Search Results

The PROBEAT-FR is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.

The PROBEAT-FR is a proton beam irradiation system, which provides a therapeutic proton beam for clinical treatment. It is designed to deliver a proton beam with the prescribed dose, dose distribution and directed to the prescribed patient treatment site.

The PROBEAT-FR is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.
The performance data presented in the 510(k) summary focuses on demonstrating that the PROBEAT-FR functions as intended and meets its specifications for various aspects, thus establishing substantial equivalence to its predicate device, the PROBEAT-CR.

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 Data Provenance

The provided text does not specify a sample size for a test set in the context of patients or cases. The performance data described refers to engineering and system-level testing rather than clinical trials with patient data.

• Sample Size: Not applicable in the context of clinical patient data for this submission. The tests performed are on the device itself and its components.
• Data Provenance: Not applicable in the context of clinical patient data. The tests are system-level and engineering evaluations.

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

The provided text does not mention the use of expert radiologists or other medical professionals to establish ground truth for a test set in the context of a diagnostic or therapeutic performance evaluation involving medical images or patient outcomes. The testing described is focused on the technical performance and safety of the proton beam therapy system.

4. Adjudication Method for the Test Set

Since there is no mention of a test set involving human interpretation or decision-making on patient data, an adjudication method (like 2+1 or 3+1) is not applicable to the described performance tests.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not mentioned in the provided text. The submission focuses on demonstrating substantial equivalence based on the technical performance and safety of the device's features, not on improved human reader performance with AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The provided text does not describe a standalone algorithm-only performance study. The device is a proton beam therapy system, not an AI-driven diagnostic or image analysis algorithm that would typically undergo such a study. While it contains "Real Time Image Gating System software" and a "Positioning Image Analysis System (PIAS)," the performance testing described is at the total system level, not specifically isolating the performance of these software components as standalone algorithms.

7. Type of Ground Truth Used

The "ground truth" for the tests described is based on the engineering specifications and design requirements of the PROBEBEAT-FR system, as well as compliance with relevant international standards (e.g., IEC 60601-1, IEC 60601-1-2). For instance:

• For mechanical performance, "ground truth" would be the specified movement ranges, precision, and stability.
• For beam performance, "ground truth" would be the specified dose accuracy, beam shape, and energy.
• For safety interlocks, "ground truth" would be the successful triggering of safety mechanisms under defined conditions.

8. Sample Size for the Training Set

The provided text does not mention a training set size. This type of information would typically be relevant for machine learning or AI-driven devices that learn from data. The PROBEAT-FR is a hardware-intensive proton beam therapy system with integrated control software, not an AI model that undergoes a "training set" in the conventional sense.

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

Since there is no mention of a "training set" for an AI or machine learning model, the method for establishing its ground truth is not applicable.

Ask a specific question about this device

The Small Field Applicator is an accessory to the PROBEAT-V system that is intended to assist the radiation oncologist in the delivery of proton radiation to defined target volumes while sparing surrounding normal tissue and critical organs from excess radiation.

Small Field Applicator is an optional accessory to the proton beam therapy system which can be added to the nozzle configuration of the cleared PROBEAT-V system to make the lateral penumbra sharp, as needed. The Small Field Applicator may be used in place of the optional removable Applicator having an aperture (collimator) that has been cleared as part of the PROBEAT-V system.

The Small Field Applicator is composed of a cylinder part with touch sensors, a 4-legged table, and a plate part. The Small Field Applicator is inserted at the end of the nozzle to obtain a sharp lateral penumbra in the lateral dose distribution, and it can reduce the dose to the surrounding normal tissue than the case in which the Small Field Applicator is not used.

The provided FDA 510(k) summary for the "Small Field Applicator" does not contain the information requested regarding acceptance criteria, study details, and ground truth establishment typically found in AI/ML device submissions.

This document describes a physical accessory for a radiation therapy system, not a software-based AI/ML device that requires extensive performance studies against clinical ground truth. The "Performance Data" section briefly mentions mechanical testing, interface evaluation, dose distribution, end-to-end testing, and radiation safety, but these are engineering and physics validations for a physical medical device, not a performance study for an AI algorithm as typically requested in your prompt.

Therefore, I cannot extract the requested information points from this document. The prompt asks for details pertinent to an AI/ML device "study that proves the device meets the acceptance criteria," which is not applicable to this physical accessory.

If you have a different document describing an AI/ML device, please provide that, and I will be happy to attempt to answer your questions.

Ask a specific question about this device

The PROBEAT-CR is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.

