Search Results

The VHA Radiotherapy Bolus product is a device that will be placed on the skin of a patient as a radiotherapy accessory intended to help control the radiation dose received by the patient. VHA Radiotherapy Boluses are designed by radiation therapy professionals for a unique patient and are intended to modify the shape of a beam from a radiation therapy source. The VHA Radiotherapy Bolus product must be verified and approved by the radiation therapy professional prior to use on a patient. The VHA Radiotherapy Bolus is intended for patients of all ages receiving radiotherapy treatment.

VHA Radiotherapy Bolus was evaluated using 6 MV photons and 9MeV electrons but has not been assessed for use with protons or at orthovoltage X-rays.

Boluses are used in external beam radiation therapy (EBRT) to change the depth of the radiation dose delivered, thereby overcoming the skin-sparing effect. Using clinical treatment planning software (TPS) and clinical expertise, a radiotherapy clinician designs the bolus to conform with the patient anatomy. The bolus is produced using additive manufacturing in a soft elastomeric material to conform to the patient's skin. The bolus is placed on the patient and verified for fit and acceptance to the clinical treatment plan prior to initiating treatment.

The provided text (P0-P6) is a 510(k) Premarket Notification from the FDA regarding the "VHA Radiotherapy Bolus" device. It primarily focuses on demonstrating substantial equivalence to a predicate device (VSP Bolus, K214093) rather than detailing a specific study proving the device meets acceptance criteria through algorithm performance. The device described is a patient-specific physical bolus created through 3D printing for radiotherapy, not an AI/ML algorithm.

Therefore, many of the requested details, such as sample size for test/training sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone algorithm performance, and how ground truth was established for training data, are not applicable to this document because the submitted device is a physical medical device, not a software algorithm requiring such clinical study designs.

However, I can extract information related to the acceptance criteria and performance testing that was conducted for this physical device.

Here's the analysis based on the provided text:

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

The document does not provide a quantitative table of acceptance criteria with specific performance metrics (e.g., accuracy, sensitivity, specificity) for the device itself. Instead, it states that the device's performance was evaluated through "Simulated use testing" and that "All acceptance criteria for performance testing were met." The nature of these acceptance criteria appears to be qualitative or based on successful functionality within the simulated environment.

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

• Sample Size for Test Set: Not specified. The document mentions "clinically relevant cases" for simulated use testing but does not provide a number or details about these cases.
• Data Provenance: Not applicable in the traditional sense for an AI/ML model's test set. The "testing" refers to physical performance and biocompatibility of the 3D-printed bolus.

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

Not explicitly stated or applicable for a physical device. The device is "designed by radiation therapy professionals" and "must be verified and approved by the radiation therapy professional prior to use on a patient." The "ground truth" for its performance would implicitly be its ability to correctly modify dose distribution per a treatment plan, which is verified by radiation therapy professionals.

4. Adjudication method for the test set

Not applicable as it's not a study involving human readers or AI output adjudication. The verification is done by a "radiation therapy professional" for the physical bolus.

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. Therefore, no MRMC comparative effectiveness study was conducted or is relevant.

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

Not applicable. This is a physical device, not an algorithm. Its function is to be placed on a patient.

7. The type of ground truth used

The "ground truth" for this device's performance is its ability to accurately alter the radiation dose distribution as intended by the radiation therapy professional's treatment plan. This is verified indirectly through "simulated use testing" and the requirement for verification by a "radiation therapy professional" via a CT scan prior to first treatment. It's not a 'ground truth' in the context of diagnostic imaging outcomes (e.g., pathology, clinical outcomes).

8. The sample size for the training set

Not applicable. This is a physical device, not an AI/ML algorithm that requires a training set.

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

Not applicable. This is a physical device, not an AI/ML algorithm that requires a training set and associated ground truth establishment.

