(171 days)
Not Found
Yes
The device description explicitly states that the semi-automatic segmentations are based on deep convolutional neural networks (DCNN) and that the software combines deep learning, image analysis, and regression-based machine methods. It also includes a section on "Machine Learning Methodology" and "Machine Learning Performance Evaluation Summary".
No.
The software is explicitly stated to not produce or recommend any type of medical diagnosis or treatment, and it is described as an adjunct tool that does not detect, diagnose, or identify any abnormalities. Its purpose is to assist in visualizing and documenting measurements from previously acquired images, not to provide therapy.
No
The software explicitly states it "does not produce or recommend any type of medical diagnosis or treatment" and "does not detect, diagnose or identify any abnormalities." Its purpose is to assist users in visualizing and documenting measurements, acting as an adjunct tool rather than a primary diagnostic one.
Yes
The device is explicitly described as "software as a medical device (SaMD)" and its functionality is solely based on processing previously acquired DICOM images. It does not include or interface directly with any hardware for data acquisition or treatment.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- IVD Definition: In vitro diagnostics are tests performed on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections. They are used to examine specimens outside of the body.
- Device Function: The ScanDiags Ortho L-Spine MR-Q software processes and analyzes previously acquired medical images (MRI scans) of the lumbar spine. It does not interact with or analyze biological samples taken from the patient.
- Intended Use: The intended use is to provide quantitative measurements from existing images to assist users in visualizing and documenting anatomical structures. It explicitly states it does not produce or recommend any type of medical diagnosis or treatment and is an adjunct tool to a radiologist's review.
Therefore, because the device operates on medical images rather than biological specimens, it falls outside the scope of an In Vitro Diagnostic device. It is a software as a medical device (SaMD) used for image processing and analysis.
No
The provided text does not explicitly state that the FDA has reviewed, approved, or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
ScanDiags Ortho L-Spine MR-Q software is an image-processing and measurement software tool that provides quantitative spine measurements from previously-acquired DICOM lumbar spine Magnetic Resonance (MR) images for users' review, analysis, and interpretation. It provides the following functionality to assist users in visualizing, and documenting area and distance measurements of relevant anatomical structures (vertebral body, intervertebral disc, neuroforamina, thecal sac) of the lumbar spine:
Feature Segmentation;
Feature measurement; and
Export of measurement results to a PDF report containing measurement results and overlay images for user's review, revise and approval.
ScanDiags Ortho L-Spine MR-Q software does not produce or recommend any type of medical diagnosis or treatment. Instead, it simply helps users to more easily identify and classify features in lumbar MR images and compile a report. The user is responsible for reviewing and verifying the software-generated measurements and approving draft report content using their medical judgment and discretion.
The device is intended to be used only by hospitals and other medical institutions.
Only DICOM images of MRI acquired from lumbar spine exams of patients aged 22 and above are considered to be valid input. ScanDiags Ortho L-Spine MR-Q software does not support DICOM images of patients that are pregnant, undergo MRI scan with contrast media, have post-operational complications or infections.
Product codes
QIH
Device Description
ScanDiags Ortho L-Spine MR-Q software is a software as a medical device (SaMD) intended for visualization, and quantification of lumbar spine anatomical structures including vertebral bodies, intervertebral discs, neuroforamina, thecal sacs from a set of standard lumbar spine MRI images in DICOM (Digital Imaging and Communications in Medicine) format. The semi-automatic segmentation of these structures forms the bases for the distance and area measurement outputs. The software has features for log-in, viewing, revising, and saving measurement results in addition to generating PDF reports. The PDF report includes images, measurements.
ScanDiags Ortho L-Spine MR-Q software includes a viewing application (ScanDiags DICOM Viewer) to visualize, review, and apply corrections to the measurement results shown as overlay on the original lumbar spine MRI images. Pre-existing MR images of the lumber spine are uploaded into the software for analysis. The semi-automatic segmentations are based on deep convolutional neural networks (DCNN) which are developed by applying well-established supervised deep learning methods on unstructured MRI scans (DICOM image format). ScanDiags Ortho L-Spine MR-Q combines deep learning, image analysis, as well as regression-based machine methods. The segmentations and distance measurements are user modifiable. Results are reviewed and approved by the radiologist's user before a PDF report is generated. Once approved, the result PDF report is sent to the clinician's PACS system. The PACS system stores the PDF report within the corresponding patient MRI study.
