Search Results

Ethos Treatment Management is indicated for use in managing and monitoring radiation therapy treatment plans and sessions.

Ethos Treatment Planning is indicated for use in generating and modifying radiation therapy treatment plans.

Ethos Treatment Management is a software product designed to help radiation therapy medical professionals manage treatments for patients with malignant or benign diseases for whom radiation therapy is indicated. It allows the physician to create and communicate radiation treatment intent (RT intent) to the treatment planner, review and approve candidate plans, and monitor treatment progress. It is intended to be used with a treatment planning system to treat or alleviate disease in humans by streamlining the treatment management and monitoring processes.

Ethos Treatment Planning is a standalone software device designed to generate and modify radiation therapy treatment plans and manage treatment sessions. The device supports the traditional and adapted treatments, in which the scheduled plan is adapted to the patient's anatomy at the time of treatment.

Here's a breakdown of the acceptance criteria and the study details for the AI segmentation models within the Ethos Treatment Management 3.0 and Ethos Treatment Planning 2.0 devices, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance (AI Model Validation for Contouring)

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

• Test Set Sample Size: 1045 scans from various body sites.
  • Full body: (part of 179 total patients)
  • Head and Neck: (part of 1173 total patients)
  • Thorax: (part of 600 total patients)
  • Abdomen: (part of 527 total patients)
  • Bowel: (part of 507 total patients)
  • Pelvis: (part of 1192 total patients)
• Data Provenance: The largest number and percentage proportionally of scans originated from patients in the United States. Other country origins are not specified but implied to be varied due to "various healthcare facilities worldwide" mentioned for expert evaluation. The data appears to be retrospective, collected from patients with existing treatment indications for various cancers.

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

• Number of Experts: Not explicitly stated, but referred to as "Experts" (plural).
• Qualifications of Experts: Radiation oncologists, dosimetrists, and physicists from various healthcare facilities worldwide, with "significant clinical experience in segmentation of CT imaging for the different disease sites covered by the AI models."

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated as a formal adjudication method (like 2+1 or 3+1). The text mentions that "Experts... evaluated the quality of the contours across test sets to assess the need and the type of contour adjustments." This suggests a consensus-based or individual expert assessment of the AI-generated contours against their clinical judgment, but not a specific multi-reader adjudication protocol for the initial ground truth creation for the test set. For the model validation of contour quality, experts assessed the AI output.

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

• A formal MRMC comparative effectiveness study comparing human readers with AI vs. without AI assistance was not explicitly described in the provided text. The validation process involved experts evaluating the AI-generated contours to assess "the time saved on contouring tasks," which hints at an indirect measure of assistive benefit, but not a direct MRMC study.

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

• Yes, a standalone performance assessment was done. The "Contouring performance undergoes rigorous evaluation through verification and validation processes." This included quantitative metrics like the DICE similarity coefficient. The validation also focused on the AI models producing contours that required "minor or no adjustments in at least 80% of the test cases," which is a metric of the AI's standalone output quality observed by experts.

7. The Type of Ground Truth Used

• Ground Truth Type: Expert consensus based on "human anatomy experts" following "RTOG and DAHANCA clinical guidelines." Pathology or outcomes data were not mentioned as ground truth for segmentation.

8. The Sample Size for the Training Set

• Training Set Sample Size: 4769 scans from various body sites.
  • Full body: (part of 179 total patients)
  • Head and Neck: (part of 1173 total patients)
  • Thorax: (part of 600 total patients)
  • Abdomen: (part of 527 total patients)
  • Bowel: (part of 507 total patients)
  • Pelvis: (part of 1192 total patients)

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

• Ground Truth Establishment for Training Set: "Ground truth annotations were established by human anatomy experts as part of the algorithm development following RTOG and DAHANCA clinical guidelines. A single set of contours was produced for each training image. These clinical experts have significant clinical experience in segmentation of CT imaging for the different disease sites covered by the AI models. To ensure accuracy, contour definitions available in contouring guidelines are established prior to contouring tasks."

Ask a specific question about this device

The Universal Endometrial Applicator Set is indicated for use for treating cancer of the vagina, cervix, endometrium and uterus using HDR or PDR brachytherapy.