Ask a specific question about this device

The 3D Systems VSP® Bolus product is a device that will be placed on the skin of a patient as a radiotherapy accessory intended to help control the radiation dose received by the patient. VSP Bolus is generated using input from radiation therapy professionals and medical imaging data to produce a bolus that is specific to the patient being treated. The VSP Bolus product is verified and approved by the radiation therapy professional prior to use on the patient, and is intended for patients of all ages receiving radiotherapy treatment.

VSP Bolus was evaluated using 6 MV photons but has not been assessed for use with protons. electrons, or at orthovoltage X-rays.

Boluses are used in external beam radiation therapy (EBRT) to change the depth of the radiation dose delivery to overcome the skin-sparing effect. The bolus is generated in accordance with a clinical treatment plan. The patient-specific bolus conforms to the patient anatomy to reduces airgaps for complex patient contours. The bolus is produced with additive manufacturing in a soft elastomeric material to conform to the patient's skin. The bolus is placed on the patient and verified for fit and accordance to the treatment plan prior to a radiation dose delivery to the patient.

The provided document is a 510(k) summary for the VSP® Bolus, a device used in radiation therapy. It does not describe an AI/ML device or a study comparing AI assistance with human readers. Therefore, I cannot extract information related to AI/ML specific acceptance criteria or an MRMC study from this document.

However, I can provide the acceptance criteria and performance data for the VSP® Bolus as described in the document.

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

The document does not explicitly list "acceptance criteria" in a quantitative format for the VSP® Bolus. Instead, it describes performance characteristics and validation activities demonstrating the device's fitness for clinical use and substantial equivalence to a predicate device. The performance is primarily assessed through simulated use testing and biocompatibility.

• Sensitization: Passed ISO 10993-10 (Guinea Pig Maximization Test)
• Irritation: Passed ISO 10993-10 (Primary Dermal Irritation Test)
• Patient Contact Materials: Biocompatible for intact skin contact. |
  | Simulated Use Testing | - Clinically relevant validation study performed.
• VSP Bolus was deemed fit for clinical use by radiation therapy professionals. |
  | Clinical Acceptance (Post-Manufacturing) | Each VSP® Bolus must be validated and approved by the radiation therapy professional through a CT scan prior to the first treatment fraction. |
  | Performance (General) | - Clinically oriented validation test cases were written and executed.
• VSP Bolus was deemed fit for clinical use by radiation therapy professionals. |
  | Intended Use | The device is placed on the skin of a patient to help control the radiation dose received, generated using input from radiation therapy professionals and medical imaging data to produce a patient-specific bolus. Verified and approved by professionals prior to use. Intended for patients of all ages receiving radiotherapy. |

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

The document states, "Clinically relevant validation study was performed." However, it does not specify the sample size for this simulated use test set, nor does it provide details on the data provenance (e.g., country of origin, retrospective or prospective nature of the simulated cases).

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 states that "VSP Bolus was deemed fit for clinical use by radiation therapy professionals." However, it does not specify the number of experts used or their specific qualifications (e.g., number of years of experience, specific certifications) for establishing this ground truth in the simulated use testing.

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

The document does not explicitly describe an adjudication method for the simulated use testing. It only states that the device was "deemed fit for clinical use by radiation therapy professionals," implying a consensus or approval process, but no specific adjudication method (e.g., 2+1, 3+1) is mentioned.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study in the document. This device (VSP® Bolus) is a physical, patient-specific bolus used in radiation therapy and does not involve AI assistance for human readers in its described function or evaluation.

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

The VSP® Bolus is a physical device, not an algorithm. Therefore, a standalone (algorithm-only) performance study is not applicable and was not performed. The device requires human input (radiation therapy professional input, DICOM data) for its design and human verification/approval (radiation therapy professional) prior to use.

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

For the simulated use testing, the ground truth was established by the judgment and approval of "radiation therapy professionals" who "deemed [the device] fit for clinical use." This can be considered a form of expert consensus or professional judgment.

8. The sample size for the training set

The document describes performance testing for a physical device and states, "Clinical testing was not performed as part of the development of this product." It refers to "clinically relevant validation study" and "simulated use testing." There is no mention of a training set in the context of machine learning or algorithm development, as this is not an AI/ML device.

