Search Results

CADstream is intended to be used in the visualization, analysis, and reporting of magnetic resonance imaging (MRI) studies. CADstream supports evaluation of dynamic MR data acquired during contrast administration. CADstream performs other user selected processing functions (such as image registration, subtractions, measurements, 3D renderings, and reformats).

CADstream also includes user-configurable features for reporting on findings in breast or general MRI studies. Additionally, CADstream assists users in planning MRI guided interventional procedures.

When interpreted by a skilled physician, this device provides information that may be used for screening, diagnosis, and interventional planning. Patient management decisions should not be made based solely on the results of CADstream.

CADstream may also be used as an image viewer of multi-modality, digital images, including ultrasound and mammography. CADstream is not intended for primary interpretation of digital mammography images.

Device Description

CADstream is an image processing system designed to assist in the visualization, analysis, and reporting of magnetic resonance imaging (MRI) studies. CADstream also is intended to provide workflow efficiency and interventional planning tools.

CADstream receives DICOM magnetic resonance images from a PACS of directly from the MRI scanner. As they are received, CADstream processes and displays the results on the CADstream server or a client personal computer.

Available features support:

. Visualization (standard image viewing tools, MIPs, and reformats)
Analysis (registration, subtractions, coil inhomogeneity correction, kinetic curves, parametric image maps, apparent diffusion coefficient maps, automatic and manual segmentation and 3D volume rendering)
Reporting of user-selected findings and assessment
Interventional planning
Workflow efficiency ■
예 Communication and storage (DICOM import/export, query/retrieve, and study storage)

The CADstream system consists of proprietary software developed by Merge Healthcare installed on an off-the-shelf computer.

AI/ML Overview

The provided 510(k) summary for CADstream Version 5 (K092954) states that the device modification primarily involves adding capabilities for calculating and presenting apparent diffusion coefficient (ADC) maps and values. It emphasizes that this change is consistent with previously cleared indications for use and does not alter the fundamental scientific technology.

Therefore, the performance testing described focuses on demonstrating that the new ADC functionality meets acceptance criteria related to its implementation and the existing functionalities.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria	Reported Device Performance
New ADC functionality:

Correct calculation and presentation of ADC maps and values.
Integration into existing CADstream workflow.
No adverse impact on previously cleared functionalities. | The submission states: "The potential hazards of adding the ADC map functionality have been studied and controlled as part of the product development process, including risk analysis and design considerations." and "The successful completion of verification testing has demonstrated conformance to design controls, user needs, and intended use, and that the device is safe and effective." |
| Overall Device Safety and Effectiveness (for the modified device):
Continues to meet intended use as an image processing system for visualization, analysis, and reporting of MRI studies.
Maintains safety and effectiveness as demonstrated by the predicate devices. | The submission concludes: "Based on the information supplied in this 510(k), we conclude that the subject device is safe, effective, and substantially equivalent to the predicate devices." |

2. Sample size used for the test set and the data provenance

The document states "verification testing was completed" but does not provide details regarding the sample size of the test set, or the specific provenance (country of origin, retrospective/prospective nature) of the data used for this testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The 510(k) summary does not specify the number of experts or their qualifications used to establish ground truth for the verification testing. Given that the modification is primarily software-based for a calculation and presentation feature (ADC maps), the "ground truth" for this specific modification would likely relate to the accuracy of the algorithm's output compared to expected mathematical results or established reference methods, rather than expert interpretation of a diagnostic outcome. The general indications for use, however, mention interpretation by a "skilled physician."

4. Adjudication method for the test set

The document does not specify any adjudication method used for the test set.

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

No MRMC comparative effectiveness study was done or reported in this 510(k) summary. The modification described is focused on the technical implementation of ADC calculation and presentation, not on evaluating human reader performance with or without AI assistance.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

The provided information indicates that "verification testing was completed," but does not explicitly detail whether standalone algorithm-only performance testing was conducted for the ADC functionality. Given the nature of ADC calculation, it is highly probable that the verification testing involved evaluating the algorithm's output accuracy against known inputs or established methods, which can be considered a form of standalone performance evaluation for that specific feature. However, the document does not break down the testing in this way.

7. The type of ground truth used

For the specific modification (ADC map functionality), the ground truth would likely be mathematical accuracy and fidelity to established methods for calculating ADC values. This would involve comparing the device's calculated ADC maps and values against highly accurate reference calculations or values derived from well-defined input MRI sequences. The document does not explicitly state the type of ground truth beyond "conformance to design controls, user needs, and intended use."

8. The sample size for the training set

The 510(k) summary does not mention a training set sample size or details about any machine learning training for this specific modification. The change described (ADC map calculations) suggests a deterministic algorithmic implementation rather than a machine learning model that would require a distinct training set.

