(56 days)
The intended use of syngo® Dosimetrist Workspace is as an accessory to the linear accelerator system to aid and support in the planning of delivery of x-ray photon and electron radiation for the therapeutic treatment of cancer.
The syngo® Dosimetrist Workspace v2.7 is a comprehensive oncology workflow software package that allows for both CT simulation as well as inverse radiation therapy treatment planning and optimization to aid in the oncology clinical workflow where indicated. The syngo® Dosimetrist workspace is comprised of (wo major components, the CT Simulation component (VSIM) and the inverse radiation therapy treatment planning component (KonRad) to be used in the creation, evaluation and approval of radiation treatment plans.
The VSIM component permits CT simulation to be performed on the syngo® Dosimetrist workstation. The CT scans are imported into the VSIM software component and the user is able to create threedimensional models of targets and organs. The VSIM application supports the use of automatic contouring and seamentation or a model based segmentation (MBS) library of anatomical regions may be used. The contours and segmentation can be manually adjusted prior to use by the treatment planning system.
Additionally, the user is able to identify the patient isocenter, place treatment beams, and identify beam modifiers (blocks, apertures, and MLCs). The simulation is then available for radiation treatment planning for dose calculation via the KonRad software component or other treatment planning systems. The plans are then reviewed and approved by the clinician prior to transfer to the delivery system for the actual treatment.
The KonRad software component is intended to optimize multi-leaf (MLC) positions or partial attenuation block shapes for intensity modulated external beam radiation therapy (IMRT). Once the optimization is complete, the dose distribution and dose volume histogram curves are displayed for the user to evaluate. After approval, the results are exported to the delivery equipment, linear accelerator, or record and verify system, for final verification prior to treatment delivery. The KonRad TPS software component allows for efficient inverse radiation therapy treatment planning and optimization.
The syngo® Dosimetrist Workspace v2.7 supports configuration of both a Virtual Simulation [VSIM] and a Treatment Planning System [TPS] called KonRad™. The syngo® Dosimetrist Workspace v2.7 is based on the currently cleared SIEMENS COHERENCE™ Dosimetrist Workspace v2.2 and is intended to be marketed as an update. The basic design, safety features and function of the Dosimetrist Workspace v2.7 remain unchanged from their currently cleared intended use and functions.
The syngo® Dosimetrist Workspace v2.7 supports the visualization and clinical assessment of the treatment area using a variety of digital images. The VSIM application supports a three dimensional graphical representation allowing for a virtual setup and treatment of the patient without involving the patient. A variety of software tools are supplied to assist in the delineation of structures for rapid contouring plus segmentation tools for beam profiles and placement on target organ(s) or structures prior to the use by the treatment planning function ITPS1.
New features for the VSIM module are the Advanced Segmentation application for rapid contouring and segmentation using the Random Walker algorithm. Additionally, the contouring process can be assisted by the use of Model Based Segmentation for the prostate, bladder, rectum and femurs/hips based on anatomical libraries.
The syngo® Dosimetrist Workspace v2.7, when configured with the KonRad inverse planning system, is a radiation therapy treatment planning package designed to optimize multi-leaf collimator (MLC) positions or partial attenuation block shapes for intensity modulated external beam radiation therapy (IMRT). The KonRad component uses the defined anatomical structures for the optimization and treatment planning process.
The final treatment plan can be exported to the appropriate delivery equipment such as a medical linear accelerator, and/or record and verify system. The final treatment plan does not activate the radiation therapy delivery equipment, as all information must be verified by the user prior to the initiation of radiation therapy treatment. The approved treatment plan facilitates the delivery of radiation to defined target volumes while sparing surrounding normal tissue and critical organs from excess radiation using the conventional linear accelerator.
Here's an analysis of the provided text regarding the acceptance criteria and study proving the device meets those criteria:
The provided document, K101119 for the syngo® Dosimetrist Workspace v2.7, is a 510(k) summary for regulatory clearance. It focuses on demonstrating substantial equivalence to previously cleared predicate devices rather than establishing novel safety and effectiveness criteria through a new clinical study with specific performance endpoints. Therefore, the information typically found in a clinical study report for device acceptance (like a detailed table of acceptance criteria vs. reported performance metrics, specific sample sizes for test sets with ground truth qualifications, MRMC studies, or standalone performance) is largely absent or presented at a high level.
The "acceptance criteria" discussed in this document primarily refer to the successful verification and validation of software requirements to ensure the new features (Advanced Segmentation and Model Based Segmentation) function as intended and are substantially equivalent to the predicate devices.
