Search Results

The Compass Steerable Needle is a steerable transbronchial biopsy needle intended to be used through a compatible working channel bronchoscope or Medtronic Extended Working Channel (EWC) for the collection of tissue from the intrapulmonary regions.

The Compass Steerable Needle (CSN) is sterile, single use, 22-gauge transbronchial needle with a unidirectional, steerable distal tip for the acquisition of tissue from the intrapulmonary regions. The Compass Steerable Needle include two model numbers, Model CSN1001 and Model CSN1002. Model CSN1001 includes two accessory adapters for attachment to bronchoscopes.

The subject of this 510(k) is the addition of two new adapters to Model CSN1002. Adapter SRA-1-01 connects the Model CSN1002 to the Ion™ Endoluminal System, and Adapter SRA-2-01 connects the Model CSN1002 to the Monarch™ Platform or Galaxy System™.

N/A

Ask a specific question about this device

These single-use biopsy forceps are specifically designed to collect tissue endoscopically for histologic examination. These forceps should not be used for any purpose other than their intended function.

The Radial Jaw™ 4 Pulmonary Biopsy Forceps (RJ4 Pulmonary) is a sterile, single-use device. The RJ4 Pulmonary Biopsy Forceps are available in two jaw sizes: RJ4 Pulmonary Large Capacity is compatible with a 2.8 mm or larger working channel endoscope and the RJ4 Pulmonary Standard Capacity is compatible with a 2.0 mm or larger working channel endoscope. The RJ4 Pulmonary Large Capacity is only available without a needle. The RJ4 Pulmonary Standard Capacity is available with or without a needle. Both the RJ4 Pulmonary Large Capacity and Standard Capacity devices have a 100cm working length, and are offered in Box 5 and Box 20 packaging configurations.

To operate the device, the user slides the spool back and forth over the handle body to open and close the jaws. The spool simultaneously actuates the dual pull wires, each of which run the length of the device and terminate with a connection to the jaw. The dual pull wire design allows the jaws to pivot, thus enabling tissue acquisition with a tangential approach if desired. Using RJ4 Pulmonary Biopsy Forceps the user can obtain a tissue sample by opening the jaws, pressing the jaws against the biopsy site, closing the jaws, and pulling the jaws away from the biopsy site.

N/A

Ask a specific question about this device

The sterile single-use flexible video bronchoscopes are designed to be used with the Himaging endoscopic video processor, monitor, endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree.

The Himaging bronchoscope system is applicable to hospital environment or medical office environment.

The Himaging bronchoscopes are sterile single-use devices designed for use in adults.

The subject device, Himaging Bronchoscope System, is consisting of a single-use flexible video Bronchoscope and an endoscopic video processor. The subject device has been designed to be used for endoscopy within the airways and tracheobronchial tree.

N/A

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis and is not for pediatric use.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion Endoluminal System, Model IF1000, is a software-controlled, electro-mechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint Software, a System Cart with System Software, a Controller, Instruments, and Accessories.

The IF1000 Instruments include the Ion Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint Software.

The System Cart contains the Instrument Arm, electronics for the follower portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the leader in the leader-follower relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The Ion Endoluminal System integrates an optional Tomosynthesis feature, optimizes the existing Cone Beam CT workflow, improves the Navigation View, troubleshoots the airway tree, and enhances the control algorithm to provide an additional safety margin.

N/A

Ask a specific question about this device

The Ion™ Endoluminal System (Model IF1000) assists the user in navigating a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. The Ion™ Endoluminal System enables fiducial marker placement. It does not make a diagnosis. The system is indicated for use with adult and pediatric populations. Pediatric use is limited to patients who are 5 ft (152.5 cm) or taller and weigh 102 lbs (46 kg) or greater.

The PlanPoint™ Software uses patient CT scans to create a 3D plan of the lung and navigation pathways for use with the Ion™ Endoluminal System.

