Search Results

AmCAD-UT® Detection is a Windows-based computer-aided detection (CADe) device intended to assist the medical professionals in analyzing thyroid ultrasound images, acquired from FDA-cleared ultrasound systems, with user-selected regions of interest (ROI). After the initial review of the ultrasound images by the physicians, the device further provides detailed information with quantification of sonographic characteristics of thyroid nodules. The device is intended for use on ultrasound images of discrete thyroid nodules larger than 1cm, for which a biopsy recommendation is required.

AmCAD-UT® Detection 2.2 is a Windows-based computer-assisted detection (CADe) software application device designed to assist medical professionals in analyzing thyroid ultrasound images of user selected regions of interest (ROI).

After the initial review of thyroid ultrasound images by the physician, he/she can use AmCAD-UT Detection to analyze thyroid images for further interpretation. The physician selects an ROI to define the initial boundary of the ROI. Once the ROI is confirmed, the physician may process the image for detection and quantification of sonographic characteristics (i.e., hyperechoic foci, echogenicity, texture, margin, orientation and anechoic areas) by AmCAD-UT Detection. The device provides more detailed information with quantification and visualization of the sonographic characteristics of thyroid nodule that may assist physician in his/her complete interpretation.

The software application automatically generates reports given the user preference inputs (e.g., the nodule size, nodule location and shape, and the presence or absence of the sonographic characteristics) annotated during the image analysis process. A report form has been designed by AmCad to be consistent with the conventional clinical thyroid report form. An output of the report may be viewed and sent to paper printers or saved on the standalone PC or review station as PDF file.

The provided text describes the AmCAD-UT® Detection 2.2 device and its performance study to support its substantial equivalence to a predicate device. Here's a breakdown of the requested information:

Device Acceptance Criteria and Performance

The document doesn't explicitly lay out a table of "acceptance criteria" with specific numerical thresholds for performance metrics. Instead, it describes "performance data" that "demonstrates that the proposed device performs as safely and effectively as the predicate devices." The core acceptance is based on demonstrating substantial equivalence to the predicate device (AmCAD-UT® Detection, Version 2.0) through standalone and clinical performance testing.

However, the "Functional Capability of Image Processing" for the device (AmCAD-UT® Detection 2.2) provides implicit performance goals related to the detection and quantification of certain sonographic characteristics.

Here’s a table presenting the device's functional performance capabilities as described, rather than explicit acceptance criteria with numerical targets:

Study Details

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

   • Test set sample size: Not explicitly stated. The document refers to "the test set" for ground truth establishment but does not provide a specific number of cases or images used for the performance studies.
   • Data Provenance:
     • Country of origin: Not explicitly stated in the provided text. The manufacturer is AmCad BioMed Corporation, located in Taipei, Taiwan, R.O.C., suggesting the data could be from Taiwan, but this is not confirmed.
     • Retrospective or Prospective: Not explicitly stated.

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

   • Number of experts: Not explicitly stated. The document mentions "clinical reader performance studies" and "ground truth to be established... include the ROI, the presence of each sonographic characteristic, and the surgical pathology examination result." It does not specify how many experts were involved in establishing the ground truth from the images themselves.
   • Qualifications of experts: Not explicitly stated beyond "medical professionals" or "physicians."

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • Not explicitly stated. The document mentions "ground truth to be established" but does not detail the adjudication process (e.g., consensus, majority vote with tie-breaker).

4. 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:

   • MRMC study: Yes, a "clinical Multiple-Reader-Multiple-Case (MRMC) study" was done for the AmCAD-UT® Detection 2.2.
   • Effect size: The document states: "The results of the MRMC study demonstrated that the physician reading thyroid nodule sonography images with the assistance of AmCAD-UT® Detection 2.2 can enhance their ability in analyzing the sonographic characteristics and has led to a significant increase in effectiveness of making clinical judgment." However, it does not provide a specific numerical effect size (e.g., AUC increase, sensitivity/specificity improvement). It only states that the improvement was "significant."

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

   • Yes, "standalone performance testing" was conducted. It evaluated the device's effectiveness in detecting and quantifying sonographic characteristics on images from various ultrasound systems.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The ground truth for performance studies included:
     • Region of Interest (ROI)
     • Presence of each sonographic characteristic
     • Surgical pathology examination result (This is a strong objective ground truth for malignancy status where available).

7. The sample size for the training set:

   • The document does not provide the sample size used for the training set.

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

   • The document does not describe how the ground truth for the training set was established. It only mentions "The ground truth to be established for performance studies of the device includes the ROI, the presence of each sonographic characteristic, and the surgical pathology examination result." This statement appears in the context of "Ground Truth Establishment" for the device itself and its performance evaluation, not specifically for a separate training set if machine learning was involved. Given it's a CADe device, it likely involved training, but the details are not provided.

Ask a specific question about this device