Search Results

The X-ray Imaging System is intended to be used as a patient setup and localization tool that is capable of processing orthogonal or CBCT images acquired at the start of the treatment. The images will be compared against Digitally Reconstructed Radiographs or CTs that were used to define the treatment plan. The comparison will generate position correction vectors if required and provide them to the McLaren Proton Treatment System for patient position corrections prior to treatment.

The X-ray Imaging System controls the x-ray generation, image processing and patient registration of the McLaren Proton Treatment System (K160063). The software product described by this document is considered a sub-system of the McLaren Proton Treatment System. The software product integrates with the following components of the McLaren Proton Treatment System: . X-ray generator & tube assembly Amorphous silicon flat-panel detector . Electro-mechanical controls of the imaging c-ring to enable system positioning and rotation around the patient The software will permit a radiation technician to set the desired energy levels and field of view. Once set the software can acquire orthogonal or CBCT x-ray images of the region of interest. When images are acquired the software will process them to create viewable images for patient location registration. The patient's position will be adjusted, if needed, based on a comparison of the current patient location, the defined treatment plan, and Digitally Reconstructed Radiographs or CTs.

Here's a breakdown of the acceptance criteria and study information for the EhmetDx X-ray Imaging System (K181498), based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states: "Imaging performance and radiography and cone beam CT was assessed using standard measurement tools and phantoms and passed all tests." This indicates that the testing was performed on phantoms (simulated objects used for testing), not human patient data.

• Sample Size for Test Set: Not explicitly stated in terms of number of cases, but involved "standard measurement tools and phantoms."
• Data Provenance: Not human patient data; generated in a controlled environment using phantoms. No country of origin is specified for clinical data, as no clinical data was used.

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

The provided text does not mention the use of experts to establish ground truth for the test set. Given that the testing involved phantoms and standardized measurements, the ground truth would have been established by the inherent properties of the phantoms and the measurement protocols.

4. Adjudication Method for the Test Set

No adjudication method is described. As no human readers or expert evaluations were explicitly mentioned for ground truth establishment, no adjudication method would have been necessary in the context of expert review.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No. The document explicitly states: "EhmetDx did not perform clinical testing for the X-ray Imaging System and no clinical data was collected during device validation activity and substantial equivalence testing." Therefore, a human-in-the-loop MRMC study comparing human readers with and without AI assistance was not conducted.

6. Standalone (Algorithm Only) Performance

Yes. The provided performance metrics in the table (CBCT distance accuracy, spatial resolution, low-contrast resolution, CT number accuracy, CT number uniformity) are all standalone performance metrics of the imaging system and its image processing capabilities, without human intervention in the interpretation of the output for these specific technical aspects.

7. Type of Ground Truth Used

The ground truth used for performance assessment was based on the physical properties and known measurements of standard phantoms.

8. Sample Size for the Training Set

The document does not provide any information regarding a training set size. This is likely because the device, as described, is an X-ray imaging system with image processing capabilities, and the focus of the 510(k) submission is on its technical imaging and registration performance compared to a predicate, rather than an AI/ML algorithm that requires extensive training data.

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

Since no information on a training set or AI/ML algorithm requiring such a set is provided, there is no mention of how ground truth for a training set was established.

Ask a specific question about this device