(136 days)
VBrain is a software device intended to assist trained medical professionals, during their clinical workflows of radiation therapy treatment planning, by providing initial object contours of known (diagnosed) brain tumors (i.e., region of interest, ROI) on axial T1 contrast-enhanced brain MRI images.
VBrain uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) brain tumor on MRI images for trained medical professionals' attention, which is meant for informational purposes only and not intended for replacing their current standard practice of manual contouring process. VBrain does not alter the original MRI image, nor does it intend to be used to detect tumors for diagnosis. VBrain is intended only for generating Gross Tumor Volume (GTV) contours of brain metastases, meningiomas, and acoustic neuromas on axial T1 contrast-enhanced MRI images; It is not intended to be used with images of other brain tumors. The user must know the tumor type when they use VBrain. VBrain is intended to be used on adult patients only.
Medical professionals must finalize (confirm or modify) the contours generated by VBrain, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
VBrain is a software device indicated for use in the analysis of brain MRI images. The device consists of image preprocessing, deep learning neural networks, and postprocessing components, and is intended to assist trained medical professionals, during clinical workflows of radiation therapy treatment planning, by highlighting and contouring known (diagnosed) brain tumors on the axial T1 contrast-enhanced MRI images. The software is configured to work on a PACS network. Upon user's request, it will patient scans or users can send corresponding MR images, and the device will utilize deep learning neural networks to generate contours for the detected/diagnosed brain tumors and export the results as DICOM-RT objects (using the RT Structure Set ROI Contour attribute, RTSTRUCT) back to the network. The medical professionals must finalize (confirm and modify) the contours produced by VBrain as necessary using an external platform that supports RT DICOM viewing/editing, such as a treatment planning system.
The provided text describes the performance data for Vysioneer's VBrain device. Here's a breakdown of the acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
| Performance Metric | Acceptance Criteria/Performance Goal (Implicitly "As Demonstrated") | Reported Device Performance (95% Confidence Interval) |
|---|---|---|
| Lesion-wise Sensitivity | Meets performance goals | 90.3% (86.1-93.7%) |
| False-Positive Rate (tumors/case) | Meets performance goals | 0.681 (0.500-0.879) |
| Lesion-wise Dice Similarity Coefficient (DSC) | Meets performance goals | 0.793 (0.775-0.811) |
| Average Hausdorff Distance (in terms of lesion size) | Meets performance goals | 5.0% (4.4-5.6%) |
| Centroid Distance (in terms of lesion size) | Meets performance goals | 5.6% (5.0-6.2%) |
Note: The document explicitly states "VBrain meets all performance goals" and "All the metrics were demonstrated to pass the performance goals," implying that the reported performance values themselves serve as the acceptance criteria being met.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 116 cases with 238 tumors.
- Data Provenance: Retrospective, multicenter, multinational. The data was acquired from 4 different institutions: 3 from the U.S. and 1 non-U.S.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Three.
- Qualifications of Experts: Board-certified radiation oncologists.
4. Adjudication Method for the Test Set
- Method: Consensus. The ground truth of each tumor contour was generated from the consensus of the three board-certified radiation oncologists.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study to evaluate how human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the VBrain algorithm relative to ground truth established by expert consensus.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Yes, a standalone performance study was conducted. The reported metrics (Sensitivity, False-Positive Rate, DSC, Hausdorff Distance, Centroid Distance) directly evaluate the VBrain algorithm's performance in segmenting tumors against an expert-defined ground truth, without measuring human-in-the-loop performance improvement.
7. Type of Ground Truth Used
- Type: Expert Consensus. The ground truth for tumor contours was established by the consensus of three board-certified radiation oncologists.
8. Sample Size for the Training Set
- The document does not explicitly state the sample size used for the training set. It mentions that VBrain uses an "artificial intelligence algorithm (i.e., deep learning neural networks)" which implies a training phase, but the details of the training data are not provided in this specific excerpt.
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly state how the ground truth for the training set was established. While it describes the ground truth process for the test set, it does not detail the methodology for the training data used to develop the deep learning model.
{0}------------------------------------------------
March 19, 2021.
Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" in a square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION".
Vysioneer Inc % Chiu S. Lin Consultant 33 Rogers Street, # 308 CAMBRIDGE MA 02142
Re: K203235
Trade/Device Name: VBrain Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: QKB Dated: February 9, 2021 Received: February 10, 2021
Dear Chiu Lin:
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/cfpmp/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 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
{1}------------------------------------------------
https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) 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 medical devices and radiation-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) K203235
Device Name V Brain
Indications for Use (Describe)
V Brain is a software device intended to assist trained medical professionals, during their clinical workflows of radiation therapy treatment planning, by providing initial object contours of known (diagnosed) brain tumors (i.e., region of interest, ROI) on axial T1 contrast-enhanced brain MRI images.
V Brain uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) brain tumor on MRI images for trained medical professionals' attention, which is meant for informational purposes only and not intended for replacing their current standard practice of manual contouring process. VBrain does not alter the original MRI image, nor does it intend to be used to detect tumors for diagnosis. VBrain is intended only for generating Gross Tumor Volume (GTV) contours of brain metastases, meningiomas, and acoustic neuromas on axial T1 contrast-enhanced MRI images; It is not intended to be used with images of other brain tumors. The user must know the tumor type when they use VBrain. VBrain is intended to be used on adult patients only.
Medical professionals must finalize (confirm or modify) the contours generated by VBrain, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
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}------------------------------------------------
Image /page/3/Picture/1 description: The image features the logo for Vysioneer, a company name displayed in a bold, sans-serif font. Above the name is a stylized 'V' shape, rendered in a shade of purple. Below the name is a horizontal purple line, and underneath that is the alphanumeric code 'K203235'.
Section 5 510(k) Summary
5.1 Submitter
Vysioneer Inc.
33 Rogers St. #308, Cambridge, MA 02142
| Contact Person: | Jen-Tang Lu, PhD (Chief Executive Officer) |
|---|---|
| Phone: | 609-865-8659 |
| Email: | jt@vysioneer.com |
| Date Summary Prepared: | February 09, 2021 |
5.2 Device Name
| Trade Name: | VBrain |
|---|---|
| Common Name: | Radiological Image Processing Software forRadiation Therapy |
| Regulation Number / Product Code: | 21 CFR 892.2050 / QKB |
5.3 PREDICATE DEVICE
Primary Predicate #1: AccuContour™, K191928, Xiamen Manteia Technology LTD Primary Predicate #2: MIM - MRT Dosimetry, K182624, MIM Software Inc.
Intended Use / Indications for Use 5.4
VBrain is a software device intended to assist trained medical professionals, during their clinical workflows of radiation therapy treatment planning, by providing initial object contours of known (diagnosed) brain tumors (i.e., the region of interest, ROI) on axial T1 contrast-enhanced brain MRI images.
{4}------------------------------------------------
Image /page/4/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of a stylized "V" shape in purple, with the company name "VYSIONEER" written in a sans-serif font below it, also in purple. The logo is simple and modern.
VBrain uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) brain tumor on MRI images for trained medical professionals' attention, which is meant for informational purposes only and not intended for replacing their current standard practice of manual contouring process. VBrain does not alter the original MRI image, nor does it intend to be used to detect turnors for diagnosis. VBrain is intended only for generating Gross Tumor Volume (GTV) contours of brain metastases, meningiomas, and acoustic neuromas on axial T1 contrast-enhanced MRI images; It is not intended to be used with images of other brain tumors. The user must know the tumor type when they use VBrain is intended to be used on adult patients only.
Medical professionals must finalize (confirm or modify) the contours generated by VBrain, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
Device Description ર્ રંડ
VBrain is a software device indicated for use in the analysis of brain MRI images. The device consists of image preprocessing, deep learning neural networks, and postprocessing components, and is intended to assist trained medical professionals, during clinical workflows of radiation therapy treatment planning, by highlighting and contouring known (diagnosed) brain tumors on the axial T1 contrast-enhanced MRI images. The software is configured to work on a PACS network. Upon user's request, it will patient scans or users can send corresponding MR images, and the device will utilize deep learning neural networks to generate contours for the detected/diagnosed brain tumors and export the results as DICOM-RT objects (using the RT Structure Set ROI Contour attribute, RTSTRUCT) back to the network. The medical professionals must finalize (confirm and modify) the contours produced by VBrain as necessary using an external platform that supports RT DICOM viewing/editing, such as a treatment planning system.
