope5 Laparoscope is intended to be used in diagnostic procedures for endoscopy and endoscopic surgery within the thoracic and peritoneal cavities including the female reproductive organs.

The Articulating Xenoscope™ System is being renamed the SaberScope5 Laparoscope. The subject device contains two separate functioning components. First is the single-use, sterile SaberScope5 Laparoscope Device, which includes a 0° camera on 5 mm rigid shaft with a ± 90° articulating tip, 10 - 36 cm long shaft, and high-definition video image. For certain procedures the shorter 10 cm laparoscope is preferred. Likewise, for other procedures, the longer 36 cm laparoscope is preferred. Except for the length difference, the scientific principles, materials of construction and design are otherwise identical. The second is the XenoBox™, which converts the digital signal from the camera to HDMI signal for display onto the HD video screen for the surgeon to view.

Here's an analysis of the provided text regarding the acceptance criteria and supporting study for the Xenocor® SaberScope5 Laparoscope, addressing your specific points:

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

The document provides a comparative table (Table 2) between the predicate device (Articulating Xenoscope™ Laparoscope, K193315) and the subject device (SaberScope5 Laparoscope). The acceptance criteria implicitly are that the subject device's performance attributes are "Same" as the predicate device or demonstrate equivalent performance, with some notable differences.

Ask a specific question about this device

The Video Endoscopy System & 3D Video Endoscopy System are intended to be used to provide illumination and visualization of surgical field in a wide variety of diagnostic abdominal and thoracic minimally invasive procedures, including female reproductive organs (gynecology) and urological anatomy.

The proposed Video Endoscopy Systems include the Video Endoscopy System and 3D Video Endoscopy System, Video Endoscopy System supports 2D imaqe output, 3D Video Endoscopy System supports 2D/3D image output.

Video Endoscopy System is composed of Video Endoscope (LPS21000/LPS21030) and Video Endoscopy processor (EVS100).

The Video Endoscopy Processor is a video processor, which receives the electrical signals from the Video Endoscope and process it and output the final image to the monitor. Two models 2D Video Endoscope (LPS21000/LPS21030) are available, one image sensor is located at the distal of the endoscope (LPS21000/LPS21030), they are used in conjunction with Video Endoscopy Processor (EVS100) to output 2D images.

3D Video Endoscopy System is composed of Video Endoscope (LPS31000/LPS31030) and Video Endoscopy Processor (EVS200).

The Video Endoscopy Processor is a video processor, which receives the electrical signals from the Video Endoscope and process it and output the final image to the monitor. Two models 3D Video Endoscope (LPS31000/LPS31030) are available, two image sensors are located at the distal of the endoscope (LPS31000/LPS31030), they are used in conjunction with Video Endoscopy Processor (EVS200) to output 2D/3D images.

Video Endoscopy processor is non-sterile device. The Video Endoscope is terminallysterilized device. The Video Endoscope must be sterilized by users before being used in surgery.

This submission describes the Surgnova Healthcare Technologies (Zhejiang) Co., Ltd. Video Endoscopy System & 3D Video Endoscopy System (K210116).

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly list quantitative acceptance criteria for optical performance. Instead, it states that "The device met all acceptance criteria for optical performance testing and was shown to have equivalent image quality to the predicate." This implies a comparative standard rather than absolute numerical targets.

The reported device performance is qualitative for equivalence.

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 provide details on sample sizes for the "test set" in terms of images or data points for the individual optical performance tests. The testing described is non-clinical bench testing rather than a study involving clinical data from patients. Therefore, terms like "country of origin of the data," "retrospective or prospective," or "test set" in the context of patient data do not apply here. The testing was performed on the device prototypes or production units.

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

Not applicable. The performance evaluation was based on bench testing against established standards and comparison to a predicate device's specifications, not on human expert review of clinical images to establish ground truth such as disease presence/absence.

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

Not applicable. There was no adjudication method used, as the testing involved objective measurements and comparisons against technical specifications and standards, not subjective expert reviews requiring consensus.

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 done. This submission is for a video endoscopy system as a medical device for visualization, not an AI-powered diagnostic or assistive tool.

