(144 days)
Yes
The device description explicitly states it uses a "deep learning based reconstruction method" and a "dedicated Deep Neural Network (DNN)".
No.
This device is an image reconstruction method used to produce cross-sectional images for diagnostic purposes, not for direct therapeutic treatment.
Yes
The "Intended Use / Indications for Use" states that the device is "intended to produce cross-sectional images... for all ages," and the "Summary of Performance Studies" notes that images were assessed for "diagnostic quality" and "diagnostic use." This indicates the device's output is used to aid in diagnosis.
No
The device is described as an "image reconstruction method" that is "integrated into the scanner's existing raw data-based image reconstruction chain". This indicates it is a software component that is part of a larger hardware system (the CT scanner), not a standalone software-only device.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- IVD Definition: In Vitro Diagnostics are medical devices used to perform tests on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections.
- Device Function: The description clearly states that this device is an "image reconstruction method" that processes "X-ray transmission data" to produce "cross-sectional images." It is a software option integrated into a CT scanner.
- Lack of Sample Analysis: There is no mention of analyzing biological samples from the patient. The input is raw X-ray data acquired directly from the patient's body.
- Output: The output is a medical image, not a diagnostic result derived from a biological sample analysis.
Therefore, this device falls under the category of medical imaging software or a component of a medical imaging system, not an In Vitro Diagnostic device.
No
The letter does not state that the FDA has reviewed and approved or cleared a PCCP for this specific device. The summary indicates "Not Found" for the "Control Plan Authorized (PCCP) and relevant text" section.
Intended Use / Indications for Use
The Deep Learning Image Reconstruction option is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages.
Deep Learning Image Reconstruction can be used for head, whole body, cardiac, and vascular CT applications.
Product codes
JAK
Device Description
Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT lmages to give an image appearance, as shown on axial NPS plots, similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression.
The images produced are branded as "TrueFidelity™ CT Images". Reconstruction times with Deep Learning Image Reconstruction support a normal throughput for routine CT.
Deep Learning Image Reconstruction was trained specifically on the Revolution CT family of systems (K163213, K133705). The deep learning technology is integrated into the scanner's existing raw data-based image reconstruction chain to produce DICOM compatible "TrueFidelity™ CT Images".
The system allows user selection of three strengths of Deep Learning Image Recon: Low, Medium or High. The strength selection will vary with individual users' preferences and experience for the specific clinical need.
As compared to the primary predicate device, the intended use of Deep Learning Image Reconstruction does not change (head and whole body CT image reconstruction). Both algorithms are designed to produce cross-sectional images of the head and body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions for all ages.
Mentions image processing
Not Found
Mentions AI, DNN, or ML
Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT lmages
The deep learning technology is integrated into the scanner's existing raw data-based image reconstruction chain to produce DICOM compatible "TrueFidelity™ CT Images".
Utilizes a dedicated Deep Neural Network (DNN) which is trained on the CT Scanner and designed specifically to generate high quality CT images
Utilizes a trained Deep Neural Network (DNN) which models the scanned object using information obtained from extensive phantom and clinical data
Input Imaging Modality
Computed tomography x-ray system
X-ray transmission data
CT scans
Anatomical Site
head and whole body
head, whole body, cardiac, and vascular
Indicated Patient Age Range
all ages
Intended User / Care Setting
Not Found
Description of the training set, sample size, data source, and annotation protocol
Deep Learning Image Reconstruction was trained specifically on the Revolution CT family of systems (K163213, K133705).
Utilizes a trained Deep Neural Network (DNN) which models the scanned object using information obtained from extensive phantom and clinical data
Description of the test set, sample size, data source, and annotation protocol
The reader study used a total of 60 retrospectively collected clinal cases. The raw data from each of these cases was reconstructed with both ASiR-V and Deep Learning Image Reconstruction and presented side by side to each reader independently.
These images were read by 9 board-certified radiologists with expertise in the specialty areas that align with the anatomical region of each case. Each image was read by 3 different radiologists who provided an assessment of image quality related to diagnostic use according to a 5-point Likert Scale. Three readers read the cases primarily covering body and extremity anatomy, three different readers read the cases primarily covering head/neck anatomy, and three different readers read the cases primarily covering cardiac/vascular.
Additionally, the readers were asked to compare directly the ASIR-V and Deep Learning Image Reconstruction images according to three key metrics of image quality preference – image noise texture, image sharpness, and image noise texture homogeneity.