Comparison with Predicate Devices 5.6
VBrain is substantially equivalent to a combination of the primary predicate devices AccuContour™ (K191928) and MIM - MRT Dosimetry (K182624).
The proposed device, VBrain, and the primary predicates, AccuContour™ (K191928) and K182624 (MIM - MRT Dosimetry), are all software devices intended to be used in the workflow of radiation therapy by providing tools of segmenting (contouring) of tumors and/or organs on MRI and/or CT images. Both the proposed device and AccuContour™ (K191928) are AI-based (deep learning) software regulated under the Product Code QKB (Radiological Image Processing Software For Radiation Therapy). On the other hand, both the proposed device and K182624 (MIM - MRT Dosimetry) provide tools for tumor contouring. The only difference is that VBrain uses deep learning (neural networks) to automatically generate tumor contours as a starting point for user's review and edit, while K182624 (MIM - MRT Dosimetry) provides a semi-automatic
{5}------------------------------------------------
Image /page/5/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of a stylized letter "V" formed by two diagonal lines in a purple color. Below the symbol, the word "VYSIONEER" is written in a sans-serif font, also in purple. A thin purple line is located below the word.
tool (propagation tool) that requires user's input to start the image segmentation (contouring) process.
Although the proposed new device. VBrain, uses a data-driven deep learning-based algorithm for contouring of known brain tumors, the primary predicate MIM - MRT Dosimetry (K182624) uses a semi-automatic algorithm that requires user's input to start the contouring process. The specific design of the proposed device does not raise different questions of safety and effectiveness, because the new device only provides initial object contours of known (diagnosed) brain tumors for the medical professionals' attention, which are meant for informational purposes only and not intended for replacing their current standard practice of manual contouring process. Medical professionals must use VBrain in conjunction with appropriate software to review and edit results generated automatically by VBrain. In addition, VBrain does not alter the original MRI image, nor does it intend to be used to detect tumors for diagnosis. The medical professionals must know the tumor type when they use VBrain. Consequently, the new device does not change any medical professionals' workflow planning procedure and therefore does not raise different questions of safety and effectiveness.
Please see Table 5-1 comparing the intended use and key technological characteristics of the proposed device and the predicate devices.
| Company | Vysioneer Inc. | Xiamen Manteia Technology LTD. (Primary) | MIM Software Inc. (Primary) |
|---|---|---|---|
| Device Name | VBrain | AccuContour™ | MIM - MRT Dosimetry |
| 510k Number | Pending | K191928 | K182624 |
| Regulation No. | 21CFR 892.2050 | 21CFR 892.2050 | 21CFR 892.2050 |
| Classification | II | II | II |
| Product Code | QKB | QKB | LLZ |
| Intended Use/Indication for Use | VBrain is a software device intended to assist trained medical professionals, during their clinical workflows of radiation therapy treatment planning, by providing initial object contours of known (diagnosed) brain tumors (i.e., the region of interest, ROI) on axial T1 contrast-enhanced brain MRI images. | It is used by radiation oncology department to register multimodality images and segment (non-contrast) CT images, to generate needed information for treatment planning, treatment evaluation and treatment adaptation. The product has two image process functions: (1) Deep learning contouring: it can automatically contour | MIM software is used by trained medical professionals as a tool to aid in evaluation and information management of digital medical images. The medical image modalities include, but are not limited to, CT, MRI, CR, DX, MG, US, SPECT, PET and XA as supported by ACR/NEMA DICOM 3.0. |