The PROBEAT-CR is a proton beam irradiation system. which provides a therapeutic proton beam for clinical treatment. It is designed to deliver a proton beam with the prescribed dose. dose distribution and directed to the prescribed patient treatment site. The PROBEAT-CR has two main subsystems: (1) equipment necessary to generate the proton beam and direct it to the beam delivery system for patient treatment, and (2) a beam delivery system whose primary responsibility is to ensure that the desired prescription parameters are properly delivered. The PROBEAT-CR comprises the following components and subsystems: Beam production system (Accelerator system (LINAC. Synchrotron), Beam transport system (Low/High Energy Beam Transport systems)), Beam delivery system in 4 separate treatment rooms. Each of 3 rooms will have a rotating gantry and 1 room will have a fixed beam. (Gantry Room (Scanning Nozzle, Rotating Gantry, Patient Positioning System, Orthogonal X-ray system, Cone Beam CT), Fixed Beam Room (Patient Positioning System, Orthogonal X-ray system, Treatment Control and Safety System)). The subject PROBEAT-CR is a modification to the cleared PROBEAT-CR to include the incorporation of the previously cleared Real Time Image Gating System for Proton Beam Therapy Systems ("RGS" or "RGPT") (K171049) for tracking implanted fiducials to qate the delivery of the proton beam, and the addition of an optional patient couch top extension as an accessory to allow for different patient positioning configurations.

The provided document is a 510(k) summary for a medical device (PROBEAT-CR Proton Beam Therapy System) seeking substantial equivalence to a predicate device. It does not contain the detailed information required to answer the specific questions about acceptance criteria, clinical study design, and ground truth establishment for an AI/ML powered device.

Based on the provided text, the device is a proton beam irradiation system, and the submission is for a modification to an already cleared device. The modifications include:

1. Incorporation of a previously cleared Real Time Image Gating System (RGS or RGPT) for tracking implanted fiducials.
2. Addition of an optional patient couch top extension.

The document explicitly states: "The following testing was performed to validate the modifications to the device: Design verification and validation testing for the addition of the optional top couch extension. Software verification and validation for the updated RGS (RGPT) software."

This implies that the testing was primarily focused on engineering validation of the new components and software, rather than a clinical effectiveness study of an AI/ML algorithm's diagnostic or prognostic performance. The document doesn't mention any AI/ML components performing tasks like image analysis or disease detection/classification, which would necessitate the detailed study information requested.

Therefore, I cannot provide the requested information about acceptance criteria, study design, sample sizes, expert qualifications, or ground truth for an AI/ML device because:

• The document does not describe an AI/ML powered device with new functionality that would require such studies. The Real Time Image Gating System (RGS) is mentioned as previously cleared (K171049) and the current submission is for an "updated RGS (RGPT) software." It's likely this update pertains to changes in its existing functionality, not the introduction of new AI-driven diagnostic capabilities.
• The document does not specify acceptance criteria in the context of clinical performance metrics (e.g., sensitivity, specificity, AUC) for an AI/ML algorithm. The "performance data" section is very brief and refers to design and software verification and validation, which are typical for any medical device modification, not necessarily for an AI/ML component's effectiveness.
• No clinical study to evaluate AI/ML performance compared to human readers or standalone AI performance is described.

In summary, the provided text does not contain the detailed information necessary to answer the questions about acceptance criteria, study design, and ground truth for an AI/ML powered device. The submission focuses on device modifications and internal verification/validation, not on the clinical performance evaluation of a new AI-driven diagnostic or prognostic capability.

Ask a specific question about this device

The PROBEAT-CR is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.

The PROBEAT-CR is a proton beam irradiation system, which provides a therapeutic proton beam for clinical treatment. It is designed to deliver a proton beam with the prescribed dose, dose distribution and directed to the prescribed patient treatment site. The PROBEAT-CR is a modification to the cleared PROBEAT-V system, for installation at a different clinical site.

The PROBEAT-CR has two main subsystems: (1) equipment necessary to generate the proton beam and direct it to the beam delivery system for patient treatment, and (2) a beam delivery system whose primary responsibility is to ensure that the desired prescription parameters are properly delivered. The PROBEAT-CR comprises the following components and subsystems:

• Beam production system
  • Accelerator system (LINAC, Synchrotron).
  • Beam transport system (Low/High Energy Beam Transport systems).
• Beam delivery system in 4 separate treatment rooms. Each of 3 rooms will have a rotating gantry and 1 room will have a fixed beam.
  • Gantry Room
    • Scanning Nozzle
    • Rotating Gantry
    • Patient Positioning System
    • Orthogonal X-ray system
    • Cone Beam CT
  • Fixed Beam Room
    • Patient Positioning System .
    • Orthogonal X-ray system .
• Treatment Control and Safety System

The provided text is a 510(k) summary for the PROBEAT-CR Proton Beam Therapy System. It describes the device, its intended use, and a comparison to predicate devices, but it does not contain information regarding software performance, acceptance criteria for an AI/algorithm, or a study that specifically proves the device meets such criteria.

