Search Results

This device is indicated to acquire and display cross sectional volumes of the whole body, to include the head, with the capability to imaqe whole orqans in a sinqle rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire orqan. These volume sets can be used to perform specialized studies, usinq indicated software/hardware, of the whole organ by a trained and qualified physician.

FIRST 2.0 is an iterative reconstruction alqorithm intended to reduce exposure dose and improve high contrast spatial resolution for abdomen, pelvis, chest, cardiac and extremities applications.

Aquilion ONE Vision with FIRST 2.0 (CCRS-001B) V7.4 is a whole body multi-slice helical CT scanner, consisting of a gantry, couch and a console used for data processing and display. This device captures cross sectional volume data sets used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician. This system is based upon the technology and materials of previously marketed Toshiba CT systems. In addition, the subject device incorporates the latest iterative reconstruction technology, FIRST 2.0, intended to reduce exposure dose while maintaining and/or improving image quality.

The provided text describes a 510(k) premarket notification for a Computed Tomography (CT) system named Aquilion ONE Vision with FIRST 2.0 (CCRS-001B) V7.4. The documentation focuses on demonstrating substantial equivalence to a predicate device (Aquilion ONE Vision with FIRST 1.0) by updating an iterative reconstruction algorithm (FIRST 2.0).

Based on the provided document, here's a breakdown of the requested information:

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

The document does not explicitly state "acceptance criteria" in a numerical or pass/fail table format for clinical performance. Instead, it describes performance in terms of improvements or equivalency compared to the predicate device and filtered back projection (FBP).

• Contrast-to-noise ratio
• CT number accuracy
• Uniformity
• Slice sensitivity profile
• Modulation transfer function
• Line pair gauge
• Low contrast detectability
• Standard deviation of noise
• Noise power spectra. |
  | Diagnostic Quality | Representative diagnostic images reviewed by an American Board Certified Radiologist demonstrated that the device produces images of diagnostic quality and performs as intended. |

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

• Test Set Sample Size: The document mentions "Representative diagnostic images... including chest, abdomen and pelvis, extremity and cardiac exams." However, it does not specify the number of images or cases used for this review.
• Data Provenance: The document implies the data was collected from the device itself ("obtained using the subject device"). There is no information about the country of origin of the data or whether it was retrospective or prospective. Given it's a premarket submission for a new version of an existing device, it's likely part of internal validation testing.

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

• Number of Experts: "an American Board Certified Radiologist" – indicates one expert was used.
• Qualifications: "American Board Certified Radiologist" – this implies a board certification, which generally requires specific training, residency, and passing board examinations, demonstrating a certain level of expertise in radiology. The document does not specify the years of experience of this radiologist.

4. Adjudication method for the test set

• Since only one radiologist was used for the diagnostic image review, an adjudication method (like 2+1 or 3+1) was not applicable/performed. The single expert's review served as the assessment.

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 study was mentioned or performed as part of this submission. The evaluation was primarily focused on technical image quality metrics and a single radiologist's review of diagnostic image quality, not the impact on human reader performance with or without AI assistance. The "AI" here (FIRST 2.0) is an iterative reconstruction algorithm, which enhances image quality/dose reduction, rather than an AI-driven diagnostic aid that would typically warrant a comparative reader study.

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

• Yes, an algorithm-only (standalone) performance evaluation was done in terms of quantitative image quality metrics (e.g., contrast-to-noise ratio, spatial resolution, dose reduction claims) using phantoms.
• "A model observer evaluation" directly assessed the algorithm's performance in achieving "equivalent low contrast detectability" with reduced dose, which is a standalone assessment of the algorithm's output.

7. The type of ground truth used

• For quantitative image quality metrics and dose reduction claims: Phantoms (e.g., MITA-FDA phantom) were used to provide a known, controlled ground truth.
• For diagnostic image quality review: The "ground truth" was established by the expert opinion of an American Board Certified Radiologist who reviewed representative images for "diagnostic quality." This is essentially expert consensus (albeit from a single expert).

8. The sample size for the training set

• The document does not provide any information about the sample size used for training the FIRST 2.0 iterative reconstruction algorithm. This information is typically proprietary to the manufacturer and not required in this level of 510(k) summary.

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

• The document does not provide any information on how the ground truth for the training set (if any, as iterative reconstruction algorithms might use phantoms or specific patient data for training their models without needing human-labeled "ground truth" for diagnosis) was established. This detail is also not typically shared in a 510(k) summary.

