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 respect to the 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 in the clinic or hospital networks. It returns the reconstructed BoneMRI images as DICOM images. 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.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: 73 patients.
• Data Provenance:
  • Country of Origin: Europe, Asia.
  • Retrospective/Prospective: The imaging data consists of BoneMRI and standard CT from the same patient and anatomical region, acquired during "previously conducted clinical investigations." This indicates the data was retrospective.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the number of experts used or their qualifications for establishing ground truth for the test set. Instead, it states that the ground truth was established by comparing BoneMRI images to co-registered CT scans, which served as the "reference standard." The validations were conducted by MRIguidance "based on an algorithm to detect bone images from MRIs." This implies an algorithmic, rather than human expert-based, determination of ground truth for the quantitative analysis.

4. Adjudication Method for the Test Set

The document does not describe an adjudication method for the test set in the context of human expert review. Given that the study was a quantitative voxel-by-voxel analysis comparing BoneMRI to CT as a reference standard, expert adjudication in the traditional sense (e.g., for disagreements in human annotations) would not be applicable here.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance?

No, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human reader improvement with AI assistance was not described in this document. The study described is a quantitative technical validation of the device's ability to reconstruct bone morphology and radiodensity compared to CT as a reference.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, a standalone performance evaluation was done. The study focused on the quantitative accuracy of the BoneMRI application (the algorithm) in reconstructing 3D bone morphology, radiodensity, and radiodensity contrast, using CT as the reference standard. This was a "voxel-by-voxel validation" of the algorithm's output.

7. The Type of Ground Truth Used

The ground truth used was co-registered CT scans (reference standard). The study aimed to validate the quantitative accuracy of BoneMRI by comparing its output (3D bone morphology, radiodensity, and radiodensity contrast) directly against the corresponding measurements from CT images.

8. The Sample Size for the Training Set

The document states, "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." However, it does not specify the sample size for the training set. It explicitly mentions, "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 "parameters of the model were obtained through an algorithm development pipeline." While it doesn't explicitly describe the method for establishing ground truth for individual training cases, given that the validation focused on comparing against CT, it is highly likely that CT images also served as the ground truth (or a strong reference for ground truth) during the training phase to enable the algorithm to learn the relationship between MRI data and CT-like bone characteristics (e.g., radiodensity, morphology). The mention of "assign[ing] a Hounsfield Unit (HU) value to a single volume element" suggests a quantitative ground truth for training.

Ask a specific question about this device