The Ion™ Endoluminal System, Model IF1000, is a software-controlled, electromechanical system designed to assist qualified physicians to navigate a catheter and endoscopic tools in the pulmonary tract using endoscopic visualization of the tracheobronchial tree for diagnostic and therapeutic procedures. It consists of a Planning Laptop with PlanPoint™ Software, a System Cart with System Software, a Controller, Instruments, and Accessories. The IF1000 Instruments include the Ion™ Fully Articulating Catheter, the Ion™ Peripheral Vision Probe, and the Flexision™ Biopsy Needles.

The Planning Laptop is a separate computer from the System Cart and Controller. A 3D airway model is generated from the patient's chest CT scan using the PlanPoint™ Software.

The System Cart contains the Instrument Arm, electronics for the follower portion of the servomechanism, and two monitors. The System Cart allows the user to navigate the Catheter Instrument with the Controller, which represents the leader in the leader-follower relationship. For optimal viewing, the physician can position the monitors in both vertical and horizontal axes.

The Controller is the user input device on the Ion™ Endoluminal System. It provides the controls to command insertion, retraction, and articulation of the Catheter. The Controller also has buttons to operate the Catheter control states.

The IF1000 System and PlanPoint Software are modified to enable Remote Software Updates from the Intuitive server via secure network communication.

N/A

Ask a specific question about this device

The Flexible Bronchoscopes have been designed to be used with the video processor, endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree.

The Flexible Bronchoscope is for use in a hospital environment. The Flexible Bronchoscope is a single-use device designed for use in adults.

The Flexible Bronchoscope (Model: BS27U-12EU, BS27U-12US, BS38U-20EU, BS38U-20US) is intended to be used with the Portable Video Processor (cleared via K243497). The Flexible Bronchoscope is inserted through the airways and tracheobronchial tree during bronchoscopy, and when used with the compatible video processor and monitor, the endoscope system can be operated as intended and indicated. The Flexible Bronchoscope is a single-use endoscope, which consists of a Handle, an Insertion Section, and an Endoscope Connector. The handle includes a deflection lever, a lever lock, a push button for picture taking/video recording, a push button for suction, a connector for suction tubing, a Luer port for insertion of accessory devices and irrigation to the working channel and a LED for illumination. The insertion section contains one working channel, wiring to transmit the image signals to the video processor, and two optical fibers to transmit illumination from the handle to the distal tip. The distal bending section of the insertion section is controlled by the user via the deflection lever on the handle. The distal end of the insertion section contains a CMOS sensor for capturing image and transmitting it to the video processor, optical fibers for transmitting illumination from the LED inside the handle, and the distal opening of the working channel. The Endoscope Connector connects the endoscope handle to the video processor, which provides power and processes video signals from the endoscope. Same as the predicate, the subject device is also provided in 2 deflection versions (US/EU deflection).

This document is an FDA 510(k) clearance letter for a Flexible Bronchoscope, indicating substantial equivalence to a predicate device. However, it does not contain the level of detail requested regarding acceptance criteria and a specific study proving the device meets those criteria, particularly in the context of an AI/algorithm-driven device.

The provided text focuses on the physical and performance characteristics of the bronchoscope itself, its intended use, technological comparison to a predicate device, and various non-clinical tests (electrical safety, photobiological safety, mechanical/optical performance, biocompatibility, sterilization, shelf life, and package validation).

There is no mention of an AI component, an algorithm, or any study involving human readers, ground truth establishment, or performance metrics like sensitivity, specificity, or AUC. The "device performance" in this context refers to the bronchoscope's mechanical and optical functionality, not the diagnostic accuracy of an AI algorithm.

Therefore, most of the requested information cannot be extracted from this document.

Here's an attempt to answer based on the provided text, highlighting what is missing:

1. Table of acceptance criteria and reported device performance

The document does not present a formal table of "acceptance criteria" for a diagnostic algorithm with corresponding "reported device performance" in terms of clinical accuracy metrics (like sensitivity, specificity, AUC). Instead, it states that various non-clinical tests were performed to demonstrate compliance with recognized standards and that the device is "as safe, as effective, and performs as well as the legally marketed device identified above."

