Search Results

The Low Dose CT Lung Cancer Screening Option for Canon/Toshiba CT systems is indicated for using low dose CT for lung cancer screening. The screening must be conducted with the established program criteria and protocols that have been approved and published by a governmental body, a professional medical society and/or Canon.

Information from professional societies related to lung cancer screening can be found, but is not limited to: American College of Radiology® (ACR)-resources and technical specification; accreditation American Association of Physicists in Medicine (AAPM) - Lung Cancer Screening Protocols; radiation management.

The low dose lung cancer screening option is an indication being added to the following existing, previously FDA-cleared scanners: [List of Aquilion and Lightning CT scanner models and their corresponding 510(k) numbers]. No functional, performance, feature, or design changes are being made to the devices that will be indicated for low dose lung cancer screening. The devices already include low dose lung screening protocols, intended for use in the review of thoracic CT images within the established inclusion criteria of programs/protocols that have been approved and published by either a governmental body or professional medical society.

The provided text describes a 510(k) premarket notification for a "Low Dose CT Lung Cancer Screening Option" from Canon Medical Systems Corporation. The submission seeks to add this indication to existing, previously FDA-cleared CT scanners. The key claim is substantial equivalence to a predicate device (Aquilion RXL, K121553, which is a successor to the Aquilion 16 used in the National Lung Screening Trial - NLST). The device's performance is demonstrated through bench testing only, not a clinical study involving human subjects or AI-assisted readings.

Therefore, the following information can be extracted/inferred:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that performance was "substantially equivalent" to the predicate. Specific numerical values for the reported performance are not provided in this regulatory summary.

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

• Test Set Sample Size: Not applicable in the traditional sense of a clinical test set with patient data. The "test set" consists of bench testing data from representative scanners from different CT system families. One device from each of the three identified families (Aquilion 16/32/64/RXL, PRIME/PRIME SP, ONE/ViSION/Genesis, and Lightning) was used for bench testing.
• Data Provenance: The data is from bench testing performed by Canon Medical Systems Corporation. The document does not specify the country of origin for this bench testing data, but the manufacturer is Canon Medical Systems Corporation (Japan) with a U.S. agent. The original NLST data (which the predicate is compared against) was from a large-scale, prospective clinical trial conducted in the United States.

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

Not applicable. This submission relies on bench testing for substantial equivalence, not a clinical study requiring expert ground truth for image interpretation.

4. Adjudication Method for the Test Set

Not applicable, as no human readers or clinical image interpretation were part of the presented performance data.

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 submission is for a CT scanner's indication for low-dose lung cancer screening, not an AI-powered diagnostic assist device. The performance demonstration is based on the physical imaging characteristics of the CT system.

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

Not applicable. This is for a CT imaging device, not a standalone algorithm.

7. The Type of Ground Truth Used

The "ground truth" for this substantial equivalence argument is the performance of the predicate device (Aquilion RXL), which is stated to have similar technological characteristics and performance equivalent to the Aquilion 16 used in the NLST. The "ground truth" for the benefit of low-dose CT lung cancer screening itself comes from clinical literature, specifically referencing the National Lung Screening Trial (NLST) results, which demonstrated reduced mortality from lung cancer with low-dose CT screening. However, the device's performance itself is measured against established phantom-based image quality metrics.

8. The Sample Size for the Training Set

Not applicable. This is a CT imaging device, not an AI/ML algorithm that requires a training set of data.

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

Not applicable.

Ask a specific question about this device

The Angio Workstation (XIDF-AWS801) is used in combination with an interventional angiography system (Infinix-i series systems and INFX series systems) to provide 2D and 3D imaging in selective catheter angiography procedures for the whole body (includes heart, chest, abdomen, brain and extremity).

When XIDF-AWS801 is combined with Dose Tracking System (DTS), DTS is used in selective catheter angiography procedures for the heart, chest abdomen, pelvis and brain.

The XIDF-AWS801 Angio Workstation is used for images input from Diagnostic lmaging System and Workstation, image processing and display. The processed images can be outputted to Diagnostic Imaging System and Workstation.

This document is a 510(k) premarket notification for the Toshiba Medical Systems Corporation's XIDF-AWS801, Angio Workstation, v5.31. It describes an update to an existing device rather than a de novo submission. Therefore, it primarily focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study proving the device meets specific acceptance criteria in the same way a new device with novel claims would.

However, based on the provided text, I can infer and extract some information relevant to your request, particularly regarding the additional software features introduced in this version (Left Atrium Segmentation, Parametric Images, and MAR – Metal Artifact Reduction). The document states that "Testing was performed using archived clinical images, simulation testing and bench (phantom) testing."

Here's an attempt to answer your questions based on the available information, noting where specific details are not provided in this 510(k) summary:

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

The document does not explicitly state quantitative acceptance criteria or detailed performance metrics for the new software features. The overarching "acceptance criterion" for this 510(k) submission is that the modifications (new software features) retain the safety and effectiveness of the cleared predicate device.