9. How the ground truth for the training set was established

As no training set is mentioned, this information is not applicable and not provided in the document.

Ask a Question

Ask a specific question about this device

K Number

K081556

Device Name

CADSTREAM, VERSION 5.0

Manufacturer

CONFIRMA, INC.

Date Cleared

2009-02-02

(244 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K043216,K031779,K041286,K031350,K050862,K960265,K080196

Intended Use

CADstream also includes user-configurable features for reporting on findings in breast or general MRI studies. Additionally, CADstream assists users in planning MRI guided interventional procedures.

Device Description

CADstream receives DICOM magnetic resonance images from a PACS or directly from the MRI scanner. As they are received, CADstream processes and displays the results on the CADstream server or a client personal computer.

Available features support:

Visualization (standard image viewing tools, MIPs, and reformats)
Analysis (registration, subtractions, coil inhomogeneity correction, kinetic curves, parametric image maps, and 3D volume rendering)
Reporting of user-selected findings and assessment
Interventional planning
Workflow efficiency
Communication and storage (DICOM import/export, query/retrieve, and study storage)

The CADstream system consists of proprietary software developed by Confirma installed on an off-the-shelf computer.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the CADstream Version 5 device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The provided text does not explicitly state specific numerical acceptance criteria for performance metrics (e.g., sensitivity, specificity, accuracy, or quantitative measures of visualization/analysis improvement). Instead, the performance testing is described in a more general sense, focusing on verification and validation against requirements and substantial equivalence to predicate devices.

Therefore, the table will reflect the general statements made about performance rather than specific, measurable criteria.

Acceptance Criteria (Implied from text)	Reported Device Performance
Device meets input requirements (Verification Testing)	CADstream version 5 has successfully undergone extensive verification testing to verify the device meets input requirements.
Product modifications do not raise new safety or effectiveness concerns	Bench validation testing was also performed to demonstrate the product modifications from version 4 resulted in a substantially equivalent product and did not raise any new safety or effectiveness concerns.
Device conforms to user needs and intended uses (Clinical Validation)	Additionally, the completed clinical validation testing demonstrates the device conforms to user needs and intended uses per 21CFR820.30(g).
Device is safe and effective	"The successful completion of verification and validation testing has demonstrated conformance to design controls, user needs, and intended use, and that the device is safe and effective."
"Based on the information supplied in this 510(k), we conclude that the subject device is safe, effective, and substantially equivalent to the predicate devices."
Substantially equivalent to predicate devices	Bench validation testing demonstrated substantial equivalence to version 4 and other predicate devices in terms of features (as shown in Table 1 and Table 2 comparison) and overall safety and effectiveness. The 510(k) summary explicitly concludes substantial equivalence to predicate devices based on the submitted information.
Provides features for visualization, analysis, and reporting of MR images	Device description and feature comparison tables illustrate the capability to perform:

Visualization (standard image viewing tools, MIPs, reformats, 3D volume rendering)
Analysis (registration, subtractions, coil inhomogeneity correction, kinetic curves, parametric image maps)
Reporting of user-selected findings and assessment
Interventional planning
Workflow efficiency
Communication and storage (DICOM import/export, query/retrieve, and study storage) |

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

Sample Size for Test Set: The document does not specify the sample size (number of patients or cases) used for the "clinical validation testing."
Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective.

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

Number of Experts: The document does not specify the number of experts used to establish ground truth for the test set.
Qualifications of Experts: The document does not specify the qualifications of any experts involved in establishing ground truth. The "Indications for Use" section mentions interpretation "by a skilled physician," but this is a general statement about clinical use, not a description of ground truth establishment during testing.

4. Adjudication Method for the Test Set:

The document does not mention any specific adjudication method (e.g., 2+1, 3+1, none) used for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it discuss the effect size of human readers' improvement with or without AI assistance. The focus is on device features and general validation, not comparative reader performance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

The document describes "Performance Testing" including "extensive verification testing," "bench validation testing," and "clinical validation testing." While these tests would involve evaluating the algorithm's functionality, the document does not explicitly state that a standalone performance study comparing the algorithm's diagnostic accuracy against a ground truth was conducted without a human in the loop. The device is described as an "image processing system designed to assist," implying a human-in-the-loop context for its intended use and evaluation.

7. The Type of Ground Truth Used:

The document does not explicitly state the type of ground truth used for any testing (e.g., expert consensus, pathology, outcomes data). It broadly refers to "user needs and intended uses" for clinical validation.

8. The Sample Size for the Training Set:

The document does not mention a training set or its sample size. This is typical for 510(k) submissions of this era for image processing systems, as they often leverage established algorithms or feature sets rather than reporting on deep learning model training.

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

Since a training set is not mentioned, the document does not describe how ground truth for a training set was established.

Ask a Question

Ask a specific question about this device

Page 1 of 1