(112 days)
Not Found
Yes
The description mentions an "atlas pool" of 300 brain MRIs with segmentation labels used for training, and performance metrics like Dice coefficient and Coefficient of Variation are reported, which are common in the evaluation of ML-based segmentation algorithms. While the terms "AI" or "ML" are not explicitly used, the methodology described strongly suggests the use of a learning-based approach for automated segmentation.
No
The device is described as post-processing software that provides measurements and analysis for diagnosis and assessment, not for direct treatment or therapy.
Yes
The software provides "volumetric quantification of hippocampus" and is a "support tool for clinicians in assessment of structural MRIs", which are diagnostic functions.
Yes
The device is explicitly described as "fully automated post-processing software" and its output is a "morphometric report in PDF format." There is no mention of any accompanying hardware or hardware components included with the device.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs analyze samples taken from the human body. This device analyzes medical images (T1W MRIs) which are generated by the human body, but are not biological samples like blood, urine, or tissue.
- The intended use is image processing and analysis. The software processes existing medical images to provide quantitative measurements and visualizations. It does not perform tests on biological specimens to diagnose or monitor a condition.
- The output is a morphometric report. This report contains measurements and visualizations derived from the image data, not results from a laboratory test on a biological sample.
The device falls under the category of medical image processing software, which is regulated differently than IVDs. The predicate devices listed (NeuroQuant and NeuroReader) are also medical image processing software, further supporting this classification.
No
The text states "Not Found" under "Control Plan Authorized (PCCP) and relevant text," and there is no explicit language stating that the FDA has reviewed, approved, or cleared a PCCP for this specific device.
Intended Use / Indications for Use
AccuBrain is a fully automated post-processing software that provides automatic labeling, visualization and volumetric quantification of hippocampus from a set of MRIs and returns an analysis report.
Product codes
LLZ
Device Description
AccuBrain is a fully automated post-processing software that provides automatic labeling, visualization and volumetric quantification of hippocampus from a set of T1W MRIs and returns an analysis report. The resulting output is a morphometric report in PDF format. The software is suitable for use in both clinical trial research and routine patient care as a support tool for clinicians in assessment of structural MRIs.
AccuBrain provides morphometric measurements based on 3D T1 MRI series. The output of the software includes volumes of hippocampus.
The AccuBrain processing architecture includes an automated internal pipeline that performs artifact correction, segmentation, hippocampus quantification, volume calculation and report generation.
Additionally, automated safety measures include automated quality control functions, such as DICOM check, age check and image resolution check and image quality check.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Not Found
Input Imaging Modality
3D T1 MRI
Anatomical Site
Hippocampus (brain)
Indicated Patient Age Range
Not Found
Intended User / Care Setting
Clinical trial research and routine patient care as a support tool for clinicians.
Used by medical professional, such as radiologists, neurologists and neuroradiologists, as well as by clinical researchers.
Description of the training set, sample size, data source, and annotation protocol
The atlas pool, consisting of 300 brain MRIs together with their segmentation labels, were previously obtained from different individuals using different scanners and have highly variable appearances. Each atlas contains both brain MRI and the prior encoded radiologist-specified anatomy information for hippocampus.
Demographic information of the atlas data (N=300):
Gender: Female (151), Male (149)
Disease Status: AD (123), NC (115), MCI (62)
Age: 51-60 (25), 61-70 (96), 71-80 (118), 81-90 (61)
Magnetic Field Strength: 1.5T (68), 3T (232)
Manufacturer: GE (131), Philips (44), Siemens (125)
In-plane resolution: 1x1 (214), 0.9375x0.9375 (84), 0.8594x0.8594 (2)
FOV (mm²): 220 (2), 230 (135), 240 (84), 256 (79)
Slice Thickness(mm): 1 (216), 1.2 (84)
Description of the test set, sample size, data source, and annotation protocol
The subjects upon whom the device was tested include healthy subjects, Alzheimer's disease patients and Mild Cognitive Impairment patients.
With 135 data provided by the EADC-ADNI HarP. AccuBrain segmentation accuracy with 3D T1 MRI scans was evaluated by comparing AccuBrain results and manual segmentation results.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Performance Testing: Accuracy and Reproducibility.
Sample Size: 135 data for accuracy, unknown for reproducibility (repeated 3D T1 MRI scans for the same subjects).
Key results:
Accuracy: The mean Dice coefficient by comparing AccuBrain results and manual segmentation results was 0.89 (std: 0.03), 0.89 (std: 0.03) and 0.89 (std: 0.03) for right, left and total hippocampal volumes, respectively.
