Search Results

The TomoTherapy Treatment System is intended to be used as an integrated system for the planning and precise delivery of radiation therapy, stereotactic radiotherapy, or stereotactic radiosurgery to tumors or other targeted tissues while minimizing the delivery of radiation to vital healthy tissue. The megavoltage x-ray radiation is delivered in a rotational, non-rotational, modulated (IMRT), or non-modulated (non-IMRT/three dimensional conformal) format in accordance with the physician prescribed and approved plan.

The TomoTherapy Treatment System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT imaging for IGRT functionality, and helical (rotational) and fixed beam (non-rotational) radiation therapy treatment capabilities into a single comprehensive system. The TomoTherapy Treatment System is a prescription device. It delivers radiation in accordance with a physician approved plan. The device does not diagnose disease, recommend treatment regimens, or quantify treatment effectiveness. The megavoltage CT imaging functionality is not intended for diagnostic use. The TomoTherapy Treatment System with Fast Optimizer is a modification that allows for increased efficiency and speed during the treatment planning process through the use of modified hardware and software.

The provided text describes a 510(k) premarket notification for the "TomoTherapy Treatment System Next Generation Fast Optimizer." This filing is for a modification to an existing device, the TomoTherapy Hi-Art System (K082005), to increase efficiency and speed during the treatment planning process. The key takeaway is that the modification primarily involves new hardware (Graphics Processing Unit (GPU)) and revised software to accommodate it, while maintaining unchanged dose accuracy constraints and not affecting the radiation delivery system.

Therefore, the performance data presented focuses on demonstrating that these modifications do not degrade performance and that the updated system remains as safe and effective as the predicate device.

Here's a breakdown of the requested information 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 document does not provide specific details about the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective). It generally refers to "verification and validation tests." Given the nature of the modification (software/hardware for faster optimization), it's highly likely these tests would involve in silico simulations and phantom measurements rather than patient data.

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

The document does not mention the involvement of experts in establishing ground truth for the test set. Given that the focus is on a technical upgrade to a simulation and planning system, ground truth would likely be established through physical dosimetry measurements (phantoms) and computational models (physics-based simulations) rather than expert clinical review.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method. This is consistent with a technical performance evaluation where quantitative measurements and computational comparisons are the primary means of verification.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical tests were required to establish substantial equivalence." This type of study would involve human readers and clinical cases.

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

Yes, implicitly, a standalone evaluation of the algorithm's performance (specifically the "Fast Optimizer" component) was done. The performance data section refers to "verification and validation tests" that confirmed performance within design specifications and conformance to standards. These tests would evaluate the algorithm's output (e.g., dose calculations, plan optimization speed) directly, without human intervention in the loop of measuring that performance itself. However, it's important to note that the device is a "prescription device" and intended to be used with a physician-approved plan, meaning a human is always in the loop for the end-to-end clinical process. The standalone performance here refers to the technical accuracy and speed of the planning system's calculations.

7. The Type of Ground Truth Used

The ground truth for this device's performance evaluation would primarily be derived from:

• Physics-based models and calculations: For dose accuracy and optimization.
• Physical phantom measurements: For verifying radiation dose delivery and distribution against the planned dose.
• Industry standards and regulatory requirements: For demonstrating conformance.

8. The Sample Size for the Training Set

The document does not provide any information about a training set size. This modification focuses on optimizing the speed and efficiency of an existing planning algorithm, rather than developing a new AI model that requires a large training dataset in the conventional sense. The "Fast Optimizer" component likely involves algorithmic improvements and hardware acceleration rather than a machine learning model trained on a data set.

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

As no specific training set is mentioned in the context of conventional machine learning, this question is not directly applicable. If "training" refers to the development and refinement of the optimization algorithms, the "ground truth" would have been established through a combination of physics principles, engineering specifications, and iterative testing against known or simulated scenarios to ensure the algorithm generates accurate and clinically acceptable treatment plans while achieving the desired speed improvements.

Ask a specific question about this device

The TomoTherapy Treatment System is intended to be used as an integrated system for the planning and precise delivery of radiation therapy, stereotactic radiotherapy, or stereotactic radiosurgery to tumors or other targeted tissues while minimizing the delivery of radiation to vital healthy tissue. The megavoltage x-ray radiation is delivered in a rotational, non-rotational, modulated (IMRT), or non-modulated (non-IMRT/three dimensional conformal) format in accordance with the physician prescribed and approved plan.

