MAM-CH22S WITH AUTOMATIC FILTER SELECTION OPTION by ELSCINT, INC.

the intended use and the indications of use of the MAM-CH22S with the Automatic Filter Selection Option are identical to those of the MAM-CH22S. With the Automatic Filter Selection mode, dense or thick breasts can be imaged with improved contrast and/or less radiation dose when the mammography system automatically selects the rhodium filter.

Device Description

The 510(k) premarket notification for the Automatic Filter Selection Option for the MAM-CH22S mammography system describes a modification of the legally marketed mammography system (K941353/S1) by the addition of the optional filter assembly (including molybdenum and rhodium filters) and its automatic mode of operation.

AI/ML Overview

This document (K960381) is a 510(k) premarket notification for a modification to an existing mammography system, the Automatic Filter Selection Option for the MAM-CH22S. It focuses on demonstrating substantial equivalence to a legally marketed device (MAM-CH22S, K941353/S1) rather than presenting a performance study with detailed acceptance criteria for a new device's diagnostic performance. Therefore, most of the requested information regarding acceptance criteria, performance studies, sample sizes, ground truth, and expert involvement is not available in this specific document.

Here's a breakdown of what can be extracted and what cannot:

1. Table of Acceptance Criteria and Reported Device Performance:

Acceptance Criteria	Reported Device Performance (as per K960381)
Safety:	Compliance with International Standard IEC 601-1 (Medical Electrical Equipment, Part 1: General Requirements For Safety). No significant new safety hazard.
Effectiveness:	Intended Use: Identical to MAM-CH22S.
	Indications of Use: Identical to MAM-CH22S.
	Benefit of Automatic Filter Selection: Dense or thick breasts can be imaged with improved contrast and/or less radiation dose when the system automatically selects the rhodium filter.
	Substantial Equivalence: Deemed substantially equivalent to the legally marketed MAM-CH22S in safety and effectiveness.

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

Not applicable / Not provided. This document does not describe a clinical performance study using a test set of patient data to evaluate a diagnostic algorithm. It's about a hardware/software modification to an existing device.

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

Not applicable / Not provided. No diagnostic performance test set is described.

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

Not applicable / Not provided. No diagnostic performance test set is described.

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:

Not applicable / Not provided. This document describes an automated hardware/software feature for optimal imaging, not an AI diagnostic algorithm assisting human readers.

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

Not applicable / Not provided. The "Automatic Filter Selection Option" is a feature that optimizes image acquisition parameters. While it makes an "automatic" selection, it's not a standalone diagnostic algorithm that produces a finding or diagnosis independent of a human. Its performance is implicitly tied to the quality of the image produced for human interpretation.

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

Not applicable / Not provided. No diagnostic performance study is described that would require a ground truth for diagnostic accuracy. The "effectiveness" mentioned refers to improving image quality/dose, which would be assessed by technical metrics and potentially subjective radiologist review of image quality rather than a definitive diagnostic truth.

8. The sample size for the training set:

Not applicable / Not provided. No machine learning algorithm requiring a "training set" in the modern sense is described. The "automatic" selection logic for the filters would be based on predefined rules or parameters related to breast density/thickness, not learned from a large dataset.

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

Not applicable / Not provided. No training set is described.

Study Description (as per K960381):

The "study" described in the 510(k) is a design and risk analysis to demonstrate the safety and effectiveness of the modification.

Safety: The device was designed to comply with International Standard IEC 601-1. An analysis was performed to determine if the modification added significant risk, and preventive measures were taken. The conclusion was that it "does not add a significant risk that can cause a safety hazard."
Effectiveness: The effectiveness is based on the claim that the intended use and indications of use remain identical to the predicate device (MAM-CH22S). The specific benefit of the automatic filter selection is highlighted: "dense or thick breasts can be imaged with improved contrast and/or less radiation dose when the mammography system automatically selects the rhodium filter." This is a claim of technical improvement rather than diagnostic accuracy improvement demonstrated through a clinical study with patient outcomes.

In summary, this 510(k) is a regulatory submission for a device modification, not a clinical trial report. It relies on demonstrating substantial equivalence and compliance with safety standards rather than presenting a detailed diagnostic performance study with statistical endpoints.

Summary

{0}------------------------------------------------

K960381

APR 2 9 1996

SUMMARY OF SAFETY AND EFFECTIVENESS

With reqards to effectiveness, the intended use and the indications of use of the MAM-CH22S with the Automatic Filter Selection Option are identical to those of the MAM-CH22S. With the Automatic Filter Selection mode, dense or thick breasts can be imaged with improved contrast and/or less radiation dose when the mammography system automatically selects the rhodium filter.

With regards to safety, the MAM-CH22S mammography system with the Automatic Filter Selection Option was designed to comply with International Standard IEC (International Electrotechnical Commission) 601-1. Medical Electrical Equipment, Part 1: General Requirements For Safety, The modification was analyzed and preventive measures were taken.

Based on this analysis, to the best of our judgment, the addition of the Automatic Filter Selection Option modification to the MAM-CH22S mammography system. does not add a significant risk that can cause a safety hazard.

Based on the above, it is Elscint's opinion that the MAM-CH22S mammography system with the Automatic Filter Selection Option, is substantially equivalent in safety and effectiveness to the legally marketed device, MAM-CH22S.

Regulation Number and Section

§ 892.1710 Mammographic x-ray system.

(a)
Identification. A mammographic x-ray system is a device intended to be used to produce radiographs of the breast. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.