Below is a table summarizing the types of tests and the general conclusion, but without specific quantitative acceptance criteria or performance metrics related to diagnostic accuracy.

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

• Sample Size for Test Set: Not applicable/Not mentioned. This document describes a medical device (bronchoscope) itself, not an AI algorithm performing a diagnostic task on a dataset. The "tests" mentioned are non-clinical engineering and biological safety tests, not tests on a dataset.
• Data Provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable/Not mentioned.

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

• Not applicable. There is no mention of "ground truth" in the context of an AI algorithm's diagnostic performance for which experts would be needed. The "ground truth" for the non-clinical tests would be the established performance specifications and standards for a bronchoscope.

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

• Not applicable. As no expert ground truth establishment for a diagnostic AI is mentioned, no adjudication method would be relevant.

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. This document describes the clearance of a flexible bronchoscope, a physical medical device. It does not mention any AI component or a MRMC study.

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

• Not applicable. There is no mention of an algorithm in this document that would perform as a standalone device.

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

• Not applicable. Ground truth in the context of diagnostic AI is not mentioned. For the non-clinical tests, the "ground truth" is compliance with established engineering and safety standards.

8. The sample size for the training set

• Not applicable. There is no mention of an AI model or a training set.

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

• Not applicable. There is no mention of an AI model or a training set.

Ask a specific question about this device

UE BRONCHO Single-Use Bronchoscope: The UE BRONCHO Single-Use Bronchoscopes has been designed to be used with the UE Display, endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree. The UE BRONCHO Single-Use Bronchoscopes is for use in a hospital environment. The UE BRONCHO Single-Use Bronchoscopes is single-use device designed for use in adults.

UE Display: The UE Display is reusable digital monitor, intended to display live imaging data from UE Medical visualization devices.

The bronchoscope system consists of UE BRONCHO Single-Use Bronchoscopes and UE Display. The UE BRONCHO Single-Use Bronchoscopes (the bronchoscopes) are sterile, single-use flexible video bronchoscopes available in three sizes (Slim, Regular, Large). The bronchoscopes have been designed to be used with the UE Display (reusable, non-sterile), endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree. The bronchoscope system is designed for use by adults in a hospital environment.

The provided FDA 510(k) clearance letter details the clearance of the UE BRONCHO Single-Use Bronchoscopes and UE Display. However, it does not contain specific acceptance criteria or details of a clinical study that demonstrates the device's performance against such criteria. The document explicitly states "Clinical study: Not applicable."

The clearance is based on non-clinical data, specifically performance testing and compliance with voluntary standards, which demonstrates substantial equivalence to a predicate device (Ambu® aScope™ 4 Broncho, Ambu® aView™ Monitor - K173727).

Therefore, I cannot populate the requested table and answer questions 2-9 with the provided text. The document refers to "bench performance testing" which includes optical performance, color reproduction, geometric distortion, resolution, depth of field, image intensity uniformity, noise, dynamic range, and frame rate, comparing these aspects with the predicate device. However, it does not specify quantitative acceptance criteria for these tests nor provide the reported device performance against such criteria in the detail requested.

Here's an attempt to populate the table and address the questions based only on the information available in the provided text. Where information is missing, it will be stated as "Not provided in the text."

1. Table of Acceptance Criteria and Reported Device Performance

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

Not provided in the text. The document refers to "bench performance testing" which typically uses a limited number of physical units or simulated conditions, rather than a "test set" of patient data as might be relevant for AI/ML devices. No human patient data was used for testing.

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

Not applicable, as no clinical study or expert-based ground truth establishment for a test set is mentioned. The testing was non-clinical bench testing.

4. Adjudication method for the test set

Not applicable, as no clinical study involving expert interpretation or adjudication is mentioned.

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

No. The document explicitly states "Clinical study: Not applicable." Therefore, an MRMC study was not performed. This device is a bronchoscope system, not an AI-assisted diagnostic tool.

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

Not applicable. This device is a bronchoscope system. While it has software and display capabilities, it is not an algorithm that performs a diagnostic or analytical function independently of a human operator, and no standalone performance study in this context was mentioned.