The document primarily focuses on demonstrating the substantial equivalence of the PROBEAT-CR to its predicate devices (PROBEAT-V systems K151132 and K152592) in terms of hardware components, technological characteristics, and overall function as a proton beam therapy system.

The "Performance Data" section discusses:

• Mechanical performance of the rotating gantry and patient couch.
• Beam performance testing (dose shape and dose).
• Safety interface testing (beam stop control, dose monitor, area safety, mechanical interlocks).
• Electrical safety and electromagnetic compatibility (IEC 60601-1 and IEC 60601-1-2).

It states: "In all instances, the PROBEAT-CR functioned as intended and met its specifications. Testing demonstrated substantial equivalence to the predicates." However, it does not specify what those "specifications" or "acceptance criteria" were, nor does it detail the study design, sample sizes, or ground truth for any algorithmic performance evaluation.

Therefore, I cannot provide the requested information about acceptance criteria and a study proving an AI/algorithm meets those criteria based solely on the provided text. The document describes a physical medical device (proton beam therapy system), not an AI or algorithm with associated performance metrics.

Ask a specific question about this device

The PROBEAT-V is a medical device designed to produce and deliver a proton beam for the treatment of patients with localized tumors and other conditions susceptible to treatment by radiation.

The PROBEAT-V is a proton beam irradiation system, which provides a therapeutic proton beam for clinical treatment. It is designed to deliver a proton beam with the prescribed dose, dose distribution and directed to the prescribed patient site. The equipment to perform the above work is composed of two main components: (1) a beam delivery system properly delivered and (2) equipment necessary to generate the proton beam and direct it to the beam delivery system for patient treatment.

The beam delivery system is composed of the following components

• Gantry Room o
• . Rotating Gantry
• Scanning Nozzle .
• . Patient Positioning System
• Cone Beam CT / X-ray Imaging System .
• Fixed Beam Room o
• . Scanning Nozzle
• Patient Positioning System 트
• . Cone Beam CT / X-ray Imaging System

The beam production system is composed of the following components

• Accelerator system (LINAC, Synchrotron) o
• O Beam transport system (Low/High Energy Beam Transport systems)

The system incorporates several optional features and accessories, namely:

• The Mini Ridge Filter ("mRF") is an optional accessory to modify the beam of the o PROBEAT-V system. The mRF is installed manually and may be used in conjunction with the range shifters inside the nozzle or extended range shifter. The mRF can be added to the cleared PROBEAT-V nozzle to spread out the Bragg peak along the axis of the beam in order to reduce the amount of beam energy in the delivery of proton radiation to defined target volumes.
• Beam gating function allowing for interface with cleared external gating systems to o control the beam delivery for treatment such as to synchronize irradiation with respiration. Although the overall treatment time tends to be longer than the treatment time without gating, the extension of the treatment time will not affect irradiation performance to the target treatment site. Instead, the gating functionality may limit radiation exposure to regions outside of the target treatment volume.
• Allows for use of fluoroscopy during proton irradiation at the physician's discretion. o Fluoroscopy may be used for observation of treatment site during treatment, which could be used for interruption of the treatment or analysis for treatment planning.

The provided text describes a 510(k) premarket notification for a medical device called PROBEAT-V, a proton beam therapy system. It outlines additional optional features and the performance data for these features.

However, the document does not contain the following information typically found in a comprehensive acceptance criteria and study report:

• A table of acceptance criteria and reported device performance: While it states "All tests were successful and confirmed the performance of these additional optional features," it does not specify quantitative acceptance criteria or the numerical performance metrics.
• Sample size used for the test set and data provenance.
• Number of experts used to establish the ground truth for the test set and their qualifications.
• Adjudication method for the test set.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done, or the effect size of human readers improve with AI vs without AI assistance. (This is not an AI device, so an MRMC study related to AI assistance would not be applicable here).
• If a standalone performance study (algorithm only without human-in-the-loop performance) was done. (Again, not an AI device).
• The type of ground truth used.
• The sample size for the training set. (Not an AI/machine learning device that typically requires a training set in that context).
• How the ground truth for the training set was established. (Not an AI/machine learning device).