| VBrain uses an artificialintelligence algorithm(i.e., deep learningneural networks) tocontour (segment) braintumor on MRI imagesfor trained medicalprofessionals' attention,which is meant forinformational purposesonly and not intendedfor replacing theircurrent standard practiceof manual contouringprocess. VBrain does notalter the original MRIimage, nor does it intendto be used to detecttumors for diagnosis.VBrain is intended onlyfor generating GrossTumor Volume (GTV)contours of brainmetastases,meningiomas, andacoustic neuromas onaxial T1 contrast-enhanced MRI images; itis not intended to beused with images ofother brain tumors. Theuser must know thetumor type when theyuse VBrain. VBrain isintended to be used onadult patients only.Medical professionalsmust finalize (confirm ormodify) the contoursgenerated by VBrain, asnecessary, using anexternal platformavailable at the facilitythat supports DICOM-RT viewing/editingfunctions, such as imagevisualization softwareand treatment planningsystem | the organ-at-risk,including head and neck,thorax, abdomen andpelvis (for both male andfemale),(2) AutomaticRegistration, and(3) Manual Contour.It also has the followinggeneral functions:(1) Receive,add/edit/delete, transmit,input/export, medicalimages and DICOMdata;(2) Patient management;(3) Review of processedimages;(4) Open and Save offiles. | MIM assists in thefollowing indications:• Receive, transmit,store, retrieve,display, print, andprocess medicalimages and DICOMobjects.• Create, display andprint reports frommedical images.• Registration, fusiondisplay, andreview of medicalimages for diagnosis,treatment evaluation,and treatment planning.• Evaluation of cardiacleft ventricular end-diastolic volume,end-systolic volume, andejectionfraction.• Localization anddefinition of objects,such as tumors andnormal tissues inmedical images.• Creation,transformation, andmodification of contoursfor applicationsincluding, but notlimited to, quantitativeanalysis, aiding adaptivetherapy, transferringcontours to radiationtherapy treatmentplanning systems, andarchiving contours forpatient follow-up andmanagement.• Quantitative andstatistical analysis ofPET/SPECT brain scansby comparing to otherregistered PET/SPECTbrain scans | |
| • Planning andevaluation of permanentimplant brachytherapyprocedures (notincludingradioactivemicrospheres).• Calculating absorbedradiation dose as a resultof administering aradionuclide. | |||
| When using deviceclinically, the usershould only use FDAapprovedradiopharmaceuticals. Ifusing with unapprovedones, this device shouldonly be used for researchpurposes. | |||
| Lossy compressedmammographic imagesand digitized film screenimages must not bereviewed forprimary imageinterpretations.Images that are printedto film must be printedusing an FDA-approvedprinter for the diagnosisof digital mammographyimages. | |||
| Mammographic imagesmust be viewed on adisplay system that hasbeen cleared by the FDAfor the diagnosis ofdigital mammographyimages. The software isnot to be used formammography CAD. | |||
| Segmentation(Contouring)Technology | Deep learning | Deep learning | Atlas-based algorithmand propagation tools(requiring user's input to |
| start the imagesegmentation process) | |||
| Operating System | Linux operating system | Microsoft Windows | Microsoft Windows andApple macOS operatingsystems |
| User Population | Trained medicalprofessionals including,but not limited to,radiologists, oncologists,physicians, medicaltechnologists,dosimetrists, andphysicists. | It is used by radiationoncology department. | Trained medicalprofessionals |
| Supported Modalities | Axial T1 contrast-enhanced MRI images | Segmentation Features:Non-Contrast CTRegistration Features:CT, MRI, PET | CT, MRI, CR, DX, MG,US, SPECT, PET andXA as supported byACR/NEMA DICOM3.0. |
| Localization andDefinition of Objects(ROI) | Qualified brain tumors -brain metastases,meningiomas, andacoustic neuromas | Organ-at-risk, includinghead and neck, thorax,abdomen and pelvis (forboth male and female) | Tumors and normaltissues |
| Performance Testing &Software V & V | To support the intendeduse of the VBrain AIsoftware for brain tumorcontouring(segmentation)performance, Vysioneerconducted aretrospective, blinded,multicenter,multinational study withthe VBrain software. Thetest data sets consisted of116 cases acquired from4 different institutions (3US and 1 non-US). Fivemetrics are evaluated: (1)lesion-wise sensitivity,(2) false-positive rate, (3)lesion-wise Dicecoefficient, (4) averageHausdorff distance, and(5) average centroiddistance between | Segmentationperformance testThe segmentationperformance test wasperformed on proposeddevice and predicatedevice to evaluate theautomated segmentationaccuracy. Two separatetests were performed.One test involvedimages generated inhealthcare institutions inChina using scannermodels available inChina covering threemajor vendors. The otherinvolved imagesgenerated in healthcareinstitutions in US usingscanner models availablein US covering threemajor vendors. The threemajor vendors were GE, | MIM Software Inc. hasconducted performanceand integration testingon MIM - MRTDosimetry software witha comparison to acommercially availablesolution for internalradionuclide dosimetry.Standard quality controlphantoms, simulatedphantoms based on theNEMA IEC BodyPhantom, simulatedphantoms based onpatient data, and clinicalpatient data were usedfor verification testing.All tests were performedusing standard clinicalacquisition andreconstruction protocols.The accuracy of planarcorrections for |