The Universal Endometrial Applicator Set (GM11009840) consists of key device components and accessories made of titanium tandems and PEEK vaginal cylinder to allow for adaptation to individual anatomical situations for intracavitary brachytherapy. The Applicator is inserted into the patient and connected to an afterloader. The applicator acts to guide the radioactive source from the afterloader to the correct location or locations for treatment. This combination places the remote-controlled radioisotope treatment source (brachytherapy source) nearby the target tissue. The key device components include: Intrauterine tandems (left angle, straight and right angle) Endometrial applicator clamping unit with grub screws & allen wrench Vaginal cylinder with lever handle Sterilization box Cleaning caps

This document, a 510(k) Premarket Notification from the FDA, describes the Universal Endometrial Applicator Set. However, it does not contain the type of acceptance criteria or study details typically associated with AI/ML-powered medical devices. Instead, it focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing for material changes, biocompatibility, cleaning, sterilization, and compliance with various standards.

Therefore, I cannot provide the requested information in the format given because the document is for a physical medical device (an applicator set) and not for an AI/ML device that would have performance metrics like sensitivity, specificity, or AUC, nor study details like sample sizes for test/training sets, expert ground truth establishment, or MRMC studies.

The document explicitly states: "No clinical tests have been included in this pre-market submission." This further confirms that the type of performance data and study details requested are not present in this submission.

If the request was based on a misunderstanding of the document's content, please clarify if you have a document pertaining to an AI/ML medical device.

Ask a specific question about this device

Halcyon and Ethos radiotherapy system are indicated for the delivery of stereotactic radiosurgery and precision radiotherapy for lesions, tumors and conditions anywhere in the body where radiation is indicated for adults and pediatric patients.
The Halcyon and Ethos Radiotherapy System produce CBCT images that can be used in Image Guided Radiation Therapy, and the simulation and planning for radiation therapy.

Halcyon and Ethos radiotherapy system are single energy medical linear accelerators (linacs) designed to deliver Image Guided Radiation Therapy and radiosurgery, using Intensity Modulated and Volumetric Modulated Arc Therapy techniques. They consist of the accelerator and patient support within a radiation shielded treatment room and a control console outside the treatment room.
An electron gun generates electrons which are accelerated by radio frequency (RF) power from a magnetron. The electrons strike a tungsten target producing photons (X-rays) for treatment and MV Imaging. The photons produced by the target are monitored and controlled by a pressurized ion chamber.
A beam collimation subsystem consisting of a primary and secondary collimator and two stacked multileaf collimators (MLCs) shapes the photon beam to define the treatment area.
X-Ray images of the patient are used by the treater to verify the correct treatment location. MV Imaging uses the treatment beam and a flat panel imager whereas kV imaging uses a high-capacity kV X-ray tube, a kV collimation system with full fan bowtie filter with movable y-blades to define the imaging beam size and to capture the image, a kV imager.
Halcyon and Ethos radiotherapy system deliver a treatment generated by a Treatment Planning System from a physician's prescription. kV CBCT images from HyperSight can additionally be used for planning treatments. Ethos radiotherapy system is capable of delivering adaptive treatments which can take into account changes in tumour geometry between treatment sessions.

The provided text describes a 510(k) submission for the Halcyon and Ethos Radiotherapy System, focusing on expanding the indications for use of its HyperSight CBCT images for primary treatment planning, effectively proving it is clinically equivalent to plans generated from conventional and simulator CT images.

Here's an analysis of the acceptance criteria and the study that proves the device meets them:

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

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

• Sample Size: 26 human subject cases.
• Data Provenance: Obtained from three institutions in the US and Europe. The data was from institutionally approved prospective single-site clinical studies. All cases were adult patients planned to receive radiation therapy for head/neck, thorax (including breast), abdomen, or pelvis conditions.

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

• The text states that for each case, a "summary list identifying the dosimetrist and physician involved with each case" was provided. It does not specify the exact number of experts involved in establishing ground truth (e.g., contours, clinical planning objectives) for the test set, nor their specific qualifications (e.g., years of experience).