The TomoTherapy Treatment System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT imaging for IGRT functionality, and helical (rotational) and fixed beam (non-rotational) radiation therapy treatment capabilities into a single comprehensive system. The TomoTherapy Treatment System is a prescription device. It delivers radiation in accordance with a physician approved plan. The device does not diagnose disease, recommend treatment regimens, or quantify treatment effectiveness. The megavoltage CT imaging functionality is not intended for diagnostic use.

Here's a breakdown of the acceptance criteria and study information for the TomoTherapy Treatment System, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state specific numerical acceptance criteria (e.g., minimum accuracy percentages, maximum deviation values). Instead, it refers to general conformity to standards and design specifications. Therefore, the table below reflects the qualitative statements made in the document regarding performance.

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

• Sample Size: The document does not specify a numerical sample size for the test set. It mentions "verification and validation tests, including extensive tests of imaging and radiation delivery functionality."
• Data Provenance: The document does not provide information on the country of origin of the data or whether the study was retrospective or prospective. It is a premarket notification for a medical device (510(k)), typically relying on engineering and bench tests for this type of submission rather than large-scale clinical studies.

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

The document does not mention the use of experts to establish "ground truth" in the context of diagnostic interpretation for the tests performed. The tests described are primarily focused on the engineering and physical performance of the radiation delivery system and imaging functionality, not on diagnostic accuracy requiring expert interpretation of images or patient outcomes.

4. Adjudication Method for the Test Set

As the tests described are technical performance evaluations rather than clinical assessments requiring human interpretation or decision-making, an adjudication method (like 2+1 or 3+1) is not applicable and therefore not mentioned in the document.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical tests were required to establish substantial equivalence." The focus was on demonstrating substantial equivalence to a predicate device through technical performance data.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, in essence, standalone performance was assessed. The "verification and validation tests" for imaging and radiation delivery functionality would constitute evaluations of the system's performance without human intervention in the primary operational loop being tested (e.g., how accurately the system delivers radiation according to a plan, or how consistently the dose rate is maintained). The device's primary function is radiation delivery, not diagnostic interpretation by an AI algorithm.

7. The Type of Ground Truth Used

The "ground truth" for the tests performed would be established by engineering specifications, physical measurements, and recognized consensus standards. For example, the ground truth for dose consistency would be the expected dose output based on the physics of the system and calibration, measured against actual output. Similarly, imaging functionality would be assessed against expected image quality and resolution for megavoltage CT. There is no mention of pathology, outcomes data, or expert consensus related to diagnostic accuracy as the "ground truth" for these tests, as the device is not a diagnostic tool.

8. The Sample Size for the Training Set

The document does not specify a "training set" sample size. This type of device classification (510(k) for a radiation therapy system) generally does not involve machine learning algorithms that require a distinct training set in the way a diagnostic AI would. The performance data comes from verification and validation of the hardware and software systems.

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

As no specific "training set" for an AI algorithm is indicated, the concept of establishing ground truth for it is not applicable or mentioned in this document. The system's operation is based on pre-defined physics models and engineering designs, not learned patterns from a training dataset like a typical AI diagnostic tool.

Ask a specific question about this device

The TomoTherapy HI-ART System is intended to be used as an integrated system for the planning and precise delivery of radiation therapy, stereotactic radiotherapy, or stereotactic radiosurgery to tumors or other targeted tissues while minimizing the delivery of radiation to vital healthy tissue. The megavoltage x-ray radiation is delivered in a rotational, non-rotational, modulated (IMRT), or non modulated (non-IMRT/three dimensional conformal) format in accordance with the physician approved plan.

The TomoTherapy HI-ART System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT scanning for IGRT functionality, and helical radiation therapy treatment capabilities into a single comprehensive system. The megavoltage CT image is not for diagnostic use. This modification provides a licensable option that adds the capability for fixed beam treatments from multiple user defined angles as well.

The provided text is a 510(k) Premarket Notification for the TomoTherapy HI-ART System, which is a radiation therapy system. It describes the device, its intended use, safety considerations, and compliance with standards. However, it does not contain the detailed information necessary to complete a table of acceptance criteria and reported device performance, nor does it describe a study in the way typically required for AI/ML-based medical devices.