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

As there is no mention of a training set or AI/ML components, this question is not applicable to the provided document.

Ask a specific question about this device

.decimal's Aperture manufacturing service manufactures the ring and solid core apertures for intensity modulation of external beam proton radiation therapy. The apertures are designed by the customer's treatment planning system to block radiation from hitting critical structures and healthy tissue while guiding the radiation to the targeted area.

The .decimal Proton Aperture is a Brass Core encased in a reusable steel ring (or material with similar attenuating properties) with a 2D hole cut from it, which defines the area that is to be treated with a proton beam. The design for a .decimal Proton Aperture is generated out of a customer's treatment planning system (TPS) or physician's specifications and is unique to each patient. The device functions as a beam shaping block. The apertures are inserted into the gantry's snout to shape and focus the beam as it exits the gantry en route to the targeted area. As radiation is passed through the gantry, the beam passes through aperture and it will be blocked. The opening of the aperture where there is no brass, the radiation will pass through targeted area defined by the radiation therapy professional.

The provided text does not contain specific acceptance criteria, reported device performance metrics, or details about a study that quantitatively measures the device's performance against such criteria.

The document states:

• "Clinical testing was not performed as part of the development of this product. Clinical testing is not advantageous in demonstrating substantial equivalence or safety and effectiveness of the device since testing can be performed such that no human subjects are exposed to risk. Clinically oriented validation test cases were written and executed in house by .decimal personnel where Proton Apertures were deemed safe and effective for clinical use. The tests show that .decimal Proton Apertures performed as well as the predicate device."
• The device is a ".decimal Proton Aperture," which is a physical device (a brass core encased in a steel ring) used to shape proton beams in radiation therapy. Its performance is related to its physical dimensions and ability to block radiation as designed by a treatment planning system.

Therefore, many of the requested categories of information are not present in the provided text, as this is a 510(k) summary for a physical medical device, not an AI/software-as-a-medical-device (SaMD) that typically relies on the detailed performance studies described in your query.

Here's an attempt to answer based on the available information, with many points noted as "Not applicable" or "Not provided":

1. Table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance
Not provided. The text mentions "clinically oriented validation test cases" but does not specify the sample size or their provenance. Given it's a physical device, these "test cases" likely refer to physical prototypes or manufactured units rather than patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. Ground truth as typically defined for AI/SaMD (e.g., radiologist consensus on images) is not relevant for this physical device. "Clinical use" and "safety and effectiveness" were "deemed" by ".decimal personnel."

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
Not applicable. No expert adjudication method is described 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
Not applicable. This is a physical radiation therapy beam-shaping block, not an AI system or software. No MRMC study was performed.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Not applicable. This is a physical device, not an algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable in the context of typical AI/SaMD studies. For this physical device, "ground truth" would relate to its manufacturing accuracy and material properties, ensuring it matches the design output from the TPS. The document states "clinically oriented validation test cases were written and executed in house by .decimal personnel." This implies internal testing against design specifications and functional requirements.

8. The sample size for the training set
Not applicable. This is not an AI/machine learning device. No "training set" in that sense was used.

9. How the ground truth for the training set was established
Not applicable, as no training set was used.

Ask a specific question about this device

The Cura Compensator is a solid, machine-shaped acrylic block intended to attenuate external radiation beam and block radiation from hitting critical structures and healthy tissue while allowing the radiation dose to the targeted area. The Cura Compensator may be used as an accessory whenever external beam radiation therapy is indicated for the treatment of patients with localized tumors or other conditions susceptible to treatment by radiation.

Cura Compensators are custom beam blocks with machined cutout to allow beam passage per prescription and sized to attenuate and block all remaining beam in the radiation field. The Compensator is made of acrylic or wax with notch to match radiation machine manufacturer use specifications. No software is included in this device.

I am sorry, but the provided text does not contain information about the acceptance criteria and the study that proves the device meets those criteria. The document is a 510(k) summary for a medical device called "Cura Compensator," which is a range compensator used in radiation therapy.

