Search Results

BoneMRI is an image processing software that can be used for image enhancement in MRI images. It can be used to visualize the bone structures in MRI images with enhanced contrast with surrounding soft tissue. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones and femoral heads; and the lumbar spine region, which includes the bony anatomy of the vertebrae from L3 to S1. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors.

Warning: BoneMRI images are not intended to replace CT images.

The BoneMRI application is a standalone image processing software application that analyses 3D gradient echo MRI scans acquired with a dedicated MRI scan protocol. From the analysis, 3D tomographic radiodensity contrast images, called BoneMRI images, are constructed.

The BoneMRI images can be used to visualize the bone structures in MR images with enhanced contrast with respect to the surrounding soft tissue. The application is designed to be used by imaging experts, such as radiologists or orthopedic surgeons, typically in a physician's office.

The BoneMRI application is a server application running on the clinic or hospital networks. It is available as fully on-premise software with specific GPU hardware requirements, or partly running as a managed service, for which the environment in which the managed modules run is controlled by MRIquidance, but the managed service will not receive protected health information (PHI). Within the hospital network, the application communicates with a DICOM compatible imaging archive (e.g., a PACS) to receive input MRI and to return BoneMRI images. Reading of the resulting BoneMRI images is performed using reqular DICOM compatible medical imaging viewing software.

The application uses an algorithm to detect bone images from MRIs obtained using a specific acquisition sequence. The algorithm training sets included information from multiple clinical sites, multiple anatomies, and multiple scanners to ensure that the trained algorithm was robust with respect to the approved indications for use. None of the data used in the training dataset was used subsequently in the validation dataset.

The document describes the performance testing of BoneMRI v1.6, an image processing software designed to enhance bone structures in MRI images of the pelvic and lumbar spine regions. The study aims to demonstrate that BoneMRI v1.6 meets specified accuracy acceptance criteria for bone morphology, radiodensity, and radiodensity contrast.

Here's the breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria were established for the accuracy of 3D bone morphology, radiodensity, and radiodensity contrast when compared to co-registered CT scans.

The results from the validation testing were found to fall within the pre-specified acceptance criteria (p<0.05).

2. Sample Size Used for the Test Set and Data Provenance

• Pelvic Region: 101 patients
• Lumbar Spine Region: 103 patients

Data Provenance: The imaging data consists of BoneMRI and CT images from the same patients and anatomical regions, acquired during previously conducted clinical investigations.
Country of Origin: USA, Europe, Asia.
Retrospective/Prospective: The data is described as collected during "previously conducted clinical investigations," indicating a retrospective nature for this validation study.

3. Number of Experts and Qualifications for Ground Truth

The document does not explicitly state the number of experts or their qualifications used to establish ground truth. However, it mentions that the validation was conducted by MRIguidance, comparing BoneMRI images to co-registered CT scans. This implies that CT scans serve as the ground truth comparator, and their interpretation and co-registration would typically involve expert oversight, though not detailed here.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the test set. The validation was a quantitative voxel-by-voxel comparison against CT images.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No multi-reader multi-case (MRMC) comparative effectiveness study was mentioned. The study focused on the quantitative accuracy of the BoneMRI output against CT.

6. Standalone (Algorithm Only) Performance

Yes, the performance validation described is a standalone (algorithm only) performance study. The objective was to validate the quantitative accuracy of BoneMRI by comparing its output (BoneMRI images) directly to co-registered CT scans in terms of bone morphology, radiodensity, and radiodensity contrast.

7. Type of Ground Truth Used

The primary ground truth used was co-registered CT scans. The study quantitatively compared the BoneMRI output against the CT images in terms of voxel-by-voxel Hounsfield Units (HUs) and standard deviations, as well as 3D bone morphology and radiodensity contrast.

8. Sample Size for the Training Set

The sample size for the training set is not explicitly stated. However, the document mentions that the "algorithm training sets included information from multiple clinical sites, multiple anatomies, and multiple scanners." It also clarifies that "None of the data used in the training dataset was used subsequently in the validation dataset."

9. How the Ground Truth for the Training Set Was Established

The document mentions that the algorithm training sets were obtained from "multiple clinical sites, multiple anatomies, and multiple scanners." While it doesn't specify the exact method for establishing ground truth for training, given the nature of the device (enhancing MRI by providing CT-like bone visualization), it is highly probable that the training data also leveraged CT images or similar detailed anatomical references to teach the convolutional neural network to assign Hounsfield Units and reconstruct bone structures. The "algorithm development pipeline" is mentioned as the process through which the parameters of the model were obtained.

Ask a specific question about this device