The document is a traditional 510(k) submission for a modified radiation therapy system, not for an AI/ML-based diagnostic or prognostic device that would involve performance metrics like sensitivity, specificity, or reader studies. The validation section mentions "system functionality, including planning, imaging, delivery, database management, DICOM communications, etc." and that "Test tools utilized in this testing included IMRT phantoms, ion chambers and other test phantoms." This indicates performance validation against physical phantoms and established engineering/system metrics, rather than clinical performance based on patient data and ground truth as would be the case for an AI/ML device.

Therefore, many of the requested fields cannot be filled from the provided text.

Here's a breakdown of what can be extracted and what cannot:

1. Table of acceptance criteria and the reported device performance:

• Acceptance Criteria: Not explicitly stated in terms of quantitative performance metrics (e.g., accuracy, sensitivity, specificity) for clinical outcomes in the provided text. The document refers to compliance with safety standards and system functionality.
• Reported Device Performance: Not detailed in terms of clinical performance metrics. It mentions validation using IMRT phantoms and ion chambers, implying physical measurement of radiation delivery accuracy and dose calculation, but specific numerical results or criteria are not provided.

2. Sample size used for the test set and the data provenance: Not applicable in the context of clinical data for AI/ML. The validation involved test tools like phantoms.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for phantoms is typically derived from physical measurements and established parameters, not expert consensus on clinical findings.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: No. This is not an AI/ML device, and no MRMC study is mentioned. The device assists in planning and delivering radiation, not in interpreting medical images or making diagnoses.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The device is a system with human-in-the-loop for planning and operation. The validation concerns the system's performance, not an isolated algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the described validation, the ground truth would be based on physical measurements of dose, system functionality, and compliance with engineering specifications when tested with phantoms and other test tools. It is not clinical ground truth from patient data.

8. The sample size for the training set: Not applicable. This is not an AI/ML device that requires training data in the computational sense.

9. How the ground truth for the training set was established: Not applicable.

Summary based on the provided text:

Reported Device Performance: Validation included "system functionality, including planning, imaging, delivery, database management, DICOM communications, etc." No specific numerical performance values are provided. |
| 2. Sample size for test set & data provenance | Not applicable for clinical data. Validation involved "IMRT phantoms, ion chambers and other test phantoms." The 'sample size' would pertain to the set of tests conducted on these physical phantoms. |
| 3. Number of experts & qualifications for ground truth | Not applicable. Ground truth for phantom testing is based on known physical properties and measurements, not expert consensus on clinical findings. |
| 4. Adjudication method for test set | Not applicable. |
| 5. MRMC comparative effectiveness study | No. This document does not describe an AI/ML device or an MRMC study. |
| 6. Standalone (algorithm only) performance study | Not applicable. The device is an integrated system (hardware and software) with human-in-the-loop operation for radiation therapy planning and delivery. |
| 7. Type of ground truth used | For the validation described, the ground truth would be based on established physical measurements and engineering specifications for system components when tested with IMRT phantoms and ion chambers. It is not expert consensus, pathology, or outcomes data from patients. |
| 8. Sample size for training set | Not applicable. This is not an AI/ML device that undergoes a training phase with a dataset. |
| 9. How ground truth for training set was established | Not applicable. |

Conclusion:

The provided document describes a 510(k) submission for a conventional medical device (radiation therapy system) with modifications, not an AI/ML-driven device. Therefore, the request for detailed information on acceptance criteria, reader studies, and training/test set specifics, which are typical for AI/ML device evaluations, cannot be fulfilled from this text. The "study" mentioned is a system validation against engineering standards and physical test phantoms, rather than a clinical performance study with patient data and expert ground truth.

Ask a specific question about this device

The TomoTherapy HI-ART System® is intended to be used as an integrated system for the planning and delivery of intensity modulated radiation therapy (IMRT). The HI-ART System provides precise delivery of radiation to tumors or other targeted tissues while minimizing the delivery of radiation to vital healthy tissue.

The HI-ART System's planning station or operator station is intended to be used by the physician/oncologist to prescribe a radiation therapy plan for a particular patient. The HI-ART System then calculates the treatment plan which the physician reviews and approves.

