(110 days)
Yes
The document explicitly states that the segmentation is performed using "classical machine learning and deep learning (in our case supervised voxel classication with Convolutional Neural Networks)".
No
The device is intended for automatic labeling, visualization, and volumetric quantification of brain structures from medical images, which is a diagnostic function, not a therapeutic one.
Yes
The device is intended for automatic labeling, visualization, and volumetric quantification of brain structures from MR or NCCT images. This process supports the identification and quantification of brain structures, which is a diagnostic function.
Yes
The device is described as software that processes medical images (MR and NCCT) to perform segmentation and volumetric quantification of brain structures. The description focuses on the software architecture and processing pipelines, and there is no mention of accompanying hardware components that are part of the device itself. While it relies on input images from imaging modalities, the device itself is the software performing the analysis.
Based on the provided information, it is highly likely that this device is not an In Vitro Diagnostic (IVD).
Here's why:
- Intended Use: The intended use clearly states that icobrain is for the automatic labeling, visualization, and volumetric quantification of brain structures from MR or NCCT images. This is a process performed on medical images, not on biological specimens (like blood, urine, or tissue) in vitro (outside the body).
- Device Description: The description focuses on image processing pipelines, converting image formats, segmentation, and calculating measurements from images. This aligns with medical image analysis software, not IVD devices which analyze biological samples.
- Input: The input is explicitly stated as MR or NCCT images, which are medical imaging modalities, not biological specimens.
- Lack of IVD Characteristics: There is no mention of analyzing biological samples, detecting specific biomarkers, or providing diagnostic information based on laboratory tests.
In summary, the device's function is centered around analyzing medical images to provide anatomical measurements and visualizations, which falls under the category of medical image analysis software, not In Vitro Diagnostics.
No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR or NCCT images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR or NCCT images.
Icobrain consists of two distinct image processing pipelines: icobrain cross and icobrain long.
icobrain cross is intended to provide volumes from MR or NCCT images acquired at a single time point. icobrain long is intended to provide changes in volumes between two MR images that were acquired on the same scanner, with the same image acquisition protocol and with same contrast at two different timepoints. The results of icobrain cross cannot be compared with the results of icobrain long.
Product codes
LLZ
Device Description
The icobrain device processes input images, which can be MR images or CT images, initially in DICOM format. During pre-processing, the modality and sequence of each scan are detected, and scans are converted to NIFTI format. Image processing then performs segmentation and calculates measurements of brain structures and abnormalities. Finally, computed measurements are summarized into an electronic report, and some segmentations are overlaid on the input images to generate output DICOM images. The CT pipeline of the device focuses on processing CT images.
The outputs of the CT pipeline include two types of reports:
Report 1:
- normalized volume of the whole brain (sum of white and grey matter)
- normalized volume of the lateral ventricles
This report is useful for (potential) dementia patients.
Report 2:
- measurement of the midline shift, i.e. the shift of the brain past its center line.
- normalized volume of basal cisterns (suprasellar, quadrigeminal, prepontine)
- volume (total, highest) of hyperdensities
This report is useful for (potential) TBI patients.
Mentions image processing
Yes
Mentions AI, DNN, or ML
segmentation by classical machine learning (unsupervised voxel classication with Gaussian Mixture Models)
segmentation by classical machine learning and deep learning (in our case supervised voxel classication with Convolutional Neural Networks)
Input Imaging Modality
MR or NCCT images (from a single or multiple time points)
Anatomical Site
Brain
Indicated Patient Age Range
Not Found
Intended User / Care Setting
icobrain is used by trained professionals in hospitals, imaging centers or in image processing labs.
Description of the training set, sample size, data source, and annotation protocol
Not Found
Description of the test set, sample size, data source, and annotation protocol
The subjects upon whom the CT software was tested include TBI patients and potential dementia patients.