4. Adjudication method for the test set:

• The text does not explicitly describe an adjudication method for the test set data. It mentions that "planning CT and HyperSight CBCT image sets, contours, and clinical planning objectives were provided to Varian," implying these were already established by the contributing institutions.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done in the context of human readers improving with AI assistance. This study focused on the equivalence of treatment plans generated from different image sources (conventional CT vs. HyperSight CBCT) by the system (RapidPlan), rather than evaluating human reader performance with or without AI assistance. The "AI" aspect is more embedded in or implied by the "RapidPlan" system's ability to generate plans.

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

• Yes, a standalone study was effectively performed. Varian "created radiation treatment plans for each type of image separately, using a standardized planning approach (RapidPlan) available in the Varian Eclipse treatment planning system." This indicates an algorithm-driven comparison of plans generated from different image inputs, rather than focusing on human interaction with the device for performance improvement.

7. The type of ground truth used:

• The ground truth primarily consisted of:
  • Clinical Planning Objectives: These were established by the contributing institutions, including target coverage goals and normal tissue constraints.
  • Contours: Provided for each case, likely drawn by clinicians at the institutions, representing the anatomical structures for planning.
  • Conventional CT Images: These served as a "gold standard" or reference against which the HyperSight CBCT image-based plans were compared for clinical equivalence.
  • Measurements: Ionization chamber measured dose and 2D gamma analysis were used for patient-specific QA, which are objective physical measurements.

8. The sample size for the training set:

• The document does not specify the sample size for the training set. The study described is a clinical validation (test set) for the expanded indication of the already existing device. It focuses on the performance comparison for the intended use, not on the details of the model's training.

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

• Not applicable/Not provided in the document. The document describes a study to support a change in the Indications for Use for an existing device, specifically validating the use of HyperSight CBCT images for primary treatment planning. It does not detail how the ground truth for the original training of the Halcyon/Ethos system or its RapidPlan component was established.

Ask a specific question about this device

IDENTIFY is indicated for adult patients undergoing radiotherapy treatment simulation and/or delivery. IDENTIFY is indicated for positioning of patients, and for montoring patient motion including respiratory patterns. It allows for data output to radiotherapy devices to synchronize image acquisition or treatment delivery with the acquired motion information.

IDENTIFY is a system for motion monitoring during radiotherapy treatment simulation and delivery. It incorporates patient safety, quality, and workflow efficiency. Its high precision SGRT cameras support proper patient positioning and enable to monitor the patient's respiratory motion and to detect intra-fraction patient position changes during the treatment.

This FDA 510(k) summary for Varian Medical Systems Inc.'s IDENTIFY device mentions non-clinical testing for hardware and software verification and validation, electrical safety, and electromagnetic compatibility. However, it does not include a study specifically demonstrating device performance against pre-defined acceptance criteria for its intended use (patient positioning and motion monitoring, including respiratory patterns).

The document focuses on conformance to regulatory standards and a conclusion that the product conformed to defined user needs and intended uses, and is considered safe and effective. It explicitly states: "The Verification and Validation demonstrates that the device is as safe and effective as the predicate." This implies that the validation activities were largely focused on ensuring the new device performs at least as well as its predicate and meets safety standards, rather than proving performance against specific quantitative metrics for its core functionality in a study format.

Therefore, many of the requested sections regarding a specific performance study (e.g., sample size, ground truth establishment, MRMC study, standalone performance) cannot be answered from the provided text.

Here's a breakdown of what can and cannot be extracted from the provided text:

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

The document does not provide a table of acceptance criteria for device performance (e.g., accuracy of positioning, respiratory motion tracking accuracy, beam-hold trigger accuracy) nor does it report specific quantitative performance metrics for these functions. It states that "Test results showed conformance to applicable requirements specifications and assured hazard safeguards functioned properly," but does not detail what these requirements or results were in measurable terms related to the device's clinical indications.

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

Not provided in the document.

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 provided in the document.

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

Not provided in the document.

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 provided in the document. The device is not described as an AI-assisted diagnostic tool that would typically involve human readers. Its primary function is motion monitoring and synchronization with treatment delivery.

