(151 days)
Not Found
Yes
The device description explicitly states that it uses "locked Artificial Intelligence (AI)" for fine-tuning tissue matching.
No
ViewFinder is an image viewing and processing software that aids qualified interpreting physicians in the review of digital breast tomosynthesis datasets by providing visualization and image enhancement tools. It does not directly provide therapy.
No
The device is described as an image viewing and processing software environment that aids qualified interpreting physicians in the review of digital breast tomosynthesis datasets. It explicitly states that "The qualified interpreting physician is responsible for making the diagnosis of the images presented," indicating that the device itself does not make a diagnosis.
Yes
The device description explicitly states "ViewFinder is software" and describes its function as a software application for displaying and processing medical images. While it runs on a PC and requires cleared monitors, these are external hardware components, and the device itself is presented as a software product.
Based on the provided information, ViewFinder is an IVD (In Vitro Diagnostic).
Here's why:
- Intended Use: The intended use clearly states that ViewFinder is a "dedicated softcopy review environment for both screening and diagnostic digital breast tomosynthesis." It is designed to "aid a qualified interpreting physician in the review of digital breast tomosynthesis datasets." This indicates its use in the diagnostic process by providing tools for interpreting medical images.
- Device Description: The description details how the software processes and displays medical images (DBT views) to assist in the interpretation of tissue. While it doesn't directly analyze biological samples, it processes and presents data derived from the patient's body (the breast images) for diagnostic purposes.
- Input Imaging Modality: It uses Digital Breast Tomosynthesis (DBT), which is a medical imaging technique used for diagnosis.
- Intended User: The intended users are "Qualified interpreting physicians in both screening and diagnostic reading," who are the professionals responsible for making diagnoses based on medical images.
- Performance Studies: The summary of performance studies describes testing related to the accuracy of the software's tissue matching feature, which is a function designed to aid in the diagnostic review of the images.
- Predicate Device: The mention of a predicate device (MAMMOVISTA B.smart) with a K number (K212621) strongly suggests that this device is being compared to a previously cleared medical device, which is a common process for IVDs seeking regulatory clearance.
While ViewFinder doesn't directly analyze biological samples in the traditional sense of a lab test, it falls under the broader definition of an IVD because it is a medical device intended for use in the examination of specimens derived from the human body (the breast images) to provide information for the purpose of diagnosis. It is a tool used by medical professionals to interpret diagnostic images.
No
The letter does not state that the FDA has explicitly reviewed, approved, or cleared a PCCP for this specific device. The field "Control Plan Authorized (PCCP) and relevant text" is listed as "Not Found".
Intended Use / Indications for Use
ViewFinder is a dedicated softcopy review environment for both screening and diagnostic digital breast tomosynthesis. Its user interface and workflow have been optimized to support qualified interpreting physicians in both screening and diagnostic reading. Efficiency and reading quality are supported by various specialized features. ViewFinder provides visualization and image enhancement tools to aid a qualified interpreting physician in the review of digital breast tomosynthesis datasets. The qualified interpreting physician is responsible for making the images presented.
Product codes
QIH
Device Description
ViewFinder is software which displays two Digital Breast Tomosynthesis (DBT) views of the same breast and dynamically indicates correlated (matched) tissue. The benefit is that clinicians can compare matched tissue quickly and with less cognitive load.
It works by simulating the tissue movements between Cranio-Caudal (CC) and Medio-Lateral Oblique (MLO) compressions and views for a gross approximation of tissue matching, followed by a second fine tuning using locked Artificial Intelligence (AI). Users operate the device by pointing the cursor at tissue in one view and ViewFinder indicates the matching tissue in the other view.
ViewFinder is a standalone software application or can be integrated into medical image management and processing systems. ViewFinder is an image viewing and processing software environment dedicated to breast image display.
It is designed to provide the performance required for the high data volume of DBT.