Reproducibility: The mean intrascanner CV values were 3.20% and 1.23%, the mean percentage absolute volume differences DIFF values were 4.52% and 1.74% for left and right hippocampus, respectively.
Compared with the performances of the predicate devices, the results show that the subject device is safe and effective and performs as well as the predicate devices.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Dice coefficient, Coefficient of Variation (CV), Percentage absolute volume differences (DIFF).
Predicate Device(s)
Reference Device(s)
Not Found
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 contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
BrainNow Medical Technology Limited % You Yijie General Manager Qimmiq Medical Consulting Service Co., Ltd. RM.1711, Building K. NO.101 Science Ave International Creative Valley Guangzhou, Guangdong 510663 CHINA
January 15, 2021
Re: K202847
Trade/Device Name: AccuBrain Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: LLZ Dated: September 11, 2020 Received: December 11, 2020
Dear You Yijie:
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 may, 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 aware 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 807); labeling (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/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); 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 https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). 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 (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
For
Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K202847
Device Name AccuBrain
Indications for Use (Describe)
AccuBrain is a fully automated post-processing software that provides automatic labeling, visualization and volumetric quantification of hippocampus from a set of MRIs and returns an analysis report.
Type of Use (Select one or both, as applicable)
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
510(k) Summary
"510(k) Summary" as required by 21 CFR Part 807.92.
1. Submitter's Information
Establishment Registration Information
Name: BrainNow Medical Technology Limited Address: Unit 201, 2/F, Lakeside 2, No. 10 Science Park West Avenue, Hong Kong Science Park, Shatin, N.T., Hong Kong ZIP/Postal Code: 999077
Contact Person of applicant
Contact Person: Junbing Huang Telephone Number: 86-13416183887 Fax Number: 852-36221760 Email: 417731983@qq.com
Contact Person of the Submission:
Name: You Yijie Address: RM.1711, Building K, NO.101 Science Ave International Creative Valley Development Zone, Guangzhou China TEL: +86 020-8224 5821 FAX: +86 020-8224 5821 Email: Jet.you@qimmig-med.com
Date to prepare: 9/11/2020
2. Device Information
Device Name: AccuBrain Common Name: Neuroimage Analysis Software Model: AccuBrain_Intl Software version: V1.0.0.200703 Classification Name: System, Image Processing, Radiological Regulation Number: 21 CFR 892.2050 Regulation Description: Picture archiving and communications system Product Code: LLZ Classification Panel: Radiology Regulation Class: -
3. Predicate Device Information
| Item | Primary Predicate(A) | Predicate or Reference Device (B) |
|---|---|---|
| 510(k) submitter/holder | CorTechs Labs, Inc | Brainreader Aps |
| 510(K) Number | K170981 | K140828 |
| Device name | NeuroQuant | NeuroReader Medical |
| Image Processing Software | ||
| Common name | Medical Image | |
| Processing Software | Neuroreader |
4
| Regulation Description | Picture archiving and
communications system | Picture archiving and
communication system |
|------------------------|------------------------------------------------|-----------------------------------------------|
| Review panel | Radiology | Radiology |
| Product code | LLZ | LLZ, LNH |
| Regulation Class | Class II | Class II |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 |
4. Device Description
AccuBrain is a fully automated post-processing software that provides automatic labeling, visualization and volumetric quantification of hippocampus from a set of T1W MRIs and returns an analysis report. The resulting output is a morphometric report in PDF format. The software is suitable for use in both clinical trial research and routine patient care as a support tool for clinicians in assessment of structural MRIs.
AccuBrain provides morphometric measurements based on 3D T1 MRI series. The output of the software includes volumes of hippocampus.
The AccuBrain processing architecture includes an automated internal pipeline that performs artifact correction, segmentation, hippocampus quantification, volume calculation and report generation.
Additionally, automated safety measures include automated quality control functions, such as DICOM check, age check and image resolution check and image quality check.
5. Principle of operation
AccuBrain automatically segmented the subject's hippocampi using the uploaded T1W MRIs in a multi-atlas-based segmentation manner. The quantification and visualization of hippocampal segmentation results were output in the form of a morphometric analysis report.