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

A standalone performance study against specific clinical metrics for motion tracking or positioning accuracy is not described in the provided text. The non-clinical testing mentions "hardware and software verification and validation testing," which would imply testing the algorithm, but the specifics of such testing in terms of clinical performance metrics are absent.

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

Not provided in the document.

8. The sample size for the training set

Not applicable, as this document does not describe a machine learning model's training phase for a diagnostic or predictive task. The device is for motion monitoring and synchronization, not typically modeled through a "training set" in the sense of supervised learning for image interpretation.

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

Not applicable, as a training set for machine learning is not discussed.

Ask a specific question about this device

The ARIA Radiation Therapy Management product is a treatment plan and image management application. It enables the authorized user to enter, access, modify, store and archive treatment plan and image data from diagnostic studies, treatment planning, simulation, plan verification and treatment. ARIA Radiation Therapy Management also stores the treatment histories including dose delivered to defined sites and provides tools to verify performed treatments.

The ARIA Radiation Therapy Management product is a treatment plan and image management application. It enables the authorized user to enter, access, modify, store and archive treatment plan and image data from diagnostic studies, treatment planning, simulation, plan verification and treatment. ARIA Radiation Therapy Management also stores the treatment histories including dose delivered to defined sites and provides tools to verify performed treatments. ARIA Radiation Therapy Management supports the integration of all data and images in one central database including archiving and restoration. The different ARIA Radiation Therapy Management features support the visualization, processing, manipulation and management of all data and images stored in the system. Images can also be imported through using DICOM, the available image import filters or by means of film digitizers.

The provided text is a 510(k) summary for Varian Medical Systems' ARIA Radiation Therapy Management (v18.0) device. It describes the device, its intended use, comparison to a predicate device, and performance data from non-clinical testing.

However, the document does not contain the following information necessary to describe acceptance criteria and the study that proves the device meets those criteria:

• Specific acceptance criteria: The document mentions "applicable requirements were met" and "safeguards against hazards functioned properly" but does not detail what these specific quantitative or qualitative acceptance criteria were for the software verification and validation.
• Reported device performance: While it states "test results showed that applicable requirements were met," it does not provide any specific performance metrics or data (e.g., accuracy, precision, error rates) that were measured and compared against acceptance criteria.
• Sample size and data provenance for test set: No information is given about a test set, as all testing was non-clinical software verification and validation.
• Experts for ground truth and adjudication method: These are typically relevant for studies involving human interpretation or clinical endpoints, which this submission explicitly states were not conducted.
• MRMC comparative effectiveness study: The document clearly states that "No data from animal studies or clinical tests have been included" and "no animal or clinical studies were conducted for the subject device." Therefore, no MRMC study was performed.
• Standalone performance: Since no clinical studies were performed, there are no reported standalone performance metrics in the context of interpretation or diagnosis. The performance mentioned refers to software functionality.
• Type of ground truth: Ground truth is usually associated with clinical or pathological verification in studies, which are absent here.
• Training set information: As this is primarily a software update and management system, not a machine learning algorithm that requires a "training set" in the conventional sense, this information is not applicable and not provided.

Based on the provided text, I can only state what is mentioned regarding performance, rather than providing the requested table and details about a clinical study:

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

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

• Sample Size: Not applicable. The submission describes software verification and validation, not a test set of patient data.
• Data Provenance: Not applicable. Testing was based on software functionality and engineering requirements.

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

• Not applicable. No test set involving human interpretation or clinical ground truth was used.

4. Adjudication method for the test set:

• Not applicable. No test set requiring expert adjudication was used.

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

• No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No data from animal studies or clinical tests have been included in this pre-market submission" and "no animal or clinical studies were conducted for the subject device."

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

• Yes, in the context of software verification and validation, the performance of the software (algorithm) was assessed standalone against its functional and safety requirements. However, this is not a standalone diagnostic performance study as typically understood for AI/ML devices. The document states: "The non-clinical data support the safety of the software verification and validation demonstrate that ARIA Radiation Therapy Management should perform as intended in the specified use conditions."