ScanDiags Ortho L-Spine MR-Q does not interface directly with any MR or data collection equipment; instead, the software uploads data files previously generated by such equipment. Its functionality is independent of the vendor type of the acquisition equipment. The analysis results are available on the ScanDiags DICOM Viewer screen and can be edited, saved, and approved. The approved measurement results are sent back to the PACS system as a Measurement Result PDF Report. The software does not perform any functions that could not be accomplished by a trained user with manual tracing methods; the purpose of the software is to save time and automate the tedious manual task of segmentation and distance measurement.
ScanDiags Ortho L-Spine MR-Q software is an adjunct tool and is not intended to replace a radiologist's review of the MRI study, nor is it intended to replace his or her clinical judgment, and it does not detect, diagnose or identify any abnormalities. Radiologists must not use the generated output as a primary interpretation.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Radiological images: MRI
Anatomical Site
Lumbar spine
Indicated Patient Age Range
Adult ≥ 22 years of age
Intended User / Care Setting
Intended user: Clinicians
Care setting: hospitals and other medical institutions.
Description of the training set, sample size, data source, and annotation protocol
Not Found
Description of the test set, sample size, data source, and annotation protocol
Sample size: 100 individual patient MRI studies
Data source: collected from two hospital groups, one in Missouri (18 patients served by a rural hospital group) and one in North Carolina (82 patients served by urban and rural hospital groups). The 100 studies were acquired from GE, Siemens Healthineers and Philips systems: Siemens: 42 GE: 40 Philips: 18.
Annotation protocol: Ground truth annotated by 3 US board certified MSK radiologist. Consent ground truth for anatomic structure segmentation determined by pixel-based majority opinion between the three radiologists. Consent ground truth for area and distance measurements determined by averaging the measurements of all three readers.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Study type: Machine Learning validation study (standalone performance assessment); retrospective, multicenter study.
Sample size: 100 individual patient MRI studies
Key results:
- Intraclass Correlation Coefficient (ICC): The device successfully passed the primary ICC acceptance criteria across all structures.
- Vertebra Area: 0.95 [0.94 - 0.96]
- Vertebra Anterior Height: 0.85 [0.30 - 0.94]
- Vertebra Middle Height: 0.91 [0.63 - 0.96]
- Vertebra Posterior Height: 0.89 [0.87 - 0.91]
- Neuroforamen Area: 0.90 [0.86 - 0.93]
- Intervertebral Disc Area: 0.92 [0.87 - 0.94]
- Intervertebral Disc Anterior Height: 0.78 [0.73 - 0.82]
- Intervertebral Disc Middle Height: 0.85 [0.18 - 0.95]
- Intervertebral Disc Posterior Height: 0.74 [0.68 - 0.78]
- Thecal Sac Area: 0.94 [0.91 - 0.96]
- Thecal Sac Anteroposterior Diameter: 0.92 [0.90 - 0.94]
- Thecal Sac Mediolateral Diameter: 0.86 [0.83 - 0.88]
- Dice Similarity Coefficient (DSC): The device successfully passes the secondary DICE acceptance criteria across all structures.
- Vertebra: 0.95 [0.95 - 0.96]
- Neuroforamen: 0.86 [0.85 - 0.86]
- Intervertebral Disc: 0.89 [0.89 - 0.90]
- Thecal Sac: 0.89 [0.89 - 0.90]
- Mean Absolute Error (MAE): The device successfully passes the co-secondary MAE acceptance criteria across all structures.
- Vertebra Anterior Height [mm]: 1.17
- Vertebra Middle Height [mm]: 0.86
- Vertebra Posterior Height [mm]: 0.79
- Intervertebral Disc Anterior Height [mm]: 1.1
- Intervertebral Disc Middle Height [mm]: 1.19
- Intervertebral Disc Posterior Height [mm]: 0.96
- Thecal Sac Anteroposterior Diameter [mm]: 0.81
- Thecal Sac Mediolateral Diameter [mm]: 1.26
Bland Altman as well as subgroup analysis based on age, sex, ethnicity, body weight, and MRI manufacturer, MR imaging parameters, underlying disease conditions, and clinical sites were also conducted.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Not Found
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 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 text logo on the right. The FDA text logo is in blue and includes the letters "FDA" in a square and the words "U.S. FOOD & DRUG ADMINISTRATION".
