K Number
K162519
Manufacturer
Date Cleared
2016-10-06

(27 days)

Product Code
Regulation Number
892.1680
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

1717WCC and 1717WGC Digital Flat Panel X-Ray Detectors are indicated for digital imaging solution designed for general radiographic system for human anatomy. It is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures. Not to be used for mammography.

Device Description

1717WCC / 1717WGC is a wired/wireless digital solid state X-ray detector that is based on flat-panel technology. The wireless LAN(IEEE 802.11a/g/n/ac) communication signals images captured to the system and improves the user operability through high-speed processing. This radiographic image detector and processing unit consists of a scintillator coupled to an a-Si TFT sensor. This device needs to be integrated with a radiographic imaging system. It can be utilized to capture and digitalize X-ray images for radiographic diagnosis The RAW files can be further processed as DICOM compatible image files by a separate console SW program (K160579 / Xmaru View V1 and Xmaru PACS/ Rayence Co.,Ltd.) for a diagnostic analysis.

AI/ML Overview

The provided text describes a 510(k) premarket notification for a medical device, specifically digital flat panel X-ray detectors (1717WCC / 1717WGC). The document aims to demonstrate substantial equivalence to a predicate device (1717SCN / 1717SGN).

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

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

The document does not explicitly state "acceptance criteria" in a numeric fashion for clinical performance. Instead, it relies on demonstrating substantial equivalence to a predicate device through a combination of non-clinical (engineering/technical) performance data and clinical considerations (expert review).

The primary non-clinical performance metrics presented are:

  • Modulation Transfer Function (MTF): Represents the ability to visualize object details of a certain size and contrast. Higher MTF values indicate better resolution.
  • Detective Quantum Efficiency (DQE): Represents the efficiency of an imaging system in converting X-ray energy into a diagnostically useful image. Higher DQE values indicate better image quality, especially at low doses.

Table of Reported Device Performance (MTF and DQE):

The document presents tables comparing the proposed device (1717WCC / 1717WGC) with the predicate device (1717SCN / 1717SGN) for MTF at various spatial frequencies and DQE(0).

Spatial Frequency1717WCC_127 (Proposed)1717SCN (Predicate)1717WGC_127 (Proposed)1717SGN (Predicate)
MTF Value (127 µm)
1.0 lp/mm0.5390.5660.5570.574
2.0 lp/mm0.2620.2510.2470.269
3.0 lp/mm0.1470.1230.1060.123
3.5 lp/mm0.1050.0860.0670.082
3.93 lp/mm0.0860.0800.0460.076
Spatial Frequency1717WCC_139 (Proposed)1717SCN (Predicate)1717WGC_139 (Proposed)1717SGN (Predicate)
MTF Value (139 µm)
1.0 lp/mm0.5370.5660.5560.574
2.0 lp/mm0.2690.2510.2600.269
3.0 lp/mm0.1450.1230.1230.123
3.5 lp/mm0.1100.0860.0840.082
3.59 lp/mm0.1040.0800.0780.076
Spatial Frequency1717WCC_140 (Proposed)1717SCN (Predicate)1717WGC_140 (Proposed)1717SGN (Predicate)
MTF Value (140 µm)
1.0 lp/mm0.5800.5660.5560.574
2.0 lp/mm0.2690.2510.2600.269
3.0 lp/mm0.1390.1230.1230.123
3.5 lp/mm0.0980.0860.0840.082
3.57 lp/mm0.0930.0810.0780.076
Metric1717WCC_127 (Proposed)1717SCN (Predicate)1717WGC_127 (Proposed)1717SGN (Predicate)
DQE(0)0.710.7000.4440.420
Metric1717WCC_139 (Proposed)1717SCN (Predicate)1717WGC_139 (Proposed)1717SGN (Predicate)
DQE(0)0.7050.7000.4460.420
Metric1717WCC_140 (Proposed)1717SCN (Predicate)1717WGC_140 (Proposed)1717SGN (Predicate)
DQE(0)0.7750.7000.4400.420

The text concludes: "1717WCC has higher MTF and DQE performance at high spatial frequencies, especially from 2 lp/mm. The comparison of the MTF and DQE for 1717WGC detector demonstrated that the performed almost same with 1717SGN."

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

The document states: "clinical images are taken from both subject devices and reviewed by a licensed US radiologist to render an expert opinion." It also mentions "taking sample radiographs of similar age groups and anatomical structures".

  • Sample Size: The exact sample size for the clinical test set is not specified in the provided text. It only states "sample radiographs".
  • Data Provenance: The images were reviewed by a "licensed US radiologist," suggesting the review occurred in the US. However, it does not state the country of origin of the patients or images.
  • Retrospective or Prospective: The text implies a prospective collection for the comparison ("taking sample radiographs"), but it's not explicitly stated.

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)

  • Number of Experts: "reviewed by a licensed US radiologist." This indicates one expert.
  • Qualifications: "a licensed US radiologist." No further details on experience (e.g., years, specialization beyond "radiologist") are provided.

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

Since only one radiologist reviewed the images, there was no adjudication method employed as it's a single-reader assessment.

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

  • MRMC Study: No, an MRMC study was not conducted based on the provided text. The study involved a single radiologist performing a qualitative comparison between images from the new device and the predicate.
  • Effect Size (AI Assistance): This device is a digital X-ray detector, not an AI algorithm designed to improve human reading. Therefore, this question is not applicable to the context of the provided document. The study's focus was on demonstrating equivalent or superior image quality for the detector itself.

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

This refers to the performance of an AI algorithm. The device here is a hardware component (X-ray detector). While non-clinical 'standalone' performance for the detector was assessed (MTF, DQE measurements), this is not an "algorithm only" performance evaluation in the context of AI. The "clinical consideration" involved a human reading the images.

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

The "ground truth" for the clinical consideration was the expert opinion/qualitative review by a single licensed US radiologist. The assessment was based on visual comparison of image quality, specifically spatial and soft tissue contrast resolution, and the ability to evaluate anatomical structures for a correct conclusion. It was a comparative rather than an absolute "truth" established by a gold standard like pathology.

8. The sample size for the training set

This document describes a 510(k) submission for an X-ray detector, which is a hardware device. It is not an AI/machine learning product that typically requires a "training set" in the conventional sense. Therefore, the concept of a "training set" sample size is not applicable here. The device's performance is based on its physical and electronic characteristics.

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

As explained in point 8, the concept of a "training set" and "ground truth for the training set" is not applicable to this type of device according to the provided text.

§ 892.1680 Stationary x-ray system.

(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.