The document includes:

• Introduction and Premarket Notification Information: Contact details, product name, and submission type.
• Classification Information: Device classification, product code, CFR reference, and review panel.
• Predicate Device Information: Mentions two predicate devices.
• Intended Use/Indications for Use: Describes the purpose and application of the Cura Compensator.
• Summary Device Description: Details the material and function of the compensator.
• Summary of Technological Characteristics: Compares its features to the predicate device.
• FDA Correspondence: A letter from the FDA determining substantial equivalence to predicate devices.

However, it does not include:

• A table of acceptance criteria and reported device performance.
• Information about sample sizes for test sets, data provenance, or the number/qualifications of experts.
• Details on adjudication methods.
• Any mention of a multi-reader multi-case (MRMC) comparative effectiveness study or related effect sizes.
• Standalone algorithm-only performance.
• The type of ground truth used, sample size for the training set, or how ground truth was established for training.

Therefore, I cannot fulfill your request for this specific information based on the provided text.

Ask a specific question about this device

The Cura Collimator is a solid, machine-shaped brass aperture intended to shape an external radiation beam to block radiation from hitting critical structures and healthy tissue while guiding the radiation to the targeted area. The Cura Collimator may be used as an accessory whenever external beam radiation therapy is indicated for the treatment of patients with localized tumors or other conditions susceptible to treatment by radition.

Cura Collimators are custom beam blocks with machined cutout to allow beam passage per prescription and sized to snugly fit the applicator or nozzle and block all remaining beam in the radiation therapy fraction delivery. The Collimator is made of high lead content brass with notch orientation to match radiation manufacturer use specifications. No software is included in this device.

Here's a breakdown of the acceptance criteria and study information for the Cura Collimator, based on the provided text:

Acceptance Criteria and Device Performance

Study Information:

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

• Sample Size for Test Set: Not explicitly stated as a number. The text mentions "Treatment plans were created at Washington University," and "Cura manufactured the Cura Collmators, based upon the communicated treatment plan." This implies multiple treatment plans were used to generate multiple collimators for testing. However, a specific count is not provided.
• Data Provenance:
  • Country of Origin: United States (Washington University, St. Louis, Missouri).
  • Retrospective or Prospective: Not explicitly stated. The description "Treatment plans were created... and transmitted to Cura" suggests a prospective setup for the purpose of this testing, where specific plans were generated to test the collimator manufacturing process and beam delivery.

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)

• Number of Experts: Not explicitly stated. The text mentions "Washington University, who physically compared the Cura Collimators to the actual treatment plan and conducted beam tests," and "Mevion Medical Systems, Inc. for physical inspection and beam test." This indicates at least two entities were involved in verification.
• Qualifications of Experts: Not explicitly stated beyond "Washington University" and "Mevion Medical Systems, Inc." It can be inferred that personnel involved in radiation therapy at these institutions (e.g., medical physicists, radiation oncologists, dosimetrists) would be qualified to perform such evaluations, but specific titles or years of experience are not provided.

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

• Adjudication Method: Not explicitly described in terms of a formal adjudication process (like 2+1). The text states "Both Mevion and Washington confirmed the accuracy," suggesting independent verification and agreement, but no formal adjudication rule is mentioned.

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

• MRMC Comparative Effectiveness Study: No. This device is a physical medical device (radiation beam-shaping block), not an AI algorithm or a diagnostic tool that involves human readers interpreting data. Therefore, an MRMC study or assessment of human reader improvement with AI assistance is not applicable.

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

• Standalone Performance: Not applicable. This is a physical device, not a software algorithm. The "Cura Collimator" itself is the standalone product. The process involves a DICOM network transmission system and machine tools, but the primary device being evaluated is the physical collimator. The testing mentioned (material performance, machine tool adherence, network transmission integrity, beam accuracy) essentially evaluates the "standalone" performance of the manufactured collimator in fulfilling its function.