7. The type of ground truth used:

• For the software verification and validation, the "ground truth" was the specified engineering requirements, functional specifications, and regulatory standards (e.g., IEC 62304, IEC 62366-1, ISO 13485, ISO 14971). There was no clinical or pathological ground truth used as no clinical studies were performed.

8. The sample size for the training set:

• Not applicable. This is a software management system, not a machine learning model that typically involves a "training set" in the AI/ML sense.

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

• Not applicable, as no training set (in the AI/ML context) was described.

Ask a specific question about this device

The Bravos Afterloader System is indicated for use in the treatment of both benign and malignant disease or other conditions, for both curative and palliative intent, in the delivery of remote-controlled High Dose Rate (HDR) brachytherapy.

The Transfer Guide Tubes are intended to connect between the Bravos Remote Afterloader system and its range of applicators. This connection creates a conduit for the source cable to travel through and allows the radioactive isotopes to be positioned within the patient's tumor site.

The Length Assessment Device is intended to allow the user to establish an approximate length of an unknown length channel prior to the afterloader performing definitive length verification.

BRAVOS Afterloader System: The BRAVOS Afterloader System is a computer controlled remote electro/mechanical system used for brachytherapy. The system automatically moves a stainless-steel cable incorporating a small, high activity Iridium-192 pellet in a steel capsule (sealed source) into applicator(s) or catheter(s) inserted into the patient close by a malignant tumor or tumor bed.

Transfer Guide Tubes (TGT): Transfer Guide Tubes (TGT) are Brachytherapy applicator accessories. They are designed to provide a path for the dummy and source cable from the BRAVOS Afterloader System to the Applicator. The applicator end of a Transfer Guide Tube can vary in design to accommodate a range of Applicators.

Length Assessment Device (LAD): The Length Assessment Device (LAD) is a Brachytherapy applicator accessory and is used to determine the approximate length of the inner lumen of the Transfer Guide Tubes (TGT) and applicator assembly.

The provided document is a 510(k) Premarket Notification for the BRAVOS Afterloader Family, specifically focusing on an updated BRAVOS Afterloader System. This submission claims substantial equivalence to a previously cleared predicate device (K191580).

Here's an analysis of the acceptance criteria and supporting study information based only on the provided text:

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

The document does not explicitly present acceptance criteria in a quantitative table with reported device performance. Instead, it focuses on demonstrating that the updated device is "substantially equivalent" to its predicate and that verification and validation testing confirms it meets "initial design input requirements."

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

The document does not provide specific details on the sample size used for any test set or the data provenance. It mentions "Verification testing was performed to verify the integrity of any changes. Validation testing was performed on production equivalent devices, under clinically representative conditions by qualified personnel." However, the number of "changes" or "production equivalent devices" is not specified, nor is the origin of the data (e.g., country).

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)

The document does not specify any experts used to establish ground truth. The testing described appears to be technical verification and validation, rather than clinical evaluation against expert-defined ground truth. It states "Validation testing was performed on production equivalent devices, under clinically representative conditions by qualified personnel," but does not detail the nature or qualifications of these "qualified personnel" beyond their role in conducting validation.

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

The document does not mention any adjudication method 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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "No animal studies or clinical tests have been included in this pre-market submission." This device is a remote-controlled radionuclide applicator system, and the submission focuses on demonstrating substantial equivalence through non-clinical performance and software verification/validation, not a human-in-the-loop study with AI assistance.

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

A standalone performance study of the algorithm itself (e.g., specific accuracy metrics for an AI component) is not explicitly described. The "BRAVOS Control Software" is mentioned as having "new and modified risks plus risk control measures" and being updated to version 2.1. The software is deemed a "major" level of concern. Performance data is mentioned as "Software verification and validation was conducted..." and "Verification testing was performed to demonstrate that the performance and functionality of the updated BRAVOS Afterloader System meets the initial design input requirements." This suggests functional testing of the software within the system context, rather than a standalone performance evaluation of a specific algorithm.

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

The document does not explicitly describe the type of "ground truth" in a clinical sense. The "ground truth" for the verification and validation appears to be the initial design input requirements and the expected functionality as part of the system's operation. No clinical ground truth (e.g., pathology, outcomes) is referenced for performance evaluation.

