(137 days)
MyAblation Guide is a software application for image processing, 2D/3D visualization, and comparison of medical images imported from multiple imaging modalities.
The software is controlled by the end user interface on a workstation with DICOM connectivity or as an integrated version on a Siemens CT scanner workstation.
The application is used to assist in the preparation and performance of ablative procedures, including of ablation targets, virtual ablation probe placement and contouring of ablated areas, as well as supporting the User in their assessment of the treatment. The application can only be used by trained Users.
The software is not intended for diagnosis and is not intended to predict ablation volumes or predict ablation success.
myAblation Guide is a software medical device that is used in the context of percutaneous ablative procedures with straight instruments. It is used by clinical professionals in a hospital premise; it can be either deployed on compatible CT scanners or a computer workstation.
The application is operated by medical professionals such as Interventional Radiologists and medical technologists with current license and/or certification as required by regional authority. myAblation Guide allows operating functions in an arbitrary sequence. In addition, it includes a structured sequence of steps for ease of utility.
The application supports anatomical datasets from CT, MR, CBCT, as well as PET/CT.
The application includes means and functionalities to support in:
· Multimodality viewing and contouring of anatomical, and multi-parametric images such as CT, CBCT, PET/CT, MRI
· Multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP), volume rendering technique (VRT)
· Freehand and semi-automatic contouring of regions-of-interest on any orientation including oblique
- Manual and semi-automatic registration using rigid and deformable registration
- · Expansion of created contour structures to visualize a safety margin
· Functionality to support the user in creating virtual ablation needle paths and associated virtual ablation zones derived from manufacturer data
- · Export of virtual needle paths in the Dicom SSO format
- · Supports the user in comparing, contouring, and ablation needle planning based on datasets acquired with different imaging modalities
- Supports multimodality image fusion
- · Supports user's procedure flow via a task stepper
Thermal ablation cannot be triggered from myAblation Guide.
The provided text details the 510(k) submission for the myAblation Guide (VB80A) device. It includes information on non-clinical testing performed to demonstrate the device meets established design criteria.
Here's an organized breakdown of the acceptance criteria and study proving the device meets them, based on the provided text:
Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Implied by Study Target/Reference) | Reported Device Performance (myAblation Guide) |
|---|---|---|
| Lesion Segmentation | Dice Score: 0.82 (from Moltz et al. study) | Dice Score: 0.65 (All Lesion Types) |
| Sensitivity: N/A | Sensitivity: 0.82 (All Lesion Types) | |
| Ablation Zone Segmentation | N/A (no specific numerical target stated) | Dice Score: 0.65 |
| N/A | Sensitivity: 0.95 |
Note on Acceptance Criteria: The document implies the Moltz et al. study's Dice coefficient of 0.82 on liver metastases as a benchmark, stating "the algorithm effectively demonstrated the segmentation of both hyperdense and hypodense lesions... With a Dice coefficient (Dice similarity index) of 0.82". For the internal study, the reported Dice scores and sensitivities appear to be the performance metrics being presented to demonstrate functionality rather than explicitly stated "acceptance criteria" that must be met. However, for the purpose of this exercise, we can infer that these reported values demonstrate the device's acceptable performance.
Study Details
-
Sample Size Used for the Test Set and Data Provenance:
- Lesion Segmentation (Moltz et al. study): 5 different datasets comprising 10 liver metastases. Data provenance is not specified (e.g., country of origin, retrospective/prospective).
- Lesion Segmentation (Internal Study): 50 patients. Data provenance is not specified (e.g., country of origin, retrospective/prospective), but it is referred to as an "internal study," suggesting it was conducted by the manufacturer or an affiliated entity.
- Ablation Zone Segmentation: 33 patients with 41 available ablation zones. Data provenance is not specified.
-
Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
- The document does not specify the number of experts or their qualifications for establishing ground truth for the test sets in either the Moltz et al. study or the internal studies.
-
Adjudication Method for the Test Set:
- The document does not provide details on any adjudication method (e.g., 2+1, 3+1, none) used for the test sets. It only mentions the comparison of algorithm performance against a reference.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study was done. The document explicitly states: "No clinical studies were carried out for the subject device, and therefore, no such clinical data is provided within this submission." The study focuses on "algorithm's performance" and "semi-automatic liver ablation zone segmentation."
-
Standalone (Algorithm Only Without Human-in-the-Loop) Performance:
- Yes, the performance data presented (Dice scores, Sensitivity) are indicative of standalone (algorithm only) performance for the semi-automatic segmentation algorithms. The phrasing "To assess the algorithm's performance" and "The internal analysis of the lesion segmentation" supports this. The device is a "software application for image processing," and the described tests evaluate the segmentation algorithms within this software.
-
Type of Ground Truth Used:
- The document does not explicitly state the type of ground truth used (e.g., expert consensus, pathology, outcomes data). However, for segmentation tasks, ground truth is typically established by expert manual annotation or referencing pathology for pathological confirmation. Given the context of "assessed" cases and "segmentation," it is highly probable that the ground truth was established by expert review/annotation of the medical images.
-
Sample Size for the Training Set:
- The document does not specify the sample size for the training set. The provided information relates only to the test sets used for evaluating the semi-automatic segmentation algorithms.
-
How the Ground Truth for the Training Set Was Established:
- The document does not provide information on how the ground truth for the training set was established, as the size and specifics of the training set are not mentioned.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).