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

• Type of Ground Truth: The ground truth used was the "actual treatment plan." The manufactured Cura Collimators and the delivered beam line field were compared directly against these established treatment plans. This would involve precise measurements and physical comparisons to the prescribed radiation field.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable. This is not an AI/machine learning device that requires a training set. The device is manufactured based on design specifications and treatment plans, not trained on data.

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

• How Ground Truth for Training Set was Established: Not applicable, as there is no training set for this device.

Ask a specific question about this device

.decimal's Photon Block manufacturing service manufactures Photon Blocks for external beam photon radiation therapy. The Photon Block is designed by the customer's treatment planning system or physician specifications to block radiation from hitting critical structures and healthy tissue while guiding the radiation to the targeted area.

Photon Blocks are intended for use by healthcare professionals.

In IMRT therapy for cancer, a photon beam is aimed at the cancerous tissue using a linear accelerator. The linear accelerator is rotated around the patient while the patient lies on a treatment table; the linear accelerator consists of the gantry, which rotates around the patient. The gantry contains a collimator, which points at pre-determined positions to maximize efficiency and dose delivery to the tumor volume. Each gantry angle, or "port", requires custom-made, beam modifying, patient specific devices called: Photon Block.

The Photon Block is inserted into the gantry's collimator to shape and focus the beam as it exits the gantry en route to the targeted area. The photon block is also called a cerrobend block, which defines the area that is to be treated with the photon beam. Photon Blocks are generated out of the treatment planning system or physician's specifications and are unique to each patient and each gantry angle.

The .decimal Photon Block is a Cerrobend block (or material with similar attenuating properties) with a 2D pattern/hole made from it, which defines the area that is to be treated with a photon beam. The design for a .decimal Photon Block is generated out of a customer's treatment planning system (TPS) or physician's specifications and is unique to each patient. The device functions as a beam shaping block. The block fits into a customer's linear accelerator. As radiation is passed through the collimator, the beam passes through cerrobend and it will be blocked the opening of the photon block where there is no ccrrobend, the radiation will pass through targeted area defined by the radiation therapy professional.

The provided document describes the .decimal Photon Block, a device used in radiation therapy to shape and focus photon beams. It details the device's description, intended use, and indications for use, and also includes a 510(k) summary for regulatory approval.

However, the document explicitly states: "Clinical testing was not performed as part of the development of this product. Clinical testing is not advantageous in demonstrating substantial equivalence or safety and effectiveness of the device since testing can be performed such that no human subjects are exposed to risk."

Instead, the document mentions: "Clinically oriented validation test cases were written and excelled in house by .decimal personnel including a Board Certified Medical Physicist where Photon Blocks were deemed safe and effective for clinical medical. The tests show that .decimal Photon Blocks performed as well as the predicate device."

This indicates that the manufacturer performed non-clinical testing to demonstrate substantial equivalence to a predicate device (.decimal Electron Aperture K111759) rather than a study with acceptance criteria and a detailed performance report in the manner expected for a device proving its efficacy via clinical trials.

Therefore, most of the requested information regarding acceptance criteria, study details involving human subjects, ground truth, expert involvement, and sample sizes for test and training sets cannot be extracted from this document because such a study was explicitly not performed.

Here's what can be inferred or extracted based on the provided text, acknowledging the absence of a typical clinical study:

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

Since no specified acceptance criteria or detailed performance metrics from a formal clinical study are provided, this section cannot be completed as requested. The document only broadly states that the device "performed as well as the predicate device."

No specific acceptance criteria or performance metrics were detailed in the provided document, as no clinical study was performed.

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

• Sample size for test set: Not applicable, as no clinical test set was used. "Clinically oriented validation test cases" were performed in-house, but the sample size of these test cases is not specified, nor is their provenance.
• Data provenance: Not applicable. The validation was described as "in house."

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)

• Number of experts: The document mentions "in house by .decimal personnel including a Board Certified Medical Physicist." It doesn't specify if multiple experts were involved or just one for establishing ground truth for the validation test cases.
• Qualifications of experts: "Board Certified Medical Physicist." No years of experience are specified.