ViewFinder runs on a PC and can be used for digital breast tomosynthesis image review together with monitors cleared for mammography diagnostics.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Digital Breast Tomosynthesis (DBT)
Anatomical Site
Breast
Indicated Patient Age Range
The test set has a median age of 58 years and 6 months, slightly lower than the mid-point of the UK screening age range of 50 - 70 years. This is shown in the figure below. It is consistent with the screening age recommendations in the USA: "The United States Preventive Services Task Force USPSTF recommends that women who are 50 to 74 years old and are at average risk for breast cancer get a mammogram every two years. Women who are 40 to 49 years" have an option.
Intended User / Care Setting
qualified interpreting physicians in both screening and diagnostic reading.
Description of the training set, sample size, data source, and annotation protocol
The algorithm was trained on a large, diversified set of Tomo cases with ground truth annotations made by a consultant radiologist.
The training data consisted of two datasets consisting of FFDMs drawn from both screening and screening assessment cases and 660 Tomos which were drawn from assessments. The images include two views of each breast, viz. Cranio-caudal and Medio-lateral oblique. The annotations included bounding boxes around landmark tissue. The finding class was used during pre-training (cancerous, benign or normal) with significant representation in each class.
Description of the test set, sample size, data source, and annotation protocol
The scientific data showing that ViewFinder is as safe and effective as the predicate consists of test result data. These are the correct mapping percentage (where the ground truth matching tissue is inside the target area) and a sample of Total Registration Errors (TRE) on a set of 34 lesions for which locations were available. These were selected from a set of 30 diverse cases acquired from assessment clinics at the King's College Hospital. These cases were selected for their high prevalence of difficult and cancerous cases which makes them suitable for algorithm testing.
There was no overlap between training and test data.
The test data collection resulted in a test set which consists of 34 CC-MLO pairs of key points in 30 cases acquired from assessment clinics at the King's College Hospital (KCH) from April 2018 to November 2021. These cases were selected for their diversity of diagnoses whose diversity makes them suitable for both human training and algorithm testing. The key points were identified by an expert radiologist at KCH.
Ground truth annotations were made by an expert radiologist.
Upon completion of the Radiologist's annotations, a technical review was conducted through visualization, checking bounding box placement, tissue matches, and that the sequence numbers and pairing were consistent.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
The scientific data showing that ViewFinder is as safe and effective as the predicate consists of test result data. These are the correct mapping percentage (where the ground truth matching tissue is inside the target area) and a sample of Total Registration Errors (TRE) on a set of 34 lesions for which locations were available. These were selected from a set of 30 diverse cases acquired from assessment clinics at the King's College Hospital. These cases were selected for their high prevalence of difficult and cancerous cases which makes them suitable for algorithm testing.
The table below shows the stratified ViewFinder performance as measured by the frequency that the ground truth matching tissue is inside the predicted region shown by the oval, stratified by BI-RADS Atlas 5th edition breast density classes A-D and feature size in square millimeters. The count of feature matches in both directions (CC to MLO and MLO to CC) is shown in brackets as the numerator, with the total number of features shown as the denominator. The total number of features is 34 (giving 68 matches including both directions) which exceeds the number of cases because some cases have more than one feature. The total number of patients was 28. It is, therefore, more appropriate to measure performance by feature than by case. The minimum performance threshold is 70% which is exceeded in aggregate and for the majority of subgroups.
The most relevant clinical subgroups and confounders are breast density and feature size, for which performances are shown separately in the performance table below.
The correct mapping percentage and TREs were from comparisons between ground truths and ViewFinder's predictions in both registration directions (CC to MLO and vice versa).
| Cancer Status | Feature Size (mm^2) | A | B | C | D | Grand Total |
|---|---|---|---|---|---|---|
| All Patients | 0 - 40 | 1.000 (1/1) | 0.739 (17/23) | 1.000 (7/7) | 0.000 (0/) | 0.806 (25/31) |
| 40 - 200 | 1.000 (1/1) | 0.700 (7/10) | 1.000 (1/1) | 0.000 (0/) | 0.750 (9/12) | |
| 200- 500 | 0.000 (0/) | 1.000 (3/3) | 1.000 (5/5) | 1.000 (2/2) | 1.000 (10/10) | |
| >500 | 1.000 (2/2) | 1.000 (6/6) | 0.857 (6/7) | 0.000 (0/) | 0.933 (14/15) | |
| Total | 1.000 (4/4) | 0.786 (33/42) | 0.950 (19/20) | 1.000 (2/2) | 0.853 (58/68) | |
| Number of cases | 2 | 16 | 9 | 1 | 28 |
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Frequency that ground truth is inside oval.