In the accuracy experiments, the lesions, basal cisterns, lateral ventricles and midline shift are compared to manually segmented ground truth, while the lateral ventricles and whole brain volumes are compared to MR images segmented by the cleared icobrain 3.0 software. Reproducibility was also tested on CT images produced in the same scanning session. The experiments encompassed 544 subject datasets in total.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Performance testing included validation for accuracy and reproducibility of the CT pipeline. Subjects included TBI and potential dementia patients.
Accuracy experiments compared lesions, basal cisterns, lateral ventricles, and midline shift to manually segmented ground truth. Lateral ventricles and whole brain volumes were compared to MR images segmented by the cleared icobrain 3.0 software.
Reproducibility was tested on CT images from the same scanning session.
Relevant acceptance criteria for each experiment type were set based on literature review, and all experiments passed these criteria.
The tests involved 544 subject datasets.
Averaged over all experiments, the Pearson correlation coefficient between compared measurements was 0.95, and the intraclass correlation coefficient was 0.94.
Validation tests demonstrated the system provides all capabilities necessary to operate according to its intended use.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Pearson correlation coefficient: 0.95
Intraclass correlation coefficient: 0.94
Predicate Device(s)
Reference Device(s)
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 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).
0
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: a symbol on the left and the text "FDA U.S. FOOD & DRUG ADMINISTRATION" on the right. The symbol on the left is a stylized representation of a human figure, while the text on the right is written in blue and white. The logo is commonly used to identify the FDA and its role in regulating food and drugs in the United States.
November 6, 2018
icometrix NV Jan Verheyden VP Kolonel Begaultlaan 1b/12 Leuven, 3012 BELGIUM
Re: K181939
Trade/Device Name: icobrain Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving And Communications System Regulatory Class: Class II Product Code: LLZ Dated: October 3, 2018 Received: October 3, 2018
Dear Jan Verheyden:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You mav, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be avare that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's
1
requirements, including, but not limited to: registration and listing (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.html; good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
Michael D. O'Hara For
Robert A. Ochs. Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K181939
Device Name icobrain
Indications for Use (Describe)
icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR or NCCT images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR or NCCT images.
Icobrain consists of two distinct image processing pipelines: icobrain cross and icobrain long.
icobrain cross is intended to provide volumes from MR or NCCT images acquired at a single time point. icobrain long is intended to provide changes in volumes between two MR images that were acquired on the same scanner, with the same image acquisition protocol and with same contrast at two different timepoints. The results of icobrain cross cannot be compared with the results of icobrain long.
X Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
K181939
Doc. 134873199.21 (Idisplay/MSMET/CT_Section+5.+510%28k%29+Summary), 2018-10-09 14:56 UTC
- · 5.1 Submitter
- 5.2 Device
- 5.3 Predicate Device
- Intended Use
- . 2.4
2.5 Device Description - 5.6 Comparison with predicate device
- 5.7 Performance testing
5.1 Submitter
| Name: | icometrix NV |
|---|---|
| Address: | Kolonel Begaultlaan lb/12 |
| 3012 Leuven | |
| Belgium | |
| Contact Person: | Jan Verheyden |
| Telephone number: | +32 16 369 000 |
| Fax Number: | N.A. |
| E-mail: | jan.verheyden@icometrix.com |
| Date Prepared: | 10 Sep 2018 |
5.2 Device
| Device Trade Name: | icobrain |
|---|---|
| Common Name | Medical Image Processing Software |
| Classification Name | System, Image processing, Radiological |
| Number | 892.2050 |
| Product Code: | LLZ |
| Classification Panel: | Radiology |
4
5.3 Predicate Device
| Device | ico brain |
|---|---|
| 510(k) Number | K180326 |
| Manufacturer | icometrix NV |
5.4 Intended Use
icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR or NCCT images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR or NCCT images.
icobrain consists of two distinct image processing pipelines: icobrain cross and icobrain long.
- · icobrain cross is intended to provide volumes from MR or NCCT images acquired at a single time point.
- · icobrain long is intended to provide changes in volumes between two MR images that were acquired on the same scanner, with the same image acquisition protocol and with same contrast at two different timepoints.
The results of icobrain cross cannot be compared with the results of icobrain long.