Ask a specific question about this device

This device is indicated to acquire and display cross sectional volumes of the whole the head, with the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire organ. These volume sets can be used to perform specialized studies, using indicated software, of the whole organ by a trained and qualified physician.

FIRST 1.0 is an iterative reconstruction algorithm intended to reduce exposure dose and improve high contrast spatial resolution for chest (excluding cardiac), abdomen and pelvis applications. This algorithm is not intended for head or extremity applications.

Aquilion ONE Vision with FIRST 1.0 (CCRS-001A) is a whole body multi-slice helical CT scanner, consisting of a gantry, couch and a console used for data processing and display. This device captures cross sectional volume data sets used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician. This system is based upon the technology and materials of previously marketed Toshiba CT systems. In addition, the subject device incorporates the latest iterative reconstruction technology, FIRST 1.0, intended to reduce exposure dose while maintaining and/or improving image quality.

The provided text describes the Aquilion ONE Vision with FIRST 1.0 (CCRS-001A) CT system and its iterative reconstruction algorithm, FIRST 1.0. Here's an analysis of its acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Quantitative Dose Reduction Evaluation: A simulated body phantom (MITA-FDA phantom with a body ellipse surrounding it) was used. This indicates a phantom study, not human data.
• Artifact Reduction: A body phantom was used for truncation and streak artifact assessment. This indicates a phantom study.
• Image Quality Check: Existing clinical data was used. The specific sample size of clinical cases is not provided. The provenance of this clinical data (e.g., country of origin, retrospective/prospective) is not specified.

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

• For the "Image Quality Check" using existing clinical data, one American Board Certified Radiologist reviewed a representative diagnostic image set for chest, abdomen, and pelvis exams. Their specific years of experience are not provided, only that they are "American Board Certified."
• For the quantitative dose reduction and artifact reduction studies, phantoms were used, so expert ground truth establishment for patient images was not directly applicable.

4. Adjudication Method for the Test Set

• For the image quality check, with only one American Board Certified Radiologist reviewing images, there was no adjudication method (e.g., 2+1, 3+1) described.
• For the phantom studies, the assessment was based on objective measurements (e.g., model observer evaluation, image SD values) and visual comparison to AIDR 3D, and thus, an adjudication method for experts was not applicable.

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

• No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was explicitly described. The document mentions a single radiologist's review of diagnostic images and phantom studies. No comparison of human reader performance with and without AI assistance is presented.

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

• Yes, a standalone performance assessment was conducted for FIRST 1.0.
  • Quantitative Dose Reduction Evaluation: This was performed using a "model observer evaluation" on a phantom, indicating an algorithm-only assessment of low contrast detectability.
  • Image Quality Evaluation (Phantom Studies): Various CT image quality metrics (spatial resolution, CT number accuracy, contrast-to-noise ratio, noise properties, uniformity, slice sensitivity profile, low contrast detectability, standard deviation of noise) were measured using phantoms, which are objective algorithm-only assessments.
  • Artifact Reduction (Phantom Studies): Objective measures like image SD values and visual comparisons (implied to be algorithm output comparison) were made.

7. The Type of Ground Truth Used

• Phantom Measurements: For quantitative dose reduction, spatial resolution, CT number accuracy, CNR, noise properties, uniformity, SSP, low contrast detectability, and artifact reduction, the ground truth was derived from objective measurements on phantoms (e.g., MITA-FDA phantom, body phantoms).
• Expert Visual Confirmation: For the "Image quality check" using clinical data, the ground truth for "diagnostic quality" and "no significant artifacts and missing anatomical structures" was established by visual confirmation from a single American Board Certified Radiologist.

8. The Sample Size for the Training Set

• The document does not provide any information regarding the sample size used for training the FIRST 1.0 algorithm.

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

• The document does not provide any information regarding how the ground truth for the training set was established.

Ask a specific question about this device

This device is indicated to acquire and display cross sectional volumes of the whole the head, with the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire organ. These volume sets can be used to perform specialized studies, using indicated software, of the whole organ by a trained and qualified physician.

The Aquilion ONE Vision, TSX-301C/1, /2, /3, /4, /5, /6, /7, /8, v7.0 are whole body CT scanners that capture cross sectional volume data sets used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician. These systems are based upon the technology and materials of previously marketed Toshiba CT systems.

The provided document is a 510(k) summary for the Toshiba Aquilion ONE Vision CT system. While it details several modifications and general safety and testing procedures, it does not provide specific acceptance criteria or a comprehensive study report with quantitative performance metrics that would directly answer your request in the format you've outlined for acceptance criteria, sample sizes, and detailed ground truth establishment.