Here's a breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
Based on the document, specific quantitative acceptance criteria and detailed reported device performance in a numerical format are not explicitly provided as would be seen in a clinical study aiming for de novo clearance. Instead, the "performance" is demonstrated through the successful completion of various software testing phases and the claim of substantial equivalence.
| Acceptance Criterion (Implicit) | Reported Device Performance (Summary from text) |
|---|---|
| Advanced Segmentation (Random Walker algorithm) Functionality: Meet Component Requirements Specifications (CRS). | "All testable requirements in the Software Requirements Specifications (SRS), Sub-System Requirements Specifications (SSRS), and specifically, the Component Requirements Specifications (CRS) for the algorithms and libraries. have been successfully verified and traced in accordance with the Siemens product development process (PDP)." |
| "The addition of the Advanced Segmentation using the Random Walker algorithm (as a Component) have been verified by Unit and Integration testing to meet the Component Requirements Specifications for this feature contained the syngo® Dosimetrist Workspace v2.7." | |
| Model Based Segmentation (MBS) Functionality: Meet Component Requirements Specifications (CRS). | "All testable requirements in the Software Requirements Specifications (SRS), Sub-System Requirements Specifications (SSRS), and specifically, the Component Requirements Specifications (CRS) for the algorithms and libraries. have been successfully verified and traced in accordance with the Siemens product development process (PDP)." |
| "The Model Based Segmentation component has been verified to meet the Component Requirement Specifications." | |
| Overall Software Quality & Safety: Meet established software testing phase requirements (Unit, Integration, System Integration, Regression). | "The software verification and regression testing has been performed successfully to meet their previously determined acceptance criteria as stated in the Test Plans." |
| "Validation of the syngo® Dosimetrist Workspace v2.7 has been performed at the System test level on production prototype devices by appropriately trained and knowledgeable test personnel. System level validation and regression testing has been performed successfully, demonstrating that the software meets the acceptance criteria as noted in the system test plans." | |
| Interoperability and Safety Tests: DICOM connectivity and VSIM module specific safety. | "Siemens has performed specific System tests to verify interoperability for DICOM connectivity within the clinical environment as well as safety tests specifically for the VSIM module." |
| Compliance with Consensus Standards: | "The syngo® Dosimetrist Workspace v2.7 has been tested to meet the requirements for conformity (where applicable) to the following standards: IEC 60601-1-4, IEC 62083, EN 62366, IEC 62304, DICOM Standards." |
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 for Test Set: Not specified. The document only mentions "production prototype devices" and "appropriate test personnel" were used for system-level validation. It does not provide numerical counts of cases or patients in any test set.
- Data Provenance: Not specified. There is no mention of the country of origin of data or whether it was retrospective or prospective. Given the nature of a 510(k) for a software update and the focus on "verification and validation of requirements" rather than a clinical study, it's highly likely synthetic or internal company data was used for testing, or existing de-identified clinical data from previous development/clearances, but this is not explicitly stated.
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: Not specified.
- Qualifications of Experts: Not specified. The document mentions "appropriately trained and knowledgeable test personnel" but does not define their qualifications as clinical experts (e.g., radiation oncologists, dosimetrists). Ground truth in this context would likely be established by comparing algorithm outputs against manually contoured structures by these "knowledgeable test personnel" or against known 'gold standard' anatomical models.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: Not specified. Given the software verification and validation context, formal clinical adjudication methods like 2+1 or 3+1 are unlikely to have been employed. Testing would likely involve comparing output to known good examples or predefined acceptance thresholds by single reviewers.
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. The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The focus is on the performance of the software features themselves (Advanced Segmentation and Model Based Segmentation) and their equivalence to existing cleared devices.
- Effect Size: Not applicable, as no such study was conducted or reported.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Yes, implicitly. The "Bench testing in the form of Unit, Integration and System Integration testing" as well as the verification that the algorithms "meet the Component Requirements Specifications" indicates that the algorithms for Advanced Segmentation (Random Walker) and Model Based Segmentation were evaluated in a standalone manner to ensure they perform their intended function (e.g., generating contours). The text states "The VSIM application supports the use of automatic contouring and segmentation or a model based segmentation (MBS) library... The contours and segmentation can be manually adjusted prior to use by the treatment planning system," implying the algorithms generate preliminary contours autonomously.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Type of Ground Truth: Not explicitly stated in clinical terms. For software verification and validation, ground truth would typically refer to:
- Predefined software requirements and specifications: The algorithms' outputs are compared against these.
- "Gold standard" or reference data: For segmentation, this would likely be manually contoured structures by qualified individuals or reference anatomical models. The "Model Based Segmentation for the prostate, bladder, rectum and femurs/hips based on anatomical libraries" suggests that these libraries serve as a form of anatomical ground truth or reference for the MBS feature.
- Outputs of predicate devices: Substantial equivalence implies that the new features perform comparably to the cleared predicate devices, meaning their outputs effectively serve as a form of "ground truth" for comparison in demonstrating equivalence.
8. The sample size for the training set
- Sample Size for Training Set: Not specified. The document mentions the use of "anatomical libraries" for Model Based Segmentation and the Random Walker algorithm but does not provide information on the size or characteristics of the datasets used to train or develop these algorithms. This type of information is often not required for a 510(k) if the algorithms themselves (like the Random Walker) are already established and cleared components.
9. How the ground truth for the training set was established
- How Ground Truth for Training Set was Established: Not specified. For the Model Based Segmentation, it mentions "predefined contours based on anatomical libraries." For the Random Walker algorithm, it references the previously cleared "syngo® CT ONCOLOGY Software Package (K071310)", implying that the ground truth for training that specific algorithm would have been established during its prior clearance. Details on how those anatomical libraries or prior training datasets' ground truth were established (e.g., expert manual segmentation, pathology) are not in this document.
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.