7. The type of ground truth used

For the non-clinical bench tests (e.g., optical performance, physical dimensions, electrical safety), the "ground truth" would be established by direct physical measurements, adherence to engineering specifications, and compliance with recognized international standards (e.g., ISO 8600, IEC 60601 series, ISO 10993 series). There is no "ground truth" in the clinical sense (e.g., pathology, outcomes data, expert consensus) as no clinical studies were performed.

8. The sample size for the training set

Not applicable. This device is a bronchoscope system and not an AI/ML device that requires a training set of data for model development.

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

Not applicable, as no training set was used.

Ask a specific question about this device

The Single Use Aspiration Needle NA-201SX-4021 is intended to be used for ultrasound guided fine needle aspiration (FNA) of submucosal and extramural lesions of the tracheobronchial tree in combination with an ultrasound endoscope.

The Single Use Aspiration Needle NA-201SX-4022 is intended to be used for ultrasound guided fine needle aspiration (FNA) of submucosal and extramural lesions of the tracheobronchial tree in combination with an ultrasound endoscope.

The Olympus Single Use Aspiration Needle NA-201SX-4021 and NA-201SX-4022 are designed for use with ultrasound endoscopes for ultrasound-guided fine needle aspiration (FNA) of submucosal and extramural lesions of the tracheobronchial tree. These devices are single-use, disposable, sterile (Ethylene Oxide) needles available in two models with different specifications:

• NA-201SX-4021:

• Working Length: 700mm
• Maximum Insertion Portion Diameter: 1.9mm
• Needle Width: 21G
• Normal Needle Length: 20mm
• Maximum Needle Length: 40mm

• NA-201SX-4022:

• Working Length: 700mm
• Maximum Insertion Portion Diameter: 1.8mm
• Needle Width: 22G
• Normal Needle Length: 20mm
• Maximum Needle Length: 40mm

Both models feature an adjustable sheath length and are intended for single use.

This document is a 510(k) clearance letter for a physical medical device (Single Use Aspiration Needle), not an AI/Software-as-a-Medical-Device (SaMD). Therefore, the requested information pertaining to AI/SaMD performance evaluation criteria (such as test set size, data provenance, expert ground truth, MRMC studies, standalone performance, training set details, etc.) is not applicable and is not present in the provided document.

The document discusses the substantial equivalence of the new aspiration needles to a predicate device based on their physical and functional characteristics. The performance data section refers to bench testing of physical attributes, not computational performance or diagnostic accuracy.

Therefore, I cannot provide the requested information as it relates to AI/SaMD. I can, however, extract the acceptance criteria and reported device performance for the physical device based on the provided text.

Acceptance Criteria and Reported Device Performance (Physical Device)

This section summarizes the performance data for the Single Use Aspiration Needle (NA-201SX-4021 and NA-201SX-4022), based on the provided FDA 510(k) summary. These criteria relate to the physical and functional performance of the device, not an AI algorithm.

1. Table of Acceptance Criteria and Reported Device Performance

Regarding the AI/SaMD specific questions:

As stated previously, the provided document is for a physical medical device (Single Use Aspiration Needle), not an AI/SaMD device. Therefore, the following information is not applicable and not provided in the source text:

2. Sample size used for the test set and the data provenance: Not applicable. Performance testing was physical bench testing, not data-driven AI evaluation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for a physical device's performance is typically established by engineering specifications and direct measurement, not expert review of AI outputs.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable.
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. This applies to AI-assisted diagnostic or interpretive systems.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This applies to AI algorithms.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable. The "ground truth" for a physical needle refers to its engineered specifications and expected mechanical/biological performance, verified through bench testing.
8. The sample size for the training set: Not applicable. This applies to machine learning models.
9. How the ground truth for the training set was established: Not applicable. This applies to machine learning models.

Ask a specific question about this device

The Vathin®H-SteriScopeTM single-use flexible video bronchoscope has been designed to be used with the Vathin display unit, endotherapy accessories and other ancillary equipment for endoscopy within the airways and tracheobronchial tree in patients.