The document states that the submitter conducted "Risk analysis and verification/validation testing through bench testing" and "clinical evaluations" to demonstrate that the modifications meet requirements and perform as intended. However, the specific metrics, thresholds for acceptance, and detailed results are not provided in this summary.

Here's a breakdown of what can be inferred or is explicitly stated, and what is missing based on your request:

1. Table of Acceptance Criteria and Reported Device Performance:

This information is not provided in the document. The document mentions "image quality metric of AIDR 3D Enhanced versus current AIDR 3D is substantially equivalent to or better than the predicate device with regard to spatial resolution, CT number and contrast-to-noise ratio, noise properties and standard deviation of noise." It also states that SurekV selects appropriate kV and SEMAR functions similarly. However, no specific numerical acceptance criteria (e.g., "spatial resolution must be > X lp/cm") or reported performance values are given.

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

• Test Set Sample Size: Not explicitly stated. The document mentions evaluation "utilizing phantoms" for image quality metrics and "clinical evaluations" for new applications. However, the number of phantoms or clinical cases is not specified.
• Data Provenance (country of origin, retrospective/prospective): Not explicitly stated. Given the nature of a 510(k) submission and the description of "clinical evaluations," it's likely conducted with clinical data, but whether it's retrospective or prospective, or the origin, is not mentioned.

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

Not explicitly stated. For the "clinical evaluations" of the new applications (4D Orthopedic Analysis and 4D Cerebral Artery Morphological Analysis), the document states that results "were comparable to manual measurements and/or segmentations." This implies expert involvement for these manual processes, but the number and qualifications of these experts are not detailed.

4. Adjudication Method for the Test Set:

Not explicitly stated. Since the number of experts and how "ground truth" was established for clinical evaluations is vague, the adjudication method is also not mentioned.

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

No, an MRMC comparative effectiveness study is not mentioned. The document describes a comparison of the modified device's performance against the predicate device and against "manual measurements and/or segmentations" for clinical applications. There's no indication of a study involving human readers' performance with and without AI assistance (as this is a CT scanner, not a diagnostic AI software).

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

Yes, a form of standalone performance evaluation was done. The testing for image quality metrics (spatial resolution, CT number, CNR, noise) using phantoms, and the confirmation that SurekV selects appropriate kV and SEMAR functions similarly, are examples of standalone algorithm/system performance evaluation.

7. The Type of Ground Truth Used:

• For image quality metrics (spatial resolution, CT number, CNR, noise): Phantom-based measurements. Phantoms represent a known, objective standard.
• For clinical evaluations of new applications (4D Orthopedic Analysis and 4D Cerebral Artery Morphological Analysis): Comparison to "manual measurements and/or segmentations." This suggests expert-derived ground truth, though the specifics are lacking.

8. The Sample Size for the Training Set:

Not applicable/Not provided. This document is for a CT scanner, which is hardware, with software modifications including image reconstruction (AIDR 3D Enhanced) and new clinical applications. While these might have internal "training" or calibration components, the concept of a "training set" in the context of a learning algorithm for diagnostic decision support is not highlighted or described. The focus is on verifying the performance of the modified system.

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

Not applicable/Not provided. (See point 8).

In summary, the provided 510(k) document is a regulatory summary focusing on demonstrating substantial equivalence to predicate devices and adherence to safety standards. It does not contain the detailed study protocols, acceptance criteria, and quantitative performance results typically found in full clinical or technical study reports.

Ask a specific question about this device

Optional movable gantry base unit for use with an Aquilion ONE (TSX-301C) system to support longitudinal movement and allow acquisition of images in the z-direction (Z-axis).

Note: When installed with the movable gantry base unit, Aquilion ONE can be used with the INFX-8000C system in the same room.

The Aquilion ONE Vision Self-Propelled Scan Base Kit for IVR-CT, CGBA-033A is an optional kit intended to be used in conjunction with an Aquilion ONE Vision / INFX-8000C based IVR-CT system. The subject device is attached to the CT gantry to support longitudinal movement and allow image acquisition in the z-direction (Z-axis), both axial and helical. When this option is selected, the standard CT patient couch is replaced with the patient handling system utilized by the interventional x-ray system, Toshiba INFX-8000C. The intended uses and technological characteristics of the Aquilion ONE Vision CT System and INFX-8000C Interventional X-Ray System with which this device is used, remain the same.