5.5 Device Description
The following flowchart illustrates the overall architecture of icobrain.
Image /page/4/Figure/10 description: The image shows a flowchart of an image processing pipeline. The pipeline starts with input images in DICOM format, followed by preprocessing and image processing steps. Next, output generation creates reports and images. Finally, the pipeline produces a final report in PDF or DICOM format, along with output images in DICOM format.
The input images can be MR images (current icobrain software - K161148 and K180326) or CT images. During the pre-processing, the modality and/or sequence of each scan is detected and each scan is converted from DICOM format to NIFTI format. The image processing then performs the actual segmentation and calculates the measurements of the brain structures and abnormalities. Finally, the computed measurements are summarized into an electronic report and (some) segmentations are overlaid on the input images, generating output images in DICOM format.
Since the processing of MR images remains unchanged compared to the currently approved icobrain software (see KI 6 I 148 and K180326), the remainder of this file will focus on the design of the software that processes CT images. We refer to the overall architecture focused on (pre)processing CT images as the CT pipeline.
outputs of CT pipeline
Report I:
5
- · normalized volume of the whole brain (sum of white and grey matter)
- · normalized volume of the lateral ventricles
This report is useful to be applied in (potential) dementia patients.
Report 2:
- · measurement of the midline shift, i.e. the shift of the brain past its center line.
- · normalized volume of basal cisterns (suprasellar, quadrigeminal, prepontine)
- · volume (total, highest) of hyperdensities
This report is useful to be applied in (potential) TBI patients.
5.6 Comparison with predicate device
Likewise our clinical product icobrain 3.0 (K180326), icobrain 4.0 intends for automatic labeling, visualization and volumetric quantification of segmentable brain structures based on 3-dimensional medical images. The devices both take 3D images of the brain as input and generate an electronic report with similar quantitative information.The main difference is that icobrain 4.0 will use CT images in addition to MR images to start from. The table below compares the device to market with the proposed predicate device. The main differences are underlined.
| Predicate device | Device to market | |
|---|---|---|
| Device Trade | ||
| Name | icobrain | icobrain |
| Version | 3.0 | 4.0 |
| Common | ||
| Name | Medical Image Processing Software | Medical Image Processing Software |
| 510(k) | ||
| Number | K180326 | |
| Manufacturer | icometrix NV | icometrix NV |
| Kolonel Begaultlaan Ib / 12 | ||
| 3012 Leuven | ||
| BELGIUM | Kolonel Begaultlaan Ib / 12 | |
| 3012 Leuven | ||
| BELGIUM | ||
| Regulation | ||
| Number | 21 CFR 892.2050 | 21 CFR 892.2050 |
| Device | ||
| Classification | ||
| Name | System, Image processing, Radiological | System, Image processing, Radiological |
| Product Code | LLZ | LLZ |
| Regulatory | ||
| Class | II | II |
| Classification | ||
| Panel | Radiology | Radiology |
| Function | Automatically identifying and quantifying the volumes of | |
| brain segmentable structures, automatic labeling and | ||
| visualization. | Automatically identifying and quantifying the volumes of brain | |
| segmentable structures, automatic labeling and visualization. | ||
| Intended use | icobrain is intended for automatic labeling, visualization and | |
| and volumetric quantification of segmentable brain structures from | ||
| structures from a set of MR images. This software is | ||
| intended to automate the current manual process of | ||
| identifying, labeling and quantifying the volume of | ||
| segmentable brain structures identified on MR images. |
icobrain consists of two distinct image processing
pipelines: icobrain cross and icobrain long.
icobrain cross is intended to provide volumes
from images acquired at a single timepoint.icobrain long is intended to provide changes in
volumes between two images that were acquired
on the same scanner, with the same image
acquisition protocol and with same contrast at two
different timepoints.
