(146 days)
True Enhance DL is a deep learning-based image processing method trained to estimate monochromatic, 50 keV GSI images. The algorithm is intended to improve the contrast of 120 kVp, single energy images of the body.
This device is intended to provide non-quantitative, adjunct information and should not be interpreted without the original 120 kVp image.
True Enhance DL may be used for patients of all ages.
True Enhance DL is a deep learning-based image processing method for contrast enhanced images of the body obtained using the Revolution Ascend Family (K213938), which consists of multiple commercial configurations: Revolution Ascend Elite, Revolution Ascend Plus, and Revolution Ascend Select. True Enhance DL is intended to post-process single energy, 120 kVp images to output nonquantitative, adjunctive information with better contrast than single energy input data.
True Enhance DL brings four deep leaning models that the user can choose depending on different contrast enhancement phases. These four models are CT Angiography, Arterial, Portal/Venous, and Delayed True Enhance DL.
True Enhance DL is not intended to replace hardware based Monochromatic Imaging by Gemstone Spectral Imaging (GSI) technology or replicate GSI dual energy acquisitions. The device was trained to estimate monochromatic, 50 keV GSI images, and only enhances images from 120 kVp acquisitions on non-GSI Revolution Ascend systems.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Primary Goal: Improve the contrast of 120 kVp, single energy images of the body. | "The result of this reader study and head-to-head material comparison validated that True Enhance DL software provides additional benefit by improving contrast in the True Enhance output when compared to the original 120 kVp single energy images." |
| Provide non-quantitative, adjunct information. | The device's indication explicitly states it "is intended to provide non-quantitative, adjunct information." |
| Not replace hardware-based Monochromatic Imaging by Gemstone Spectral Imaging (GSI) technology or replicate GSI dual energy acquisitions. | "True Enhance DL is not intended to replace hardware based Monochromatic Imaging by Gemstone Spectral Imaging (GSI) technology or replicate GSI dual energy acquisitions." |
| Output estimable as 50 keV GSI images. | "The device was trained to estimate monochromatic, 50 keV GSI images." |
| No new or different questions of safety or effectiveness compared to the predicate device. | "GE's quality system's design verification, and risk management processes did not identify any new questions of safety or effectiveness, hazards, unexpected results, or adverse effects stemming from the changes to the predicate." |
| Achieve adequate image quality. | "The changes associated with True Enhance DL do not create a new Intended Use and represent technological characteristics that produce images that have demonstrated adequate image quality..." |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated as a number of cases. The text mentions "sample clinical data" and "Additional representative clinical cases and anthropomorphic phantom cases."
- Data Provenance: Retrospective. The study used "retrospectively collected representative clinical cases." The country of origin is not specified.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:
- Number of Experts: Four.
- Qualifications of Experts: "Four board certified radiologists." Specific years of experience are not mentioned.
4. Adjudication Method for the Test Set:
- The text does not explicitly state a formal adjudication method (e.g., 2+1, 3+1). It indicates that the four radiologists each provided a comparative assessment of image quality related to diagnostic use. This suggests individual reader assessment rather than a consensus-building adjudication process for ground truth. However, they were asked to "rate the contrast enhancement in the True Enhance DL series vs the native image series," which implies a comparative evaluation.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size:
- A MRMC-like study was done, as "four board certified radiologists" read the images.
- Effect Size: The text states, "the readers were asked to rate the contrast enhancement in the True Enhance DL series vs the native image series" and "validated that True Enhance DL software provides additional benefit by improving contrast." However, a quantitative effect size of human readers' improvement with AI vs. without AI assistance is not provided in this summary. The focus was on the software's ability to improve contrast rather than a comparative effectiveness of human performance with and without the tool.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:
- Yes, a standalone evaluation was conducted to assess image characteristics. The text mentions "Additional representative clinical cases and anthropomorphic phantom cases from a GSI system generating both single energy 120 kVp and 50 keV monochromatic images were evaluated for CT number in various anatomical regions to study image characteristics for different materials of the device output compared to 50 keV and 120 kVp reference images." This assesses the algorithm's output properties directly against a reference, which constitutes a standalone performance aspect.
7. The Type of Ground Truth Used:
- Expert Consensus / Reader Assessment: For the image quality and contrast improvement aspects, the subjective assessment of "four board certified radiologists" served as the ground truth.
- Reference Images / Clinical Data: For the standalone evaluation, "50 keV and 120 kVp reference images" (likely derived from GSI systems with known energy characteristics) were used to study the algorithm's output. Clinical cases with "disease/pathology" were used, implying the presence of known conditions, although how these conditions served as "ground truth" for the AI's performance beyond simply being present in the data is not fully detailed.
8. The Sample Size for the Training Set:
- The sample size for the training set is not provided in this document. The text only states, "The device was trained to estimate monochromatic, 50 keV GSI images."
9. How the Ground Truth for the Training Set Was Established:
- The document implies that the training was based on "to estimate monochromatic, 50 keV GSI images." This suggests that 50 keV monochromatic GSI images (likely acquired from dual-energy CT scans, which serve as a form of ground truth for spectral decomposition) were used as the target output for the deep learning model during training. The process of generating these reference 50 keV GSI images themselves would involve the CT system's physics and reconstruction algorithms.
§ 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.