| VBrain's segmentationand clinicians' segmentation. All themetrics weredemonstrated to pass theperformance goals.Software verificationand validation testingwere conducted, anddocumentation wasprovided asrecommended by FDA'sGuidance for Industryand FDA Staff,"Guidance for theContent of PremarketSubmissions forSoftware Contained inMedical Devices" forsoftware devicesidentified as MajorLevel of Concern relatedto radiation therapytreatment planning. | Siemens and Philips. Foreach body parts, allintended organs wereincluded in images of theUS and China. Groundtruthing of each imagewas generated from theconsensus of at leastthree licensedphysicians. DICEsimilarity coefficients(DSC) was used forevaluation. DSC valueswere calculated on twosets of images for testgroup and control group,respectively. Accordingto the results, it could beconcluded that the DSCof proposed device wasnon-inferiority comparedwith that of the predicatedevice.Registrationperformance testThe registrationperformance test wasperformed on proposeddevice and predicatedevice to evaluate theautomated registrationaccuracy. Two separatetests were performed.One test involvedimages generated inhealthcare institutions inChina using scannermodels available inChina covering threemajor vendors. And theimage registrationfeature is tested onmulti-modality imagesets from same patients.The other involved mostimages generated inhealthcare institutions in | attenuation, scatter, andbackground wereverified in simulatedphantoms. The averageerrors were less than12% for all regionsexcept for the smallestregion (2.6 cm) with21% error for Lu-177and 17% error for I-131where the partial volumeeffect lowered accuracyas expected. In all cases,the software passed itsperformancerequirements and metspecificationsThe accuracy of area-under-the curve (AUC)calculations wereverified for differentfitting options usingsimulated data withdifferences less than3.1% compared tomanual AUCcalculations which metpredefined acceptancecriteria whenconsidering the presenceof Poison noise in theimage data.The accuracy of thegeneration of CT-derivedphysical density mapswere verified in clinicalpatient data andcompared to publishedresults with less than 5%difference for soft tissueregions and less than10% difference for boneregions. The differencefor lung density fellwithin the range ofexpected density values. | |
| most moving images | - MRT Dosimetry was | ||
| came from U.S and a | verified in simulated | ||
| small amount of moving | phantoms and clinical | ||
| images adopted from | patient data for I-131 | ||
| online database were | and Lu-177. The | ||
| originally from non-US | acceptance criterion for | ||
| sources. All the scanner | MIM - MRT Dosimetry | ||
| models covered three | is a difference of mean | ||
| major vendors. And the | dose of smaller or equal | ||
| image registration | to 20% in comparison to | ||
| feature is only tested on | a commercially available | ||
| multi-modality image | solution after correction | ||
| sets from different | of the standard phantoms | ||
| patients. Both tests | in the commercial | ||
| covered various | solution to match the | ||
| modalities, including | mass of the patient data. | ||
| CT/CT, CT/MR and | Additionally, | ||
| CT/PET. The | comparison of the Voxel | ||
| Normalized Mutual | S Value method in MIM | ||
| Information (NMI) was | - MRT Dosimetry to | ||
| used for evaluation. NMI | Local Deposition Model | ||
| values were calculated | values for Lu-177 | ||
| on two sets of images for | showed a difference less | ||
| both the proposed device | than 1% for all organs | ||
| and predicate device, | tested. In all cases the | ||
| respectively. The NMI | software demonstrated | ||
| value of proposed device | acceptable agreement | ||
| was compared with that | between the different | ||
| of the predicate device. | dose methods. | ||
| According to the results, | |||
| it could be concluded | |||
| that the NMI of | |||
| proposed device was | |||
| non-inferiority compared | |||
| with that of the predicate | |||
| device. | |||
Table 5-1. Comparison with the Predicate Devices.