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

• Not applicable. The in-house validation did not describe a formal adjudication method.

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

• No MRMC comparative effectiveness study was done. The device described (Photon Block) is a physical beam-shaping device, not an AI-assisted diagnostic or therapeutic tool for human readers.

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

• Not applicable in the context of an algorithm. The device is a physical component. Its "performance" was likely assessed against physical specifications and its ability to shape the beam accurately, which would be a standalone evaluation of the physical device. The document mentions "validation test cases," suggesting a standalone performance evaluation of the device's manufacturing and function.

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

• For the "clinically oriented validation test cases," the ground truth was established by ".decimal personnel including a Board Certified Medical Physicist." This suggests an expert-driven assessment of whether the Photon Blocks met their design specifications and functioned correctly to achieve the intended beam shaping, likely comparing actual block dimensions and beam profiles against design specifications.

8. The sample size for the training set

• Not applicable, as this is a physical device and no machine learning model requiring a training set is described.

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

• Not applicable, as no machine learning model requiring a training set is described.

Ask a specific question about this device

Apex is an add-on microMLC system. It is an accessory to the linear accelerator used for radiation therapy and it is intended to shape the X-ray field both in static (fixed) or dynamic mode with rotating gantry as a function of the gantry angle. It is provided to assist the radiation oncologist to deliver radiation to the target tissue while sparing the surrounding normal tissues.

This Traditional 510(k) describes modifications made to the add-on DMLC accessory for the Elekta range of digital linear accelerators. The primary reason for these enhancements is to improve the leaf resolution - Apex 11 has a reduced leaf width of 2.5mm and increased field size. The add-on MLC Apel M consist of a 112 leaves individually controlled and monitored having a 2.5mm thickness at the isocenter and a field size of 120 mm x 140 mm.

The provided document {0} is a 510(k) summary for the Elekta Apex microMLC, an add-on accessory for linear accelerators used in radiation therapy. This submission focuses on modifications to improve leaf resolution (2.5mm leaf width and increased field size) compared to its predicate device, the DMLC IV (K001163). The core of the submission revolves around demonstrating substantial equivalence to the predicate device.

Based on the information provided, the document describes the device, its intended use, and its technological characteristics but does not contain information about specific acceptance criteria, performance studies, sample sizes, ground truth establishment, or comparative effectiveness studies (MRMC or standalone) in the manner typically associated with clinical performance evaluation of medical devices where diagnostic accuracy or similar metrics are assessed.

The document is a regulatory submission for a device that shapes radiation beams. The evaluation of such devices primarily focuses on their technical performance in shaping the beam accurately and safely, rather than a clinical study evaluating diagnostic accuracy or treatment efficacy as might be seen with an AI-powered diagnostic tool.

Therefore, for most of the requested points, the answer derived from the provided text will indicate that the information is "Not provided in the document."

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

Acceptance Criteria and Device Performance

Study Details

1. 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. The 510(k) summary provided here is a technical and regulatory declaration of substantial equivalence, not a report of a clinical performance study with a test set of data. The "study" mentioned mainly refers to the comparison against the predicate device based on technical specifications and functional equivalence.

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

   • Not applicable / Not provided in the document. There is no indication of a "test set" with a ground truth established by experts. The device's function is to shape radiation beams, and its performance is typically evaluated through engineering tests and phantom studies rather than expert-labeled clinical data.

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

   • Not applicable / Not provided in the document. No test set or expert adjudication is described.

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

   • No MRMC study was done, or at least, it is not mentioned in this document. This device is a radiation therapy accessory (a microMLC), not an AI-powered diagnostic tool that assists human readers. Its function is mechanical beam shaping.

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

   • Not applicable / Not provided in the document. The device is a physical component (microMLC) that operates as an accessory to a linear accelerator, not a standalone algorithm. Its performance is inherent to its mechanical and control accuracy.