Total Registration Errors (TRE).
Minimum performance threshold is 70% which is exceeded in aggregate and for the majority of subgroups.
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
April 21, 2023
Image /page/0/Picture/1 description: The image shows the logos of the Department of Health and Human Services and the U.S. Food and Drug Administration (FDA). The Department of Health and Human Services logo is on the left, and the FDA logo is on the right. The FDA logo is a blue square with the letters "FDA" in white. To the right of the square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
Elaitra Ltd % Stephen Morrell Managing Director 8B Buckland Crescent, Belsize Park London. NW3 5DX UNITED KINGDOM
Re: K223501
Trade/Device Name: ViewFinder Software Version 1.1 Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: March 23, 2023 Received: March 24, 2023
Dear Stephen Morrell:
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 requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part
1
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 (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 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,
Yanna S. Kang -S
Yanna Kang, Ph.D. Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K223501
Device Name ViewFinder Software (Version 1.1)
Indications for Use (Describe)
ViewFinder is a dedicated softcopy review environment for both screening and diagnostic digital breast tomosynthesis. Its user interface and workflow have been optimized to support qualified interpreting physicians in both screening and diagnostic reading. Efficiency and reading quality are supported by various specialized features. ViewFinder provides visualization and image enhancement tools to aid a qualified interpreting physician in the review of digital breast tomosynthesis datasets. The qualified interpreting physician is responsible for making the images presented.
Type of Use (Select one or both, as applicable)
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
K223501 510(k) Summary:
Company: Elaitra Ltd 8B Buckland Crescent, Belsize Park London, NW3 5DX, UK
Date Prepared: April 20, 2023
This 510(k) summary of safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR § 807.92.
1. Submitter
Importer / Distributor: To be determined Establishment Registration Number:
Location of Manufacturing Site:
8B Buckland Crescent, Belsize Park London, NW3 5DX, UK Establishment Registration Number:
2. Contact Person:
Stephen Morrell Chief Executive Officer Elaitra Ltd 8B Buckland Crescent, Belsize Park London, NW3 5DX, UK stephen.morrell@kcl.ac.uk +44 (777) 180-6100 (UK) +1 (347) 796-4466 (USA)
Alternate Contact Person:
Michael Hütel FLAT B, 183 Haverstock Hill London, NW3 4QS, UK michael.hutel@kcl.ac.uk
3. Device Name and Classification
| Trade Name: | ViewFinder Software Version 1.1 |
|---|---|
| Classification Name: | Medical image management and processing system |
| Classification Panel: | Radiology |
| Intended Submission Type: | 510(k) Traditional |
| Classification Regulation: | 21 CFR §892.2050 |
| Device Class: | Class II |
4
Image /page/4/Picture/0 description: The image shows a logo on the left and the text "ViewFinder 510(k) Summary" on the right. The logo consists of a blue circle with a stylized letter A inside. The text is in a sans-serif font and is aligned to the right of the logo. The image is clean and simple, with a focus on the logo and the text.
Image /page/4/Picture/1 description: The image shows the word "ELAITRA" in a light blue color. Below the word is the phrase "lets doctors fly" in a smaller font size and the same light blue color. The text is simple and clean, with a focus on the brand name and tagline.