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

Yes, the primary evaluation was standalone performance simulation/bench testing of the device's optical and functional characteristics. The device itself (the video endoscopy system) is essentially the "algorithm only" in this context, as its performance is independently measured without human operators for the technical specifications listed.

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

The "ground truth" for the non-clinical testing was based on:

• Established engineering and performance standards: e.g., IEC 60601 series, ISO 10993 series, IEC 62471.
• Predicate device specifications: The comparison table explicitly states characteristics like resolution, field angle, and depth of field that are identical or comparable to the predicate.
• Objective measurements: The various optical performance tests (Resolution, Brightness, White Balance, Color Performance, etc.) would have involved objective measurement techniques with specific targets or ranges derived from industry standards or performance requirements for such devices.

8. The sample size for the training set

Not applicable. This device is a video endoscopy system, not an AI or machine learning algorithm that requires a training set of data.

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

Not applicable, as there is no training set for this type of medical device submission.

Ask a specific question about this device

This instrument is intended to be used with a video system center, light source, documentation equipment, monitor. hand instruments, electrosurgical unit, and other ancillary equipment for endoscopic surgery within the thoracic and abdominal cavities including female reproductive organs.

The LTF-S190-5 is a video endoscope consisting of three parts: the control section, the insertion section, and the connector section. The device uses an objective lens and light guide lens for capturing images/videos from the distal end of the endoscope.

Here's an analysis of the provided text regarding the acceptance criteria and supporting studies for the ENDOEYE FLEX DEFLECTABLE VIDEOSCOPE OLYMPUS LTF-S190-5:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size for Test Set and Data Provenance

The provided text describes various engineering and performance tests (reprocessing, biocompatibility, software V&V, electrical safety, EMC, and bench performance). These types of tests typically do not involve "test sets" in the clinical sense with human data. Instead, they involve testing the physical device, its materials, and its software against established technical and safety standards.

• No "sample size" for a clinical test set is mentioned.
• No "data provenance" (e.g., country of origin, retrospective/prospective) for clinical data is mentioned, as clinical data was not part of this submission's performance data section. The submission focuses on substantial equivalence based on technical characteristics and non-clinical performance data.

3. Number of Experts and Qualifications for Ground Truth Establishment

Not applicable. The performance data presented are based on engineering tests and adherence to recognized standards, not on expert-established ground truth from clinical cases.

4. Adjudication Method for Test Set

Not applicable. There is no clinical test set requiring adjudication in the provided performance data.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned. This evaluation focuses on the safety and effectiveness of the device itself, rather than comparing human reader performance with and without AI assistance. The device is a videoscope, not an AI diagnostic tool.

6. Standalone (Algorithm Only) Performance Study

Not applicable. This device is a physical videoscope, not an algorithm, so a standalone algorithm-only performance study is not relevant.

7. Type of Ground Truth Used

The "ground truth" for the various performance tests is defined by:

• Established national and international standards (e.g., FDA guidance documents, ISO 10993, ANSI/AAMI ES 60601-1, IEC 60601-1-2)
• Manufacturer's design specifications and requirements.

8. Sample Size for Training Set

Not applicable. This device is a physical videoscope, not a machine learning model, so there is no concept of a "training set."

9. How Ground Truth for Training Set Was Established

Not applicable, as there is no training set mentioned or implied for this device.

Ask a specific question about this device

The SurroundScope System is designed to be used with documentation equipment, monitor, hand instruments, electrosurgical unit, and other ancillary equipment for endoscopy and endoscopic surgery within the thoracic and abdominal cavities, including the female reproductive organs.

The SurroundScope System (SS) is an endoscopic platform for visualization during surgery. The SS System is a modification of the previously cleared WV1 Endoscope (K190190) developed by 270Surgical. The SS System is designed to be used with documentation equipment, monitor, hand instruments, electrosurgical unit, and other ancillary equipment. The SS System features two viewing capabilities: standard and extended. The standard view uses one lens and displays a 90 degree field of view while the extended view uses two additional lenses on the side of the tip and displays a 270 degree field of view. Each lens has its own set of LEDs for illumination.