The hippocampal segmentation procedure is described as follows. 1) Pre-processing to increase the image quality, including noise reduction, bias field correction, and intensity normalization to normalize intensity level of MRIs from different scanners. For noise reduction method, we used non-local mean filtering method [1]. Bias correction method used in AccuBrain is N4 bias correction [2]. Intensity Normalization method used in AccuBrain is histogram matching [3]. 2) Atlas selection. The atlas pool, consisting of 300 brain MRIs together with their segmentation labels, were previously obtained from different individuals using different scanners and have highly variable appearances. Each atlas contains both brain MRI and the prior encoded radiologist-specified anatomy information for hippocampus. The detailed of demographic information about the atlas data was described in Table 1. During processing, AccuBrain selects a number of brain images from the atlas pool based on similarity with the subject images. The similarity measures used in this step is Normalized Cross correlation (NCC). AccuBrain will select 10 images from the atlas pool with highest NCC scores. 3) Image segmentation. The non-rigid image registration is performed to match the selected image with the subject image. The resulting transformation field will be applied to transform the predefined atlas label to the subject image. As 10 template images are selected, 10 segmentation results are obtained and will be merged using STAPLE label fusion method l41 to fuse the final segmentation labels of the subject image.
5
| Demographic Categories | Frequency (subject
number) | Percentage(%) |
|-------------------------|-------------------------------|---------------|
| Gender | | |
| Female | 151 | 50.3 |
| Male | 149 | 49.7 |
| Disease Status | | |
| AD | 123 | 41 |
| NC | 115 | 38.3 |
| MCI | 62 | 20.7 |
| Age | | |
| 51-60 | 25 | 8.3 |
| 61-70 | 96 | 32 |
| 71-80 | 118 | 39.3 |
| 81-90 | 61 | 20.3 |
| Magnetic Field Strength | | |
| 1.5T | 68 | 22.7 |
| 3T | 232 | 77.3 |
| Manufacturer | | |
| GE | 131 | 43.7 |
| Philips | 44 | 14.7 |
| Siemens | 125 | 41.7 |
| In-plane resolution | | |
| 1x1 | 214 | 71.3 |
| 0.9375x0.9375 | 84 | 28 |
| 0.8594x0.8594 | 2 | 0.7 |
| FOV (mm²) | | |
| 220 | 2 | 0.7 |
| 230 | 135 | 45 |
| 240 | 84 | 28 |
| 256 | 79 | 26.3 |
| Slice Thickness(mm) | | |
| 1 | 216 | 72 |
| 1.2 | 84 | 28 |
Table 1. Demographic information of the atlas data
6. Indications for Use
AccuBrain is a fully automated post-processing software that provides automatic labeling, visualization and volumetric quantification of hippocampus from a set of T1W MRIs and returns an analysis report.
7. Comparison of Predicate Devices
Summary Comparison Table for the subject device and predicate devices (K170981 and K140828):
| Comparison
Elements | Subject Device | Predicate
Device (A) | Predicate or
Reference
Device (B) | Discussion of
difference |
|------------------------|----------------|-------------------------|-----------------------------------------|-----------------------------|
| Device Name | AccuBrain | NeuroQuant | NeuroReader | / |
| 510(k) No | / | K170981 | K140828 | / |
6
| Regulation No | 21 CFR
892.2050 | 21 CFR
892.2050 | 21 CFR
892.2050 | Same | | | | | according to the ANSI
AAMI IEC
62304:2006/A1:2016
(Software
Documentation,
section 004) and the
Accuracy and
Reproducibility of the
Subject Device was
verified (section 006).
The difference does
not affect the
determination of
substantial
equivalence. |
|------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------|------------------------------------------------------------------------------|------------------------------------------------------------------------------|------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Regulation
Description | "Picture
archiving and
communications
system" | "Picture
archiving and
communications
system" | "Picture
archiving and
communications
system" | Same | Processing
architecture | Automated
internal pipeline
that performs: | Automated
internal pipeline
that performs: | Information not
publicly
available | SE-within the
predicate |
| Classification
name | System, Image
Processing,
Radiological | System, Image
Processing,
Radiological | System, Image
Processing,
Radiological | Same | | -artifact
correction | -artifact
correction | | Both are performed: |
| Classification | Class II | Class II | Class II | Same | | -segmentation | -segmentation | | -artifact correction |
| Product code | LLZ | LLZ | LLZ | Same | | -hippocampus
quantification | -lesion
quantification | | -segmentation |
| Indications for
use | AccuBrain is a
fully automated
post-processing
software that
provides
automatic
labeling,
visualization
and volumetric
quantification of
hippocampus
from a set of
T1W MRIs and
returns an
analysis report. | Automatic
labeling,
visualization and
volumetric
quantification of
segmentable
brain structures
and lesions from
a set of MR
images.