Product Code: Level of Concern QIH Moderate
Predicate
4. Legally Marketed Predicate Device
| Trade/Device Name: | MAMMOVISTA B.smart |
|---|---|
| 510(k) number: | K212621 (Cleared November 12, 2021) |
| Classification Name: | Medical image management and processing system |
| Classification Panel: | Radiology |
| Classification Regulation: | 21 CFR §892.2050 |
| Device Class: | II |
| Product Code: | LLZ |
| Level of Concern | Moderate |
Device Description:
5. Description Summary
ViewFinder is software which displays two Digital Breast Tomosynthesis (DBT) views of the same breast and dynamically indicates correlated (matched) tissue. The benefit is that clinicians can compare matched tissue quickly and with less cognitive load.
It works by simulating the tissue movements between Cranio-Caudal (CC) and Medio-Lateral Oblique (MLO) compressions and views for a gross approximation of tissue matching, followed by a second fine tuning using locked Artificial Intelligence (AI). Users operate the device by pointing the cursor at tissue in one view and ViewFinder indicates the matching tissue in the other view.
ViewFinder is a standalone software application or can be integrated into medical image management and processing systems. ViewFinder is an image viewing and processing software environment dedicated to breast image display.
It is designed to provide the performance required for the high data volume of DBT.
ViewFinder runs on a PC and can be used for digital breast tomosynthesis image review together with monitors cleared for mammography diagnostics.
Indications for Use: 6.
ViewFinder is a dedicated softcopy review environment for both screening and diagnostic digital breast tomosynthesis. Its user interface and workflow have been optimized to support qualified interpreting physicians in both screening and diagnostic reading. Efficiency and reading quality are supported by various specialized features. ViewFinder provides visualization and image enhancement tools to aid a qualified interpreting physician in the review of digital breast tomosynthesis datasets. The qualified interpreting physician is responsible for making the diagnosis of the images presented.
5
Image /page/5/Picture/0 description: The image shows a logo on the left and the text "ViewFinder 510(k) Summary" on the right. The logo consists of a stylized letter A inside a circle. The letter A and the circle are both light blue. The text is black and is written in a sans-serif font. The text is aligned to the left and is centered vertically with the logo.
Image /page/5/Picture/1 description: The image shows the logo for ELATRA. The logo is in a light blue color. Below the main logo, there is a tagline that reads "lets doctors fly".
Comparison
The Indications for Use statement for ViewFinder is not identical to the predicate device; however, the differences do not alter the intended use of the device, nor do they affect the safety and effectiveness of the device relative to the predicate. Both the subject and predicate devices have the same intended use for assisting reading DBT and mammogram images.
Substantial Equivalence
-
- Substantial Equivalence:
Refer to the Predicate Comparison Table below.
- Substantial Equivalence:
ViewFinder Software is substantially equivalent to the commercially available MAMMOVISTA B.smart software (K212621, cleared November 12, 2021).
The device remains within the same classification regulation for the same technology as the predicate device. The new software design was completed in accordance with Quality Management System Design Controls under IEC 62304. The scope of internationally recognized standards compliance includes those recognized at the time of the design of the software.
The intended use of the subject device is a subset of the predicate's intended use. The predicate has an identical feature (Link Views, chapter 6 of the Operator Manual) to the subject device as well as many other additional features (segmentation tools, magnifier, movie mode, viewing Computer Aided Detection and Decision Support, etc. as described in the remaining 12 chapters). Therefore, the intended use differences pose no additional safety or effectiveness concerns.
-
- Summary of Technological Characteristics of the Subject Device as Compared with the Predicate Device:
ViewFinder Software is a software-only solution to run on compatible client server environment together with monitor displays cleared for Mammography.
- Summary of Technological Characteristics of the Subject Device as Compared with the Predicate Device:
The predicate device includes a feature called "Link Views" which matches correlating tissue between two 3D (DBT) images. (It also matches tissue between 2D and 3D images).
The predicate device has features which the subject device does not. These include interactive decision support powered by Artificial Intelligence by Transpara™, ScreenPoint Medical.
The following table compares the main performance data of the subject device with the predicate device.
