(148 days)
Ezra Flash is an image processing software used for image enhancement of MR images. It can be used to reduce image noise in images acquired as part of non-contrast MRI exams on 1.5-Tesla and 3-Tesla Siemens and GE scanners for patients > 18 years of age:
- · Sagittal T1, Axial T2 and Axial Flair sequences within the head region
- · Axial T2, Coronal T2 within the Abdomen region.
- · Sagittal T2, Axial T2, Coronal T2 within the Pelvis region
Ezra Flash is a Software as a Medical Device (SaMD) consisting of a software algorithm that enhances images of the head, abdomen, and pelvis regions taken by MRI scanners. As it only processes images for the end user, the device has no interface. It is intended to be used by radiologists in an imaging center, clinic, or hospital. The software can be used with MR images acquired as part of MRI exams on 1.5-Tesla and 3-Tesla scanners from Siemens and GE.
The outputs are images with enhanced image quality. Both the original non-enhanced studies and the Ezra Flash-enhanced studies are available to the end user.
Ezra Flash receives DICOM-compliant non-contrast MR image inputs acquired on 1.5-Tesla and 3-Tesla scanners within the head, abdomen and pelvis regions. The software uses a convolutional neural network-based algorithm to improve image quality by reducing noise. The device outputs a DICOM-compliant copy of the images with improved image quality.
Ezra Flash is tested for performance on Sagittal T1, Axial T2, Axial T2 Flair images of the head, Coronal T2, Axial T2 images of the abdomen, Sagittal T2, Axial T2, and Coronal T2 images of the pelvis.
The provided text describes the Ezra Flash, an image processing software for MRI image enhancement. Here's a breakdown of the acceptance criteria and the study proving the device meets them:
1. A table of acceptance criteria and the reported device performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Signal-to-Noise Ratio (SNR) Improvement: SNR of selected region of interests (ROI) in each test dataset is on average improved by > 5% after Ezra Flash enhancement compared to original MR-acquired images (raw). | The text states that this criterion was met as part of the performance testing. Specific numerical results beyond "improved by > 5%" are not provided. |
| Contrast-to-Noise Ratio (CNR) Improvement: CNR of selected region of interests (ROI) in each test dataset is on average improved by > 0% after Ezra Flash enhancement compared to the MR-acquired raw images. | The text states that this criterion was met as part of the performance testing. Specific numerical results beyond "improved by > 0%" are not provided. |
| Image Quality Perceived Noise Reduction: The mean Likert results for the Ezra Flash-enhanced images compared to the original MR-acquired images (raw) is greater than or equal to 0.5 Likert scale points. | The text states that this criterion was met as part of the performance testing. Specific numerical results beyond "greater than or equal to 0.5 Likert scale points" are not provided. |
2. Sample size used for the test set and the data provenance:
- Sample Size for Test Set: Not explicitly stated. The document mentions "each test dataset" but does not provide the total number of images or patients included in the test set.
- Data Provenance: Not explicitly stated. There is no information regarding the country of origin of the data or whether it was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided in the document. The document describes performance testing for objective metrics (SNR, CNR) and a subjective perceived noise assessment using a Likert scale, but it does not detail how the ground truth for these assessments was established or how many experts were involved.
4. Adjudication method for the test set:
- This information is not provided in the document. The text mentions "mean Likert results" but does not specify any adjudication method (e.g., 2+1, 3+1, none) used for subjective assessments or for establishing ground truth if it involved multiple readers.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:
- A MRMC comparative effectiveness study is not explicitly mentioned or described in the document. The performance testing focuses on the device's ability to improve image quality through objective metrics (SNR, CNR) and perceived noise, not on its impact on human reader performance or diagnostic accuracy.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the performance testing described appears to be a standalone (algorithm only) performance evaluation. The criteria focus on the intrinsic image quality improvements achieved by the Ezra Flash software itself (SNR, CNR, perceived noise comparison between raw and enhanced images), rather than its performance in conjunction with a human reader for diagnostic tasks.
7. The type of ground truth used:
- The ground truth for the objective metrics (SNR, CNR) is inherently tied to the raw MR-acquired images as the baseline for comparison.
- For the subjective "Image Quality Perceived Noise" criterion, the ground truth appears to be based on mean Likert scale results, which represent expert assessment of noise rather than a definitive pathological or outcomes-based ground truth.
8. The sample size for the training set:
- The sample size for the training set is not provided in the document.
9. How the ground truth for the training set was established:
- How the ground truth for the training set was established is not provided in the document. The document mentions that the algorithm uses a "convolutional neural network-based algorithm" and that "The parameters of the filters were obtained through an image-guided optimization process," which implies a training process, but details on the ground truth used for this training are absent.
§ 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).