Search Results

Follicle Clarity Software is a software application package. It is designed to view and quantify image data acquired on compatible ultrasound systems. Follicle Clarity is used as an aid to interpreting clinicians by calculating the number and size of ovarian follicles in a transvaginal ultrasound volume sweep of the ovaries.

Follicle Clarity is a cloud-based software application package (software as a medical device, SaMD). Follicle Clarity automatically calculates the number and size of hypoechoic structures in the received transvaginal ultrasound images and displays the data graphically and in tabular format in the Follicle Clarity application. Graphic displays include both measurements made by the clinician (as measured by the ultrasonographer) as well as those calculated by Follicle Clarity. Graphs can be adjusted for various views of the data. Ultrasound images received are also displayed within the Application to allow the user to verify the resolution, contrast and anatomic completeness. The user is able to enter patient information such as cycle day, estradiol level and progesterone level in the patient profile for tracking. The user also has the ability to add or delete measurements as they feel are appropriate.

The provided text describes the Follicle Clarity Software, a medical device for quantifying ovarian follicles in ultrasound images. Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a formal "acceptance criteria" table with specific quantitative thresholds. However, it describes validation activities and states that the device "met the predetermined endpoints" and "demonstrated substantially equivalent performance." Based on the performance data section, the implicit acceptance criteria would likely be a demonstration of accuracy, precision, and agreement with established manual/SonoAVC measurements within a clinically acceptable margin of error.

2. Sample Size and Data Provenance

• Test Set Sample Size: The document does not specify the exact sample sizes for the "second validation trial" (ovaries with ≤ 3 follicles) and "third validation trial" (ovaries with ≥ 10 follicles) or the "prospective study." It broadly refers to "a phantom trial" and "a prospective study."
• Data Provenance: The document only states that the clinical validation was performed in a "prospective study." It does not specify the country of origin.

3. Number of Experts and Qualifications for Ground Truth

• The document implies that "manual measurements" by "ultrasonographer" were used as a basis for comparison in the validation trials.
• For the clinical study, it compares Follicle Clarity to "manual (ultrasonographer) measurements" and "SonoAVC measurements."
• The number of ultrasonographers or their specific qualifications (e.g., years of experience, board certification) are not specified in the provided text.

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 for the test set. It suggests direct comparison to "manual measurements" and SonoAVC.

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

• No, an MRMC comparative effectiveness study was not explicitly stated as having been done involving human readers improving with AI vs. without AI assistance. The clinical study focused on comparing Follicle Clarity's performance to manual measurements and SonoAVC, not on human-in-the-loop performance improvement with the AI.

6. Standalone (Algorithm Only) Performance

• Yes, standalone performance was assessed. The "Validation of the tracking and measurement accuracy of the platform was conducted through a phantom trial" and the "second and third validation trials" which compared Follicle Clarity results directly to manual measurements or internal controls appear to be assessments of the algorithm's standalone performance. The clinical study also directly evaluated Follicle Clarity's measurements against SonoAVC and manual measurements without necessarily describing human-AI interaction.

7. Type of Ground Truth Used

• Expert Consensus/Manual Measurements and Predicate Device Output:
  • For the phantom trial and two ovarian follicle validation trials (low and high count), the ground truth appears to be based on "manual measurements of phantom targets" or "manual measurements of follicles" conducted "within a DICOM viewer." This implies expert-derived measurements.
  • For the clinical validation, the algorithm's performance was compared to "manual (ultrasonographer) measurements" and "SonoAVC measurements." SonoAVC is a component of a predicate device (Voluson E6/E8/E8 Expert/E10 Diagnostic Ultrasound System), effectively serving as a form of established clinical truth or a benchmark cleared device.

8. Sample Size for the Training Set

• The document mentions "Machine Learning Algorithm Training" but does not specify the sample size used for the training set.

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

• The document states: "The software utilizes 'locked' (non-adaptive) machine learning algorithms to identify the contours of the targeted structure within the ultrasound image."
• It does not explicitly detail how the ground truth for training data used by these machine learning algorithms was established (e.g., by manual annotation by experts, specific protocols, etc.).

Ask a specific question about this device