(109 days)
Yes
The device description explicitly states that the fundamental technology has been replaced by deep learning technology, specifically algorithms based on Convolutional Neural Networks, and mentions that the predicate device used Machine Learning.
No
The device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules; it does not directly treat or cure any condition.
Yes
Explanation: The device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules, which is a diagnostic activity.
Yes
The device is described as a software tool that processes images from a CT scanner and provides output to a visualization application. There is no mention of accompanying hardware components included with the device itself.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs analyze biological samples: In Vitro Diagnostics are designed to examine specimens taken from the human body, such as blood, urine, or tissue, to provide information about a person's health.
- This device analyzes medical images: The syngo.CT Lung CAD VC30 processes and analyzes medical images (CT scans) of the chest. It does not interact with or analyze biological samples.
- Its purpose is image analysis for diagnostic assistance: The device's intended use is to assist radiologists in interpreting medical images by highlighting potential areas of interest (pulmonary nodules). This is a function of medical image analysis, not in vitro diagnostic testing.
Therefore, while it is a medical device used in the diagnostic process, it falls under the category of medical imaging software or computer-aided detection (CAD) tools, not In Vitro Diagnostics.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
The syngo.CT Lung CAD VC30 device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest that may have been initially overlooked. The syngo.CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read.
Product codes
OEB
Device Description
Siemens Healthcare GmbH intends to market the syngo.CT Lung CAD which is a medical device that is designed to perform CAD processing in thoracic CT examinations for the detection of solid pulmonary nodules ≥ 3.0 mm in size. The device processes images acquired with Siemens multi-detector CT scanners with 4 or more detector rows.
The syngo.CT Lung CAD device supports the full range of nodule locations (central, peripheral) and contours (round, irregular). The detection performance of the syngo.CT Lung CAD device is optimized for nodules between 3.0 mm and 20.0 mm in size.
The syngo.CT Lung CAD sends a list of nodule candidate locations to a visualization application, such as syngo MM Oncology, or a visualization rendering component, which generates output images series with the CAD marks superimposed on the input thoracic CT images for use in a second reader mode. syngo MM Oncology (FDA clearance K191309) is implemented on the syngo.via platform (FDA clearance K191040), which provides a common framework for various other applications implementing specific clinical workflows (but are not part of this clearance) to display the CAD marks. The syngo.CT Lung CAD device is intended to be used as a second reader only after the initial read is completed.
The subject device and the predicate device has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep learning technology. Specifically, the predicate VC20 uses feature-based and Machine Learning whereas the current VC30 uses algorithms based on Convolutional Neural Networks. This does not introduce new types of safety or effectiveness concerns.
Mentions image processing
Yes
Mentions AI, DNN, or ML
The subject device and the predicate device has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep learning technology. Specifically, the predicate VC20 uses feature-based and Machine Learning whereas the current VC30 uses algorithms based on Convolutional Neural Networks.
Input Imaging Modality
Multi-detector Computed Tomography (MDCT)
Anatomical Site
Chest / Lungs
Indicated Patient Age Range
Not Found
Intended User / Care Setting
Radiologists in a second reader workflow.
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
Not Found
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
The standalone performance test proved that the standalone sensitivity of syngo.CT Lung CAD VC30 is superior to that of syngo.CT Lung CAD VC20 (predicate) and the false positive rate improved (reduced). Furthermore, both true positive and false positive syngo.CT Lung CAD VC30 marks were shown to be reasonably consistent with marks produced by syngo.CT Lung CAD VC20 (predicate) in both location and extent.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Standalone sensitivity and false positive rate.
Predicate Device(s)
Reference Device(s)
Predetermined Change Control Plan (PCCP) - All Relevant Information for the subject device only (e.g. presence / absence, what scope was granted / cleared under the PCCP, any restrictions, etc).
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
FDA U.S. FOOD & DRUG
ADMINISTRATION
Siemens Healthcare GmbH % Mr. Abhineet Johri Regulatory Affairs Manager Siemens Medical Solutions, Inc. 65 Valley Stream Parkway MALVERN PA 19355
March 9, 2020
Re: K193216
Trade/Device Name: syngo.CT Lung CAD Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: OEB Dated: February 4, 2020 Received: February 6, 2020
Dear Mr. Johri:
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 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for
1
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.
