Search Results

The Lorad M-Ille Mammography System is intended to produce radiographic images of the breast. Its specific intended use is screening and diagnostic mammography. Screening mammography involves the production of images for initial examination for breast cancer diagnosis. Diagnostic mammography includes the production of magnified images for more thorough examination of areas of the breast determined suspicious through screening mammography, special views, spot compression views, and the production of images used by a physician in preparation for biopsy.

Screening and diagnostic mammography, including magnification studies, special views, spot compression views, as well as images used by a physician in preparing for a biopsy.

The Lorad M-IIIe mammoqraphy system is based on Lorad's currently marketed M-III, with changes to add features of Lorad's M-IV. The mechanical package, layout and basic electrical design of the M-III are used, but the x-ray tube of the M-IV, as well as the M-IV user interface and several M-IV software feature algorithms are incorporated. The changes made to the M-III to create the M-IIIe are summarized in the table below.

The Lorad M-Ille is a stand alone mammography device, mounted on a base with casters which allow positioning in the room where it is installed. A foot-operated mechanical lock prevents movement during clinical use of the device. The unit is AC powered, and must be connected to a 220 VAC/50-60 hertz (nominal) line to operate.

The standalone unit has two major assemblies: the C-arm and the Control Console. An M-Ille configuration tree, identifying the major components and subassemblies that comprise the M-IIIe, is provided in Attachment 1. The C-arm, which contains an x-ray tube, an image receptor support, compression device, a beam limiting device, switches that actuate the C-arm functions, and sensors for detecting installed accessories and making radiation measurements, is attached to the front (patient side) of the machine. The C-arm frame is constructed of two vertical steel rails, which are precision machined to accept the components which it supports. Molded plastic covers enclose the x-ray tube, which is purchased from OEM manufacturers, and the beam limiting device, while aluminum covers enclose the sides, back, top and bottom of the C-arm framework. The bottom panel of the C-arm is spring loaded and attached to a safety switch which disables C-arm vertical movement downward should it contact an object, such as a wheelchair.

The C-arm is attached by a locking pivot mechanism to the Control Console. The pivot allows the C-arm to be manually rotated about its central axis. The pivot mechanism is attached to the control console via a vertically moving carriage. This carriage is screw mounted to the base of the Control Console. The pivoting action of the C-arm is locked by an electromagnetic brake attached to the vertical carriage which, in its actuated condition, prevents rotation. The brake is de-actuated to release the C-arm for movement. The Control Console is constructed of a welded steel frame, to which the electrical assemblies and components of the unit are mounted. At the top of the Control Console, an operator station, consisting of a keyboard, a panel of individual pushbuttons and a Liquid Crystal Display (LCD) are mounted. Steel and aluminum panels enclose the Control Console. At the rear of the Control Console, opposite the operator station, there is a input power connector and input circuit breaker.

The M-IIIe is equipped with accessories necessary in the performance of mammography. Bucky grid accessories, containing either conventional linear or air-interspaced High Transmission Cellular grids, and a motor system to move the grid during exposure, are provided to reduce the effects of scattered radiation on the image. Compression plates to accommodate different sized patients and different mammographic applications are supplied and are interchangeable by the operator. A magnification table is provided, which provides a means to obtain geometrically enlarged views of suspicious areas of the breast. Footswitches are provided that operate (1) the C-arm vertical position function, to place the breast platform appropriately to the patient's height, and (2) the compression function, allowing the operator to use both hands to position the patient while applying and releasing breast compression position the patient while applying and releasing breast compression.

The M-IIIe is capable of use with Lorad's StereoLoc II Breast Biopsy system which was separately cleared by FDA. Use of the M-IIIe with the StereoLoc does not alter the operation of the M-IIIe.

Here's an analysis of the provided text regarding the Lorad M-IIIE Mammography System's acceptance criteria and study data:

It's important to note that this document describes an X-ray mammography machine, not an AI/CAD (Computer-Aided Detection) device. Therefore, many of the typical acceptance criteria and study designs associated with AI devices (like standalone performance, multi-reader multi-case studies, and ground truth establishment by experts for AI training) are not applicable here. The "algorithms" mentioned refer to internal device control logic, not AI for diagnosis.

The acceptance criteria are primarily technical specifications and performance measurements for an imaging device, ensuring it produces high-quality images and operates safely and effectively.

Acceptance Criteria and Reported Device Performance

Study Details:

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

   • Focal Spot Measurement: 2 tests for large focal spot, 2 tests for small focal spot. (Presumably internal lab data, USA, prospective for this device).
   • Line Pair Evaluation: 2 tests for large focal spot, 2 tests for small focal spot. (Presumably internal lab data, USA, prospective for this device).
   • Object Phantom Tests: 2 phantom films were used. (Presumably internal lab data, USA, prospective for this device).
   • AEC Tracking: Tests performed using breast equivalent phantom materials from 2 to 8 cm. (Number of exposures not specified, but implied to be sufficient for evaluating consistency across the range. Presumably internal lab data, USA, prospective).
   • Stereotactic Localization: Tests performed with a single simulated lesion (1mm diameter) positioned at a known 3D point (X=10mm, Y=20mm, Z=30mm) for 3 different configurations (DSM 512 mode, DSM 1024 mode, Film). The number of repetitions for each configuration is not explicitly stated but implies single assessments for each, measuring the "localized" vs "set" position. (Presumably internal lab data, USA, prospective).

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

   • Object Phantom Tests: "three readers for each of two phantom films readers" were used to score the images. Their qualifications are not explicitly stated, but it's implied they are qualified to interpret mammography phantom images according to ACR procedures (likely radiologists or medical physicists specializing in mammography QA).
   • Other tests: For technical measurements like focal spot size, line pair resolution, AEC optical density, and stereotactic localization accuracy, the "ground truth" is based on precise physical measurements using calibrated equipment (e.g., star patterns, line pair phantoms, known phantom thicknesses, known target positions). Human experts were not needed to establish this type of ground truth.

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

   • Object Phantom Tests: "The phantom images were scored according to standard ACR procedure, using three readers for each of two phantom films readers. The results are averaged summarized below." This implies a form of consensus or averaging, not a specific adjudication method like 2+1.
   • Other tests: Not applicable as ground truth is a physical measurement.

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:

   • No. This document describes a mammography X-ray machine, not an AI/CAD device. Therefore, no MRMC comparative effectiveness study involving AI assistance for human readers was performed or applicable.

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

   • No. This is a hardware mammography machine. Standalone performance for an AI algorithm is not applicable here. The "software feature algorithms" mentioned are for internal device control (e.g., Auto-Filter, Auto-Time, Auto-kV) and not for diagnostic image analysis.

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

   • Objective Physical Measurements: For most tests (focal spot, line pair, AEC tracking, stereotactic accuracy), the "ground truth" is derived from objective physical measurements using phantoms or calibrated instruments, compared against established technical standards (NEMA, ACR, IEC, 21 CFR).
   • Phantom Scoring by Multiple Readers: For the object phantom tests, the "ground truth" for the phantom image quality score is an average score from three readers, indicating agreement against standardized phantom criteria (ACR/MQSA).

7. The sample size for the training set:

   • Not applicable. This document is about a hardware device approval, not an AI model. There is no "training set" in the context of machine learning. The device's internal control algorithms are designed and programmed, not trained on data in a ML sense.

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

   • Not applicable. As above, no training set for an AI model.

Ask a specific question about this device