I am sorry, but the provided text does not contain the detailed information required to describe the acceptance criteria and the study that proves the device meets them in the format you requested.

The document is a 510(k) premarket notification for an accessory to a Computed Tomography (CT) system (an optional movable gantry base unit). It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a clinical study with acceptance criteria for device performance in detecting or diagnosing conditions, which is typically what your request implies.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• Acceptance Criteria Table and Device Performance: The document describes the device's function (supporting longitudinal movement and allowing image acquisition in the z-direction) and notes modifications from a predicate device. It does not provide specific performance metrics (e.g., sensitivity, specificity, accuracy, resolution) with numerical targets that would constitute acceptance criteria, nor does it present "reported device performance" in that context.
• Sample Size, Data Provenance, Experts, Adjudication, MRMC, Standalone Performance: These items are relevant for studies evaluating diagnostic or prognostic accuracy, often involving image interpretation by human readers or an algorithm. This document describes a hardware accessory for a CT system, and the "testing" mentioned is primarily engineering verification and validation (bench testing) to ensure that the modifications function as intended and meet safety standards. There's no indication of a clinical study involving patients, image interpretation, or ground truth establishment in the manner your questions suggest.
• Type of Ground Truth: Since there's no clinical study described, there's no ground truth (pathology, expert consensus, outcomes data) discussed.
• Training Set Sample Size and Ground Truth Establishment (for training set): These questions are relevant for AI/ML-based devices. The device described here is a hardware accessory for a CT system, not an AI/ML algorithm.

What the document does provide regarding "testing" (which is more about engineering validation than clinical performance):

• Non-Clinical Tests: "This submission includes summary tables detailing the risk analysis and verification/validation testing conducted through bench testing which demonstrates that the requirements for the modifications made to the system have been met. Evaluation of the modified device included, but was not limited to, confirmation that base movement speed, scanogram and axial/helical scan functions, and interlocks including contact detection, performed according to specifications."
• Software Documentation: "Software Documentation for a Moderate Level of Concern, per the FDA guidance document, 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices Document' issued on May 11, 2005, is also included as part of this submission."
• Standards Compliance: "Additionally, testing of the modified system was conducted in accordance with the applicable standards published by the International Clectrotechnical Commission (IEC) for Medical Devices and CT Systems."

In summary, the provided text describes a regulatory submission for a hardware component where the "evidence" is primarily engineering verification and validation against design specifications and international safety standards, not a clinical study assessing diagnostic performance against specific acceptance criteria.

Ask a specific question about this device

This device is indicated to acquire and display cross sectional volumes of the whole body, to include the head, with the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire organ. These volume sets can be used to perform specialized studies, using indicated software/hardware, of the whole organ by a trained and qualified physician.

The Aquilion ONE Vision, TSX-301C/3 and 301C/4, v6.00 are 320-row CT Systems and the TSX-301C/5, v6.00 is a 160-row CT system consisting of the same gantry, couch and console used for data processing and display. These devices capture cross sectional volume data sets used to perform specialized studies, using indicated software, by a trained and qualified physician. These systems are based upon the technology and materials of previously marketed Toshiba CT systems.

The provided 510(k) summary focuses on demonstrating substantial equivalence of a modified CT system (Aquilion ONE Vision, TSX-301C/3, 301C/4 and 301C/5, v6.00) to its predicate device. This submission is for a hardware and associated software modification to an existing CT scanner, not a new AI/CADe device. Therefore, many of the typical acceptance criteria and study elements pertinent to AI systems that you requested are not directly applicable or explicitly detailed in this document.

However, I can extract the information that is present and explain why some of your requested details might not be found in this type of submission.

1. Table of Acceptance Criteria and Reported Device Performance

For this type of device modification, the "acceptance criteria" are generally related to demonstrating that the modified device performs at least as well as the predicate device in terms of image quality and safety, and continues to meet relevant standards. The performance is assessed through various tests, primarily utilizing phantoms and review by an expert.

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

• Sample Size for Test Set: The document mentions "representative diagnostic images" but does not specify a numerical sample size for the clinical image review. This type of submission often relies on a qualitative assessment of a small, representative set of images rather than a large statistical study.
• Data Provenance: Not explicitly stated (e.g., country of origin). Since it's a Toshiba America Medical Systems submission, the testing would likely have occurred in the US or Japan. The assessment of diagnostic images by an "American Board Certified Radiologist" suggests at least some of the data review, if not acquisition, was US-based.
• Retrospective or Prospective: Not specified. Given the nature of a device modification test, it could involve prospective acquisition of new images for evaluation, or retrospective review of images acquired with the modified device.