The Vathin® Video Bronchoscope System is for use in a hospital environment.

The Vathin®H-SteriScopeTM single-use flexible video bronchoscope is a single-use device designed for use in adults, with the BCV1-02 and BCV1-C2 also designed for pediatric use (BCV1-02: 6 months to 6 years; BCV1-C2: 6 years and older).

The Vathin® Video Bronchoscope System consists of Vathin®H-SteriScopeTM Single use flexible Video Bronchoscope (model: BCV1-02, BCV1-C2) to be introduced within the airways or tracheobronchial tree and Vathin®VisionCenterTM Digital Video Monitor (model: DVM-B1, DVM-B2) for clinical image processing.

The Vathin®H-SteriScopeTM Single-use flexible bronchoscope is inserted through the airways and tracheobronchial tree during Bronchoscopy. The Vathin®VisionCentereTM Digital Video Monitor provides power and processes the images for medical electronic endoscope.

Vathin®H-SteriScopeTM Single-use flexible Video Bronchoscope is a sterile single-use flexible bronchoscope. Vathin®H-SteriScopeTM Digital Video Monitor is a reusable monitor.

I regret to inform you that the provided FDA 510(k) clearance letter and accompanying 510(k) Summary for the Vathin® Video Bronchoscope System do not contain the specific information required to answer your detailed questions about acceptance criteria and the study proving device performance as it relates to AI/software functionality.

This document focuses on justifying Substantial Equivalence for a bronchoscope system based on its physical characteristics, safety standards (electrical, biocompatibility, sterilization), and basic performance (optical, mechanical). It mentions "Software verification and validation" in Section 7.4, citing the "FDA guidance: Content of Premarket Submissions for Device Software Functions," but does not provide any specific acceptance criteria, study data, or details about the software's functionality, especially regarding AI capabilities.

Therefore, I cannot populate the table or answer the specific questions about AI performance, test set details, ground truth establishment, or human reader studies.

Here's why the document is insufficient for your request:

• No AI/Algorithm Claims: The document describes a video bronchoscope and its display unit. It doesn't mention any AI or advanced algorithmic functions (e.g., automated lesion detection, image enhancement using AI, diagnostic support) that would necessitate performance criteria like sensitivity, specificity, or reader studies.
• Focus on Hardware/System Performance: The performance data section (7.1-7.6) primarily addresses the physical and electrical safety, biocompatibility, sterilization, and basic optical/mechanical functions of a medical device (bronchoscope). The "Software verification and validation" entry is generic and doesn't detail any specific software performance study.
• Substantial Equivalence Justification: The entire 510(k) submission aims to prove that the Vathin® Video Bronchoscope System is "substantially equivalent" to existing cleared bronchoscopes. This process typically focuses on demonstrating comparable safety and effectiveness, not necessarily advanced algorithmic performance.

To answer your questions, one would need a 510(k) that specifically addresses an AI/ML-enabled medical device. Such a submission would include detailed performance studies with metrics like sensitivity, specificity, AUC, and often include multi-reader, multi-case (MRMC) studies to demonstrate clinical impact.

If you had provided a 510(k) document for an AI-powered device, the table and answers would look something like this (conceptual example):

Conceptual Example - This section is not based on the provided document as it does not contain the necessary information.

For an AI-powered medical device, the acceptance criteria and study proving its performance would be detailed as follows:

1. Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Test Set Size: 500 unique patient studies (e.g., Chest CT scans).
• Data Provenance:
  • Country of Origin: Multi-centric from USA (40%), Europe (30%), Asia (30%).
  • Retrospective/Prospective: Primarily retrospective, collected from hospital PACS archives. Data selection ensured diversity in pathology, image quality, and scanner types.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: 3 independent expert readers.
• Qualifications: All were board-certified radiologists with subspecialty training in thoracic imaging and a minimum of 10 years of experience in interpreting chest CT scans for pulmonary nodules.

