Search Results

DTS is intended to display an approximation of both skin dose distribution and skin dose rate in real time during fluoroscopic interventional procedures of cardiac angiography. This software is intended for use on the Toshiba INFX-8000F CSi cardiac labs.

The dose tracking system (DTS) is an application software package intended to provide the estimated dose distribution information during X-ray fluoroscopic procedures. The dose tracking system (DTS) calculates the radiation dose of the patient's skin using the exposure technique parameters and exposure geometry obtained from the x-ray imaging system (Toshiba Infinix-i) and presents the cumulative results in a color mapping on a 3D graphic of the patient model.

Toshiba America Medical Systems, Inc. Pre-Market Notification 510(k) XIDF-DTS801; Dose Tracking Software

Here's an analysis of the provided 510(k) summary regarding the Dose Tracking System (DTS):

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

The provided document (K123097) is a 510(k) summary for a dose tracking system. It does not explicitly state specific acceptance criteria with numerical thresholds or reported device performance metrics in a direct table format as one might find in a detailed clinical study report. Instead, it generally states that "Testing was performed using anthropomorphic phantoms and Lexan phantoms to verify and validate the performance of the system. Based upon this testing the accuracy of the displayed estimated dose was determined and is included in the user information."

Without access to the "user information" or a more detailed test report, specific acceptance criteria and detailed performance metrics cannot be tabulated from this document. The existing information only confirms that some form of testing was conducted to verify accuracy.

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

The document does not specify the exact sample size for the test set. It mentions "anthropomorphic phantoms and Lexan phantoms" were used.

The data provenance is not explicitly stated regarding country of origin or whether it was retrospective/prospective. Given the nature of phantom testing, it's likely that the data was generated specifically for this pre-market notification (prospective) and would have occurred at the manufacturer's facility or a contracted testing facility.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

The document does not provide any information about experts being used to establish ground truth for the test set, nor their qualifications. Given that the testing involved phantoms, the ground truth would likely be based on physical measurements or known properties of the phantoms and applied radiation, rather than expert interpretation of medical images.

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

The document does not describe any adjudication method for the test set. This is consistent with testing on phantoms where objective measurements are typically compared against the device's output, rather than subjective human interpretation 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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted or described in this 510(k) summary. The device in question is a "Dose Tracking System" that calculates and displays estimated skin dose, not an AI diagnostic tool intended to assist human readers in image interpretation. Therefore, a study to measure improvement in human reader performance with or without AI assistance is not relevant to this type of device.

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

Yes, the testing described appears to be a standalone (algorithm only) performance evaluation. The device (DTS software) calculates and displays dose information based on exposure parameters and geometry from the X-ray system. The "testing was performed using anthropomorphic phantoms and Lexan phantoms to verify and validate the performance of the system," which implies evaluating the accuracy of the system's dose estimations against known phantom conditions, independent of human interaction beyond operating the system.

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

The type of ground truth used would have been based on physical measurements or known radiation dose characteristics applied to the phantoms. For instance, dosimeters might have been used to precisely measure actual dose delivery to the phantoms under specific conditions, which would then serve as the ground truth to evaluate the accuracy of the DTS's estimated dose. It would not be expert consensus, pathology, or outcomes data, as these are typically relevant for diagnostic or clinical decision-making devices.

8. The sample size for the training set

The document does not mention a training set or any details related to machine learning model training. The DTS calculates dose based on "exposure technique parameters and exposure geometry obtained from the x-ray imaging system" and "a reference dose table." This suggests a deterministic calculation based on established physics principles and possibly pre-calibrated data (reference dose table), rather than a machine learning approach requiring a distinct training set.

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

As no training set is described or implied for a machine learning model, the question of how its ground truth was established is not applicable to this 510(k) submission. If the "reference dose table" is considered a form of pre-established data, its ground truth would have been established through physicist-derived radiation dose models and calibration measurements.

Ask a specific question about this device