A final evaluation of low contrast and small lesions in the abdominal and pelvis region by a board-certified radiologist confirmed that the images produced are of diagnostic quality.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Clinical Testing:
The reader study used a total of 60 retrospectively collected clinal cases. The raw data from each of these cases was reconstructed with both ASiR-V and Deep Learning Image Reconstruction and presented side by side to each reader independently. The results of the study support substantial equivalence and performance claims.
These images were read by 9 board-certified radiologists with expertise in the specialty areas that align with the anatomical region of each case. Each image was read by 3 different radiologists who provided an assessment of image quality related to diagnostic use according to a 5-point Likert Scale. Three readers read the cases primarily covering body and extremity anatomy, three different readers read the cases primarily covering head/neck anatomy, and three different readers read the cases primarily covering cardiac/vascular.
Additionally, the readers were asked to compare directly the ASIR-V and Deep Learning Image Reconstruction images according to three key metrics of image quality preference – image noise texture, image sharpness, and image noise texture homogeneity.
A final evaluation of low contrast and small lesions in the abdominal and pelvis region by a board-certified radiologist confirmed that the images produced are of diagnostic quality.
Additional Non-Clinical Testing:
Engineering bench testing was performed to support substantial equivalence and the product performance claims. The evaluation and analysis used the identical raw datasets obtained on GE's Revolution CT and then applies the Deep Learning Image Reconstruction or ASiR-V reconstruction (hence the dose (CTDIvol) is identical for both). The resultant images were then compared for:
- Low Contrast Detectability (LCD) using the head and body MITA/FDA low contrast phantoms and a model observer
- Image Noise (pixel standard deviation) using both head and body uniform phantoms
- High-Contrast Spatial Resolution (MTF) using a quality assurance phantom with a small diameter tungsten wire surrounded by water inside the phantom to generate the point spread function
- Streak Artifact Suppression using an oval uniform polyethylene phantom with embedded high attenuation objects to produce the artifacts
- Spatial Resolution, longitudinal (FWHM slice sensitivity profile)
- Low Contrast Detectability/resolution (statistical)
- Noise Power Spectrum (NPS) and Standard Deviation of noise
- CT Number Uniformity
- CT Number Accuracy
- Contrast to Noise (CNR) ratio
- Artifact analysis – metal objects, unintended motion, truncation
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Not Found
Predicate Device(s)
Reference Device(s)
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.
0
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which consists of the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
GE Medical Systems, LLC. % Lee Bush Regulatory Affairs Manager 3000 N. Grandview Blvd. WAUKESHA WI 53188
Re: K183202
Trade/Device Name: Deep Learning Image Reconstruction Regulation Number: 21 CFR 892.1750 Regulation Name: Computed tomography x-ray system Regulatory Class: Class II Product Code: JAK Dated: March 14, 2019 Received: March 15, 2019
Dear Lee Bush:
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
April 12, 2019
1
devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.html); 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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
Michael D. O'Hara
For
Thalia Mills, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K183202
Device Name Deep Learning Image Reconstruction
Indications for Use (Describe)
The Deep Learning Image Reconstruction option is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages.
Deep Learning Image Reconstruction can be used for head, whole body, cardiac, and vascular CT applications.
| Type of Use (Select one or both, as applicable) | |
|---|---|
| ☑ Prescription Use (Part 21 CFR 801 Subpart D) | ☐ Over-The-Counter Use (21 CFR 801 Subpart C) |
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
Image /page/3/Picture/0 description: The image shows the logo for General Electric (GE). The logo is a blue circle with the letters "GE" in a stylized, cursive font in the center. The circle is surrounded by three swirling shapes, also in blue, that give the impression of movement or energy. The logo is simple, clean, and recognizable, and it is often used to represent the company's brand and identity.