4. Adjudication Method for Test Set

• Method: 2+1 Adjudication.
  • Initial reads by two independent expert radiologists.
  • If their interpretations differed, a third, senior-most expert radiologist reviewed the case and made the final decision.
  • Discrepancies were resolved through consensus or majority vote. All disagreements requiring a third read were documented.

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

• Was it done? Yes.
• Effect Size (Human Readers Improvement with AI vs. Without AI):
  • The MRMC study demonstrated a statistically significant improvement in diagnostic accuracy (measured by ROC AUC) for radiologists using the AI device compared to those reading without AI assistance.
  • Mean ROC AUC: 0.85 (without AI) vs. 0.895 (with AI).
  • Effect Size: Mean improvement in AUC was 0.045 (absolute difference), which corresponds to a relative improvement of approximately 5.3% in diagnostic accuracy. The 95% confidence interval for this improvement did not include zero, confirming statistical significance (p < 0.001).
  • Additional Finding: Average reading time per case decreased by 15% when using AI.

6. Standalone Performance Study

• Was it done? Yes.
• Details: The algorithm's performance was evaluated independently against the established ground truth for nodule detection and characterization. Standalone metrics included sensitivity, specificity, and FROC analysis, as detailed in the acceptance criteria table above.

7. Type of Ground Truth Used for Test Set

• Type: Expert Consensus, supported by available pathology reports (where biopsy was performed) and longitudinal follow-up data (e.g., 2-year stability on subsequent CT scans for benign lesions, or growth for malignant lesions). Pathology or follow-up was prioritized when available.

8. Sample Size for Training Set

• Training Set Size: 50,000 unique patient studies (e.g., Chest CT scans).

9. How Ground Truth for Training Set was Established

• Method: A combination of automated data labeling (using existing radiology reports, structured data, and keywords) followed by expert review and annotation.
  • An initial pass of automated labeling identified potential regions of interest.
  • These regions were then reviewed and carefully annotated by a team of trained radiology residents and fellows under the supervision of experienced radiologists.
  • For ambiguous cases, a consensus reading of at least two radiologists was required.
  • Pathology reports and longitudinal follow-up data (when available) were also incorporated to refine annotations and confirm ground truth.

Ask a specific question about this device

The ULTRASONIC PROBE UM-S20-17S has been designed to be used with an endoscopic ultrasound center, a probe driving unit, and an endoscope for intraluminal ultrasonic imaging of the upper airways and tracheobronchial tree.

The ULTRASONIC PROBE UM-S20-20R has been designed to be used with an endoscopic ultrasound center, a probe driving unit, and an endoscope for intraluminal ultrasonic imaging of the upper airways and tracheobronchial tree.

The Ultrasonic Probes have been designed to be used with an Olympus Endoscopic Ultrasound Center, a Probe Driving Unit, other ancillary equipment and an endoscope for intraluminal ultrasonic imaging of the of the upper airways and tracheobronchial tree and surrounding organs.

Ultrasonic Probes UM-S20-17S and UM-S20-20R are designed to be used in conjunction with bronchoscopes. The Probes are inserted into the patient through a channel of the endoscope.

The Ultrasonic Probes consist of an insertion tube and a connector section. The connector section is connected to the Probe Driving Unit and the Probe Driving Unit is connected to the Ultrasound Center.

The Ultrasonic Probe sends and receives electrical signals to and from the Ultrasound Center through the Probe Driving Unit. The Probes use a 20MHz frequency piezoelectric transducer and produce B-mode scan. They produce 360-degree mechanical/radial sonograms.

The transducer is built into the insertion tube at the tip of the Probe. The transducer is rotated by the Probe Driving Unit within the insertion tube.

The transducer converts the electrical signal to the ultrasound wave, sends it to the object, receives the reflected wave from the object and converts it to the electrical signal. The electrical signal is input to the Endoscopic Ultrasound Center and the ultrasound image is generated by the Endoscopic Ultrasound Center.

UM-S20-17S and UM-S20-20R use direct contact method only.

The Subject devices submitted for clearance each include one (1) major component: the Ultrasonic Probe, which is packaged with a Probe Holder (MH-245) and a Water-resistant Cap (MH-244).

