MLC FIT

• K Number: K991133
• Device Name: MLC FIT
• Manufacturer: IMPAC MEDICAL SYSTEMS, INC.
• Date Cleared: 2000-03-27 ( 360 days)
• Product Code: IYE
• Regulation Number: 892.5050
• Type: Traditional
• Panel: RA
• Reference & Predicate Devices: K962335

Intended Use

MLC Fit is to be used to define leaf plans for use with radiation treatment machines equipped with multileaf collimators manufactured by Siemens Medical Systems, Varian Associates, and With manned conniness Inc. This method of defining the geometric parameters associated with treatment fields can be used whenever a conformal treatment field is desired.

Device Description

The primary function of MLC Fit is to provide a means to define multileaf collimator leaf plans based on a user defined shape of a desired treatment area for use with a cancer radiotherapy treatment machines equipped with multileaf collimators manufactured by Siemens Medical Systems, Varian Associates, or Elekta Oncology Systems, Inc. Users may create, view, and edit MLC leaf data as well as other geometric parameters associated with treatment field definitions.

AI/ML Overview

The provided document MLC Fit - 510(k) - Response to Request for Additional Information is a 510(k) submission from 1999 and therefore does not contain the structured information typically found in modern AI/ML device submissions regarding acceptance criteria and performance studies. The document describes a software called MLC Fit designed to define multileaf collimator leaf plans for cancer radiotherapy. It emphasizes the software's function in eliminating manual calculation errors and its compliance with quality systems but does not detail specific performance metrics, clinical studies, or acceptance criteria in the manner requested.

However, based on the text, we can infer some aspects and highlight what is missing relative to modern AI/ML device descriptions.

Inferred Information and Missing Details:

1. A table of acceptance criteria and the reported device performance:

   • Inferred Acceptance Criteria: The primary goal of MLC Fit is to "provide the leaf positions for a given treatment shape in a manner that eliminates the slow and error prone method of hand calculating the position for each leaf." This suggests implicit acceptance criteria related to accuracy and efficiency compared to manual methods.
   • Reported Device Performance: The document states, "The primary functions of MLC Fit are, in effect, the same as those of MLC Fit product (K962335) currently being marketed by IMPAC Medical Systems, Inc." This implies equivalence to a previously cleared device, which served as its predicate. However, no specific quantitative performance metrics (e.g., accuracy, precision, speed improvements) are provided in this document. There is no table presenting performance data against defined thresholds.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

   • Not provided. The document does not mention any specific test sets, sample sizes, or data provenance from clinical sources.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

   • Not applicable/Not provided. Since no specific test set or ground truth establishment based on expert consensus for clinical accuracy is described, this information is not present. The software's function is geometrical definition, not diagnostic interpretation.

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

   • Not applicable/Not provided. There is no mention of an adjudication process for a clinical test set.

5. If a multi-reader multicase (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, not done/applicable. This device is not an AI/ML diagnostic or assistive tool for human readers in the traditional sense of interpreting images. It is a tool for defining treatment field geometry. The effect size of how human planners improve in efficiency and accuracy with MLC Fit vs. manual methods is implied as beneficial ("eliminates the slow and error prone method"), but no quantitative study or effect size is provided.

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

   • The MLC Fit is a standalone algorithm in its core function: "It only provides the definition of the treatment field as a hardcopy and to a database file." However, this is not an "AI algorithm" in the modern sense. Its performance relates to its ability to generate correct geometric parameters based on user input, not to make independent clinical decisions or interpretations. The users can "adjust" parameters, indicating it's a human-in-the-loop tool whose output can be modified. No formal standalone performance study report is provided.

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

   • Not applicable/Not explicitly stated for a clinical context. For a geometry definition tool, the "ground truth" would likely be the mathematically correct or clinically desired geometric configuration for a given treatment plan. This would be established by physics principles and clinical requirements, rather than pathology or outcomes data. The document mentions "Software Requirements Specifications and documented by Software Design Descriptions" which would define the expected behavior and correctness (the 'truth') of the geometric calculations.

8. The sample size for the training set:

   • Not applicable/Not provided. This device, as described in 1999, does not appear to be an AI/ML device that uses a "training set" in the contemporary sense. It is a rule-based or algorithmic software tool implementing geometric calculations.

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

   • Not applicable/Not provided. As there's no mention of a training set, the establishment of its ground truth is also not applicable or discussed.

Summary of Missing Information (Common in Modern AI/ML Submissions):

• Quantitative performance metrics (e.g., sensitivity, specificity, accuracy, precision, AUC)
• Specific acceptance criteria with numerical thresholds
• Details of a validation dataset (size, characteristics, provenance)
• Methodology for establishing clinical ground truth (e.g., expert panel, histopathology, long-term outcomes)
• Results of comparative studies (e.g., non-inferiority trials, MRMC studies)
• Specific information about AI/ML model training (training set size, annotation methods, type of model)

This 510(k) submission from 1999 primarily focuses on describing the device's function, its equivalence to a predicate device, and the adherence to quality systems in its development. It predates the widespread regulatory requirements for detailed performance evaluation of AI/ML-driven medical devices.

Regulation Number and Section

§ 892.5050 Medical charged-particle radiation therapy system.

(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.