Summary of available information regarding acceptance criteria and study:

The device's additional optional features are the Mini Ridge Filter (mRF), an external beam gating function, and the ability to use fluoroscopy during proton irradiation.

1. Acceptance Criteria and Reported Device Performance:

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

• Not specified. The document mentions "testing" but does not detail the number of tests performed or the data used.

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

• Not applicable / not specified. For a physical device like a proton therapy system, "ground truth" relates to physical measurements and engineering specifications, not expert interpretation of outputs in the same way it would for diagnostic imaging devices.

4. Adjudication method for the test set:

• Not applicable / not specified.

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 is not an AI-assisted device, so an MRMC study for AI assistance is not relevant.

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

• Yes (for the device's functions). The "Performance Data" section describes testing conducted on the device's features (mRF, gating, fluoroscopy) to confirm their intended function. This is a standalone performance evaluation of the device itself rather than an AI algorithm.

7. The type of ground truth used:

• Physical measurements and engineering specifications. For a proton therapy system, "ground truth" would be established through calibrated instruments measuring beam properties (range, dose falloff, spot size) and system responses to ensure they meet pre-defined engineering tolerances and physical laws.

8. The sample size for the training set:

• Not applicable. This device is not an AI/machine learning system that requires a "training set" in the conventional sense. Its functionality is based on established physics and engineering.

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

• Not applicable. As above, no training set in the context of machine learning.

Ask a specific question about this device

The Real Time Image Gating System for Proton Beam Therapy Systems is intended for use with compatible Hitachi proton beam therapy systems and is designed to generate gating signals to deliver a proton beam when the position of a fiducial marker, which is implanted near a tumor and tracked by use of X-ray fluoroscopy, is within a given tolerance from its planned position.

The Real-time Image Gating System for proton beam therapy (RGS) is a gating signal generator accessory to proton beam therapy systems (PBTS) and used to track an implanted fiducial and to control the proton beam. The RGS is installed on the PBTS workstation and receives information from the PBTS imaging systems, processes the images, and sends timing signals to the PBTS irradiation controller. This RGS system recognizes the position of a fiducial marker in the human body at a regular frame rate using the X-ray imaging systems. The marker is implanted near the tumor using image guided implantation. Using two diagnostic X-ray sources and two X-ray FPDs configured around the treatment isocenter, the imaging data are combined to obtain precise 3D trajectories in the RGS. The RGS tracks the implanted marker on the image, and this chosen marker's position viewed in 3 dimensions. Using X-ray fluoroscopy devices in two distinct planes, the location of marker on the fluoroscopic image is automatically extracted using the pattern recognition technology of the RGS and the spatial position of the marker is calculated and monitored throughout the treatment. Synchronized irradiation of the tumor with gating control occurs only when the marker is within a given tolerance from its planned coordinates relative to the beam isocenter. This synchronized irradiation is performed at high speed which enables accurate irradiation of a tumor whose position may move inside the body, e.g., due to respiration.

The provided text describes a 510(k) premarket notification for a Medical Device, the "Real Time Image Gating System for Proton Beam Therapy Systems." While the document outlines performance tests conducted, it does not provide detailed acceptance criteria or the specific results of these tests in a quantitative manner that would allow for a complete table of acceptance criteria and reported performance.

The document primarily focuses on establishing substantial equivalence to predicate devices based on intended use, technological characteristics, and general safety/effectiveness. It lists the types of performance tests performed but lacks the specific metrics (e.g., "accuracy > 95%") and the outcome of those metrics.

Therefore, for aspects requested in the prompt that are not explicitly present in the provided text (e.g., exact acceptance criteria values, specific performance metrics, sample sizes for test/training sets, detailed ground truth establishment for training, number of experts, adjudication methods, MRMC study details), the answer will state that the information is not provided in the source document.

Here is a summary of the information available and what is missing based on your request:

Overview of Device Performance and Equivalence Study

The Real Time Image Gating System for Proton Beam Therapy Systems is designed to generate gating signals to deliver a proton beam when the position of an implanted fiducial marker (tracked by X-ray fluoroscopy) is within a given tolerance from its planned position. The system uses pattern recognition technology to automatically extract the marker's location and calculates its spatial position in 3D throughout treatment.

The performance data presented in the 510(k) summary aims to establish substantial equivalence to predicate devices (MedCom GmbH's Verisuite and Elekta Ltd.'s XVI R5.0). The study was conducted by Hitachi, Ltd. Healthcare.