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

• Number of Experts: "an American Board Certified Radiologist" (singular).
• Qualifications: "American Board Certified Radiologist." The duration of experience is not specified.

4. Adjudication method for the test set

• Adjudication Method: Not applicable or specified. With only one radiologist reviewing, there is no inter-reader discrepancy to adjudicate.

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 Study: No, an MRMC comparative effectiveness study was not done. This device is a CT scanner itself, not an AI/CADe accessory intended to assist human readers in image interpretation. Therefore, assessing human reader improvement with/without "AI assistance" is not relevant to this submission.

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

• Standalone Performance: Not applicable. This is a conventional CT imaging system, not an algorithm being evaluated for standalone performance. The "softwar" mentioned refers to control software and image processing pathways within the CT system, not an independent AI diagnostic algorithm.

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

• Type of Ground Truth: For the image quality assessment, the "ground truth" was the qualitative judgment of an "American Board Certified Radiologist" that the images were of "diagnostic quality" and that the device "performs as intended." For the phantom studies, the ground truth is against known physical properties and measurements within the phantoms, assessed by quantitative metrics (spatial resolution, CT number, CNR, noise, uniformity).

8. The sample size for the training set

• Sample Size for Training Set: Not applicable/not provided. This submission is for a hardware and control software modification to a CT scanner. The concept of a "training set" in the context of machine learning (AI) does not apply here. The system's performance is based on engineered design and physical principles, not on being trained on a dataset of images with ground truth labels.

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" in the AI sense for this device. The system's operational parameters and calibration are established through design specifications, factory calibration, and quality control processes.

In summary: This 510(k) submission is for a modification to a general-purpose CT imaging system. The performance evaluation focuses on demonstrating that the modified hardware and software maintain or improve the fundamental imaging capabilities and safety profiles compared to the predicate device, primarily through phantom testing and qualitative clinical image review by a radiologist. It does not involve the a-typical AI/CADe specific study designs and ground truth methodologies you would expect for an AI-powered diagnostic tool.

Ask a specific question about this device

This device is indicated to acquire and display cross sectional volumes of the whole body, to include the head, with the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire organ. These volume sets can be used to perform specialized studies, using indicated software/hardware, of the whole organ by a trained and qualified physician.

The Aquillion ONE Vision TSX-301C/1 and TSX-301C/Z, v6.00 is a whole body CT scanner. This device captures cross sectional volume data sets. The device consists of a gantry, patient couch (table) and peripheral cabinets used for data processing and display. These systems are based upon the technology and materials of previously marketed Toshiba CT systems.

The provided text describes a 510(k) summary for the Aquilion ONE Vision CT scanner (K132222) and its modifications. However, it does not contain information about specific acceptance criteria or a study proving the device meets them with performance metrics related to diagnostic accuracy, sensitivity, or specificity.

The document states that the submission includes "summary tables detailing the risk analysis and verification/validation testing conducted through bench testing which demonstrates that the requirements for the modifications made to the system have been met." It also mentions "successful completion of software validation" and compliance with various IEC, NEMA, and CFR standards.

This kind of 510(k) submission, particularly a "Special 510(k)" for modifications to a cleared device, often focuses on demonstrating that the changes do not adversely affect safety and effectiveness, and that the device still meets the performance specifications of the predicate device. It typically doesn't involve new clinical performance studies to establish acceptance criteria for diagnostic accuracy metrics in the same way a de novo device or a device with new clinical claims might.

Therefore, many of the requested categories related to clinical performance studies (e.g., sample size for test sets, number of experts for ground truth, MRMC studies, standalone performance) cannot be extracted from this document as such studies are not described.

Here's an attempt to answer the questions based only on the provided text, indicating where information is not available:

1. Table of Acceptance Criteria and Reported Device Performance

Not available in the provided text. The document refers to "requirements for the modifications" and "applicable standards" but does not define specific clinical acceptance criteria (e.g., sensitivity, specificity, accuracy) or report device performance against such metrics. The changes are primarily technical (OS change, image quality improvements, dose reduction availability, addition of previously cleared software).

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

Not available in the provided text. The document mentions "bench testing" and "software validation" but does not specify a test set of patient data or its characteristics.

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

Not available in the provided text.

4. Adjudication method for the test set

Not available in the provided text.

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/Not mentioned. The device is a CT scanner, and the modifications are largely technical and do not appear to involve AI-assisted reading or a direct comparison of human reader performance with and without AI.