Volumetric data
may be
compared to
reference
percentile data | Automatic
labeling,
visualization
and volumetric
quantification of
segmentable
brain 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. | SE-within the
predicate
Both are indicated to
automatic labeling,
visualization and
volumetric
quantification of
hippocampus from a
set of T1W MRIs Is
and returns an
analysis report. | | -volume
calculation | -volume
calculation | | -hippocampus
quantification |
| Design and
incorporated
technology | • Automated
measurement of
hippocampus
volumes
• Automatic
atlas-based
segmentation
and
quantification of
hippocampus
using an atlas
pool consisting
of difference | • Automated
measurement of
brain tissue
volumes and
structures and
lesions
• Automatic
segmentation
and
quantification of
brain structures
using a dynamic
probabilistic | Information not
publicly
available | SE
Both are indicated to
automate
measurement of
hippocampus
volumes through
automatic atlas-based
segmentation and
quantification of
hippocampus base on
an atlas pool
consisting of
difference template | | -report
generation | -report
generation | | -volume calculation |
| template
images with
highly variable
appearance
together with
their prior
encoded
radiologist-
specified
anatomy
information | images with highly
variable appearance
together with their
prior encoded
radiologist-specified
anatomy information | neuroanatomical
atlas, with age
and gender
specificity,
based on the
MR image
intensity | Information not
publicly available | images with highly
variable appearance
together with their
prior encoded
radiologist-specified
anatomy information.
The difference does
not affect the
determination of
substantial
equivalence. | | | | | -report generation |
| Physical
characteristics | • Web-based
application
• Operates on
off-the -shelf
hardware
(multiple
vendors) | • Software
package
• Operates on
off-the-shelf
hardware
(multiple
vendors) | Information not
publicly
available | SE
The Cybersecurity of
Subject Device was
verified
(Cybersecurity
Information
Document, section
005).
And the Subject
Device was verified
according to the
ANSI AAMI IEC
62304:2006/A1:2016
(section 004) and
the Accuracy and
Reproducibility of
the Subject Device
was verified (section
006).
The difference does
not affect the
determination of
substantial
equivalence. | | | | | The difference does
not affect the
determination of
substantial
equivalence. |
| Operating
system | Supports
Windows | Supports Linux,
Mac OS X and
Windows. | Information not
publicly
available | SE--within the
predicate.
The Operating
system of Subject
Device is fewer than
Predicate Device (A),
the risk of the Subject
Device is fewer than
Predicate Device (A).
And the Subject
Device was verified | Data source | • MRI scanner:
3D T1 MRI
scans acquired
with specified
protocols | • MRI scanner:
3D T1 MRI
scans acquired
with specified
protocols | Information not
publicly
available | Same |
| | • AccuBrain
supports
DICOM format
as input | • NeuroQuant
supports DICOM
format as input | | | | | | | |
| Output | -Provides
volumetric | • Provides
volumetric
measurements | Information not
publicly
available | SE-within the
predicate | | | | | |
7
8
9
| | measurements
of hippocampus
-Includes
segmented
color overlays
and an analysis
report (just
volumetric of
the
hippocampus) | of brain
structures and
lesions
• Includes
segmented color
overlays and
morphometric
reports
• Automatically
compares
results to
reference
percentile data
and to prior
scans when
available
• Supports
DICOM format
as output of
results that can
be displayed on
DICOM
workstations
and Picture
Archive and
Communications
Systems | | Both provide
volumetric
measurements of
hippocampus
-Includes segmented
color overlays and an
analysis report
including the
volumetric of the
hippocampus.
The difference does
not affect the
determination of
substantial
equivalence. |
|----------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Accuracy | The mean DICE
of AccuBrain
results and
manual
segmentation
results is 0.89,
0.89 and 0.89
for right, left and
total
hippocampus,
respectively. | For major
subcortical brain
structures Dice's
coefficients are
in the range of
80%-90%. | NeuroReader
can segment
the
hippocampus
with a Dice
similarity index
of 0.87 for both
the right and left
hippocampus. | SE
The accuracy and
reproducibility of
hippocampus
segmentation of
AccuBrain with T1W
MRI images are
comparable with
Predicate Device
(A) and Predicate
Device (B). The
accuracy and
reproducibility of
Subject Device was
verified (Accuracy
and Reproducibility
Test Report, section
006). |
| | | | | The difference does
not affect the
determination of
substantial
equivalence. |
| Safety | • Automated
quality control
functions
- DICOM check
- Age check
- Image
resolution check - Image quality
check
Diagnostic
decisions
should be made
by trained
clinicians. | • Automated
quality control
functions - Tissue contrast
check - Scan protocol
verification - Atlas alignment
check
• Results must
be reviewed by
a trained
physician | Information not
publicly
available | SE
Both are conducted
the - DICOM check,
Age check, Image
resolution check,
Image quality check.