The HI-ART system's operator station and status console is then intended to be used by the therapist to select and implement the patient's treatment plan. The treatment process will begin by performing a TomoImage™ (MVCT) scan (a CT using the onboard linear accelerator as the radiation source). This Tomolmage (MVCT) will confirm that the patient's position is correct for the radiation therapy as well as assist in patient repositioning when necessary. The Tomolmage (MVCT image) is not for diagnostic use.

When patient positioning is complete, the HI-ART System is then intended to be used by the therapist to treat the patient using the selected treatment plan. The HI-ART System delivers the radiation therapy, stereotactic radiotherapy or stereotactic radiosurgery treatment in accordance with the physician approved plan delivered in a helical tomographic pattern.

The TomoTherapy HI-ART System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT scanning, and helical radiation therapy treatment capabilities into a single comprehensive IMRT system.

The HI-ART System's planning station or operator station is used by the physician to prescribe and enter the radiation therapy plan. A diagnostic CT image imported via a DICOM protocol from another diagnostic CT device or a TomoImage (MVCT) scan is used as the basis for the plan. The regions of interest, regions to avoid, and other prescribing information are entered in a manner that is similar to other commercially available planning systems.

The HI-ART System utilizes a 6 MV linear accelerator as the radiation source. The linear accelerator along with the primary collimator, multi-leaf collimator (MLC), detector, various control devices and power supplies are mounted on a rotating gantry, much like a CT gantry. During treatment or imaging, the patient is positioned on the couch support, and the couch moves axially through the bore of the gantry, and the radiation is delivered in a helical pattern.

The primary collimator and the MLC control the beam dimensions during radiation delivery so that the range of collimated beam size can vary from 0 to 400 mm wide by 5 to 50 mm at the isocenter. The MLC is constructed of 64 tungsten leaves that open and close as determined by the radiation therapy plan. The intensity of the radiation beam is proportional to the length of time that a particular leaf is open. The opening and closing of various leaves as the radiation is delivered in this helical pattern allows for an IMRT plan to be delivered with precise control. The result is a highly conformal dose to the region of interest with low doses to surrounding healthy tissue.

Because the HI-ART System is operating in a helical mode similar to CT systems, it inherently has the ability to obtain a CT image. The system utilizes the linear accelerator to obtain a megavoltage (MVCT) scan of the region of interest prior to the delivery of radiation therapy. This MVCT image is then used to ascertain that the patient is correctly positioned prior to treatment. The radiation dose to the patient from an MVCT scan is comparable to diagnostic CT or portal imaging.

The provided text describes a medical device, the TomoTherapy HI-ART System®, which is a radiation therapy system. However, the document primarily focuses on regulatory approval (510(k) submission for substantial equivalence) and does not contain specific acceptance criteria or an in-depth study proving the device meets those criteria in the manner typically expected for AI/ML device evaluations (e.g., performance metrics like sensitivity, specificity, AUC).

Instead, the "Validation" section describes a more general approach, focusing on system functionality and compliance with safety standards rather than quantitative performance metrics against a defined ground truth for a diagnostic or AI-driven task.

Therefore, for aspects like "Table of acceptance criteria and reported device performance," "Sample size for the test set," "Number of experts for ground truth," "Adjudication method," "MRMC study," "Standalone performance," "Type of ground truth," "Sample size for training set," and "How ground truth for training set was established," the provided document does not contain this information.

It is important to note that this document is a 510(k) summary, which typically focuses on demonstrating substantial equivalence to a predicate device and compliance with general safety and performance principles, rather than presenting detailed clinical trial results or AI/ML performance metrics.

Here's a summary of what can be extracted or inferred from the provided text, along with the information that is not present:

Acceptance Criteria and Study for TomoTherapy HI-ART System® (modified)