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)
K193216
Device Name
syngo.CT Lung CAD (VC30)
Indications for Use (Describe)
The syngo.CT Lung CAD VC30 device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest that may have been initially overlooked. The syngo.CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read.
| Type of Use (Select one or both, as applicable) | |
|---|---|
| Prescription Use (Part 21 CFR 801 Subpart D) | Over-The-Counter Use (21 CFR 801 Subpart C) |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
510(k) Summary
for
Siemens Healthcare GmbH
syngo.CT Lung CAD (Previously cleared as syngo.CT Lung CAD, K143196) Version VC30
4
510(k) Summary
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR §807.92.
Date prepared: March 05, 2020
1. Submitter (Legal Manufacturer):
Siemens Healthcare GmbH Henkestrasse 127 91052 Erlangen Germany
Manufacturing Location (Facility)
Siemens Medical Solutions USA, Inc. 65-3 Valley Stream Parkway Malvern PA. 19355
Establishment Registration Number:
3004977335
2. Contact Person:
Mr. Abhineet Johri Regulatory Affairs Manager Siemens Healthcare GmbH, 65-3 Valley stream parkway Malvern, PA 19355. U.S.A E-mail: abhineet.johri@siemens-healthineers.com Telephone: +1 (484) 680-8723 Fax: +1 610-448-6557
3. Device Name and Classification:
| Trade Name: | syngo.CT Lung CAD |
|---|---|
| Classification Name: | Lung computed tomography system, computer-aided detection |
| Classification Panel: | Radiology |
| CFR Section: | 21 CFR §892.2050 |
| Device Class: | Class II |
| Product Code: | OEB |
5
-
- Legally Marketed Predicate Device:
| Trade Name: | syngo.CT Lung CAD |
|---|---|
| 510(k) Clearance: | K143196 |
| Clearance Date: | May 2015 |
| Classification Name: | Lung computed tomography system, computer-aided detection |
| Classification Panel: | Radiology |
| CFR Section: | 21 CFR §892.2050 |
| Device Class: | Class II |
| Product Code: | OEB |
| Recall Information: | This predicate device has not been the subject of any |
| design related recalls. |
5. Device Description:
Siemens Healthcare GmbH intends to market the syngo.CT Lung CAD which is a medical device that is designed to perform CAD processing in thoracic CT examinations for the detection of solid pulmonary nodules ≥ 3.0 mm in size. The device processes images acquired with Siemens multi-detector CT scanners with 4 or more detector rows.
The syngo.CT Lung CAD device supports the full range of nodule locations (central, peripheral) and contours (round, irregular). The detection performance of the syngo.CT Lung CAD device is optimized for nodules between 3.0 mm and 20.0 mm in size.
The syngo.CT Lung CAD sends a list of nodule candidate locations to a visualization application, such as syngo MM Oncology, or a visualization rendering component, which generates output images series with the CAD marks superimposed on the input thoracic CT images for use in a second reader mode. syngo MM Oncology (FDA clearance K191309) is implemented on the syngo.via platform (FDA clearance K191040), which provides a common framework for various other applications implementing specific clinical workflows (but are not part of this clearance) to display the CAD marks. The syngo.CT Lung CAD device is intended to be used as a second reader only after the initial read is completed.
The subject device and the predicate device has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep learning technology. Specifically, the predicate VC20 uses feature-based and Machine Learning whereas the current VC30 uses algorithms based on Convolutional Neural Networks. This does not introduce new types of safety or effectiveness concerns. In particular, as demonstrated by the statistical analysis and results of the standalone benchmark evaluations:
6
- i. The standalone accuracy has been shown not only to be non-inferior but actually superior to that of the device and
- The marks generated by the two devices have been shown to be reasonably conii. sistent.
This device description holds true for the subject device, syngo.CT Lung CAD, software version VC30, as well as the predicate device, syngo.CT Lung CAD, software version VC20.
6. Intended Use:
The syngo.CT Lung CAD device is a computer-aided detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multidetector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest (ROI) that may have been initially overlooked. The syngo.CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read.
Safety and Effectiveness Information
Software design description, hazard analysis, and technical and safety information have also been completed and provided in support of this device. The results of the hazard analysis, combined with the appropriate preventive measures taken indicate the device is of moderate level of concern, as per Guidance for the Content of Premarket Submission for Software Contained in Medical Devices, May 2005
The device has no patient contacting materials and is utilized only by trained professionals. The output of the device is evaluated by trained professionals as a second reader. Use of this device does not impact the quality or status of the original acquired data.