1. Table of Acceptance Criteria and Reported Device Performance

As stated above, the document does not explicitly list quantitative acceptance criteria or specific reported device performance values for the tests conducted. It only lists the types of tests performed.

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

• Sample Size for Test Set: The document does not specify the sample size used for any of the performance tests (e.g., number of images, number of instances of fiducial tracking, or number of patients/phantoms).
• Data Provenance (e.g., country of origin, retrospective/prospective): The document does not explicitly state the country of origin for the data used in the performance tests. The submitter is Hitachi Ltd. Healthcare in Japan. It also does not specify if the data was retrospective or prospective.

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

The document does not specify if human experts were involved in establishing ground truth for the performance tests, nor does it mention the number or qualifications of any such experts. The system uses "pattern recognition technology" to automatically extract marker positions.

4. Adjudication Method for the Test Set

As there is no mention of human expert involvement in ground truth establishment for the test set, an adjudication method (e.g., 2+1, 3+1) is not applicable or not described in the provided text.

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

An MRMC study was not conducted or described in this 510(k) submission. The performance tests appear to be focused on the device's technical specifications and functionality, not a comparison of human reader performance with and without AI assistance. Therefore, an effect size of human reader improvement with AI assistance cannot be determined from this document.

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

The performance tests described (Recognition accuracy of a static fiducial marker, System latency, Tracking of moving marker, etc.) appear to be standalone assessments of the device's technical capabilities, without human intervention as part of the primary performance evaluation. The device is described as an "accessory" that processes images and sends timing signals automatically.

7. The Type of Ground Truth Used

The document implies that the ground truth for "recognition accuracy of a static fiducial marker" and "tracking of moving marker" would be based on the known, controlled, or planned positions of the fiducial markers (e.g., in a phantom or controlled experimental setup). It does not mention expert consensus, pathology, or outcomes data as sources for ground truth in these specific performance tests. The system itself "recognizes the position" and "tracks the implanted marker," suggesting a comparison against a known physical position.

8. The Sample Size for the Training Set

The document does not provide any information regarding a training set or its sample size. This type of detail is typically not required for a 510(k) submission focused on substantial equivalence where the device's core technology (pattern recognition) is presumed to be developed prior to the specific product's submission.

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

Since no information about a training set is provided, how its ground truth was established is also not described in the document.

Ask a specific question about this device

The SANGRAY is an x-ray irradiation system intended for use in the irradiation of blood products packaged in transfusion bags to inactivate lymphocytes for the prevention of graft versus host disease (GVHD).

The X-ray irradiation system SANGRAY consists of a power supply (high-voltage generation unit), controller panel (console), and a shielded protection unit which contains two vertically opposed X-ray tube assemblies that generate X-ray beams. Blood products are placed into a tray and irradiated with the X-rays in a sample chamber. The system has a built-in dosimeter which measures the exposure dose in real time and ensures that the X-ray irradiation is stopped automatically when the preset dose is reached. If the power supply fails during the X-ray irradiation, the dosimeter keeps the integral dose value in memory, which allows the operator to continue the X-ray irradiation after power is recovered.

The provided text describes a 510(k) submission for the SANGRAY X-ray irradiation system. The document focuses on demonstrating substantial equivalence to predicate devices for regulatory clearance, rather than presenting a clinical study to prove the device meets specific performance criteria through a traditional clinical trial or AI algorithm validation study. Therefore, most of the requested information regarding acceptance criteria and studies proving the device meets them, especially in the context of AI, cannot be extracted from this document.

Here's what can be gathered, addressing your points where possible:

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

The document does not explicitly state acceptance criteria in the format of a clinical study or AI performance metrics. Instead, it presents a comparison of technological characteristics between the SANGRAY and two predicate devices (Rad Source X-ray Blood Irradiator, Model RS-3400 and Raycell X-ray Blood Irradiator). These characteristics serve as points of comparison to demonstrate substantial equivalence, rather than strict performance acceptance thresholds for a new, independent claim.

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 explicitly states: "6.8 Clinical Performance Test Summary: None." This indicates that no clinical performance study was conducted or presented in this submission. The "test set" in this context refers to non-clinical performance and safety tests, not a clinical data set for evaluating an AI algorithm or human reader performance. The provenance of such non-clinical test data is not detailed beyond compliance with specified safety standards.

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)

Not applicable. As no clinical performance study was conducted, there were no experts used to establish ground truth for a clinical test set.

