(78 days)
CADstream™ is a Computer Aided Detection (CAD) system intended for use in analyzing magnetic resonance imaging (MRI) studies. CADstream automatically registers serial patient image acquisitions (in 2D or 3D) to minimize the impact of patient motion, segments and labels tissue types based on enhancement characteristics (parametric image maps, referred to as angiogenesis maps), and performs other userdefined post-processing fimage subtractions, multiplanar reformats, maximum intensity projections).
CADstream also can be used to provide accurate and reproducible measurements of the longest diameters and volume of segmented tissues. including automated determination of volumes of interest (VOI), calculation of the longest diameter in X, Y and Z dimensions, the areas of VOI, the volume measurements of VOI (reported in cc), and 3D renderings of VOI.
The system includes an optional remote image viewer (CADalyst™), optimized for viewing breast MR studies processed by CADstream.
CADstream™ includes software to support the use of breast interventional coils and MR stereotactic localization devices to perform breast interventional procedures (SureLoc™). Using information from MR images regarding the coordinates of a user-specified region of interest, and fiducial coordinates, the software provides an automatic calculation of the location and depth of the targeted region of interest, such as a lesion or suspected lesion.
When interpreted by a skilled physician, this device provides information that may be useful in screening and diagnosis. Patient management decisions should not be made based solely on the results of CADstream analysis.
The CADstream device relies on the assumption that pixels having similar MR signal intensities represent similar tissues. The CADstream software simultaneously analyzes the pixel signal intensities from multiple MR sequences and applies multivariate pattern recognition methods to perform tissue segmentation and classification. CADstream is designed to analyze dynamic breast MRI studies.
The CADstream system consists of proprietary software developed by Confirma installed on an off-the-shelf personal computer and a monitor configured as a CADstream display station.
The CADstream System consists of the following key components:
- . A PC Server: a desk-side or rack mount PC capable of running the Server software, Client User Interface software, and Study Viewer software
- . Server software: performs CADstream analysis and processing
- Client User Interface software: an administrative web page hosted on the Server .
- Study Viewer software (CADalyst): an optional Image Viewer component. . optimized for viewing breast MR studies processed by CADstream
- Archive System: a PC with CD burner and printer .
In all cases, images are acquired and pushed to the CADstream system from the MR scanner. CADstream is configured to automatically process the images and create additional series. In this configuration, CADstream forwards the processed and original images to the existing softcopy reading station.
Here's a summary of the acceptance criteria and study information for the CADstream™ Version 3.1 device, based on the provided 510(k) summary:
Acceptance Criteria and Reported Device Performance
The provided document does not explicitly state quantitative acceptance criteria for the CADstream™ Version 3.1 device. Instead, it relies on successful completion of internal testing and comparison to predicate devices, focusing on the functionality and safety aspects. The performance is broadly described as:
| Acceptance Criteria Category | Reported Device Performance (as described in the 510(k) summary) |
|---|---|
| Functional Performance | - Automatically registers serial patient image acquisitions (in 2D or 3D). |
- Segments and labels tissue types based on enhancement characteristics (parametric image maps / angiogenesis maps).
- Performs user-defined post-processing functions (image subtractions, multiplanar reformats, maximum intensity projections).
- Provides accurate and reproducible measurements of the longest diameters and volume of segmented tissues including: automated determination of volumes of interest (VOI), calculation of the longest diameter in X, Y and Z dimensions, the areas of VOI, the volume measurements of VOI (reported in cc), and 3D renderings of VOI.
- Provides automatic calculation of the location and depth of the targeted region of interest (e.g., lesion) using MR images and fiducial coordinates for interventional procedures (SureLoc™). |
| Software Development | - Designed, developed, tested, and validated according to written procedures. - Successfully completed required integration and verification testing. |
| Safety | - Assessment performed throughout the design development process in accordance with internal procedures and IEC 601-1-4. - Potential hazards studied and controlled as part of product development, risk management, test, and design considerations, and planned verification and validation testing. |
| Clinical Performance | - Performance testing of features successfully completed utilizing clinical datasets. - Requirements for features have been met. |
Study Details:
The 510(k) summary provided describes the validation and verification processes for the device, rather than a specific clinical study with detailed statistical outcomes for acceptance criteria.
-
Sample size used for the test set and the data provenance:
- Sample Size: The document states that "Performance testing of the features described in the user manual has been successfully completed utilizing clinical datasets." However, it does not specify the sample size (number of cases or patients) of these clinical datasets used for testing.
- Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. It only mentions "clinical datasets."
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document does not provide details on the number of experts used to establish ground truth or their specific qualifications for the test set. It mentions the device provides information that "may be useful in screening and diagnosis" when "interpreted by a skilled physician," but this is a general statement about usage, not about the ground truth establishment for testing.
-
Adjudication method for the test set:
- The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for the test set.
-
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:
- A MRMC comparative effectiveness study is not described in this 510(k) summary. The document focuses on the device's functional performance and its substantial equivalence to predicate devices, without assessing human reader improvement with or without AI assistance.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The document implies standalone performance testing to verify the algorithm's capabilities. It states, "CADstream automatically processes the images and creates additional series" and "CADstream also can be used to provide accurate and reproducible measurements...". The "Performance testing of the features described in the user manual has been successfully completed utilizing clinical datasets" suggests testing of the algorithm's output. However, it does not explicitly detail a standalone performance study with specific metrics like sensitivity or specificity.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The document does not specify the type of ground truth used for the "clinical datasets" mentioned in the performance testing section.
-
The sample size for the training set:
- The document does not specify the sample size for any training set. It describes the software development and testing process but does not provide details on a training phase with associated data.
-
How the ground truth for the training set was established:
- Since no training set details are provided, the document does not mention how ground truth for any potential training set was established.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.