510(k) SUMMARY OF SAFETY AND EFFECTIVNESS K183202
This 510(k) summary of Safety and Effectiveness information is submitted in accordance with the requirement of 21 CFR Part 807.87(h):
| Date: | November 16, 2018 |
|---|---|
| Submitter: | GE Medical Systems, LLC |
| 3000 North Grandview Blvd | |
| Waukesha, WI 53188 | |
| Primary Contact: | Lee Bush |
| Regulatory Affairs Manager | |
| Phone 262-309-9429 | |
| Email: Lee.Bush@ge.com | |
| Secondary Contacts: | John Jaeckle |
| Chief Regulatory Affairs Engineer | |
| GE Healthcare | |
| Tel: 262-424-9547 | |
| Email: john.jaeckle@ge.com | |
| Device Trade Name: | Deep Learning Image Reconstruction |
| Device Classification | Class II |
| Regulation Number/ | |
| Product Code: | 21 CFR 892.1750 Computed tomography x-ray system / JAK |
| Primary Predicate Device Information | |
| Device Name: | ASIR-V |
| Manufacturer: | GE Medical System SCS (d.b.a GE Healthcare) |
| 510(k) Number: | K133640 cleared on March 25, 2014 |
| Regulation Number/ | |
| Product Code: | 21 CFR 892.1750 Computed tomography x-ray system / JAK |
| Secondary Predicate Device Information | |
| Device Name: | Revolution CT |
| Manufacturer: | GE Medical System SCS (d.b.a GE Healthcare) |
| 510(k) Number: | K163213 cleared on December 16, 2016 |
| Regulation Number/ | |
| Product Code: | 21 CFR 892.1750 Computed tomography x-ray system / JAK |
4
Image /page/4/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' in a stylized script, enclosed within a blue circle. There are also some white swirls around the circle.
Device Description
Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT lmages to give an image appearance, as shown on axial NPS plots, similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression.
The images produced are branded as "TrueFidelity™ CT Images". Reconstruction times with Deep Learning Image Reconstruction support a normal throughput for routine CT.
Deep Learning Image Reconstruction was trained specifically on the Revolution CT family of systems (K163213, K133705). The deep learning technology is integrated into the scanner's existing raw data-based image reconstruction chain to produce DICOM compatible "TrueFidelity™ CT Images".
The system allows user selection of three strengths of Deep Learning Image Recon: Low, Medium or High. The strength selection will vary with individual users' preferences and experience for the specific clinical need.
As compared to the primary predicate device, the intended use of Deep Learning Image Reconstruction does not change (head and whole body CT image reconstruction). Both algorithms are designed to produce cross-sectional images of the head and body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions for all ages.
Intended Use
The Deep Learning Image Reconstruction option is intended for head, whole body, cardiac, and vascular CT scans.
Indications for Use
The Deep Learning Image Reconstruction option is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages.
Deep Learning Image Reconstruction can be used for head, whole body, cardiac, and vascular CT applications.
Comparisons
The GE Deep Learning Image Reconstruction option is substantially equivalent to existing reconstruction options including the primary predicate device, ASiR-V reconstruction option. Because both reconstruction options (Deep Learning Image Reconstruction and ASiR-V) are implemented on the secondary predicate, Revolution CT family (K163213, K133705), they utilize the same hardware and software platform technology on which substantial equivalency is
5
Image /page/5/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' in a stylized, cursive font, enclosed within a circular frame. The frame has decorative swirls or flourishes around the letters. The logo is colored in a shade of blue, with a white outline around the letters and the frame.
demonstrated. The table below summarizes the substantive feature/technological differences between the predicate device and the proposed device:
| Specification/ | ASiR-V | Deep Learning Image Reconstruction |
|---|---|---|
| Attribute | (Predicate Device, K133640) | (Proposed Device) |
| Technology | Extensive system statistical | |
| model | Utilizes a dedicated Deep Neural | |
| Network (DNN) which is trained on the | ||
| CT Scanner and designed specifically to | ||
| generate high quality CT images | ||
| System statistics - | ||
| Noise modeling of | ||
| the data collection | ||
| imaging chain | ||
| (photon noise and | ||
| electronic noise) | Characterization of the photon | |
| statistics as it propagates | ||
| through the preprocessing and | ||
| calibration imaging chain | Same | |
| System statistics - | ||
| Noise characteristics | ||
| of the reconstructed | ||
| images | The characterization of the | |
| scanned object using | ||
| information obtained from | ||
| extensive phantom and clinical | ||
| data | Utilizes a trained Deep Neural Network | |
| (DNN) which models the scanned | ||
| object using information obtained from | ||
| extensive phantom and clinical data | ||
| Clinical Workflow | Select recon type and strength | |
| (percentage) | Select recon type and strength (High, | |
| Medium, Low) |
Deep Learning Image Reconstruction does not introduce any new risks/hazards, warnings, or limitations.