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

Not applicable. No clinical performance study was conducted.

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. The SANGRAY is an X-ray irradiation system, not an AI-powered diagnostic or assistive tool for human readers. No MRMC study was conducted.

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

Not applicable. SANGRAY is a medical device for irradiating blood, not an AI algorithm.

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

For the non-clinical performance tests mentioned (Section 6.7), the "ground truth" would be established by physical measurements and engineering standards, comparing the device's output (e.g., dose, dose rate, leakage) against pre-defined specifications and regulatory limits. For example, radiation leakage is compared against a specified maximum (e.g., less than 1 µSv/h). There's no clinical ground truth in the sense of disease diagnosis or outcomes.

8. The sample size for the training set

Not applicable. SANGRAY is not an AI algorithm that requires a training set.

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

Not applicable. SANGRAY is not an AI algorithm.

Ask a specific question about this device

ARIETTA Precision is intended for use by trained personnel (doctor, sonographer, etc.) for the diagnostic ultrasound evaluation of Fetal, Abdominal (Includes imaging for guidance of percutaneous biopsy of abdominal organs and structures (including amniocentesis.), Intra-operative (Includes imaging of organs and structures exposed during surgery (excluding neurosurgery and laparoscopic procedures.), Intra-operative (Neuro.), Laparoscopic, Pediatric, Small Organ (Includes thyroid, parathyroid, breast, scrotum, penis and imaging for guidance of biopsy .), Neonatal Cephalic, Adult Cephalic, Trans-rectal (Includes imaging for guidance of trans-rectal biopsy.), Trans-vaginal (Includes imaging for guidance of trans-vaginal biopsy.), Trans-esophageal (non-Cardiac - Adult/Pediatric), Musculo-skel. (Convent), Musculo-skel. (Superfic.), Other (spec.) -Wound (Includes imaging for Cavernous/Non-Cavernous wounds.), Other (spec) - Gynecological, Cardiac Adult, Cardiac Pediatric, Trans-esophageal (Cardiac - Adult/Pediatric) and Peripheral vessel clinical applications.

The Modes of Operation are B mode, M mode, PW mode (Pulsed Wave Doppler), CW mode (Continuous Wave Doppler), Color Doppler, Power Doppler (Color Flow Angiography) and TDI (Tissue Doppler Imaging), Trapezoid mode, Free Angular M mode.

The ARIETTA Precision is a compact ultrasound device that can be used by the patient bedside. Similar to the predicate: Arietta 70 cleared via K134016; the ARIETTA Precision is considered a "point of care" system that provides flexibility for patient scanning in any environment.

This instrument can be used for individual or combined display in the image display modes listed below.

• B mode is a display mode in which the tomographic image is formed with plural ultrasound beams by the methods mentioned above.
• M mode is a display mode of ultrasound beams received sequentially and repeatedly on the same direction. It indicates these reflected echoes in one direction from the interior of the patient's body's on time-series scale.
• There are two types of D (Doppler) mode and CW Doppler mode. PW Doppler mode. PW Doppler mode displays bloodstream information consecutively at a sample point that is detected by pulsed Doppler sonography. CW Doppler mode displays bloodstream information continuously in the single-direction ultrasound beam that is detected by the CW Doppler method.
• Color Doppler mode receives ultrasound from the same direction and detects any changes that occur over time to identify three types of bloodstream information: its direction, its speed, and its inconsistency. The mode then colors that information and displays it as an overlay on B mode or M mode. Color Flow Mode, Power Doppler Mode, High-Resolution Power Doppler (eFlow) Mode can be used with this instrument according to need.

The 5 methods of electronic scanning available on the ARIETTA Precision include:

• Linear Scanning Method: By this method, the ultrasound beam from the ultrasound probe is emitted in a straight line (linearly) and draws a tomographic image of the test subject.
• Convex Scanning Method: By this method, the ultrasound beam from the ultrasound probe is emitted radially and draws a tomographic image of the test subject.
• Sector Scanning Method: By this method, the ultrasound beam from the ultrasound probe is emitted in a fan shape (sector) and draws a tomographic image of the test subject.
• Radial Scanning Method: By this method, the ultrasound probe emits a 360 degree (radial) ultrasound beam and draws a tomographic image of the test subject ..
• Trapezoidal Scanning Method: By this method, the ultrasound beam from the ultrasound probe is emitted radially without regard to the form of the probe head and draws a tomographic image of the test subject.