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

   • Not applicable / Not provided in the document. No such "ground truth" as typically understood for diagnostic or prognostic AI devices is relevant or described for this device in this submission. The "ground truth" for a microMLC would relate to its physical accuracy in beam shaping, measured through dosimetry and mechanical verification, not clinical outcomes or expert consensus on clinical images/data.

7. The sample size for the training set:

   • Not applicable / Not provided in the document. This document describes a physical medical device, not an AI/ML algorithm that requires a training set.

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

   • Not applicable / Not provided in the document. As above, no training set or its associated ground truth is relevant or described for this device submission.

Ask a specific question about this device

Ask a specific question about this device

The Oncology Tech precision milled brass/aluminum compensators with tungsten fillings in the compensator walls are used for modulation of beam intensity during radiation therapy.

The Oncology Tech Mod1T Compensators for Radiation Beam Therapy are used for modulation of beam intensity during radiation therapy. Typically, a brass or aluminum round is used as a basis for the compensator. It is placed into the milling machine and worked into precise X, Y and Z dimensions. The new design of Oncology Tech Mod1T compensators mills out the compensator brass or aluminum walls and adds a high density material. The higher density of the fill material in the compensator walls provides for more attenuation and less radiation transmission at the field edges.

The provided text describes the Oncology Tech Mod1T Compensators for Radiation Beam Therapy and its substantial equivalence determination. However, it does not contain the specific details required to fully address your request regarding acceptance criteria and the study that proves the device meets those criteria.

Here's an analysis of what can and cannot be extracted from the provided document:

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

• Acceptance Criteria: The document implies an acceptance criterion related to "improvement of the attenuation under the compensator walls" and "greater attenuation of the photon beam at the field edge and less dose outside the field." However, no specific quantitative acceptance criteria or thresholds are stated.
• Reported Device Performance: The document states: "The measurement results show an improvement of the attenuation under the compensator walls for both the 6X and 18X beams. The addition of the high density fill to the compensator walls at the field edge provides greater attenuation of the photon beam at the field edge and less dose outside the field."
  • Quantitative results are referenced as being in "Appendix A, located within the step 20 clinical testing section of this submission," which is not provided in the input text. Without Appendix A, specific performance values cannot be extracted.

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

• Sample Size: The document mentions "Each compensator was irradiated." The number of compensators tested is not explicitly stated.
• Data Provenance: Not specified. The description of the testing procedure (linear accelerator, Sun Nuclear profiler) suggests a controlled laboratory setting, but the location, whether it was retrospective or prospective, etc., is not provided.

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

• Not applicable. This device is a physical compensator for radiation therapy. Its performance is measured directly (attenuation), not diagnosed by experts. Therefore, there is no "ground truth" established by experts in the context of diagnostic performance.

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

• Not applicable. As above, this is direct physical measurement, not a diagnostic assessment requiring adjudication.

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

• Not applicable. This is not an AI/diagnostic imaging device. It's a physical component used in radiation therapy.

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

• Not applicable. This is not an algorithm. The "study" described is a standalone physical measurement of the device's attenuation properties. The measurements were "recorded and compared to the brass compensator baseline."

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

• The "ground truth" or reference for comparison was the "brass compensator baseline." The goal was to show improvement over this baseline in terms of attenuation.

8. The sample size for the training set

• Not applicable. This is not a machine learning or AI device that requires a training set.

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

• Not applicable. As above.

Summary of available information:

Acceptance Criteria and Device Performance:

Study Details:

• Test Set Sample Size: Not explicitly stated (refers to "Each compensator").
• Data Provenance: Not specified (likely laboratory/controlled environment).
• Experts for Ground Truth: Not applicable (physical measurement).
• Adjudication Method: Not applicable.
• MRMC Study: Not applicable.
• Standalone Performance: Yes (physical measurement of device's attenuation properties).
• Type of Ground Truth: Comparison against "brass compensator baseline" (predicate device).
• Training Set Sample Size: Not applicable.
• Training Set Ground Truth Establishment: Not applicable.