6
Image /page/6/Picture/1 description: The image shows the word "ELAITRA" in a light blue color. Below the word is the phrase "lets doctors fly" in a smaller font and the same light blue color. The text is centered and appears to be a logo or brand name.
Comparison Table Comparison of the Subject Device (ViewFinder Software Version 1.1) to Predicate Device (MAMMOVISTA B.smart)
| Feature | Subject device | Predicate device (K212621) | Comparison | Impact to Safety & Effectiveness |
|---|---|---|---|---|
| Regulation Description | System, image processing, radiological | System, image processing, radiological | Equivalent | None |
| Device name and version (K number) | ViewFinder Software Version 1.1 | MAMMOVISTA B.smart Software | Different | None |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Equivalent | None |
| Classification Product Code | QIH | LLZ | Equivalent | None |
| Manufacturer | Elaitra Ltd | Siemens. Medical Systems, Inc. | Different manufacturer | None |
| Indications for Use | ViewFinder is a dedicated softcopy review environment for both screening and diagnostic digital breast tomosynthesis. | MAMMOVISTA B.smart is a dedicated softcopy review environment for both screening and diagnostic mammography as well as digital breast tomosynthesis. | Equivalent | |
| The subject device is more explicit. | None | |||
| Its user interface and workflow have been optimized to support qualified interpreting physicians in both screening and diagnostic reading. Efficiency and reading quality are supported by various specialized features. | Its user interface and workflow have been optimized to support experienced mammography and tomosynthesis reviewers in both screening and diagnostic reading. Efficiency and reading quality are supported by various specialized features. | The predicate device includes multi-modality images (e.g., MRI and ultrasound). | ||
| ViewFinder provides visualization and image enhancement tools to aid a qualified interpreting physician in the review of digital breast tomosynthesis datasets. The qualified interpreting physician is responsible for | MAMMOVISTA B.smart provides visualization and image enhancement tools to aid a qualified radiologist in the review of digital mammography and digital breast tomosynthesis datasets, as well as | |||
| Feature | Subject device | Predicate device | ||
| (K212621) | Comparison | Impact to | ||
| Safety & | ||||
| Effectiveness | ||||
| Architecture | making the diagnosis of | |||
| the images presented. | other modalities of | |||
| breast images. | Equivalent | None | ||
| Client / server | ||||
| environment | Client / server | |||
| environment | ||||
| Display of 3rd | ||||
| party | ||||
| Computer | ||||
| Aided | ||||
| Diagnostics | ||||
| (CAD) markers | No | Yes | The subject | |
| has fewer | ||||
| functions | None | |||
| Display and | ||||
| processing of | ||||
| DBT images | Yes | Yes | Equivalent | None |
| DICOM 3.0 | Yes | Yes | Equivalent | None |
| DICOM | ||||
| compatible | ||||
| modalities | MG Tomo | |||
| (Mammography | ||||
| Tomosynthesis images) | ||||
| DICOM DSR | ||||
| (Deformable Spatial | ||||
| Registration) | MG (Digital | |||
| Mammography X-Ray) | ||||
| MG Tomo | ||||
| (Mammography | ||||
| Tomosynthesis images) | ||||
| MR (Magnetic | ||||
| Resonance) | ||||
| US (Ultrasound) | The subject | |||
| has an | ||||
| additional | ||||
| conformant | ||||
| modality | ||||
| storing tissue | ||||
| correlation. | ||||
| The subject | ||||
| omits MR and | ||||
| US | None | |||
| Display of | ||||
| breast density | ||||
| values | No | Yes | The subject | |
| has fewer | ||||
| functions | None | |||
| Ipsilateral DBT | ||||
| tissue | ||||
| registration | Yes | Yes | Equivalent | None |
| DBT | ||||
| Registration | ||||
| Algorithms | Finite Element Model | |||
| and Deep Learning | Finite Element Model | ViewFinder's | ||
| Deep Learning | ||||
| improves | ||||
| accuracy | No detrimental | |||
| impact | ||||
| Measurements | Distance | |||
| measurements | Distance and angle | |||
| measurements | The subject | |||
| device | ||||
| excludes angle | ||||
| measurements | No detrimental | |||
| impact | ||||
| Supported | ||||
| Image | ||||
| Generating | ||||
| Manufacturers | ||||
| and Models | Only DBTs produced on | |||
| Hologic's Selenia | ||||
| Dimensions and GE | ||||
| Healthcare's SenoClaire | ||||
| and Senographe | ||||
| Pristina | No restriction given for | |||
| manufacturer or | ||||
| model. | The subject | |||
| device is | ||||
| restricted to | ||||
| fewer | ||||
| manufacturers | ||||
| and models. It | ||||
| does not | ||||
| process | ||||
| combinations | ||||
| which are out | ||||
| of scope. | None |
7
Image /page/7/Picture/0 description: The image shows a logo on the left and the text "ViewFinder 510(k) Summary" on the right. The logo is a blue circle with the letter A inside. The text is in black and is aligned to the right of the logo. The image is likely a title or heading for a document or presentation.