ext

Ask a specific question about this device

ARIETTA Prologue is intended for use by trained personnel (doctor, sonographer, etc.) for the diagnostic ultrasound evaluation of following clinical applications: FETAL; ABDOMINAL - (Includes imaging for guidance of percutaneous biopsy of abdominal organs and structures (including amniocentesis)); INTRA-OPERATIVE (SPEC.)-(Includes imaging of organs and structures exposed during surgery (excluding neurosurgery and laparoscopic procedures)); INTRA-OPERATIVE (NEURO); LAPAROSCOPIC; PEDIATRIC; SMALL ORGAN (SPEC.)-(Includes thyroid, parathyroid, breast, scrotum, penis and imaging for guidance of biopsy): NEONATAL CEPHALIC: ADULT CEPHALIC; TRANS-RECTAL - (Includes imaging for guidance of trans-rectal biopsy); TRANS-VAGIAL -(Includes imaging for guidance of trans-vaginal biopsy); TRANS-ESOPHAGEAL (NON-CARDIAC & CARDIAC) -ADULT/PEDIATRIC; MUSCULOSKELETAL (CONVENT./SUPERFIC.); Other (spec.) -WOUND (Includes imaging for Cavernous/Non-Cavernous wounds); Other (spec) - GYNECOLOGICAL; CARDIAC: ADULT/ PEDIATRIC and PERIPHERAL VESSEL.

An ultrasound diagnostic system with the following features:

• Ultrasound transducer(s) to generate the transmitted ultrasound energy and detect the reflected echoes
• Ultrasound transducer accessories (standard and optional) to maximize functional usage of transducer(s) in various modes of operation
• A computer system to control the transducer and analyze the signals resulting from the reflected echoes
• A video monitor with optional image recorder to display the computed image or derived Doppler data

The provided text is a 510(k) Premarket Notification for the ARIETTA Prologue Diagnostic Ultrasound System and Transducers. It focuses on demonstrating substantial equivalence to a predicate device (Noblus K142368, and K134016 for some indications) and does not contain detailed information about specific performance acceptance criteria or a dedicated study proving performance against such criteria in the way a clinical trial for an AI/CADe device would.

Instead, the document asserts substantial equivalence based on similarities in intended use, clinical applications, modes of operation, technology, and adherence to safety standards. The "study that proves the device meets the acceptance criteria" in this context refers to the non-clinical testing performed to ensure the device is safe and effective as per FDA regulations for ultrasound devices, rather than a clinical performance study with specific quantifiable metrics.

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

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

The document does not specify quantitative performance acceptance criteria (e.g., sensitivity, specificity, accuracy) for an AI/CADe component, as it is a diagnostic ultrasound system, not an AI/CADe device with specific diagnostic algorithms being validated. The acceptance criteria described are broadly related to safety and effectiveness compared to a predicate device.

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 describe a test set or data provenance in the context of a performance study for an AI/CADe device. The evaluations conducted were non-clinical tests (acoustic output, biocompatibility, EMC, electrical/mechanical safety) which typically involve testing the physical device and its components according to engineering standards, rather than analyzing clinical 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)

Not applicable, as this is not a study for an AI/CADe device requiring expert-established ground truth from clinical data. The "ground truth" for the non-clinical tests would be the established engineering standards and specifications.

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

Not applicable. No clinical data test set or adjudication method 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

Not applicable. The document describes a diagnostic ultrasound system, not an AI-assisted diagnostic tool subject to MRMC studies comparing human readers with and without AI assistance.

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

Not applicable. This is a diagnostic ultrasound system, not a standalone algorithm.

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

For the non-clinical testing, the "ground truth" would be engineering specifications, applicable safety standards (e.g., IEC 60601-1, IEC 62304, ISO 10993-1), and FDA guidance documents. There is no mention of clinical ground truth (like pathology or outcomes data) being used for performance evaluation in this 510(k) submission.

8. The sample size for the training set

Not applicable. This is not an AI/CADe device, and no training set for an algorithm is mentioned.

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

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

Ask a specific question about this device

ALOKA LISENDO 880 is intended for use by trained personnel (doctor, sonographer, etc.) for the diagnostic ultrasound evaluation of Fetal, Abdominal, Pediatric, Small Organ (Spec.), Intra-operative (Spec.), Neonatal Cephalic, Musculo-skel. (Convent./Superfic.), Peripheral vessel, Cardiac Adult, Cardiac Pediatric, Trans-esophageal (card), Adult Cephalic clinical applications.