ScanDiags AG Stefan Voser COO, Product Manager Zwicky-Platz 1 Wallisellen, 8304 Switzerland
February 21, 2025
Re: K242607
Trade/Device Name: ScanDiags Ortho L-Spine MR-O Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH Dated: January 21, 2025 Received: January 21, 2025
Dear Stefan Voser:
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 (the 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 available 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.
1
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rue"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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.
2
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,
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
3
Indications for Use
Submission Number (if known)
Device Name
ScanDiags Ortho L-Spine MR-Q
Indications for Use (Describe)
ScanDiags Ortho L-Spine MR-Q software is an image-processing and measurement software tool that provides quantitative spine measurements from previously-acquired DICOM lumbar spine Magnetic Resonance (MR) images for users' review, analysis, and interpretation. It provides the following functionality to assist users in visualizing, and documenting area and distance measurements of relevant anatomical structures (vertebral body, intervertebral disc, neuroforamina, thecal sac) of the lumbar spine:
Feature Segmentation;
Feature measurement; and
Export of measurement results to a PDF report containing measurement results and overlay images for user's review, revise and approval.
ScanDiags Ortho L-Spine MR-Q software does not produce or recommend any type of medical diagnosis or treatment. Instead, it simply helps users to more easily identify and classify features in lumbar MR images and compile a report. The user is responsible for reviewing and verifying the software-generated measurements and approving draft report content using their medical judgment and discretion.
The device is intended to be used only by hospitals and other medical institutions.
Only DICOM images of MRI acquired from lumbar spine exams of patients aged 22 and above are considered to be valid input. ScanDiags Ortho L-Spine MR-Q software does not support DICOM images of patients that are pregnant, undergo MRI scan with contrast media, have post-operational complications or infections.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
r-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
4
Image /page/4/Picture/1 description: The image shows the logo for ScanDiags, a company that specializes in AI interpreting orthopaedic MRI. The logo consists of a blue square with a smaller square inside, followed by the company name in large, bold, blue letters. Below the logo, in smaller gray letters, is the text "ScanDiags AG Page 1 of 7".
K242607
1. Submitter
ScanDiags AG
Switzerland
Zwicky-Platz 1
Wallisellen, 8304
Contact Person:
Stefan Voser
+41796927080
Date Prepared: January 21, 2025
2. Device Identification
2.1 Device
| Trade Name | ScanDiags Ortho L-Spine MR-Q |
|---|---|
| Common Name | Ortho L-Spine MR-Q |
| Classification Name | Automated Radiological Image Processing Software |
| Regulation Number | 21 CFR 892.2050 |
| Product Code | QIH |
| Regulatory Class | Class II |
2.2 Predicate Device
| Trade Name | CoLumbo |
|---|---|
| 510(k) Submitter/Holder | Smart Soft Healthcare AD |
| 510(k) Number | K220497 |
| Classification Name | Medical image management and processing system |
| Regulation Number | 21 CFR 892.2050 |
| Product Code | QIH |
5
3. Device Description
ScanDiags Ortho L-Spine MR-Q software is a software as a medical device (SaMD) intended for visualization, and quantification of lumbar spine anatomical structures including vertebral bodies, intervertebral discs, neuroforamina, thecal sacs from a set of standard lumbar spine MRI images in DICOM (Digital Imaging and Communications in Medicine) format. The semi-automatic segmentation of these structures forms the bases for the distance and area measurement outputs. The software has features for log-in, viewing, revising, and saving measurement results in addition to generating PDF reports. The PDF report includes images, measurements.