The results of icobrain cross cannot be compared with
the results of icobrain long. | icobrain is intended for automatic labeling, visualization and
volumetric quantification of segmentable brain structures from
a set of MR or NCCT images. This software is intended to
automate the current manual process of identifying, labeling
and quantifying the volume of segmentable brain structures
identified on MR or NCCT images.
icobrain consists of two distinct image processing pipelines:
icobrain cross and icobrain long.
icobrain cross is intended to provide volumes from
MR or NCCT images acquired at a single time point.icobrain long is intended to provide changes in
volumes between two MR images that were acquired
on the same scanner, with the same image acquisition
protocol and with same contrast at two different
timepoints.
The results of icobrain cross cannot be compared with the
results of icobrain long. |
| Technical
characteristics | Software packageOperates on off-the-shelf hardware (multiple
vendors)DICOM compatiblesegmentation by classical machine learning
(unsupervised voxel classication with Gaussian
Mixture Models)Input: TI-weighted and fluid-attenuated inversion
recovery (FLAIR) MR images from a single or
multiple time pointsOutput:
multiple electronic reports with volumetric
information of brain structuresannotated DICOM images | Software packageOperates on off-the-shelf hardware (multiple vendors)DICOM compatiblesegmentation by classical machine learning and deep
learning (in our case supervised voxel classication with
Convolutional Neural Networks)Input:
TI-weighted and fluid-attenuated inversion
recovery (FLAIR) MR images from a single or
multiple time pointsnon-contrast CT from a single time pointOutput:
multiple electronic reports with volumetric
information of brain structures and midline shiftannotated DICOM images |
| Performance
measurement
testing | Accuracy
brain segmentable structure volumes / volume
changes compared to simulated and/or manually
labeled ground truth
Reproducibility
brain segmentable structure volumes / volume
changes compared on test-retest images | Accuracy
MR measurements
brain segmentable structure volumes / volume
changes compared to simulated and/or
manually labeled ground truthCT measurements
lesions and midline shift: compared to manually
labeled ground truthlateral ventricles and whole brain: MR images
segmented by cleared icobrain 3.0 software
taken as ground truth
Reproducibility
MR measurements
brain segmentable structure volumes / volume
changes compared on test-retest imagesCT measurements
simulation study |
| Environment
of use | icobrain is used by trained professionals in hospitals,
imaging centers or in image processing labs. | icobrain is used by trained professionals in hospitals, imaging
centers or in image processing labs. |
| Testing | Product Risk AssessmentSoftware verification testsSoftware validation tests | Product Risk AssessmentSoftware verification testsSoftware validation tests |
6
5.7 Performance testing
To demonstrate the performance of the CT pipeline of icobrain 4.0, the measurements are validated for accuracy and reproducibility. The subjects upon whom the CT software was tested include TBI patients and potential dementia patients.
In the accuracy experiments, the lesions, basal cisterns, lateral ventricles and midline shift are compared
7
to manually segmented ground truth, while the lateral ventricles and whole brain volumes are compared to MR images segmented by the cleared icobrain 3.0 software. Reproducibility was also tested on CT images produced in the same scanning session. Literature review has been performed to set relevant acceptance criteria for each type of experiment. All experiments passed the acceptance criteria.
The experiments encompassed 544 subject datasets in total. Averaged over all experiments, the Pearson correlation coefficient between the compared measurements was 0.95 and the intraclass correlation coefficient was 0.94.
Besides the verification experiments, validation tests demonstrate the system as a whole provides all the capabilities necessary to operate according to its intended use.
5.8 Conclusions
The performance testing presented above establishes that the icobrain is safe and effective for its intended use. The comparison above demonstrates that the icobrain device is substantially equivalent to the predicate device.
| Declarations: | This summary includes only information that is also covered in the body of the 510(k). This summary does not contain any puffery or unsubstantiated labeling claims. This summary does not contain any raw data, i.e., contains only summary data. This summary does not contain any trade secret or confidential commercial information. This summary does not contain any patient identification information. |
|---|---|
| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
This document is reviewed and approved by Jan Verheyden, Vice President Traumatic Brain Injury of ico metrix, based on the present data and information.
Image /page/7/Figure/7 description: The image shows a signature and a date. The signature is a blue ink scribble. The date is October 1, 2018.