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

• Sample Size: Not specified in the summary. The text mentions "archived clinical images" and "data sets."
• Data Provenance: The data used for testing included "archived clinical images" as well as "simulation testing and bench (phantom) testing." The country of origin for the clinical images is not specified. "Archived clinical images" suggests the data was retrospective.

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)

This information is not provided in the summary. Given the context of a 510(k) amendment for new software features that are "not intended for stand-alone use or diagnosis" but rather to provide "information that is to be used in adjunct to the normal images," it's possible that formal expert consensus for ground truth on a large test set was not a primary focus for this specific submission's documented testing, or the details were not included in the public summary.

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

This information is not provided in the summary.

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

A multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned in the summary. The document focuses on the technical performance verification of the new features and their substantial equivalence, not on human reader performance with or without the device. The new software is explicitly stated as "not intended for stand-alone use or diagnosis" and is instead "to provide the user with information that is to be used in adjunct to the normal images."

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

Yes, testing was done on the algorithms (the new software features). The summary states "Testing was conducted using bench (phantom) tests, simulations and archived images data sets. The results of this testing verified that the performance of the changes was within the specified requirements." This indicates a standalone evaluation of the software's output, as distinct from evaluating human performance. However, it also states the software is "not intended for stand-alone use or diagnosis."

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

The specific type of ground truth for the "archived clinical images" is not specified. For bench and simulation testing, the 'ground truth' would typically be defined by the known parameters of the phantom or simulated data.

8. The sample size for the training set

This information is not provided in the summary. The document mentions "archived clinical images" were used for testing, but it doesn't discuss a separate training set for the development of the algorithms.

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

Since a training set size or its use isn't specified, how its ground truth was established is also not provided.

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.

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

The Aquilion PRIME TSX-303A/A and /B, v6.00 are 80-row CT Systems and the TSX-303A/F, v6.00 is a 40-row CT system that is intended to produce axial scans of the whole body to include the head. These systems are based upon the technology and materials of previously marketed Toshiba CT systems.

This document is a 510(k) premarket notification for a Computed Tomography (CT) system, the Aquilion PRIME, v6.00. As such, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study with specific acceptance criteria and performance metrics in the way one might expect for a novel AI-powered diagnostic device.

Therefore, the information regarding "acceptance criteria" and the "study that proves the device meets the acceptance criteria" is framed within the context of demonstrating equivalence and safety/effectiveness for a hardware/software update to an existing CT system, rather than a standalone performance study with clinical endpoints.

Here's an attempt to extract the closest available information based on your request, acknowledging that the format and detail for a conventional "acceptance criteria" study are not fully present in this type of submission.

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

Based on the document, the "acceptance criteria" are implied by demonstrating substantial equivalence to the predicate device and meeting regulatory standards for CT systems. The "reported device performance" is described in terms of improved imaging properties and diagnostic quality.

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

• Test Set Sample Size: Not explicitly stated as a number of patients or cases. The document mentions "representative diagnostic images" but does not quantify them.
• Data Provenance: Not specified. It's likely that the "representative clinical images" were obtained during internal testing or pilot sites, but no details on country or retrospective/prospective nature are provided.

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: "an American Board Certified Radiologist" (singular).
• Qualifications of Experts: "American Board Certified Radiologist." No specific experience level (e.g., 10 years) is mentioned.

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

• Adjudication Method: "Reviewed by an American Board Certified Radiologist." This implies a single reader review, so no adjudication method (like 2+1 or 3+1) was used.

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

• MRMC Study: No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This submission is for a CT system itself, not an AI-assisted diagnostic tool designed to improve human reader performance. Its purpose is to demonstrate the fundamental image quality and safety of the CT scanner.

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

• This is not applicable in the context of this submission. The device is a CT scanner, which inherently produces images for human interpretation. The "software options" mentioned (SEMAR, SURESubtraction Ortho, Dual Energy System Package) are image processing algorithms that enhance the raw CT data, but the "performance" as described (image quality metrics, diagnostic quality) still relates to the final image presented for a human in the loop. There is no "algorithm only" performance study in the sense of an automated diagnostic algorithm.

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

• The "ground truth" for evaluating image quality appears to be based on:
  • Phantom measurements: For spatial resolution, CT number, contrast-to-noise ratio, and uniformity performance.
  • Expert opinion: The "American Board Certified Radiologist" reviewing representative diagnostic images for diagnostic quality. This functions as the human expert assessment indicating the images are fit for interpretation.

8. The sample size for the training set

• Not applicable/provided. This document describes a new version of an existing CT scanner, not a novel machine learning algorithm that requires a separate training set. The "software options" mentioned were previously cleared and their development (including any training data if applicable) would have been part of their original 510(k) submissions.

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

• Not applicable. See point 8.

Ask a specific question about this device