7
Substantial Equivalence:
The syngo.CT Lung CAD is substantially equivalent, both in intended use and indication for use to the following device. The new version has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep learning technology. Specifically, the predicate VC20 uses feature-based ML CADe compared to current VC30 deep CNN-based CADe. This does not introduce new types of safety or effectiveness questions. As demonstrated by the statistical analysis and results of the standalone benchmark evaluations:
- iii. The standalone accuracy has been shown not only to be non-inferior but actually superior to that of the device and
- iv. The marks generated by the two devices have been shown to be reasonably consistent.
| Company | Product - Trade Name | 510(k) # |
|---|---|---|
| Siemens AG Medical Solutions | Syngo .CT Lung CAD | K143196 |
In summary, Siemens Healthcare GmbH is of the opinion that the syngo.CT Lung CAD software, as described within this document, does not pose any unmitigated safety risks and is substantially equivalent to the predicate device since its accuracy has been shown to be superior to the predicate device and the marks are reasonably consistent .
The difference between the predicate device syngo.CT Lung CAD VC20 and syngo.CT Lung CAD VC30 are minor in nature and both devices have the same characteristics and functionalities, as described in table below.
8
7. Summary of Differences between the Subject Device and the Predicate Device:
The differences between the subject device described in this predicate device are summarized in the following comparison table 1 and 2 below:
9
| Subject Device
Characteristic | Current Predicate Device
syngo.CT Lung CAD (VC20E)
(K)143196 | New Device
syngo.CT Lung CAD (VC30) | Type of Change and Impact to
Safety & Effectiveness |
|----------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Manufacturer | Siemens AG Medical Solutions | Siemens Healthcare GmbH | Legal manufacturer change1.
No Impact |
| Detection target | Solid pulmonary nodules in diag-
nostic chest CT acquisitions | Solid pulmonary nodules in diag-
nostic chest CT acquisitions | [Unchanged] and no Impact |
| Intended Use | The LungCAD software device is a
Computer-Aided Detection (CAD)
tool designed to assist
radiologists in the detection of solid
pulmonary nodules during review of
multi-detector
computed tomographic (MDCT)
thoracic examinations. The software
is an adjunctive tool
that alerts the radiologist to regions
of interest (ROI) that may be initial-
ly overlooked. The
LungCAD software device use is
intended to be used as a second
reader after the radiologist has com-
pleted his/her initial read. | The LungCAD software device is a
Computer-Aided Detection (CAD)
tool designed to assist
radiologists in the detection of solid
pulmonary nodules during review of
multi-detector
computed tomographic (MDCT)
thoracic examinations. The software
is an adjunctive tool
that alerts the radiologist to regions
of interest (ROI) that may be initial-
ly overlooked. The
LungCAD software device use is
intended to be used as a second
reader after the radiologist has com-
pleted his/her initial read. | [Unchanged] and no Impact |
| Indications For Use | The syngo .CT Lung CAD device is a computer-aided detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest (ROI) that may have been initially overlooked. The syngo .CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read. | The syngo .CT Lung CAD device is a computer-aided detection (CAD) tool designed to assist radiologists in the detection of solid pulmonary nodules during review of multi-detector computed tomography (MDCT) examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest (ROI) that may have been initially overlooked. The syngo .CT Lung CAD device is intended to be used as a second reader after the radiologist has completed his/her initial read. | [Unchanged] and no Impact |
| Nodule Characteristics | Size Solid nodules ≥ 3mm and ≤ 10mm Locations full range: central, peripheral Contours: round, irregular | Diameter Solid nodules ≥ 3mm and ≤ 20mm Locations full range: central, peripheral Contours: round, irregular | Extended nodule size to 20mm.