Image /page/7/Picture/1 description: The image shows the logo for ELAITRA. The text "ELAITRA" is in a large, light blue, sans-serif font. Below the main text, in a smaller font, is the tagline "lets doctors fly", also in light blue. The logo is simple and clean, with a focus on the company name and its mission.
8
Image /page/8/Picture/1 description: The image shows the logo for "ELAITRA" in a light blue color. Below the company name is the tagline "lets doctors fly" in a smaller font and the same light blue color. The logo is simple and modern, with a focus on the company name and tagline.
Conclusion Regarding Differences
There are no differences between the subject device and the predicate(s) with respect to indications and intended use which impact safety and effectiveness.
9. Summary of Non-Clinical Tests:
Non-clinical tests were conducted for the ViewFinder software during product development. The ViewFinder software conforms to the following voluntary standards:
| Standards Reference Number and
| Date | Title of Standard |
|---|---|
| ISO 14971: 2019 | Medical devices – application of risk management |
| to medical devices | |
| IEC 62304:2006/A1:2016 | Medical device software - Software life cycle |
| processes | |
| NEMA PS 3.1 - 3.20 2016 | Digital Imaging and Communications in Medicine |
| (DICOM) Set | |
| IEC 82304-1: 2016 | Health software – Part 1: General requirements |
| for product safety |
Software Documentation for a Moderate Level of Concern software per FDA's Guidance Document Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices, issued on May 11, 2005, is also included as part of this submission.
Non-clinical tests (integration and functional) were conducted on the ViewFinder during product development. The risk analysis was completed, and risk controls were implemented, to mitigate identified hazards. The test results support that all the software specifications have met the acceptance criteria. Verification and validation testing were found acceptable to support the claim of substantial equivalence.
Elaitra did not conduct any clinical tests for the subject device.
ViewFinder uses a registration process to map tissue coordinates from one compression view to the other based on the different view angles during the acquisitions. ViewFinder uses proprietary Artificial Intelligence and Machine Learning algorithms. The algorithms are 'locked' so that their output only changes in the laboratory under controlled conditions and do not change in the field. This follows the FDA's current classification framework for AI and ML algorithms. The algorithm's predictions only change when a new version of the software is released. The algorithm was trained on a large, diversified set of Tomo cases with ground truth annotations made by a consultant radiologist. There was no overlap between training and test data.
9
Image /page/9/Picture/0 description: The image shows a logo with a light blue letter 'A' inside a circle. The letter 'A' is stylized with a dot above the right leg, and the circle is partially broken on the right side. The overall design is simple and modern.
Image /page/9/Picture/2 description: The image shows the word "ELAITRA" in a light blue color. Below the word "ELAITRA" is the phrase "lets doctors fly" in a smaller font and the same light blue color. The font of the word "ELAITRA" is a serif font, while the font of the phrase "lets doctors fly" is a sans-serif font.