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

Not applicable/Not mentioned. The device is a CT scanner, not a standalone algorithm.

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

Not available in the provided text.

8. The sample size for the training set

Not applicable/Not mentioned. There is no mention of a training set for an algorithm in this document. The "training" for a CT scanner typically refers to system calibration and quality control, not machine learning model training.

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

Not applicable/Not mentioned.

Summary of what the document DOES state regarding testing and safety:

• The device is designed and manufactured under Quality System Regulations (21 CFR § 820) and ISO 13485 Standards.
• It conforms to applicable Performance Standards for Ionizing Radiation Emitting Products [21 CFR, Subchapter J, Part 1020].
• It complies with various IEC and NEMA standards (IEC60601-1 series, IEC60601-2-x series, IEC60825-1, IEC62304, IEC62366, NEMA PS 3.1-3.18, NEMA XR-25, NEMA XR-26).
• A "Special 510(k) submission includes summary tables detailing the risk analysis and verification/validation testing conducted through bench testing which demonstrates that the requirements for the modifications made to the system have been met."
• "Software Documentation for a Moderate Level of Concern" was included.
• "Testing of the modified system was conducted in accordance with the applicable standards published by the International Electrotechnical Commission (IEC) for Medical Devices and CT Systems."
• Conclusion: "Based upon bench testing, successful completion of software validation, application of risk management and design controls, it is concluded that the subject device is safe and effective for its intended use."

In essence, the document confirms that the modified CT scanner underwent rigorous engineering and software validation according to established industry standards and regulatory requirements, demonstrating that the modifications did not compromise the device's safety or effectiveness compared to the predicate device. However, it does not provide specific clinical performance metrics or studies as might be expected for an AI-powered diagnostic device.

Ask a specific question about this device

This device is indicated to acquire and display cross sectional volumes of the whole body, to include the head, with the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, pancreas, etc.

The Aquilion ONE has the capability to provide volume sets of the entire organ. These volume sets can be used to perform specialized studies, using indicated software/hardware, of the whole organ by a trained and qualified physician.

The Aquilion ONE Vision, TSX-301C/1, v4.90 is a whole body CT scanner. This device captures cross sectional volume data sets. The device consists of a gantry, patient couch (table) and peripheral cabinets used for data processing and display.

The provided text is a 510(k) summary for the Toshiba Aquilion ONE Vision CT scanner. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study to prove acceptance criteria for a new feature or algorithm. Therefore, many of the requested sections (sample size, expert qualifications, adjudication method, MRMC study, standalone performance, ground truth details, training set size) are not applicable or cannot be extracted from this type of regulatory submission.

Here's an analysis of the available information:

Acceptance Criteria and Device Performance

The submission focuses on demonstrating substantial equivalence to a predicate device by comparing technical specifications. The "acceptance criteria" here are implicitly that the new device meets or exceeds the performance of the predicate device for critical technical specifications, which in turn supports the claim that the indications for use and safety/effectiveness remain unchanged.

Table of Acceptance Criteria and Reported Device Performance

Summary of Changes:

1. Increased rotational speed from 350mS to 275mS.
2. X-ray Generator changed to match dose at new speed.
3. Tube has hardware enhancements to allow for higher rotational speed.
4. View rates have been increased.

Study Proving Device Meets Acceptance Criteria:

The submission does not describe a clinical study. Instead, it relies on technical testing and comparison to a predicate device to demonstrate substantial equivalence and adherence to safety standards.

• 17. TESTING: "Image Quality metrics utilizing phantoms are provided in this submission. Additionally, testing of the modified system was conducted in accordance with the applicable standards published by the International Electrotechnical Commission (IEC) for Medical Devices and CT Systems."

This indicates that internal performance testing, likely using phantoms, was conducted to verify the changes and ensure image quality, and that the system conforms to relevant IEC standards for safety and performance. The specific details or results of these phantom tests are not included in this summary.

Additional Information Not Available in the Provided Text:

2. Sample size used for the test set and the data provenance: Not applicable, as no human subject test set or clinical study is described. The performance data is derived from technical specifications and phantom testing.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as there is no human subject test set requiring expert ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not applicable. This device is a CT scanner, not an AI-powered diagnostic tool requiring reader performance evaluation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The submission focuses on hardware and core software modifications of a CT scanner, not on a standalone algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable, as the "ground truth" for this submission are the technical specifications and performance of the predicate device, against which the modifications are compared.
8. The sample size for the training set: Not applicable, as this is a CT scanner modification, not an AI model training.
9. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device