ScanDiags Ortho L-Spine MR-Q software includes a viewing application (ScanDiags DICOM Viewer) to visualize, review, and apply corrections to the measurement results shown as overlay on the original lumbar spine MRI images. Pre-existing MR images of the lumber spine are uploaded into the software for analysis. The semi-automatic segmentations are based on deep convolutional neural networks (DCNN) which are developed by applying well-established supervised deep learning methods on unstructured MRI scans (DICOM image format). ScanDiags Ortho L-Spine MR-Q combines deep learning, image analysis, as well as regression-based machine methods. The segmentations and distance measurements are user modifiable. Results are reviewed and approved by the radiologist's user before a PDF report is generated. Once approved, the result PDF report is sent to the clinician's PACS system. The PACS system stores the PDF report within the corresponding patient MRI study.
ScanDiags Ortho L-Spine MR-Q does not interface directly with any MR or data collection equipment; instead, the software uploads data files previously generated by such equipment. Its functionality is independent of the vendor type of the acquisition equipment. The analysis results are available on the ScanDiags DICOM Viewer screen and can be edited, saved, and approved. The approved measurement results are sent back to the PACS system as a Measurement Result PDF Report. The software does not perform any functions that could not be accomplished by a trained user with manual tracing methods; the purpose of the software is to save time and automate the tedious manual task of segmentation and distance measurement.
ScanDiags Ortho L-Spine MR-Q software is an adjunct tool and is not intended to replace a radiologist's review of the MRI study, nor is it intended to replace his or her clinical judgment, and it does not detect, diagnose or identify any abnormalities. Radiologists must not use the generated output as a primary interpretation.
4. Indications for Use
ScanDiags Ortho L-Spine MR-Q software is an image-processing and measurement software tool that provides quantitative spine measurements from previously-acquired DICOM lumbar spine Magnetic Resonance (MR) images for users' review, analysis, and interpretation. It provides the following functionality to assist users in visualizing, and documenting area and distance measurements of relevant anatomical structures (vertebral body, intervertebral disc, neuroforamina, thecal sac) of the lumbar spine:
- . Feature segmentation:
- . Feature measurement; and
- Export of measurement results to a PDF report containing measurement results and overlay ● images for user's review, revise and approval.
6
Image /page/6/Picture/1 description: The image shows the logo for ScanDiags, a company that specializes in AI interpreting orthopaedic MRI. The logo consists of a blue square made up of smaller squares, followed by the company name in blue, bold letters. Below the logo, it says "AI INTERPRETING ORTHOPAEDIC MRI" in smaller, gray letters. At the bottom right of the image, it says "ScanDiags AG Page 3 of 7" in gray letters.
ScanDiags Ortho L-Spine MR-Q software does not produce or recommend any type of medical diagnosis or treatment. Instead, it simply helps users to more easily identify and classify features in lumbar MR images and compile a report. The user is responsible for reviewing and verifying the software-generated measurements and approving draft report content using their medical judgment and discretion.
The device is intended to be used only by hospitals and other medical institutions.
Only DICOM images of MRI acquired from lumbar spine exams of patients aged 22 and above are considered to be valid input. ScanDiags Ortho L-Spine MR-Q software does not support DICOM images of patients that are pregnant, undergo MRI scan with contrast media, have post-operational complications or infections.
5. Summary of technological characteristics
The following table compares the key technological feature of the subject device (ScanDiags Ortho L-Spine MR-Q) to the predicate device (CoLumbo, K220497).