The SS System is comprised of two main components:

• SS endoscope (Video endoscope)
• Camera Controller Unit (CCU) (Video Processor)

The SS endoscope is a reusable, rigid video endoscope. It is a reusable (autoclavable) endoscope and is intended to be used in a sterile environment. It is initially supplied non-sterile to the user and requires the user to process (i.e., clean and sterilize) the device for initial use, as well as to reprocess the device after each use. The SS endoscope main components are the video and illumination system, the endoscope body, and the endoscope main connector. The endoscope consists of a camera head at the distal tip, insertion tube, control handle, umbilical cable, and main connector. The insertion tube and distal tip are made of gold coated stainless steel. The distal tip contains sapphire for the optical components. The required illumination for the endoscope is supplied by integrated LEDs, located on the endoscope's distal tip. The endoscope video system is controlled by the video processor which collects the video signal produced by the image sensors (CMOS).

The SurroundScope Camera Control Unit (CCU) processes and manages the images/video signal from the endoscope and transfers them to the monitor. The CCU video center also powers and controls the CMOS located in the SS endoscope.

The SurroundScope System is a rigid video endoscope designed for endoscopy and endoscopic surgery within the thoracic and abdominal cavities, including female reproductive organs. It supports both standard (90-degree field of view) and extended (270-degree field of view) viewing capabilities. The system comprises an SS endoscope (reusable, rigid video endoscope) and a Camera Controller Unit (CCU).

Here's an analysis of the acceptance criteria and the studies performed to demonstrate the device meets these criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of acceptance criteria with corresponding performance results in a consolidated format. However, it states that "All tests met the predefined acceptance criteria" for various bench tests. The performance data section describes the tests performed and their successful outcomes. For the purpose of this response, I will synthesize the information regarding "acceptance criteria" from the fact that studies were conducted to industry standards and FDA guidance, and "reported device performance" from the statement that the devices met these criteria.

2. Sample Size for the Test Set and Data Provenance

The document describes various bench tests, but it does not specify the sample sizes used for these tests. For cleaning, drying, and sterilization, it mentions "multiple reprocessing cycles." For biocompatibility, it refers to standard ISO test methods, which have their own sample size requirements, but these are not enumerated here.

The data provenance is from bench testing and conducted by an independent lab (Wuxi AppTec) for specified tests (cleaning, drying, sterilization). There is no indication of human subject data, country of origin is not specified for the test set, and it is entirely retrospective as it's a pre-market submission for a device.

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

Since the studies described are primarily bench testing (physical, electrical, optical, and chemical properties, as well as software validation), the concept of "ground truth" derived from human experts in a clinical context (e.g., radiologists, pathologists) does not directly apply here.

The "ground truth" for these performance tests is established by the relevant industry standards (ISO, IEC, AAMI, USP) and FDA guidance documents, which define the expected performance metrics and acceptable thresholds. The "experts" involved would be the testing engineers and scientists at the independent labs or internally, who are qualified to conduct these specific technical tests according to the standards. No specific number or qualifications of these technical experts are provided in the document.

4. Adjudication Method for the Test Set

Not applicable. The tests described are objective, quantitative bench tests against established engineering and scientific standards, not subjective interpretations requiring adjudication by human experts.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No, an MRMC comparative effectiveness study was not done. The submission focuses on demonstrating substantial equivalence through bench testing, safety, and performance against a predicate device and established standards. This type of study would typically be performed for AI-driven diagnostic or interpretative devices to assess human performance with and without AI assistance, which is outside the scope of this endoscope system's pre-market submission description.

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

Yes, standalone performance (in the context of a medical device's technical capabilities without human interaction) was assessed for various parameters of the SurroundScope System. For example:

• Optical Performance: Field of view, depth of field, signal-noise ratio, non-uniformity, distortion were measured objectively.
• Color Accuracy: Tested against colorimetry standards.
• System Functionality and Latency: Assessed as objective system performance.
• Electrical Safety and Electromagnetic Compatibility: Tested to ensure compliance with standards regardless of human interaction during use.
• Software Validation: The software itself was validated.