Supporting Scientific Data
The scientific data showing that ViewFinder is as safe and effective as the predicate consists of test result data. These are the correct mapping percentage (where the ground truth matching tissue is inside the target area) and a sample of Total Registration Errors (TRE) on a set of 34 lesions for which locations were available. These were selected from a set of 30 diverse cases acquired from assessment clinics at the King's College Hospital. These cases were selected for their high prevalence of difficult and cancerous cases which makes them suitable for algorithm testing.
Primary Performance Metric: Frequency
The table below shows the stratified ViewFinder performance as measured by the frequency that the ground truth matching tissue is inside the predicted region shown by the oval, stratified by BI-RADS Atlas 5th edition breast density classes A-D and feature size in square millimeters. The count of feature matches in both directions (CC to MLO and MLO to CC) is shown in brackets as the numerator, with the total number of features shown as the denominator. The total number of features is 34 (giving 68 matches including both directions) which exceeds the number of cases because some cases have more than one feature. The total number of patients was 28. It is, therefore, more appropriate to measure performance by feature than by case. The minimum performance threshold is 70% which is exceeded in aggregate and for the majority of subgroups.
The most relevant clinical subgroups and confounders are breast density and feature size, for which performances are shown separately in the performance table below.
| | Frequency that ground truth is
inside oval (n) | Density | | | | |
|------------------|---------------------------------------------------|-------------|---------------|---------------|-------------|---------------|
| Cancer
Status | Feature Size
(mm^2) | A | B | C | D | Grand Total |
| All Patients | 0 - 40 | 1.000 (1/1) | 0.739 (17/23) | 1.000 (7/7) | 0.000 (0/) | 0.806 (25/31) |
| | 40 - 200 | 1.000 (1/1) | 0.700 (7/10) | 1.000 (1/1) | 0.000 (0/) | 0.750 (9/12) |
| | 200- 500 | 0.000 (0/) | 1.000 (3/3) | 1.000 (5/5) | 1.000 (2/2) | 1.000 (10/10) |
| | >500 | 1.000 (2/2) | 1.000 (6/6) | 0.857 (6/7) | 0.000 (0/) | 0.933 (14/15) |
| | Total | 1.000 (4/4) | 0.786 (33/42) | 0.950 (19/20) | 1.000 (2/2) | 0.853 (58/68) |
| | Number of cases | 2 | 16 | 9 | 1 | 28 |
Patient Age Distribution
The test set has a median age of 58 years and 6 months, slightly lower than the mid-point of the UK screening age range of 50 - 70 years. This is shown in the figure below. It is consistent with the screening age recommendations in the USA: "The United States Preventive Services Task Force USPSTF recommends that women who are 50 to 74 years old and are at average risk for breast cancer
10
Image /page/10/Picture/1 description: The image shows the logo for ELATRA, a company that helps doctors fly. The word "ELATRA" is written in large, light blue letters. Below the company name is the slogan "lets doctors fly" in a smaller, dark blue font. The logo is simple and modern, and it conveys the company's mission in a clear and concise way.
get a mammogram every two years. Women who are 40 to 49 years" have an option. (Source: https://www.cdc.gov/cancer/breast/basic info/screening.htm.)
Image /page/10/Figure/3 description: The image is a bar chart titled "Age at Scan". The x-axis represents age ranges, and the y-axis represents the number of people. The highest bar is for the age range (Sep-50, Aug-55], with a value of 10. The other bars show values between 0 and 6.
Figure: Histogram of patient ages at scan showing consistency with USA screening quidelines.
Race
The distribution of race between the target population (USA) and the Test Set is sufficiently similar that it would not preclude generalization as shown in the figure below.
The gender of the test set is all women which is consistent with the population of patients in the USA as recommended for the subject device.
Image /page/10/Figure/8 description: The image is a bar chart comparing the race distribution between the USA and a test set. The x-axis represents different race categories: White, Black or African American, Two or more races, Some other race, Asian, and Native American Native Hawaiian or Alaska Native or Other Pacific Islander. The y-axis represents the percentage, ranging from 0% to 70%. For the 'White' category, the USA has approximately 61%, while the test set has around 64%.