The provided FDA 510(k) clearance letter for the Olympus Ultrasonic Probes (UM-S20-17S and UM-S20-20R) details the acceptance criteria and the study that proves the device meets those criteria. However, it's crucial to note that this document pertains to ultrasonic probes (hardware) and does not involve Artificial Intelligence (AI). Therefore, many of the typical elements related to AI/ML device testing (e.g., training set, ground truth experts, MRMC studies, standalone algorithm performance) are not applicable or described in this type of submission.

The "studies" described here are non-clinical performance tests (bench testing), demonstrating the safety and effectiveness of the physical medical device by comparing its characteristics and performance to a legally marketed predicate device.

Acceptance Criteria and Device Performance for Olympus Ultrasonic Probes

The acceptance criteria for these ultrasonic probes are predominantly based on meeting the performance specifications of the predicate and reference devices, and complying with established medical device standards for safety and functionality. The "reported device performance" indicates that the subject devices met all the acceptance criteria through various non-clinical tests.

1. Table of Acceptance Criteria and Reported Device Performance

Study Details (Applicable to Non-AI Hardware Verification)

As this is a hardware device 510(k) submission, the study methodology focuses on non-clinical performance data and bench testing rather than clinical trials with human subjects or AI-specific assessment methods.

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

• Sample Size: The document does not specify a "sample size" in terms of cases or patients, as the testing was non-clinical (bench testing). The "test set" in this context refers to the manufactured probes themselves and the conditions under which they were tested (e.g., phantom models for acoustic output, simulated use for durability, material samples for biocompatibility).
• Data Provenance: The tests were conducted internally by Olympus Medical Systems Corporation and its manufacturing site, SHIRAKAWA OLYMPUS CO., LTD. in Japan. The data is from bench testing and in-house validation, not from real-world patient data (retrospective or prospective). The manufacturing site is in Japan.

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

• This concept is not applicable to this type of hardware 510(k) submission. "Ground truth" for these tests is established by adhering to widely accepted international standards (ISO, IEC, AAMI) and FDA guidance documents for medical device performance, safety, and manufacturing. These standards define the measurable physical and electrical properties that the device must meet. The experts involved would be engineers, quality control specialists, and regulatory affairs personnel responsible for designing, manufacturing, and testing the probes to these standards.

4. Adjudication Method for the Test Set:

• This concept is not applicable. Adjudication typically refers to resolving discrepancies in expert interpretations of medical images or data, which is relevant for AI image analysis or clinical trials. For hardware testing, "adjudication" is replaced by adherence to established test protocols, measurement equipment calibration, and standard-defined pass/fail criteria.

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

• No, an MRMC comparative effectiveness study was not performed. MRMC studies are used to assess the impact of AI on human reader performance, which is not relevant for this non-AI hardware device. The equivalence claim for this device is based on technical specifications and non-clinical performance data compared to a predicate device.

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

• No, a standalone algorithm performance test was not done. This device is a physical diagnostic ultrasonic transducer, not a software algorithm. Its "performance" refers to its ability to generate images when connected to an ultrasound center, which is then interpreted by a human operator.

7. The Type of Ground Truth Used:

• The "ground truth" for this hardware device is defined by engineering specifications, physical measurements, and compliance with national and international medical device standards. For example, acoustic output parameters are measured against specific limits defined in IEC standards, and biocompatibility is confirmed by testing against ISO 10993. There is no "expert consensus" on imaging findings, pathology, or outcomes data used as ground truth for this device's clearance.

8. The Sample Size for the Training Set:

• This concept is not applicable. There is no "training set" as this is not an AI/ML device that requires machine learning.

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

• This concept is not applicable as there is no training set.

In summary, the FDA 510(k) clearance for the Olympus Ultrasonic Probes is based on a comprehensive set of non-clinical, bench-level performance tests demonstrating technical equivalence to a predicate device and compliance with relevant safety and performance standards for diagnostic ultrasonic transducers. It does not involve AI/ML components or associated clinical study designs like MRMC or standalone algorithm performance assessment.

Ask a specific question about this device