The Modes of Operation are B mode, PW mode (Pulsed Wave Doppler), CW mode (Continuous Wave Doppler), Color Doppler, Power Doppler (Color Flow Angiography), TDI (Tissue Doppler Imaging), 3D Imaging, 4D Imaging.

An ultrasound diagnostic system with the following features:

• Ultrasound transducer(s) to generate the transmitted ultrasound energy and detect the reflected echoes
• Ultrasound transducer accessories (standard and optional) to maximize functional usage of transducer(s) in various modes of operation
• A computer system - to control the transducer and analyze the signals resulting from the reflected echoes
• A video monitor with optional image recorder to display the computed image or derived Doppler data

The provided text is a 510(k) Pre-Market Notification for the ALOKA LISENDO 880 ultrasound system. It outlines the device's indications for use and compares it to a predicate device (ARIETTA 70, K134016) to establish substantial equivalence.

Here's an analysis of the acceptance criteria and supporting studies as presented in the document:

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

The document does not provide a table with specific, quantitative acceptance criteria (e.g., minimum sensitivity or specificity values, specific performance metrics) and corresponding reported performance metrics for the ALOKA LISENDO 880. Instead, it relies on a qualitative comparison to a predicate device.

The "Comparison to predicate device" section (Page 20) implicitly defines the acceptance criterion as being "substantially equivalent" to the ARIETTA 70 (K134016) in terms of:

• Indication for Use: The ALOKA LISENDO 880's indications for use are listed and shown to broadly align with those of the ARIETTA 70.
• Modes of Operation: Both devices are stated to have the same core modes of operation (B mode, M mode, PW mode, CW mode, Color Doppler, Power Doppler, TDI, 3D Imaging, 4D Imaging, and combinations).
• Probe Types: Both support Convex, Linear, Sector, and other probe types.
• Applicable Software Features: A long list of software features (e.g., DICOM, Freehand 3D, Real-time Doppler Auto Trace, Spatial Compound) are listed as being present in both the subject and predicate devices with "YES" for both, implying functional equivalence.

The "Conclusions" section (Page 21) summarizes these points, stating that the ALOKA LISENDO 880 is substantially equivalent in safety and effectiveness based on:

• Same indications for diagnostic ultrasound imaging and fluid flow analysis.
• Same gray scale and Doppler capabilities.
• Same essential technology for imaging, Doppler functions, and signal processing.
• Acoustic level below Track 3 FDA limits.
• Manufactured in accordance with FDA 21 CFR 820 Quality System Regulations.
• Designed and manufactured to the same electrical and physical safety standards.
• Materials tested in accordance with ISO 10993-1.
• Reusable probes with instructions for cleaning, disinfection, and sterilization.

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 explicitly states under "2. Clinical testing:" that "None required." This indicates that no separate clinical test set was used to establish performance for the ALOKA LISENDO 880 for the purpose of this 510(k) submission. The FDA allows clearance of devices through the 510(k) pathway if they are shown to be substantially equivalent to a legally marketed predicate device, often without new clinical studies if the technological characteristics are similar.

Therefore, there is no information on sample size, data provenance, or whether data was retrospective or prospective, as no new clinical testing was conducted.

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)

Since no clinical testing was performed for the subject device as part of this 510(k) submission, there is no mention of experts being used to establish a ground truth for a test set specifically for the ALOKA LISENDO 880. The substantial equivalence argument relies on the predicate device's established safety and effectiveness.

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

As no clinical testing was conducted for the subject device to evaluate its performance against a ground truth, there is no information on adjudication methods for a test set.

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

The document does not mention any multi-reader multi-case (MRMC) comparative effectiveness study, nor does it refer to AI assistance. The ALOKA LISENDO 880 is described as a diagnostic ultrasound system, and the submission focuses on its equivalence to a predicate ultrasound system rather than advanced AI-driven interpretation or assisted diagnostics.

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

This submission is for a diagnostic ultrasound system, not an algorithm. Therefore, "standalone" algorithm performance is not applicable or discussed. The device is intended for use by "trained personnel (doctor, sonographer, etc.)", indicating human-in-the-loop operation.

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

No new ground truth data was generated or used for the ALOKA LISENDO 880's clearance as "no clinical testing" was required. The "ground truth" for the predicate device would have been established during its own clearance process, but that information is not detailed here.

8. The sample size for the training set

The document does not discuss any training sets, as it's not describing an AI/machine learning device. The clearance is based on the device's technical specifications and substantial equivalence to a predicate, not on a machine learning model's performance.

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

As there is no mention of a training set or machine learning components, this information is not provided.

Ask a specific question about this device