8. The sample size for the training set

The document does not mention any 'training set' or provide a sample size for it. This typically pertains to machine learning or AI models, which are not the primary focus of this submission (which emphasizes electromechanical system updates and software verification/validation for an existing device type).

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

Since no training set is mentioned, information on how its ground truth was established is not provided.

Ask a specific question about this device

IDENTIFY is indicated for patient and accessory identification, positioning and tracking for imaging and radiation therapy treatments.

Identify is used for patient-setup, guidance and to monitor a patient before and during radiation treatment. The system consists of cameras, software, PC workstations, RFID kit, Interlock unit, calibration tools, Palm scan unit, RFID tags and optical markers, network components and cabling and handheld controllers.

The provided text is a 510(k) summary for the Varian Medical Systems "Identify" device. It focuses on regulatory compliance, non-clinical testing, and an argument for substantial equivalence to a predicate device. Critically, it does not include details on acceptance criteria and a study proving the device meets those criteria, especially in the context of clinical performance or the improvement of human readers with AI assistance.

The "Identify" device, as described, is for patient and accessory identification, positioning, and tracking for imaging and radiation therapy. The description of its components (cameras, software, RFID, optical markers) suggests it's a patient localization and monitoring system, not primarily an AI-driven image analysis tool for diagnosis or decision support.

Therefore, I cannot extract the requested information regarding:

• A table of acceptance criteria and reported device performance: This document does not specify quantitative performance metrics or acceptance criteria for accuracy, precision, or other operational parameters of the "Identify" system. It mentions conformance to standards and "no DRs remaining which had a priority of Safety Intolerable or Customer Intolerable," which are general quality and safety statements, not specific performance criteria.
• Sample size and data provenance for a test set: No test set is described in terms of patient data or clinical cases. The testing seems to be focused on hardware/software verification and standard compliance.
• Number of experts and qualifications for ground truth establishment: Not applicable, as there's no mention of a human-read test set or ground truth established by experts.
• Adjudication method: Not applicable.
• MRMC comparative effectiveness study: No such study is mentioned. The device's function as described (patient tracking) does not lend itself to an MRMC study comparing human reader performance with and without AI assistance in the diagnostic sense.
• Standalone (algorithm only) performance: No such
  performance metrics are provided for an AI algorithm. The device is a system.
• Type of ground truth used: Not clearly defined in the context of clinical performance data.
• Sample size for the training set: Not applicable, as there's no mention of a machine learning model training set with clinical data.
• How the ground truth for the training set was established: Not applicable.

Summary of available information related to testing:

• Non-clinical Testing: Hardware and software verification and validation testing were conducted according to FDA Quality System Regulation (21 CFR §820), ISO 13485, ISO 14971, and other FDA-recognized consensus standards (IEC 62304, ISO 15223-1, IEC 60601-1, IEC 60601-1-2, IEC 61217, AAMI RT2, IEC 62366-1).
• Software Level of Concern: "Major," indicating that a failure could result in serious injury or death.
• Electrical Safety and EMC: Complies with IEC 60601-1 and IEC 60601-1-2.
• Conclusion: "The outcome was that the product conformed to the defined user needs and intended uses and that there were no DRs (discrepancy reports/Unresolved Anomalies) remaining which had a priority of Safety Intolerable or Customer Intolerable (applicable to the US)."

This document describes a device approval process based on substantial equivalence, primarily supported by adherence to recognized standards and internal V&V testing, rather than a clinical performance study with defined acceptance criteria and human-in-the-loop evaluations typically seen for AI-diagnostic devices.

Ask a specific question about this device

IDENTIFY is indicated for patient and accessory identification, positioning and tracking for imaging and radiation therapy treatments.

Identify is used for patient-setup, guidance and to monitor a patient before and during radiation treatment. The system consists of cameras, software, PC workstations, RFID kit, Interlock unit, calibration tools, Palm scan unit, RFID tags and optical markers, network components and cabling and handheld controllers.

