Search Results
Found 1 results
510(k) Data Aggregation
(120 days)
INNOLUX CORPORATION
The Wireless/Wired INNOLUX RIC flat panel detector is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications including pediatric and neonatal exams wherever conventional film/screen or CR systems may be used. The INNOLUX RIC is not intended for mammography, fluoroscopy, tomography, and angiography applications.
The INNOLUX RIC Flat Panel Detector is a portable digital detector that integrated with an operating PC and an X-ray generator to acquire and digitize x-ray exposures from, standard radiographic systems and transfer for radiography diagnostic. The INNOLUX RIC is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults, pediatrics and neonates. The detector models support both wireless and wired data communication. Detectors can be placed in a wall bucky for upright exams, a table bucky for recumbent exams, or removed from the bucky for non-grid or free cassette exams.
The provided text describes a 510(k) premarket notification for the INNOLUX RIC flat panel detector. The document asserts the device's substantial equivalence to predicate devices based on non-clinical performance data.
Here's an analysis of the provided information concerning acceptance criteria and study details:
1. A table of acceptance criteria and the reported device performance
The document provides a comparison table between the subject device (INNOLUX RIC) and its predicate device (K142003, FDR D-EVO II Flat Panel Detector System) for various image quality and physical characteristics. The "acceptance criteria" appear to be implicit in the "Same as K142003" statements and the direct numerical comparisons, implying that the INNOLUX RIC's performance should be equivalent to or within acceptable tolerance of the predicate device.
| Characteristic | Acceptance Criteria (Implied from Predicate) | Reported Device Performance (INNOLUX RIC) |
|---|---|---|
| Scintillator | Gd2O2S:Tb for -SE models; CsI:Tl for -SE models | RIC 35G, RIC 43G Gd2O2S:Tb; RIC 35C, RIC 43C CsI:Tl (Same as K142003) |
| X-ray Conversion | Indirect conversion (a-Si) | Indirect conversion (a-Si) (Same as K142003) |
| Detector Cord | Wired / Wireless | Wired / Wireless (Same as K142003) |
| Detector Weight | DR-ID1201SE,DR-ID1211SE : Approx. 5.8 lbs; DR-ID1202SE,DR-ID1212SE : Approx. 7.1 lbs | RIC 35G, RIC 35C: Approx. 6.5 lbs; RIC 43G, RIC 43C: Approx. 8.0 lbs |
| Exposure Size/Active Area (inch) | 13.8x16.8 for -SE models; 16.8x16.7 for -SE models | RIC 35G, RIC 35C: 13.8x16.8; RIC 43G, RIC 43C: 16.8x16.7 (Same as K142003) |
| Dimensions (inch) | 18.1(W) x 15.1(D) x 0.6(H) for -SE models; 18.1(W) x 18.1(D) x 0.6(H) for -SE models | RIC 35G, RIC 35C: 18.1(W) x 15.1(D) x 0.6(H); RIC 43G, RIC 43C: 18.1(W) x 18.1(D) x 0.6(H) (Same as K142003) |
| Pixel Size | 150 μm | 150 μm (Same as K142003) |
| Acquisition Bit Depth | 16 bit | 16 bit (Same as K142003) |
| DQE (RQA5, 1 lp/mm, 1mR) – detector alone, without tabletop | DR-ID1201SE,DR-ID1202SE: 30% (±10%); DR-ID1211SE,DR-ID1212SE: 54% (Csl) (±10%) | RIC 35G,RIC 43G: 31% (±10%); RIC 35C,RIC 43C: 54% (Csl) (±10%) |
| MTF (RQA5, 2 lp/mm) | DR-ID1201SE,DR-ID1202SE: 42% (High mode) (±10%); DR-ID1211SE,DR-ID1212SE: 54% (High mode) (±10%) | RIC 35G,RIC 43G: 42% (±10%); RIC 35C,RIC 43C: 54% (±10%) |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document states, "No clinical study has been performed. The substantial equivalence has been demonstrated by non-clinical studies." Therefore, there is no clinical test set, sample size, or data provenance information related to human subjects. The non-clinical studies would involve physical devices.
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)
Since no clinical study was performed, no experts were used to establish ground truth for a clinical test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as no clinical study was performed.
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. This device is a flat panel detector, not an AI-powered diagnostic tool, and no clinical human reader study was conducted.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
The document specifies "non-clinical studies" were performed to evaluate the image quality and other characteristics of the device. This implies rigorous testing of the device itself (including its underlying software/algorithms for image acquisition and processing) in a standalone manner, without human interpretation for diagnostic purposes. The image quality evaluation concluded that the INNOLUX RIC detectors are "substantially equivalent to that of the predicate device." While not explicitly called "standalone algorithm performance," it aligns with evaluating the device's inherent technical capabilities.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the non-clinical studies, the "ground truth" would be established by objective physical measurements and comparisons against established engineering and performance standards (e.g., DQE, MTF measurements, dimensional specifications) and the performance of the predicate device. This is not clinical ground truth.
8. The sample size for the training set
Not applicable. This device is a hardware component (flat panel detector) with associated software for image acquisition and processing, not a machine learning or AI algorithm that requires a separate "training set" in the conventional sense. The "training" in this context would refer to the engineering design and optimization process.
9. How the ground truth for the training set was established
Not applicable, as there is no training set in the AI sense. The "ground truth" for the device's design and engineering would be based on engineering specifications, physical laws, and performance targets derived from the predicate device and relevant industry standards.
Ask a specific question about this device
Page 1 of 1