| | Subject Device:
ScanDiags Ortho L-Spine MR-Q | Predicate Device:
CoLumbo |
|------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 510(k) number | TBD | K220497 |
| Applicant | ScanDiags AG | Smart Soft Healthcare AD |
| Device Name | ScanDiags Ortho L-Spine MR-Q | CoLumbo |
| Regulation
Number | 21 CFR 892.2050 | 21 CFR 892.2050 |
| Product Code | QIH | QIH |
| Class | II | II |
| Image Modality | Radiological images: MRI
(Standardized images used as input) | Radiological images: MRI
(Standardized images used as input) |
| Study Type
(anatomical area
of interest) | Lumbar spine | Lumbar spine |
| Segmentation
and quantitative
analysis | Lumbar spine vertebral body area Lumbar spine intervertebral disc area Foraminal area segmentation Spinal canal area For all segmented areas the area in mm2
is calculated | Vertebral body area Intervertebral disc area Foraminal stenosis clearance size Dural sac area and stenotic ratio |
| Measurements | Vertebral body heights (anterior, middle, posterior) Vertebral body derived measurements: Height ratios | Vertebral body height (anterior, middle, posterior) Disc height (anterior, middle, posterior) Spinal canal anteroposterior diameter |
| | Angle Biconcave height losses Intervertebral disc heights
(anterior, middle, posterior) Spinal canal anteroposterior and mediolateral diameters | |
| Provided output | Report:
A Measurement Result PDF-report sent back to the PACS, which is reviewed, revised and approved by radiologist and contains cropped versions of the original MRI images, with an overlay on top of the cropped images to highlight the segmented anatomic structures and applied measurements and tables displaying quantitative data of the anatomic areas of interest. | Report:
Export of measurement results to a written report for user's review, revise and approval. |
| Human
Intervention for
Interpretation | Required | Required |
| Privacy | The ScanDiags Ortho L-Spine MR-Q Software is HIPAA Compliant by preventing unauthorized access (only authenticated and authorized users can access DICOM data and preliminary Measurement Results in built-in ScanDiags DICOM Viewer), encrypting data in transfer (both DICOM-TLS, SSL certificates in use). The DICOM data transferred to and processed by ScanDiags Ortho L-Spine MR-Q Software only temporarily stores the data until it is either approved or rejected by the intended user. The vulnerability assessment and penetration testing demonstrates satisfactory security performance. | Smart Soft Healthcare conforms to the cybersecurity requirements by implementing a process of preventing unauthorized access, modifications, misuse or denial of use, or the unauthorized use of information that is stored, accessed or transferred from a medical device to an external recipient. The vulnerability assessment and penetration testing demonstrates satisfactory security performance. |
| SaMD | Yes | Yes |
| Supported
Modality | MR | MR |
| Patient
Population | Adult ≥ 22 years of age | Patients aged ≥ 18 are considered to be valid input. |
| Intended User | Clinicians | Clinicians |
| Machine
Learning
Methodology | Supervised Deep Convolutional Neural Network (DCNN), both for classification (image-to-class) to and segmentation (image-to-image) model architectures | Deep Convolutional Image-to-Image Neural Network |
| Performance
Testing | Machine Learning validation study
(standalone performance assessment):
100 individual patient MRI studies
of different age, gender, racial
groups, collected from two
hospital groups, one in Missouri
(18 patients served by a rural
hospital group) and one in North
Carolina (82 patients served by
urban and rural hospital groups). Ground truth annotated by 3 US
board certified MSK radiologist.
Consent ground truth for anatomic
structure segmentation
determined by pixel-based
majority opinion between the
three radiologists. Consent
ground truth for area and distance
measurements determined by
averaging the measurements of
all three readers. The 100 studies were acquired
from GE, Siemens Healthineers
and Philips systems: Siemens: 42 GE: 40 Philips: 18 | Performance data based standalone
software performance assessment study
conducted in the U.S.:
101 MRI image studies for 101
patients of different ages and racial
groups, collected from seven sites
across the U.S. Ground truth defined by 3
radiologists on segmentations and
measurements (per-pixel majority
opinion of the three radiologists
established the ground truth for the
segmented tissue) The 101 study images were
acquired on MRI imaging systems
made by five manufacturers
(Toshiba 1.5T/3T: 65, Siemens
1.5T: 17, Philips 1.5T: 1, Hitachi
1.5T: 1, GE 1.5T: 17) |
7
8
Both subject and predicate devices have similar technological characteristics and principles of operation. Any differences do not raise new concerns of safety and efficacy.
6. Performance Data Substantial Equivalent Discussion
The subject device was developed and tested in accordance with ScanDiags' Design Control processes and has been subjected to extensive safety and performance testing. Verification and validation testing was conducted to demonstrate the substantial equivalence of the subject device to the predicate. The primary success criterion was that the subject device would produce segmentations within acceptable measurement range as well as Dice score above a set threshold compared to the consensus annotation of three radiologists.
Extensive algorithm development and software verification testing, assessed the performance characteristics of the algorithm, including accuracy and overall functional performance. Images and cases used for verification and validation testing were separate and carefully segregated from training datasets. Non-clinical verification and validation test results established that the device meets its design requirements and intended use.