The provided text is a 510(k) summary for Varian Medical Systems' "Identify" device. It outlines the device's intended use, classification, and non-clinical testing. However, it does not contain a detailed study report that includes specific acceptance criteria and device performance metrics, sample sizes, ground truth establishment methods, or any information regarding multi-reader multi-case comparative effectiveness studies.

The document focuses on demonstrating substantial equivalence to a predicate device (Identify K112692) through compliance with various quality and safety standards.

Therefore, I cannot provide a table of acceptance criteria and reported device performance or other specific study details based on the information given. The text explicitly states:

• "Non-clinical Testing Hardware and software verification and validation testing was conducted according to the FDA Quality System Regulation (21 CFR §820), ISO 13485 quality Management System standard, ISO 14971 Risk Management Standard and the other FDA recognized consensus standards listed below. Test results showed conformance to applicable requirements specifications and assured hazard safeguards functioned properly."
• "The outcome was that the product conformed to the defined uses and that there were no DRs (discrepancy reports/Unresolved Anomalies) remaining which had a priority of Safety Intolerable or Customer Intolerable."

This indicates that internal verification and validation testing was performed to affirm compliance with regulations and standards, but it does not detail a study designed to measure performance against specific clinical or technical acceptance criteria with quantified results. The document emphasizes "conformance to applicable requirements specifications" rather than presenting specific performance metrics.

Ask a specific question about this device

Halcyon is indicated for the delivery of stereotactic radiosurgery and precision radiotherapy for lesions, tumors and conditions anywhere in the body where radiation is indicated for adults and pediatric patients.

Halcyon is a single energy medical linac designed to deliver Image Guided Radiation Therapy and Radiosurgery, using Intensity Modulated and Volumetric Modulated Arc Therapy techniques. It consists of the accelerator and patient support within a radiation shielded treatment room and a control console outside the treatment room.

The provided text does not contain information about acceptance criteria for a device's performance that would require a study to prove it meets those criteria.

Instead, the document is a 510(k) premarket notification for a medical device called "Halcyon," a medical charged-particle radiation therapy system. The FDA's letter (pages 0-1) confirms that the device is substantially equivalent to legally marketed predicate devices.

The "510(k) Summary" (pages 3-4) describes the device, its intended use, indications for use, and differences from a predicate device (Halcyon K170817), as well as non-clinical testing and standards conformance.

Key takeaways from the document regarding testing and validation are:

• Non-clinical testing (hardware and software verification and validation) (page 4) was conducted according to:
  • FDA Quality System Regulation (21 CFR §820)
  • ISO 13485 Quality Management System standard
  • ISO 14971 Risk Management Standard
  • Other FDA recognized consensus standards (e.g., IEC 60601 series, IEC 62304, ISO 10993-1, etc.).
• Software was considered a "major" level of concern, and verification/validation testing was conducted as per FDA guidance.
• Electrical safety and EMC testing was conducted, complying with IEC 60601-1 and IEC 60601-1-2 standards.
• The outcome of non-clinical testing was that the product conformed to defined user needs and intended uses, with no remaining discrepancy reports of "Safety Intolerable" or "Customer Intolerable" priority.
• The manufacturer concludes that Halcyon is safe and effective and performs at least as well as the predicate device.

None of the requested information (acceptance criteria table, sample size, data provenance, expert ground truth, adjudication method, MRMC study, standalone performance, training set size, etc.) can be extracted from the provided text. The document focuses on regulatory compliance, safety, and substantial equivalence rather than performance metrics from a specific comparative study.

Ask a specific question about this device

The Calypso System is intended for use as an adjunct in treatment planning and radiation therapy, to align and/or monitor the patient's position relative to the isocenter of a radiation therapy system. The Calypso System provides accurate, precise, and continuous localization of a treatment isocenter by using two or more Beacon transponders.

Anchored Beacon transponders are indicated for permanent implantation in small airways in the lung to align and/or monitor the internal position of targets that move with respiratory and other patient motion in real time during radiation therapy.

The Anchored Beacon® transponder is a small passive implant, intended for permanent implantation in small airways in the lung. It is provided pre-loaded in a single-use delivery catheter for bronchoscopic implantation in a lung airway.