No impact as assessed in the evidence provided in the benchmark analysis provided in this substantial equivalence evaluation. Attachment 10 and 12 |
| Reader workflow | second reader workflow | second reader workflow | [Unchanged] and no Impact |
| Input scanning parameters | Scanners
Siemens multi-detector CT (MDCT)
scanners. | Scanners
Siemens multi-detector CT (MDCT)
scanners. | [Unchanged] and no Impact |
| | Detector rows
4 or more detector rows | Detector rows
4 or more detector rows | [Unchanged] and no Impact |
| | Scan area
The scan area needs to comprise the
entire thorax covering the lung api-
ces to the bases | Scan area
The scan area needs to comprise the
entire thorax covering the lung api-
ces to the bases | [Unchanged] and no Impact |
| | Scan direction
Cranio-caudal or caudal-cranial | Scan direction
Cranio-caudal or caudal-cranial | [Unchanged] and no Impact |
| | Voltage
120-140 kVp | Voltage
120-140 kVp | [Unchanged] and no Impact |
| | Exposure
40-120 mAs | Exposure
40-120 mAs | [Unchanged] and no Impact |
| | Collimation
1 mm or less | Collimation
1 mm or less | [Unchanged] and no Impact |
| | Slice width
1.00 - 1.25 mm | Slice Thickness
1.00 - 1.25 mm | [Unchanged] and no Impact – no-
menclature updating only |
| | Slice overlap
0-25%
Note: Reconstruction overlap is al-
lowed, but gaps are not permitted | Slice Overlap
0-25%
Note: Reconstruction overlap is al-
lowed, but gaps are not permitted | [Unchanged] and no Impact |
| | Number of images
Up to 1000 images per series. | Number of images
Up to 1000 images per series. | [Unchanged] and no Impact |
1 syngo.CT Lung CAD (VC20)was manufactured by Siemens AG Medical Solutions during the time of its filing. Later-on legal manufacturer change was performed to Siemens Healthcare GmbH. So finally, the legal manufacturer is identical for both devices.
10
11
12
| Kernel Siemens B60 | Kernel Siemens B60 | [Unchanged] and no Impact | |
|---|---|---|---|
| Hosting Platform | syngo.via | ||
| Hosting Application | syngo MM Oncology | ||
| Dose | Diagnostic |
Table 1 Summary of Differences between the Subject Device and the Predicate Device
| Functional
| Component | LungCAD VC20 | LungCAD VC30 |
|---|---|---|
| Preprocessing | ||
| Standardization of | ||
| the input images | ||
| and lung | ||
| segmentation | (a) isotropic volume resampling | |
| (b) lung segmentation is performed on a slice-by- | ||
| slice approach by identifying the middle of the | ||
| lung area, then processing first the upper half of | ||
| the lung and then the lower half of the lungs. Slice | ||
| processing identifies starting points and traces the | ||
| lung contour, slice-by slice. This is followed by | ||
| contour smooth and filling. | (a) isotropic volume resampling | |
| (b) lung segmentation is accomplished using a CCN. Initially a | ||
| coarse estimation of the lung is performed using a V-net | ||
| process. Using two predefined bounding boxes left and right | ||
| lungs are initialized. Another V-net is used to segment left and | ||
| right lungs. This is followed by up-sampling to the original | ||
| image resolution. | ||
| Candidate | ||
| Generation | ||
| Scans through all | ||
| slices of the | ||
| segmented lung to | ||
| search for | (a) isotropic volume is partitioned into subvolumes | |
| (b) Each volume is processed using the divergence | ||
| of the 3D gradient field compute a "response vol- | ||
| ume" thresholded to yield a list of candidates. | ||
| Features are computed (e.g. number of voxels, | ||
| sphericity, maximum response value, etc.) | ||
| (c) Cascade 1: candidates are passed to two-way | (a) isotropic volume is partitioned into subvolumes | |
| (b) Each subvolume is fed to a CNN to compute features | ||
| ("response volume"). Filtering and non-maximum suppression | ||
| yield a list of candidates for each subvolume | ||
| (c) Cascade 1: candidates above a certain threshold score are | ||
| passed to the next step. |
13
| candidates | gaiting classifier. Those above a certain threshold
score are kept and passed to the next step. | |
|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Feature
Calculation
Features are
computed for each
candidate. | Groups of features are computed for each
candidate. These groups of features include:
Gaussian, curvature , isotropy, wall attachment,
etc. | CNN is used for feature computation for each candidate.
(a) The input image patch is firstly processed by batch
normalization.
(b) Three blocks of operations are computed. In each block, a
convolution, with stride 2, is used for down-sampling instead
of max-pooling.
(c) Semantic features from image features are computed using |
| Candidate
Classification
Candidate
specificity is
increased by
applying a logistic
regression
classifier to the
hierarchical
features calculated | Cascade 2:
(a) A three way-gaiting classifier is applied to each
candidate based on values computed in the
previous section.
(b) Based on the gaiting, the features from
previous step are used to assign a label to the
candidate . | two fully connected layers.
CNN is used for candidate classification .
(a) A soft-max function, applied to each candidate, assigns 2
values corresponding to the probability of being a nodule or
being a false positive.
