(73 days)
syngo.via RT Image Suite is a 3D and 4D image visualization, multi-modality manipulation and contouring tool that helps the preparation of treatments such as, but not limited to those performed with radiation (for example, Brachytherapy, Particle Therapy, External Beam Radiation Therapy). It provides tools to view existing contours, create, edit, modify, copy contours of regions of the body, such as but not limited to, skin outline, targets and organs-at-risk. It also provides functionalities to create simple geometric treatment plans. Contours, images and treatment plans can subsequently be exported to a Treatment Planning System.
The subject device with the current software version SOMARIS/8 VB50 is an image analysis software for viewing, manipulation, 3D and 4D visualization, comparison of medical images from multiple imaging modalities and for the segmentation of tumors and organs-at-risk, prior to dosimetric planning in radiation therapy. syngo.via RT Image Suite combines routine and advanced digital image processing and visualization tools for manual and software assisted contouring of volumes of interest, identification of points of interest, sending isocenter points to an external laser system, registering images and exporting final results. syngo.via RT Image Suite supports the medical professional with tools to use during different steps in radiation therapy case preparation.
Here's an analysis of the acceptance criteria and study proving the device meets those criteria, based on the provided text.
Note: The provided text is a 510(k) summary for an existing device's software update, not a full clinical study report. Therefore, some details typically found in a full study report (like the exact geographic origin of all data, detailed expert qualifications and adjudication methods for ground truth, or full power analysis for sample sizes) are not explicitly stated. The information below is extracted and inferred from the available document.
Acceptance Criteria and Device Performance Study for syngo.via RT Image Suite (SOMARIS/8 VB50) automated organ segmentation algorithm
The focus of the performance evaluation in this 510(k) application is on the updated automated organ segmentation algorithm in the syngo.via RT Image Suite (SOMARIS/8 VB50), specifically its extension to additional organs compared to the predicate device (SOMARIS/8 VB40). The core algorithm is stated to be the same.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category (Implied) | Specific Acceptance Criteria (Inferred from text) | Reported Device Performance |
|---|---|---|
| Segmentation Detection Rate | Similar detection rates for organs present in the predicate device. | "The detection rates for the subject device were similar to those for the predicate device." |
| 100% detection rate for newly added organs (new functionality). | "Newly added organs in the subject device were detected at a rate of 100%." | |
| Segmentation Quality (Overlap) | Non-inferior or superior performance (measured by DICE coefficient) for all organ segmentations compared to the predicate device. | "The segmentation quality was assessed by comparing a manually annotated ground truth with the algorithm result using the overlap measure DICE coefficient. The quantitative evaluation demonstrates non-inferior or superior performance for all organ segmentations in the subject device compared to the predicate device." |
| Software Verification & Validation | Conformance with special controls for medical devices containing software; all software specifications meet acceptance criteria; mitigate identified hazards. | "The testing supports that all software specifications have met the acceptance criteria. Testing for verification and validation support the claim of substantial equivalence." and "The risk analysis was completed, and risk control implemented to mitigate identified hazards." |
| Functional Performance | Performs as intended. | "The results of these tests demonstrate that the subject device performs as intended." |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 112 subjects.
- Data Provenance: Not explicitly stated regarding country of origin. The study is described as a "performance evaluation" of the algorithm, comparing it to a predicate device. It does not explicitly state if it was retrospective or prospective, but performance evaluations of algorithms on a test set often utilize retrospectively collected data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: Not specified. The document mentions "manually annotated ground truth" but does not detail the number of annotators.
- Qualifications of Experts: Not specified. It's common in this domain for medical professionals (e.g., radiation oncologists, radiologists, medical physicists) to perform such annotations, but their specific qualifications or years of experience are not provided.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified. Since the ground truth is referred to as "manually annotated," it's possible a single expert annotated or multiple experts annotated with or without an arbitration/adjudication process. The document does not provide these details.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
- MRMC Study: No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not conducted or reported in this 510(k) summary. The evaluation focuses on the standalone performance of the automated segmentation algorithm compared to a "manually annotated ground truth" and compared to the predicate device's algorithm.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done
- Standalone Performance: Yes, a standalone (algorithm-only) performance evaluation of the automated organ segmentation algorithm was performed. The evaluation involved comparing the algorithm's output directly against a manually annotated ground truth using the DICE coefficient and assessing detection rates.
7. The Type of Ground Truth Used
- Type of Ground Truth: "Manually annotated ground truth." This typically implies expert consensus or single expert annotation, but the precise method and number of experts are not detailed. It is explicitly contrasted with the "algorithm result," confirming it's an expert-derived truth.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not specified. The document states that "The AI or deep learning-based algorithm has been initially cleared with the predicate device RT Image Suite SOMARIS/8 VB40 (K192065)," and "The fundamental algorithm did not change." This suggests the training was done for the predicate device's initial clearance, and this submission focuses on the extension of its application to more organs using the same fundamental algorithm. The size of the original training set is not provided in this document.
9. How the Ground Truth for the Training Set was Established
- Training Set Ground Truth Establishment: Not explicitly detailed in this document. Given that the fundamental algorithm was used in the predicate device, it can be inferred that the training data and corresponding ground truth were established historically for the original algorithm development. It is common for ground truth for deep learning training in medical imaging to be established through expert annotations, potentially with internal review or consensus processes, but specific details are not provided here.
§ 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.