These are all measures of the device's inherent technical performance without considering how a human user might interact with or interpret the output in a clinical scenario.

7. The Type of Ground Truth Used

The ground truth used for these studies is based on:

• Industry and International Standards: Such as ISO 8600 series for endoscopes, IEC 60601 series for electrical safety, ISO 10993 series for biocompatibility, AAMI TIRs for reprocessing, and various CIE ISO standards for colorimetry. These standards define the acceptable range and methodology for measuring performance.
• FDA Guidance Documents: For reprocessing and software validation, these documents outline the expected validation methods and content for pre-market submissions.
• Specifications: Predefined acceptance criteria for the device itself, derived from these standards and the manufacturer's own design specifications (e.g., 90°/270° field of view, 17-200mm depth of field).

8. The Sample Size for the Training Set

Not applicable. The SurroundScope System is a hardware endoscope with integrated software for image processing and control. It is not an AI/ML device that requires a "training set" of data in the sense of machine learning. The term "software validation" refers to verifying that the software performs its intended functions correctly and reliably, not to training an algorithm.

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

Not applicable, as there is no "training set" for this device. The software validation is based on requirements and specifications defined by the developer and adherence to FDA guidance.

Ask a specific question about this device

The VisionPort System is intended to be used in diagnostic and therapeutic for endoscopic surgery within the thoracic and peritoneal cavities including the female reproductive organs to establish a path of entry for endoscopic instruments and to provide an image of the surgical field. The trocar may be used with or without visualization for primary and secondary insertions.

The VisionPort System consists of an access port with an integrated camera and light source, the handpiece, a wired control pad to control the camera functions, and a control unit, specifically:

• 1. VisionPort System Handpiece single use
  • HD camera and lighting module a.
  • b. 12.9mm internal diameter access port with 5-12mm instrument seal
  • Lens cleaning system (saline wash and wiper blade) C.
  • d. Connections for saline wash source and insufflation tubing
  • e. Removable obturator designed for visible entry
• 2. VisionPort System Control Pad single use
  • a. Camera control functions (zoom, pan)
  • b. Light emitting diode (LED) adjustment
  • c. Image capture and display control buttons
• 3. VisionPort System Control Unit
  • a. System power
  • b. Image processing (no patient data recording or retention)
  • Outputs to operating room monitor(s) and/or third-party Data Control Unit (for image C. capture and printing options)

The provided text describes the VisionPort System, an endoscopic surgical device, and its substantial equivalence to predicate devices, but it does not contain information about acceptance criteria or a study proving that the device meets those criteria in the context of an AI/ML-assisted medical device.

The document is a 510(k) summary for a medical device (VisionPort System) to establish substantial equivalence with existing predicate devices. It focuses on the device's design, indications for use, and a comparison of its technological characteristics with predicate devices.

While it mentions "performance data" and "functional testing" to verify that the device met "all design specifications" and "acceptance criteria," these are general statements about the device's functionality rather than specific, quantitative acceptance criteria for an AI/ML component. The "functional testing" appears to be related to the physical and operational aspects of the endoscope and its components, referencing standards like ISO 8600.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving an AI/ML component meets those criteria, as the document does not discuss such an AI/ML feature as part of the VisionPort System.

Here's why the requested information cannot be extracted from the provided text:

• No AI/ML Component: The device description and comparisons do not indicate the presence of artificial intelligence or machine learning components within the VisionPort System. It's an endoscopic system with a camera, light source, control pad, and control unit.
• No Quantitative Acceptance Criteria for AI/ML: Since there's no mention of an AI/ML component, there are no specific quantitative acceptance criteria (like sensitivity, specificity, AUC) for such a component.
• No Study Design for AI/ML Performance: Consequently, there is no study described that would prove an AI/ML component meets acceptance criteria. The performance data section refers to sterilization, biocompatibility, electrical safety, EMC, and functional testing of the physical device.

In summary, the provided document does not align with the premise of the question, which assumes an AI/ML-assisted medical device.

Ask a specific question about this device