1. Table of Acceptance Criteria and Reported Device Performance

• Planning
• Imaging
• Delivery
• Database Management
• DICOM Communications | "The HI-ART System was extensively validated for system functionality, including planning, imaging, delivery, database management, DICOM communications, etc."
  (Evaluation against IMRT phantoms, ion chambers, and other test phantoms.) |
  | Safety Compliance:
• IEC 60601-1 (Medical electrical equipment - General requirements for safety)
• IEC 60601-2-1 (Medical electrical equipment - Particular requirements for the safety of medical electron accelerators in the range 1 MeV to 50 MeV)
• IEC 60601-1-2 (Medical electrical equipment - Collateral standard: Electromagnetic compatibility - Requirements and tests)
• IEC 60601-1-4 (Medical electrical equipment - Collateral standard: Programmable electrical medical systems)
• EN ISO 14971:2000 (Medical devices - Application of risk management to medical devices) | "The HI-ART System is designed to comply with relevant sections of the IEC 60601-1, IEC 60601-2-1, IEC 60601-1-2, IEC 60601-1-4 safety standards and EN ISO 14971:2000."
  "Validation and verification testing of the HI-ART System demonstrates the device is safe and effective for its intended use." |
  | Intended Use Fulfillment:
• Integrated system for planning and delivery of IMRT.
• Precise radiation delivery to tumors/targeted tissues.
• Minimizing radiation delivery to vital healthy tissue.
• Physician/oncologist prescribes plan; system calculates; physician approves.
• Therapist selects/implements plan.
• TomoImage (MVCT) scan for patient positioning confirmation and repositioning assist (not for diagnostic use).
• Delivers radiation therapy, stereotactic radiotherapy, or stereotactic radiosurgery in helical tomographic pattern. | The conclusion states: "Validation and verification testing of the HI-ART System demonstrates the device is safe and effective for its intended use." This implicitly means it meets the stated intended uses. |
  | Substantial Equivalence: | "The HI-ART System with modifications is substantially equivalent to the HI-ART system [Predicate Device: K042739]." (As determined by the FDA.) |

Note: The document provides high-level statements about meeting safety standards and demonstrating safety/effectiveness for intended use, rather than specific numerical performance metrics for acceptance criteria.

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

• Not present in the document. The validation section mentions "IMRT phantoms, ion chambers and other test phantoms," which are physical objects rather than patient data. There is no mention of a test set of patient data, nor its provenance (country of origin, retrospective/prospective).

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

• Not present in the document. Since there is no mention of a patient-related test set or
  ground truth establishment using experts, this information is not applicable.

4. Adjudication method for the test set

• Not present 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 present in the document. This type of study is not mentioned. The device is a radiation therapy system, not an AI diagnostic tool for human reader improvement.

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

• Not present in the document. The device is an integrated system (planning, imaging, delivery) that is always used with human operators (physicians/oncologists and therapists). The concept of "standalone algorithm performance" (e.g., for a diagnostic AI) does not directly apply here. The system's imaging component (MVCT) is explicitly stated "is not for diagnostic use."

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

• Not present in the document in the context of patient data. For the system's "functionality validation," the ground truth seems to be derived from physical measurements using tools like "IMRT phantoms, ion chambers and other test phantoms" against expected physical radiation dose distributions and system behaviors.

8. The sample size for the training set

• Not present in the document. The document describes a radiation therapy delivery system, not a machine learning model that would typically have a "training set" of data.

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

• Not present in the document. (See point 8).

In conclusion, the provided FDA 510(k) summary focuses on regulatory compliance, system functionality, safety standards, and substantial equivalence to a predicate device for a radiation therapy system. It does not include the detailed performance metrics, patient data study designs, or AI/ML-specific validation information that would be expected for a diagnostic AI device.

Ask a specific question about this device

The TomoTherapy HI-ART System is intended to be used as an integrated system for the planning and delivery of intensity modulated radiation therapy (IMRT) for the treatment of cancer. The HI-ART System provides precise delivery of radiation to tumors while minimizing the delivery of radiation to vital healthy tissue.

The HI-ART System's planning station is intended to be used by the physician/oncologist to prescribe a radiation therapy plan for a particular patient. The HI-ART System then calculates the treatment plan which the physician reviews and approves.

The HI-ART system's operator station and status console is then intended to be used by the therapist to select and implement the patient's treatment plan. The treatment process will begin by performing a Tomolmage™ (MVCT) scan (a CT using the onboard linear accelerator as the radiation source). This TomoImage (MVCT) will confirm that the patient's position is correct for the radiation therapy as well as assist in patient re-positioning when necessary. The Tomolmage (MVCT image) is not for diagnostic use.

