(88 days)
Z-DOSE29 Dose Check system is intended to provide dose check features to Computed Tomography systems. Z-DOSE29 software extracts CTDI values from CT host computer's screen, compares it to predefined thresholds, and sends notification and alert messages to the CT scanner display monitor prior to scanning.
Z-DOSE29 Dose Check provides the Dose Check feature to CT scanners as specified by the NEMA XR-25 standard and the Dose Check feature of NEMA XR-29*. This includes both Dose Notifications (for individual series) and Dose Alerts (for accumulated dose).
The Z-DOSE29 Dose Check software, which is installed on a remote computer that resides on the same local area network as the CT host computer, receives DICOM images from the CT host computer. The software captures CTDI values for each prescribed CT series, compares the values to AAPM dose check guideline (version 1.0) values and displays notification message(s) on the CT scanner operator's console. The Z-DOSE29 Dose Check software also adds the CTDI values from the individual series and displays alert message(s) on the CT scanner operator's console if the accumulated CTDI value exceeds a predefined ALERT threshold.
*NEMA XR-29 incorporates NEMA XR-25 Dose Check feature
In the event of an Alert, and in addition to displaying the alert message to the CT operator, Z-DOSE29 utilizes a relay to disable scanning until a correct password is inputted by the CT operator.
The Z-DOSE29 Dose Check software also records CTDI values and CT exam information into a local a database. Information in the database can be accessed by authorized users via a web browser.
The Z-DOSE29 Dose Check software runs on a Windows operating system 10 with a .net framework 4.0 or higher version.
Here's an analysis of the acceptance criteria and study details for the Z-DOSE29 device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are derived from the "Expected outcome" column, and the reported device performance is from the "Observed outcome" column in Table 2: Z-DOSE29 system level verification and validation summary.
| Requirement ID | Acceptance Criteria (Expected Outcome) | Reported Device Performance (Observed Outcome) | Test Result |
|---|---|---|---|
| SRS.001 | The software captures the CTDI value for the specified exam type (Adult Head, Adult Body, Pediatric Head, Pediatric Body, Perfusion) and compares it to AAPM Dose Check Guidelines suggested threshold value (Default Value). If the value exceeds the threshold, the software notifies the user by displaying a dialogue box. The dialogue box contains both captured CTDI value and the applied threshold value. The threshold value is configurable by the user in a text file. (This is repeated for each exam type). | The software captured the CTDI value for the specified exam type (Adult Head, Adult Body, Pediatric Head, Pediatric Body, Perfusion) and compared it to AAPM Dose Check Guidelines suggested threshold value (Default Value). If the value exceeded the threshold value, the software notified the user by displaying a dialogue box. The dialogue box contained both captured CTDI value and the applied threshold value. The threshold value is configurable by the user in a text file. (This is repeated for each exam type). | PASS |
| SRS.002 | The software calculates total CTDI value from each series and compares the accumulated value to AAPM Dose Check Guidelines suggested threshold value (Default Value). If the accumulated value exceeds the threshold value, the software alerts the user by displaying a dialogue box. The dialogue box contains both accumulated CTDI value and the applied threshold value. The threshold value is configurable by the user in a text file. | The software calculated total CTDI value from each series and compared the accumulated value to AAPM Dose Check Guidelines suggested threshold value (Default Value). If the accumulated value exceeded the threshold value, the software alerted the user by displaying a dialogue box. The dialogue box contained both accumulated CTDI value and the applied threshold value. The threshold value is configurable by the user in a text file. | PASS |
| SRS.003 | Software shall use relay hardware to disable system from scanning when an alert occurs. | Software used relay hardware to disable system from scanning when alert occurred. | PASS |
| SRS.004 | Software shall record and report CTDI and exam information. | Software recorded and reported CTDI and exam information. | PASS |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set (for CTDI extraction accuracy): Over 2400 image data sets were used to test the Off-the-Shelf (OTS) software component responsible for extracting CTDI information.
- Test Set (for system-level SRS requirements): The system-level verification and validation (Table 2) were performed on 4 different CT scanners from different manufacturers (GE Light Speed 32, Siemens Sensation 16, Philips Brilliance 64, Toshiba Aquilion 64). Lower-level requirements were verified on 9 different systems.
- Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It refers to "image data sets" for OTS testing and mentions specific CT scanner models from various manufacturers, suggesting a diverse, though undefined, source for testing the system.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth for the test set. However, the ground truth for dose thresholds is stated to be based on "AAPM Dose Check Guidelines suggested threshold value (Default Value)." The AAPM (American Association of Physicists in Medicine) is a professional organization, implying expert consensus in the guidelines used, but not individual experts for this specific study.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test set. The performance testing appears to be a direct comparison of the device's output against predefined guidelines or system requirements.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study was not done. The device, Z-DOSE29, is a "Dose Check system" that automates dose monitoring and alerts. It does not involve human readers interpreting images, but rather the device extracting CTDI values and comparing them to thresholds. Therefore, a study to measure human reader improvement with or without AI assistance is not applicable to this device's function.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, a standalone performance assessment was done. The entire performance testing described (SRS.001 to SRS.004) focuses on the software's ability to automatically capture, compare, alert, disable scanning, record, and report CTDI values based on predefined guidelines. The only human intervention mentioned is the ability for the CT operator to manually input CTDI values if the software misreads them and to input a password to re-enable scanning after an alert. The core functionality and its evaluation are standalone. The "OTS" software for CTDI extraction was tested separately for its accuracy (99%).
7. The Type of Ground Truth Used
The ground truth used for the dose notification and alert features (SRS.001 and SRS.002) is based on AAPM Dose Check Guidelines suggested threshold values. For requirements SRS.003 (disabling system) and SRS.004 (record and report), the ground truth is against the System Requirement Specifications (SRS) themselves, observing if the device performs as expected.
8. The Sample Size for the Training Set
The document mentions that the OTS software was tested using "more than 2400 image data sets." However, this refers to testing the OTS component, not training the Z-DOSE29 system itself. The document does not specify a separate training set size for the Z-DOSE29 software or any machine learning components within it (other than the OTS which it utilizes). Given the description of the device's function (extracting CTDI values from a screen via optical character recognition (OCR) and comparing them to static thresholds), it is likely more rule-based than machine learning dependent, potentially reducing the need for a traditional "training set" for the core logic, beyond perhaps any underlying OCR model.
9. How the Ground Truth for the Training Set Was Established
As no specific training set for the Z-DOSE29 software (excluding the OTS component it uses) is mentioned, the method for establishing its ground truth is also not detailed. For the OTS component's accuracy in CTDI extraction, its ground truth would likely involve manually verified CTDI values from those 2400+ image data sets.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.