9
Image /page/9/Picture/1 description: The image shows the logo for ScanDiags, a company that specializes in AI interpreting orthopaedic MRI. The logo consists of a blue square with a smaller blue square inside, followed by the word "SCANDIAGS" in large, bold, blue letters. Below the logo, the text "AI INTERPRETING ORTHOPAEDIC MRI" is written in a smaller font. The text "ScanDiags AG Page 6 of 7" is located on the bottom right of the image.
7. Machine Learning Performance Evaluation Summary
A retrospective, multicenter study was designed to evaluate the capability of the machine learning model in calculating the quantified values. A variety of imaging equipment manufacturers included Philips, GE and Siemens were used for the input data.
7.1 Intraclass Correlation Coefficient (ICC)
The device successfully passed the primary ICC acceptance criteria across all structures.
| Mean intraclass correlation coefficient (ICC) of measurements (heights, diameters and areas) for
| lumbar vertebrae, discs, neuroforamina and the thecal sac. | ||
|---|---|---|
| Body Region | Measurement | ICC [95% CI] |
| Vertebra | Area | 0.95 [0.94 - 0.96] |
| Anterior Height | 0.85 [0.30 - 0.94] | |
| Middle Height | 0.91 [0.63 - 0.96] | |
| Posterior Height | 0.89 [0.87 - 0.91] | |
| Neuroforamen | Area | 0.90 [0.86 - 0.93] |
| Intervertebral Disc | Area | 0.92 [0.87 - 0.94] |
| Anterior Height | 0.78 [0.73 - 0.82] | |
| Middle Height | 0.85 [0.18 - 0.95] | |
| Posterior Height | 0.74 [0.68 - 0.78] | |
| Thecal Sac | Area | 0.94 [0.91 - 0.96] |
| Anteroposterior Diameter | 0.92 [0.90 - 0.94] | |
| Mediolateral Diameter | 0.86 [0.83 - 0.88] |
7.2 Dice Similarity Coefficient (DSC)
The device successfully passes the secondary DICE acceptance criteria across all structures.
| Table 8: Mean DICE scores for lumbar vertebrae, discs, neuroforamina and the thecal sac. | Measurement |
|---|---|
| DICE [95% CI] | |
| Vertebra | 0.95 [0.95 - 0.96] |
| Neuroforamen | 0.86 [0.85 - 0.86] |
| Intervertebral Disc | 0.89 [0.89 - 0.90] |
| Thecal Sac | 0.89 [0.89 - 0.90] |
7.3 Mean Absolute Error (MAE)
The device successfully passes the co-secondary MAE acceptance criteria across all structures.
| Table 9: Mean absolute error (MAE) of measurements (heights, diameters and areas) for lumbar vertebrae, discs, neuroforamina and the thecal sac. | ||
|---|---|---|
| Body Region | Measurement | MAE |
| Vertebra | Anterior Height [mm] | 1.17 |
10
Image /page/10/Picture/1 description: The image shows the logo for ScanDiags, a company that specializes in AI interpreting orthopaedic MRI. The logo features a blue square design followed by the company name in bold, blue letters. Below the logo, it says "ScanDiags AG Page 7 of 7" in a smaller, grey font.
| Middle Height [mm] | 0.86 | |
|---|---|---|
| Posterior Height [mm] | 0.79 | |
| Intervertebral Disc | Anterior Height [mm] | 1.1 |
| Middle Height [mm] | 1.19 | |
| Posterior Height [mm] | 0.96 | |
| Thecal Sac | Anteroposterior Diameter [mm] | 0.81 |
| Mediolateral Diameter [mm] | 1.26 |
Bland Altman as well as subgroup analysis based on age, sex, ethnicity, body weight, and MRI manufacturer, MR imaging parameters, underlying disease conditions, and clinical sites were also conducted with detailed results reported in the labeling.
8. Conclusions
Performance testing demonstrated that the subject device is substantially equivalent to the predicate device. The device has the same intended use, and similar indications for use, principles of operation and technological characteristics as the predicate device. The differences do not raise new concerns of safety and effectiveness, therefore the subject device is considered substantially equivalent to the predicate device.