{6}------------------------------------------------
Image /page/6/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of the word "VYSIONEER" in a sans-serif font, with a stylized "V" shape above it. The "V" shape is made up of two diagonal lines that do not connect at the bottom. The color of the logo is a dark purple.
{7}------------------------------------------------
Image /page/7/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of the word "VYSIONEER" in a sans-serif font, with a horizontal line underneath. Above the word is a stylized "V" shape, with a small gap in the middle.
{8}------------------------------------------------
Image /page/8/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of a stylized letter V above the word "VYSIONEER". The letter V is made up of two diagonal lines that do not connect at the bottom. The logo is purple.
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of the word "VYSIONEER" in a sans-serif font, with a horizontal line underneath the word. Above the word is a stylized "V" shape, which is made up of two separate lines that do not connect. The color of the text, line, and "V" shape is a dark purple.
U.S. All fixed image and | calculations using MIM
{10}------------------------------------------------
Image /page/10/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of a stylized letter "V" in purple, with the word "VYSIONEER" in a sans-serif font below it. A horizontal purple line is located below the word "VYSIONEER".
Performance Data 5.7
Vysioneer conducted a retrospective, blinded, multicenter, multinational study with the proposed device VBrain with the primary endpoint to evaluate the software's performance on identifying axial T1 contrast-enhanced MRI scans containing brain metastases, acoustic neuromas, or meningiomas. The test dataset was an independent dataset consisting of 116 cases with 238 tumors acquired consecutively and retrospectively from 4 different institutions (3 US and 1 non-US). The ground truth of each tumor contours was generated from the consensus of three board-certified radiation oncologists. Five metrics are evaluated: (1) lesion-wise sensitivity, (2) false-positive rate,
{11}------------------------------------------------
Image /page/11/Picture/1 description: The image shows the logo for Vysioneer. The logo consists of a stylized letter V in purple, with the word "VYSIONEER" written in purple below it. The letter V is made up of two diagonal lines that do not quite meet at the top.
(3) lesion-wise Dice coefficient, (4) average Hausdorff distance, and (5) centroid distance between VBrain's segmentation and ground-truth segmentation. VBrain meets all performance goals.
Specifically, lesion-wise sensitivity of VBrain was observed to be 90.3% (95% CI: 86.1-93.7%) and the false-positive rate was observed to be 0.681 tumors/case (95% CI: 0.500-0.879) tumors/case). In addition, segmentation performance was measured with the lesion-wise Dice similarity coefficient (DSC) and average Hausdorff distance between VBrain's segmentation and ground-truth segmentation in terms of lesion size. They were observed to be lesion-wise DSC: 0.793 (95% Cl: 0.775-0.811) and average Hausdorff distance in terms of lesion size: 5.0% (95% CI: 4.4-5.6%). Centroid distance between VBrain's segmentation and ground-truth segmentation was measured in terms of lesion size and was observed to be 5.6% (95% CI: 5.0-6.2%).
Software Verification and Validation 5.8
Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" for software devices identified as Major Level of Concern related to radiation therapy treatment planning.
Conclusion રું તે તે
In conclusion, Vysioneer Inc. has conducted performance testing on VBrain. In all the cases, the software passed its requirements for safety and effectiveness and does not introduce any new potential safety risks. It demonstrates that VBrain is substantially equivalent to and performs at least as safely and effectively as the listed predicate devices.
§ 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).