The Cybersecurity of
Subject Device was
verified
(Cybersecurity
Information
Document, section
005).
And the Subject
Device was verified
according to the IEC
62304(Software
Documentation,
section 004) and the
Accuracy and
Reproducibility of
the Subject Device
was verified
(Accuracy and
Reproducibility test
report, section 006).
The difference does
not affect the
determination of
substantial
equivalence. |
10
Subject device and predicate devices are softwares for automatically identifying and quantifying volumes of brain structures. Subject and predicate devices take 3D MR images of the brain as input and generate electronic report with similar quantitative information.
AccurBrain and NeuroQuant achieve the intended use based on similar principle and processing architecture, since the quantification systems implement brain segmentation and quantification using atlas-based segmentation scheme. Both hippocampi are segmented and the volumes are calculated.
11
AccurBrain and NeuroQuant are DICOM compatible and operate on off-the-shelf hardware. Meanwhile, both devices are used by medical professional, such as radiologists, neurologists and neuroradiologists, as well as by clinical researchers, as a support tool in assessment of structural MRIs.
The output volumes which both devices provide include volumes of left hippocampus, right hippocampus and whole hippocampi.
8. Performance Testing
To demonstrate the performance of AccuBrain (model: AccuBrain_Intl), the measured volumes and volume differences of hippocampus are validated for accuracy and reproducibility. The subjects upon whom the device was tested include healthy subjects, Alzheimer's disease patients and Mild Cognitive Impairment patients. AccuBrain segmentation accuracy with 3D T1 MRI scans was evaluated using Dice coefficient metric. With 135 data provided by the EADC-ADNI HarP, the mean Dice coefficient by comparing AccuBrain results and manual segmentation results was 0.89 (std: 0.03), 0.89 (std: 0.03) and 0.89 (std: 0.03) for right, left and total hippocampal volumes, respectively. Segmentation reproducibility of repeated 3D T1 MRI scans for the same subjects was evaluated using Coefficient of Variation (CV). The mean intrascanner CV values were 3.20% and 1.23%, the mean percentage absolute volume differences DIFF values were 4.52% and 1.74% for left and right hippocampus, respectively. Compared with the performances of the predicate devices, the results presented above shows that the subject device is safe and effective and performs as well as the predicate devices. The AccuBrain (Model: AccuBrain_Intl) was designed, verified, and validated according to the company's Design Control process and has been subjected to extensive safety and performance testing as shown in the test results provided in this submission. Verification and Validation testing data demonstrate that the device meets all of its specifications.
The Accuracy and Reproducibility of AccuBrain (Model: AccuBrain Intl) was verified please see section 006 for the Accuracy and Reproducibility Test Report.
The software of AccuBrain (Model: AccuBrain Intl) was verified according to the ANSI AAMI IEC 62304:2006/A1:2016 Medical device software - Software life cycle processes [Including Amendment 1 (2016)]. Please see section 004 for the Software Documentation.
The Cybersecurity of AccuBrain (Model: AccuBrain Intl) was verified. Please see section 005 for the Cybersecurity Information Document.
During the verification and validation activity the following quidance documents were used:
General Principles of Software Validation: Guidance for Industry and FDA Staff Postmarket Management of Cybersecurity in Medical Devices: Guidance for Industry and Food and Drug Administration Staff
Content of Premarket Submissions for Management of Cybersecurity in Medical Devices: Draft Guidance for Industry and Food and Drug Administration Staff Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices: Guidance for Industry and FDA Staff
9. Conclusions
The performance testing presented above shows that the device is as safe, as effective and performs as well as the predicate devices(A) and predicate devices(B),
12
and as well as gold standard-computer-aided expert manual segmentation. By virtue of the physical characteristics and intended user, AccuBrain(AccuBrain_Intl) is substantially equivalent to its predicate devices (A) (K170981) and predicate devices (B)(K140828).
10. Bibliography
[1] Coll, Bartomeu & Morel, Jean-Michel. (2005). A non-local algorithm for image denoising. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2. 60- 65 vol. 2.
[2] Tustison NJ, Avants BB, Cook PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging. 2010;29(6):1310-1320.
[3] Laszlo G. Nyul, Jayaram K. Udupa, and Xuan Zhang, "New Variants of a Method of MRI Scale Standardization", IEEE Transactions on Medical Imaging, 19(2):143-150, 2000.
[4] Warfield SK, et al. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. Medical Imaging, IEEE Transactions on. 2004;23:903-921.