Determination of Substantial Equivalence
Summary of Non-Clinical Testing
Deep Learning Image Reconstruction has successfully completed the design control testing per our quality system. No new hazards were identified, and no unexpected test results were obtained. Deep Learning Image Reconstruction was designed under the Quality System Regulations of 21CFR 820 and ISO 13485. GE believes that the extensive bench testing performed, and the physician evaluation are sufficient for FDA's substantial equivalence determination.
The following quality assurance measures have been applied to the development of the system:
- Risk Analysis
- Required Reviews
- Design Reviews
6
Image /page/6/Picture/0 description: The image shows the logo for General Electric (GE). The logo consists of the letters "GE" in a stylized script, enclosed within a blue circle. The circle is surrounded by a series of curved lines, resembling water droplets or stylized flourishes, also in blue. The logo is simple, recognizable, and has been used by GE for many years.
- Software Development Lifecycle
- Testing on unit level (Module verification)
- Integration testing (System verification)
- . Performance testing (Verification)
- Safety testing (Verification)
- . Simulated use testing (Validation)
The testing and results did not raise different questions of safety and effectiveness than associated with predicate device. We consider the proposed device is substantially equivalent to the predicate device ASIR-V.
The substantial equivalence is also based on the software documentation for a "Moderate" level of concern device
Additional Non-Clinical Testing
Engineering bench testing was performed to support substantial equivalence and the product performance claims. The evaluation and analysis used the identical raw datasets obtained on GE's Revolution CT and then applies the Deep Learning Image Reconstruction or ASiR-V reconstruction (hence the dose (CTDIvol) is identical for both). The resultant images were then compared for:
- . Low Contrast Detectability (LCD) using the head and body MITA/FDA low contrast phantoms and a model observer
- 트 lmage Noise (pixel standard deviation) using both head and body uniform phantoms
- 트 High-Contrast Spatial Resolution (MTF) using a quality assurance phantom with a small diameter tungsten wire surrounded by water inside the phantom to generate the point spread function
- . Streak Artifact Suppression using an oval uniform polyethylene phantom with embedded high attenuation objects to produce the artifacts
- 트 Spatial Resolution, longitudinal (FWHM slice sensitivity profile)
- . Low Contrast Detectability/resolution (statistical)
- 트 Noise Power Spectrum (NPS) and Standard Deviation of noise
- 트 CT Number Uniformity
- CT Number Accuracy
- I Contrast to Noise (CNR) ratio
- 트 Artifact analysis – metal objects, unintended motion, truncation
Clinical Testing
The reader study used a total of 60 retrospectively collected clinal cases. The raw data from each of these cases was reconstructed with both ASiR-V and Deep Learning Image
7
Image /page/7/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' intertwined within a blue circle. There are decorative water droplet-like shapes surrounding the circle, giving it a distinctive and recognizable appearance.
Reconstruction and presented side by side to each reader independently. The results of the study support substantial equivalence and performance claims.
These images were read by 9 board-certified radiologists with expertise in the specialty areas that align with the anatomical region of each case. Each image was read by 3 different radiologists who provided an assessment of image quality related to diagnostic use according to a 5-point Likert Scale. Three readers read the cases primarily covering body and extremity anatomy, three different readers read the cases primarily covering head/neck anatomy, and three different readers read the cases primarily covering cardiac/vascular.
Additionally, the readers were asked to compare directly the ASIR-V and Deep Learning Image Reconstruction images according to three key metrics of image quality preference – image noise texture, image sharpness, and image noise texture homogeneity.
A final evaluation of low contrast and small lesions in the abdominal and pelvis region by a board-certified radiologist confirmed that the images produced are of diagnostic quality.
Substantial Equivalence
The changes associated with Deep Learning Image Reconstruction do not change the Indications for Use from the primary predicate, and represent equivalent technological characteristics, with no impact on control mechanism, operating principle, and energy type.
Deep Learning Image Reconstruction was developed under GE Healthcare's quality system. Design verification, along with bench testing and the clinical reader study demonstrate that Deep Learning Image Reconstruction is substantially equivalent and hence as safe and as effective as the legally marketed predicate device. GE's quality system's design, verification, and risk management processes did not identify any new hazards, unexpected results, or adverse effects stemming from the changes to the predicate.
Based on development under GE Healthcare's quality system, the successful verification testing, the additional engineering bench testing, and the clinical reader study, GE Healthcare believes that Deep Learning Image Reconstruction is substantially equivalent to the predicate device and hence is safe and effective for its intended use.