Additional Study Information from the Text:

• Measurement Method: Sun Nuclear profiler in the transverse plane.
• Setup: Compensator locked in tray holder, linear accelerator gantry at 0°, collimator rotation at 0°.
• Irradiation: 100 monitor units of radiation.
• Comparison: Compared to a brass compensator baseline.

Ask a specific question about this device

Bolus Compensators are used by radiation therapy professionals for the treatment of cancer patients. They are designed by radiation therapy professionals for a unique patient and are intended to modify the shape of a beam from a radiation therapy source. Each Bolus Compensator must be validated and approved by the radiation therapy professional prior to use on a patient.

.decimal's Bolus Compensator manufacturing service manufactures the solid Bolus Compensators for intensity modulation of external beam radiation therapy. The Bolus Compensators are designed by the customer's treatment planning system to block radiation from hitting critical structures and healthy tissue while guiding the radiation to the targeted area.

This document is a 510(k) Premarket Notification summary for a device called "Bolus Compensator". The key information related to acceptance criteria and supporting studies is as follows:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics using an established format. Instead, it states that "Clinically oriented validation test cases were written and executed in house .decimal personnel including Board Certified Medical Physicists where Bolus Compensators was deemed fit for clinical use." This implies that the acceptance criteria were met by these in-house validation tests. The "intended use" section suggests the implicit performance criteria:

• Manufactures solid Bolus Compensators for intensity modulation of external beam radiation therapy.
• Designed by the customer's treatment planning system to block radiation from hitting critical structures and healthy tissue.
• Guides radiation to the targeted area.
• Must be validated and approved by the radiation therapy professional prior to use on a patient.

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

• Sample Size for Test Set: The document mentions "Clinically oriented validation test cases were written and executed in house." It does not specify the number of test cases (i.e., sample size).
• Data Provenance: The tests were "executed in house" by .decimal personnel. This indicates the data is retrospective and generated internally for validation purposes. The country of origin would be the United States, given the company's address is in Sanford, Florida, and the submission is to the FDA.

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

• Number of Experts: The document states "including Board Certified Medical Physicists." It does not specify the exact number of medical physicists involved.
• Qualifications of Experts: The experts were "Board Certified Medical Physicists." No further details on their experience (e.g., years of experience) are provided.

4. Adjudication Method for the Test Set

The document simply states that the Bolus Compensators "was deemed fit for clinical use" based on the in-house validation. It does not describe a formal adjudication method (like 2+1 or 3+1 consensus). The "Board Certified Medical Physicists" were involved in deeming the product fit, implying their expertise formed the basis of the determination, but not a specific multi-reader adjudication process.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed. The document explicitly states: "Clinical testing was not performed as part of the development of this product. Clinical testing is not advantageous in demonstrating substantial equivalence or safety and effectiveness of the device since testing can be performed such that no human subjects are exposed to risk." This implies that no study comparing human readers with and without AI assistance was conducted.

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

The device is a "Bolus Compensator manufacturing service" and the physical bolus compensator itself. It is a physical device, not an AI algorithm. Therefore, the concept of a "standalone (algorithm only) performance" study does not apply here. The validation focused on the physical characteristics and functional performance of the manufactured compensators.

7. The Type of Ground Truth Used

The ground truth was established by "Board Certified Medical Physicists" deeming the manufactured Bolus Compensators "fit for clinical use." This suggests a form of expert judgment/consensus on the functional suitability and accuracy of the manufactured devices based on the "clinically oriented validation test cases." It is not based on pathology, outcomes data, or patient-level clinical results, as no clinical testing with human subjects was performed.

8. The Sample Size for the Training Set

This device is a physical product (.decimal's Bolus Compensator manufacturing service manufactures the solid Bolus Compensators), not an AI algorithm trained on data. Therefore, the concept of a "training set" is not applicable in the context of machine learning.

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

As stated above, this is not an AI/machine learning device, so there is no training set or ground truth for a training set in the conventional sense. The "ground truth" equivalent would be the engineering specifications and performance expectations for the manufactured bolus compensators, which were assessed by medical physicists during an in-house validation process.

Ask a specific question about this device