The Anchored Transponder is comprised of a Permanent Beacon Transponder (glassencapsulated electrical circuit) coupled to a stability feature (self-expanding 5-legged structure in a shell assembly). When implanted in a small diameter airway, the anchor legs of the stability feature expand independently to contact the airway wall.

When used with the Calypso® System, the Anchored Transponder signals enable realtime, objective measurement of the location of the treatment target in four dimensions. The system operator uses this information to align the patient's treatment target to the isocenter of the linear accelerator prior to radiation therapy and/or to monitor the position of the treatment target during treatment.

The provided document is a 510(k) summary for the Anchored Beacon® Transponder. It describes the device, its intended use, and a summary of the testing conducted to demonstrate substantial equivalence to predicate devices. However, it does not explicitly detail acceptance criteria in a table format or provide a comprehensive study report with quantitative performance metrics that would directly address all the requested points.

Based on the information available in the document, here's what can be extracted and inferred regarding the acceptance criteria and the study:

1. Table of Acceptance Criteria and Reported Device Performance

The document mentions that "Bench testing was performed and demonstrated: (1) the Anchored transponder satisfied the established performance requirements, including related to use in the lung". However, the specific quantitative acceptance criteria for these performance requirements (e.g., specific thresholds for localization accuracy, stability, or drift) are not provided in the document. Similarly, the exact reported device performance values against these established criteria are not explicitly stated in a quantitative manner.

We can infer the types of performance evaluated, but not the specific metrics or acceptance thresholds.

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

• Sample Size: "69-patient cohort"
• Data Provenance: The document states "Clinical study data obtained in lung cancer patients undergoing radiation therapy (69-patient cohort)". It doesn't explicitly state the country of origin, but it implies a prospective clinical study context. It is not explicitly stated if it was retrospective or prospective, but the phrasing "obtained in" and "undergoing" suggests a prospective collection of data for the purpose of the study.

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

The document does not provide any information about the number of experts used to establish ground truth or their qualifications. The clinical study primarily evaluates the device's ability to be localized, its stability, and its safety, which would likely rely on direct measurement, imaging, and clinical follow-up rather than expert consensus on an independent "ground truth" per se.

4. Adjudication Method for the Test Set

The document does not provide any information about an adjudication method. Given the nature of the device (a physical fiducial marker for real-time tracking), the "ground truth" would likely be derived from direct instrumental measurements or clinical observations rather than subjective interpretations requiring adjudication.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned or described. The clinical study compared the stability of the anchored transponders in a subset of study patients to "a matched cohort of patients with commercially-available fiducial markers implanted in lung (including the predicate, the superlock Cobra)". This is a comparative study, but it's focused on the device's performance (stability) rather than human reader improvement with or without AI assistance. The device itself is a passive marker, not an AI diagnostic tool that assists human readers.

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

The device is a physical transponder, not an algorithm or AI. Its performance is evaluated in conjunction with the Calypso System (which includes hardware and software to track the transponders). Therefore, the concept of a "standalone" algorithm performance study without human-in-the-loop is not directly applicable in the way it would be for a diagnostic AI. The "localization" and "stability" assessment can be considered analogous to a standalone performance in that it evaluates the device and system's objective measurement capabilities.

7. Type of Ground Truth Used

The ground truth used in the studies described appears to be based on:

• Real-time localization data: objective measurements from the Calypso System.
• Clinical observation and follow-up: for safety, monitoring of patient position, and positional stability.
• Radiographic assessment: for detecting pulmonary abnormalities attributable to the transponder.
• Biocompatibility testing: in conformance with ISO 10993 standards, involving scientific testing rather than expert consensus on a clinical case.

It is not explicitly stated as pathology or outcomes data in the sense of disease progression or diagnosis, but rather related to the physical behavior and clinical impact of the implanted device.

8. Sample Size for the Training Set

The document does not provide any information about a training set or its sample size. This device is a physical fiducial marker, not a machine learning algorithm that requires a separate training set. The descriptions of "bench testing" and "clinical study data" refer to validation and verification, not training data for an algorithm.

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

As there is no mention of a training set for an algorithm, this question is not applicable based on the provided document.

Ask a specific question about this device