(b) Cascade 2: A weighted-sum of the scores from Cascade 1
and the results of the classifier (prior step) is computed. Can-
didates above a certain threshold score are labeled as nodule
candidates. |
| Final Candidate
List | The location information of the nodule candidates
are collected into a final candidate list passed to
the hosting application | The location information of the nodule candidates are collected
into a final candidate list passed to hosting application. |
Table 2: Functional Components for syngo.CT Lung CAD VC20 (predicate) and syngo.CT Lung CAD VC30 (Subject device)
14
8. Non-clinical Performance Testing:
Non-clinical tests were conducted for the device syngo.CT Lung CAD (during product development. The modifications described in this Premarket Notification were supported with verification and validation testing.
Siemens Healthcare GmbH claims conformance to the following standards:
- -ISO 14971 Second edition 2007-03-01
- IEC 62304 Edition 1.1 2015-06 Consolidated Version -
- IEC 62366-1 Edition 1.0 2015-02 -
9. Software Verification and Validation:
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. The performance data demonstrates continued conformance with special controls for medical devices containing software. Non-clinical tests were conducted on the device syngo.CT Lung CAD during product development.
The Risk Analysis was completed, and risk control implemented to mitigate identified hazards. The testing results support that all the software specifications have met the acceptance criteria. Testing for verification and validation for the device was found acceptable to support the claims of substantial equivalence.
Summary:
Performance tests were conducted to test the functionality of the device syngo.CT Lung CAD . These tests have been performed to assess the functionality of the subject device. Results of all conducted testing were found acceptable in supporting the claim of substantial equivalence.
The standalone performance test proved that the standalone sensitivity of syngo.CT Lung CAD VC30 is superior to that of syngo.CT Lung CAD VC20 (predicate) and the false positive rate improved (reduced). Furthermore, both true positive and false positive syngo.CT Lung CAD VC30 marks were shown to be reasonably consistent with marks produced by syngo.CT Lung CAD VC20 (predicate) in both location and extent. The endpoints to establish meaningful and statistically relevant performance and equivalence of the device and sample size were considered and defined as part of the test protocols.
15
Non-clinical performance testing was performed at various levels for verification and validation of the device intended use and to ensure safety and effectiveness.
The protocol of the tests follows the testing activities of the software development and quality management process. This protocol, which ensures both verification and validation, is structured at different levels of product testing to ensure that the above objectives are met. These are:
-
- Unit test: Verify the Design Specification, Risk Mitigations, identify runtime errors and memory leaks and Verify the Logic.
-
- Integration test: Verify the correct implementation of the design and test coverage specified by the software requirements and Design Specifications. The Implementation and effectiveness of Risk mitigation classified as Hazard is also checked. (Hazard Tests).
-
- System test: It is performed on the integrated product comprising of the software units and components.
-
- System Validation: Objective is to validate the intended use defined in the requirements specifications and risk labelling mitigations. These requirements will be validated using one of the Hosting Applications.
Tests specifications used for the test levels mentioned above include test descriptions, test environment and the test cases with the requirements that were tested. Tests are passed only based on the defined acceptance criteria. To ensure continuous quality of the software, automatic testing with GUI (graphical user interface) and Non-GUI based-tests are performed to cover the software's functionality. The basis for the test automation is described in the corresponding Test Specifications. The matching of automated test cases and test results is ensured through code reviews of the automation scripts.
10. Safety and Effectiveness Information:
Software specifications, design descriptions, hazard analysis, and labeling information are submitted in support of this premarket notification. The device labeling contains instructions for use with cautions to provide for safe and effective use of the device.
The results of the hazard analysis combined with the appropriate preventive measures taken indicate the device is of moderate level of concern, as per the Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 11, 2005).
11. Conclusion as to Substantial Equivalence:
The syngo.CT Lung CAD is substantially equivalent, both in intended use and indication for use to the following device. The new version has the same basic technical characteristics as the predicate; however, the fundamental technology has been replaced by deep
16
learning technology. Specifically, the predicate VC20 uses feature-based ML CADe compared to current VC30 deep CNN-based CADe. This does not introduce new types of safety or effectiveness questions. As demonstrated by the statistical analysis and results of the standalone benchmark evaluations:
- i. the standalone accuracy has been shown not only to be non-inferior but actually superior to that of the device and
- ii. the marks generated by the two devices have been shown to be reasonably consistent.
In summary, Siemens is of the opinion that the syngo.CT Lung CAD software, as described within this document, does not pose any unmitigated safety risks and is substantially equivalent to the predicate device since its accuracy has been shown to be superior to the predicate device and the marks are reasonably consistent .
The difference between the predicate device syngo.CT Lung CAD VC20 and syngo.CT Lung CAD VC30 are minor in nature and both devices have the same characteristics and functionalities.