When patient positioning is complete, the HI-ART System is then intended to be used by the therapist to treat the patient using the selected treatment plan. The HI-ART System delivers the radiation therapy, or stereotactic radiotherapy or radiosurgery, treatment in accordance with the physician approved plan using IMRT techniques delivered in a helical tomographic pattern.

The TomoTherapy HI-ART System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT scanning, and helical radiation therapy treatment capabilities into a single comprehensive IMRT system.

The HI-ART System's planning station is used by the physician to prescribe and enter the radiation therapy plan. The patient's diagnostic CT image is imported via a DICOM protocol from another diagnostic CT device. The regions of interest, regions to avoid, and other prescribing information are entered in a manner that is similar to other commercially available planning systems.

The HI-ART System utilizes a 6 MV linear accelerator as the radiation source. The linear accelerator along with the primary collimator, multi-leaf collimator (MLC), detector, various control devices and power supplies are mounted on a rotating gantry. much like a CT gantry. During treatment or imaging, the patient is positioned on the couch support, and the couch moves axially through the bore of the gantry, and the radiation is delivered in a helical pattern.

The primary collimator and the MLC control the beam dimensions during radiation delivery so that the range of collimated beam size can vary from 0 to 400 mm wide by 5 to 50 mm at the isocenter. The MLC is constructed of 64 tungsten leaves that open and close as determined by the radiation therapy plan. The intensity of the radiation beam is proportional to the length of time that a particular leaf is open. The opening and closing of various leaves as the radiation is delivered in this helical pattern allows for an IMRT plan to be delivered with precise control. The result is a highly conformal dose to the region of interest with low doses to surrounding healthy tissue.

Because the HI-ART System is operating in a helical mode similar to CT systems, it inherently has the ability to obtain a CT image. The system utilizes the linear accelerator to obtain a megavoltage (MVCT) scan of the region of interest prior to the delivery of radiation therapy. This MVCT image is then used to ascertain that the patient is correctly positioned prior to treatment. The radiation dose to the patient from an MVCT scan is comparable to diagnostic CT or portal imaging.

Here's an analysis of the provided text regarding the acceptance criteria and study for the TomoTherapy HI-ART System (modified).

It's important to note that the provided documents are a 510(k) summary and the FDA's clearance letter. These documents primarily focus on demonstrating substantial equivalence to a predicate device and safety and effectiveness from a regulatory perspective. They generally do not contain detailed clinical study reports with specific acceptance criteria tables, sample sizes for test sets with ground truth, multi-reader multi-case studies, or detailed training set information as would be found in a full efficacy trial report.

Based on the provided text, the device's performance is demonstrated through its design and compliance with safety standards, and by showing substantial equivalence to a previously cleared device. There isn't a "study that proves the device meets the acceptance criteria" in the traditional sense of a clinical performance study with statistical endpoints outlined in the provided documents. Instead, the "acceptance criteria" are implied by the device's intended use and its compliance with relevant safety standards and technical specifications.

1. Table of Acceptance Criteria and Reported Device Performance

As mentioned, explicit quantitative acceptance criteria with reported performance metrics in a clinical study format are not present in these regulatory documents. The "acceptance criteria" are implied to be adherence to the specifications of an IMRT system for cancer treatment, safety, and functionality as described.

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

The provided documents do not describe a specific test set or clinical study with patient data (like images or clinical outcomes) used to prove performance in the way a diagnostic AI device would. The "test" for this device appears to be its engineering specifications, functional testing, and comparison to a predicate device. Therefore, information on sample size, country of origin, or retrospective/prospective nature of a clinical test set is not present.

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

Since there is no described clinical "test set" in the provided documents used to assess performance against a ground truth, this information is not available. The "ground truth" for a radiation therapy system is typically its ability to accurately deliver a planned dose to a target, which is assessed through physics measurements and phantom studies, rather than expert interpretation of images. The physician/oncologist reviews and approves the treatment plan, but this isn't a "ground truth" establishment for a device performance test in the diagnostic sense.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

Not applicable, as no clinical test set requiring expert adjudication is described in these documents.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

Not applicable. The TomoTherapy HI-ART System is a sophisticated radiation delivery system, not an AI-based diagnostic or assistive reading tool. Its purpose is to physically deliver radiation therapy, and while it has a "planning station" that "calculates the treatment plan," this is not presented as an AI assistance tool for human readers (e.g., radiologists, oncologists) in the typical MRMC study context. Thus, there is no mention of such a study or effect size.