Figure: Race distribution comparison
11
Image /page/11/Picture/1 description: The image shows the logo for "ELAITRA" in a light blue color. Below the company name is the tagline "lets doctors fly" in a smaller font, also in light blue. The logo is simple and modern, with a clean typeface.
The test data collection resulted in a test set which consists of 34 CC-MLO pairs of key points in 30 cases acquired from assessment clinics at the King's College Hospital (KCH) from April 2018 to November 2021. These cases were selected for their diversity of diagnoses whose diversity makes them suitable for both human training and algorithm testing. The key points were identified by an expert radiologist at KCH.
Ground truth annotations were made by an expert radiologist.
Upon completion of the Radiologist's annotations, a technical review was conducted through visualization, checking bounding box placement, tissue matches, and that the sequence numbers and pairing were consistent.
Regarding the details for training data: the training data consisted of two datasets consisting of FFDMs drawn from both screening and screening assessment cases and 660 Tomos which were drawn from assessments. The images include two views of each breast, viz. Cranio-caudal and Medio-lateral oblique. The annotations included bounding boxes around landmark tissue. The finding class was used during pre-training (cancerous, benign or normal) with significant representation in each class.
The correct mapping percentage and TREs were from comparisons between ground truths and ViewFinder's predictions in both registration directions (CC to MLO and vice versa).
10. General Safety and Effectiveness Concerns:
Instructions for use are included within the device labeling and the information provided will enable the user to operate the device in a safe and effective manner. Several safety features including visual and audible warnings are incorporated into the system design.
Risk management is ensured via a hazard analysis which is used to identify potential hazards. These potential hazards are controlled via software development, verification, and validation testing.
Furthermore, the operators are qualified healthcare professionals familiar with and responsible for the review of digital mammography images and digital breast tomosynthesis datasets.
11. Regulatory History
There is no regulatory history for this device or this company with the FDA.
In the UK, the device was registered as a Class I Device with the Medicines and Healthcare products Regulatory Agency (MHRA) in October 2021.
12
Image /page/12/Picture/0 description: The image shows a logo with a stylized letter 'A' inside a circle. The 'A' is light blue and has a small dot above its center. The circle is also light blue and has a gap in the upper right quadrant. The overall design is simple and modern.
Image /page/12/Picture/2 description: The image shows the logo for ELATRA, which is written in a light blue color. Below the company name is the tagline "lets doctors fly" in a smaller font and the same light blue color. The logo is simple and modern, and the tagline suggests that the company is involved in the medical or aviation industry.
12. Conclusion as to Substantial Equivalence:
The ViewFinder's Indication for Use is similar to that of the predicate device. The operating environment and software design are similar. Image display devices (monitors) with the same or similar specifications will be used to display the mammography images.
Verification and validation testing demonstrate that the ViewFinder performs as intended. The non-clinical test data demonstrate that the ViewFinder device performance is comparable to the predicate device that is currently marketed for the same intended use.
It is Elaitra's opinion that the ViewFinder does not introduce any new potential safety risks and is substantially equivalent to the predicate.
13. Guidance documents
The following FDA guidance documents were utilized in this Premarket Notification:
Content of Premarket Submission for Management of Cybersecurity in Medical Devices - Guidance for Industry and Food and Drug Administration Staff Document Issued on October 2, 2014
Guidance for Industry and FDA Staff - Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices Document issued on May 11, 2005
Appropriate Use of Voluntary Consensus Standards in Premarket Submissions for Medical Devices - Guidance for Industry and Food and Drug Administration Staff Document issued on September 14, 2018.
The 510(k) Program: Evaluation Substantial Equivalent in Premarket Notifications 510(k) - Guidance for Industry and Food and Drug Administration Staff. Document issued on July 28, 2014.
Off-The-Shelf Software Use in Medical Devices - Guidance for Industry and Food and Drug Administration Staff Document issued on September 27, 2019.