Search Results

Trained medical professionals use Contour ProtégéAl as a tool to assist in the automated processing of digital medical images of modalities CT and MR, as supported by ACR/NEMA DICOM 3.0. In addition, Contour ProtégéAl supports the following indications:

· Creation of contours using maching algorithms for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow-up and management.

· Segmenting normal structures across a variety of CT anatomical locations.

· And segmenting normal structures of the prostate, seminal vesicles, and urethra within T2-weighted MR images.

Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAI.

Contour ProtégéAl is an accessory to MIM software that automatically creates contours on medical images through the use of machine-learning algorithms. It is designed for use in the processing of medical images and operates on Windows, Mac, and Linux computer systems. Contour ProtégéAl is deployed on a remote server using the MIMcloud service for data management and transfer; or locally on the workstation or server running MIM software.

The provided text outlines the 510(k) summary for Contour ProtégéAI, but it primarily focuses on establishing substantial equivalence to predicate devices and does not detail specific acceptance criteria or a comprehensive study report with numerical performance metrics against those criteria. The information provided is more about the regulatory submission process and general claims of equivalence rather than a detailed breakdown of a validation study.

However, based on the limited information regarding "Testing and Performance Data" (page 9), I can infer some aspects and highlight what is missing.

Here's an attempt to describe the acceptance criteria and study proving the device meets them, based on the provided text, while also pointing out the lack of detailed numerical results for the acceptance criteria.

Acceptance Criteria and Device Performance Study for Contour ProtégéAI

The provided 510(k) summary for Contour ProtégéAI states that "Equivalence is defined such that the lower 95th percentile confidence bound of the Contour ProtégéAI segmentation is greater than 0.1 Dice lower than the mean MIM Maestro atlas segmentation reference device performance." This statement defines the non-inferiority acceptance criterion used to compare Contour ProtégéAI against a reference device (MIM Maestro) rather than setting absolute performance thresholds for the contours themselves.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: The document implies that the "test subjects" were used for evaluation, but the specific number of cases or patients in the test set is not explicitly stated.
• Data Provenance: The text mentions that neural network models were trained on data that "did not include any patients from the same institution as the test subjects." This implies that the test set data originated from institutions different from the training data, suggesting a form of independent validation. The countries of origin for the data are not specified. The text indicates the study was retrospective as it involved evaluating pre-existing patient data.

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

The document states that "multiple atlases were created over the test subjects" for the MIM Maestro reference device. It does not explicitly state how the ground truth for the test set was established for Contour ProtégéAI's evaluation results. Instead, it refers to the MIM Maestro's performance as a reference. There is no information provided on the number or qualifications of experts who established any ground truth used in this comparison.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth or evaluating the test set. It mentions the "leave-one-out analysis" for creating atlases for MIM Maestro, which is a method of data splitting/resampling, not an adjudication process.

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

• Was an MRMC study done? Based on the provided text, there is no indication that a multi-reader multi-case (MRMC) comparative effectiveness study was conducted to evaluate how much human readers improve with AI vs. without AI assistance. The study described focuses on the comparison of the algorithm's performance (Contour ProtégéAI) against an existing atlas-based segmentation method (MIM Maestro).

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• Was a standalone study done? Yes, the described study appears to be a standalone (algorithm-only) performance evaluation. The comparison is between the Contour ProtégéAI algorithm's output and the MIM Maestro atlas segmentation reference device, with Dice coefficients calculated directly from these automated segmentations. The "Indications for Use" explicitly state: "Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAI," implying that human modification is expected in clinical use, but the reported study does not include this human-in-the-loop performance.

7. Type of Ground Truth Used

The "ground truth" for the comparison appears to be the segmentation contours generated by the MIM Maestro atlas segmentation reference device. The study aims to demonstrate non-inferiority to this existing, cleared technology rather than a human expert-defined anatomical ground truth or pathology/outcomes data.

8. Sample Size for the Training Set

The document mentions a "pool of training data" but the specific sample size for the training set is not provided.

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

The document states that "neural network models were trained for each modality (CT and MR) on a pool of training data." However, it does not describe how the ground truth (i.e., the "correct" contours) for this training data was established. It refers to the models being trained "on a pool of training data" without detailing the annotation or ground truth generation process for this training data.

Ask a specific question about this device

Contour ProtégéAl is used by trained medical professionals as a tool to aid in the automated processing of digital medical images of modalities CT and MR, as supported by ACR/NEMA DICOM 3.0. Contour ProtégéAl assists in the following indications:

The creation of contours using machine-learning algorithms for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow-up and management.

Segmenting normal structures across a variety of CT anatomical locations.

And segmenting normal structures of the prostate, seminal vesicles, and urethra within T2-weighted MR images.

Contour ProtégéAI must be used in conjunction with MIM software to review and, if necessary, edit contours that were automatically generated by Contour ProtégAI.

Contour ProtégéAl is an accessory to MIM software that automatically creates contours on medical images through the use of machine-learning algorithms. It is designed for use in the processing of medical images and operates on Windows, Mac, and Linux computer systems. Contour ProtégéAl is deployed on a remote server using the MIMcloud service for data management and transfer.

Here's a breakdown of the acceptance criteria and study details for MIM Software Inc.'s Contour ProtégéAI, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

1. Sample sizes used for the test set and data provenance:

   • CT Images: 286 images
   • MR Images: 72 images
   • Data Provenance: The test images were gathered from "a different and disjoint set of institutions from the training data." This indicates an independent, external validation set, likely retrospective in nature given that it's an existing dataset. The specific country of origin is not specified.

2. Number of experts used to establish the ground truth for the test set and qualifications of those experts:

   • The document does not explicitly state the number of experts or their qualifications for establishing the ground truth of the test set. It mentions "associated segmentations" for the training data but not how test set ground truth was created or by whom.

3. Adjudication method for the test set:

   • The document does not specify an adjudication method (e.g., 2+1, 3+1). It states that the neural network models were evaluated against "associated segmentations," implying a reference truth was available.

4. 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:

   • No MRMC study evaluating human reader improvement with AI assistance was performed or reported in this summary. The study focused on the standalone performance of the Contour ProtégéAI against a predicate device.

5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

   • Yes, a standalone study was done. The non-inferiority test directly compared the automatically generated contours of Contour ProtégéAI against those of the predicate device, both operating without human intervention for the contouring process itself. The instructions for Contour ProtégéAI do state that it "must be used in conjunction with MIM software to review and, if necessary, edit contours." However, the reported performance study focused on the initial automated segmentation output.

6. The type of ground truth used:

   • The ground truth for both training and testing datasets consisted of "associated segmentations." While not explicitly stated, these are typically expert-generated contours, often from trained medical professionals (e.g., oncologists, radiation oncologists, dosimetrists) or highly experienced image analysts. The document does not specify if pathology or outcomes data were used as ground truth.

7. The sample size for the training set:

   • The document states that the neural networks were "trained on datasets from several large institutions." It does not provide a specific number of images or cases used in the training set.

8. How the ground truth for the training set was established:

   • The training datasets included "CT images and MR images and their associated segmentations." This implies that expert-generated contours were available alongside the images for training the machine-learning models. The specific process or number of experts involved in creating these training segmentations is not detailed in the provided text.

Ask a specific question about this device