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

This question typically refers to AI algorithms for diagnosis or analysis. The TomoTherapy HI-ART System is a physical medical device for treatment delivery. While parts of it involve calculation (treatment planning, dose calculation), its overall operation is described as intended for use by physicians and therapists, who ultimately review and approve plans and implement treatment. No "standalone algorithm-only performance" is described in the context of replacing human decision-making or interpretation.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

As discussed, a clinical "ground truth" in the diagnostic sense (like pathology for cancer detection) is not applicable here. The "ground truth" for a radiation therapy delivery system primarily revolves around:

• Physics measurements: Verification that the system delivers the prescribed radiation dose distribution accurately to a phantom.
• Engineering specifications: The device performs according to its design parameters.
• Safety standards: Compliance with international safety standards (e.g., IEC 60601 series).

The documents confirm compliance with safety standards and describe the physical mechanisms (MLC, helical delivery) that enable precise dose delivery, implying that the "ground truth" is that the system adheres to these technical and safety specifications.

8. The Sample Size for the Training Set

Not applicable in the context of these documents. This device is not an AI algorithm trained on a dataset of cases in the traditional sense. It is a physical treatment delivery system. The "training" would refer to the engineering and physics design, calibration, and testing of the components, not a machine learning training set.

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

Not applicable, for the reasons mentioned in point 8.

Ask a specific question about this device

The TomoTherapy HI-ART System is intended to be used as an integrated system for the planning and delivery of intensity modulated radiation therapy (IMRT) for the treatment of cancer. The HI-ART System provides precise delivery of radiation to tumors while minimizing the delivery of radiation to vital healthy tissue.

The HI-ART System's planning station is intended to be used by the physician/oncologist to prescribe a radiation therapy plan for a particular patient. The HI-ART System then calculates the treatment plan which the physician reviews and approves.

The HI-ART system's operator station and status console is then intended to be used by the therapist to select and implement the patient's treatment plan. The treatment process will begin by performing a TomoImage™ (MVCT) scan (a CT using the onboard linear accelerator as the radiation source). This TomoImage (MVCT) will confirm that the patient's position is correct for the radiation therapy as well as assist in patient re-positioning when necessary. The Tomolmage (MVCT image) is not for diagnostic use.

When patient positioning is complete, the HI-ART System is then intended to be used by the therapist to treat the patient using the selected treatment plan. The HI-ART System delivers the radiation therapy treatment in accordance with the physician approved plan using IMRT techniques delivered in a helical tomographic pattern.

The TomoTherapy HI-ART System is a radiation therapy system that integrates planning, dose calculation, megavoltage CT scanning, and helical radiation therapy treatment capabilities into a single comprehensive IMRT system.

The HI-ART System's planning station is used by the physician to prescribe and enter the radiation therapy plan. The patient's diagnostic CT image is imported via a DICOM protocol from another diagnostic CT device. The regions of interest, regions to avoid, and other prescribing information are entered in a manner that is similar to other commercially available planning systems.

The HI-ART System utilizes a 6 MV linear accelerator as the radiation source. The linear accelerator along with the primary collimator, multi-leaf collimator (MLC), xenon detector, various control devices and power supplies are mounted on a rotating gantry, much like a CT gantry. During treatment or imaging, the patient is positioned on the couch support, and the couch moves axially through the bore of the gantry, and the radiation is delivered in a helical pattern.

The primary collimator and the MLC control the beam dimensions during radiation delivery so that the range of collimated beam size can vary from 0 to 400 mm wide by 5 to 50 mm at the isocenter. The MLC is constructed of 64 tungsten leaves that open and close as determined by the radiation therapy plan. The intensity of the radiation beam is proportional to the length of time that a particular leaf is open. The opening and closing of various leaves as the radiation is delivered in this helical pattern allows for an IMRT plan to be delivered with precise control. The result is a highly conformal dose to the region of interest with low doses to surrounding healthy tissue.

Because the HI-ART System is operating in a helical mode similar to CT systems, it inherently has the ability to obtain a CT image. The system utilizes the linear accelerator to obtain a megavoltage (MVCT) scan of the region of interest prior to the delivery of radiation therapy. This MVCT image is then used in a non-diagnostic mode to ascertain that the patient is correctly positioned prior to treatment. The radiation dose to the patient from an MVCT scan is comparable to diagnostic CT or portal imaging.

Acceptance Criteria and Device Performance Study for the TomoTherapy HI-ART System

1. Table of Acceptance Criteria and Reported Device Performance:

The provided document (K033347) is a 510(k) summary for a modified TomoTherapy HI-ART System. As such, it does not explicitly state acceptance criteria in a quantitative table format with corresponding performance metrics as would typically be found in a detailed clinical study report. Instead, the document focuses on demonstrating substantial equivalence to a legally marketed predicate device (TomoTherapy Hi-Art System K013673) and confirming the device's safety and effectiveness for its intended use through extensive validation testing.

However, based on the information provided, we can infer the general areas of "acceptance criteria" through the descriptions of the device's intended function and the validation methods. The "reported device performance" is then described in broad terms as successful validation.

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

• Sample Size: The document does not specify a "test set" in terms of patient data. The validation relied on "test tools" such as "IMRT phantoms, ion chambers and other test phantoms" (Page 2). Therefore, the sample size refers to the number of tests performed using these phantoms, which is not quantified.
• Data Provenance: The study described is a device validation study performed by the manufacturer (TomoTherapy Incorporated). It is an internal, retrospective validation using specified test tools, not prospective clinical data from human subjects. The data is not from a specific country of origin in terms of patient population, as it involves phantoms.

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

• The document does not describe the use of "experts" to establish ground truth in the context of a clinical study or image review. The "ground truth" for the device's technical performance (e.g., dose delivery accuracy, image quality for positioning) was established through measurements with physical phantoms and established measurement devices (ion chambers).
• The validation process would have been overseen by engineers, physicists, and quality assurance personnel within TomoTherapy Incorporated, whose qualifications are not detailed in this summary but would be relevant to radiation therapy device development and testing.

4. Adjudication Method for the Test Set:

• No adjudication method (like 2+1, 3+1 consensus) is mentioned or applicable, as the validation was based on physical measurements of device output against established standards and expected performance, rather than human review of cases.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, What was the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance:

• No MRMC comparative effectiveness study was done. The HI-ART System is a radiation therapy delivery system, not an AI-assisted diagnostic or image interpretation tool for human readers in the traditional sense. Its "AI" or advanced component is the intensity-modulated radiation therapy (IMRT) plan calculation and delivery, which is integral to its function, not a separate assistance tool for human interpretation.

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

• The validation described is essentially a standalone performance assessment of the device's technical functionalities (planning, imaging, delivery, etc.) through testing with phantoms and measurements. The "algorithm only" aspect refers to the planning and dose calculation algorithms within the system, which were tested for accuracy and functionality.
• However, the device is explicitly designed for "human-in-the-loop" operation: a "physician/oncologist" prescribes the plan, reviews, and approves it, and a "therapist" selects and implements the plan, performs the MVCT scan, and treats the patient (Page 0, Intended Use). The validation ensures these components (algorithms and hardware) function correctly when used by qualified personnel as intended.

7. The Type of Ground Truth Used:

• The "ground truth" used for this validation study was physical measurements and established scientific principles related to radiation dose delivery, image quality for positioning, and system functionality. This involved:
  • IMRT phantoms: Used to simulate patient anatomy and allow for precise dose measurements in a controlled environment.
  • Ion chambers: Standard devices for measuring radiation dose, providing objective quantitative data.
  • Other test phantoms: For various aspects of system performance.
  • Compliance with IEC safety standards (Page 1).

8. The Sample Size for the Training Set:

• The concept of a "training set" in the context of machine learning or AI algorithm development is not directly applicable here. The document describes a traditional medical device validation for a radiation therapy system, not a study focused on a deep learning model. The system's design and algorithms would have been developed over time, incorporating engineering principles and potentially internal iterations and refinements, but not typically a discrete "training set" phase as seen in current AI development.

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

• As a "training set" is not explicitly mentioned or relevant in the context of this 510(k) summary for a modified radiation therapy system (not an explicit AI/ML device), the method for establishing its ground truth is not applicable to the information provided. The development of such a complex system would involve extensive engineering, physics, and clinical input during its design and optimization phases.

Ask a specific question about this device