Search Results
Found 1 results
510(k) Data Aggregation
(99 days)
ATAL 9
The ATAL 9 is indicated for use in general radiographic images of human anatomy. It is intended to replace radiographic film/screen systems in all general-purpose diagnostic procedures, excluding fluoroscopic, angiographic, and mammographic applications.
The ATAL 9 is a digital radiography system, featuring an integrated flat panel digital detector (FPD). ATAL 9 is designed to perform digital radiographic examinations as a replacement for conventional film. This integrated platform provides the benefits of PACS with the advantages of digital radiography for a filmless environment and improves cost effectiveness. The major functions and principle of operation of the modified panel are the same as our previous panel with a Wi-Fi wireless feature added.
The provided document is a 510(k) summary for the ATAL 9 digital radiography system. It focuses on demonstrating substantial equivalence to a predicate device (ATAL 8, ATAL 8c, K113812), primarily due to the addition of wireless functionality. As such, the study design and acceptance criteria are geared towards proving this equivalence rather than establishing de novo performance for a new type of device or AI algorithm.
Here's a breakdown of the requested information based on the document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit) | Reported Device Performance (ATAL 9 vs. ATAL 8/8c) |
|---|---|
| Technological Characteristics | |
| Pixel Pitch: Same as predicate | SAME (139 μm) |
| Limiting Resolution: Same as predicate | SAME (Over 3 lp/mm) |
| DQE (CSI) at 2 lp/mm: Comparable to predicate | 26% (Predicate: 27%) |
| MTF (CSI) at 2 lp/mm: Comparable to predicate | 42% (Predicate: 43%) |
| A/D Conversion: 14 bits or better | 16 bits (Predicate: 14 bits) |
| Active Area: Same as predicate | SAME (17 x 17 inch) |
| Pixels: Same as predicate | SAME (3,072 x 3072) |
| Software: Same functionality | SAME as K113812 |
| DICOM output: Yes | YES |
| Scintillator: Same options | UNCHANGED (Csl/GOS) |
| Interface: Gigabit Ethernet and/or wireless functionality | Wired: Gigabit Ethernet (1000BASE-T); Wireless: IEEE802.11ac, backward compatible |
| Power source: AC line and/or rechargeable battery | AC Line and/or Rechargeable Lithium Battery (10 hr run time) |
| Dimensions/Weights: Changed (due to wireless/battery) | 460(W)×461(L)×15(H)/ 2.9kg (2.4kg w/o Battery) (Predicate: 500(W)×500(L)×25(H)/ 7.8kg) |
| Safety and Effectiveness | |
| Electrical Safety: Compliance with IEC 60601-1 | Complies with IEC 60601-1 |
| EMC: Compliance with IEC 60601-1-2 | Complies with IEC 60601-1-2 |
| Wireless operation: Compliance with IEEE 802.11ac and FCC | Complies with IEEE 802.11ac, Meets FCC requirements |
| Image Quality (Clinical): As good as or better than predicate | Concluded "as good as or better than" by board-certified radiologist. |
| Risk Analysis: Conducted | Conducted (as per bench testing summary) |
| Software Verification: Conducted | Conducted (as per bench testing summary) |
| Wireless connectivity: Verified | Verified |
2. Sample Size Used for the Test Set and Data Provenance
The document states: "Clinical images were acquired and evaluated by a board certified radiologist..." However, it does not specify the number of clinical images (sample size) used for the test set.
- Sample Size: Not explicitly stated for the clinical image evaluation.
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). While "clinical images were acquired," it doesn't specify if these were newly acquired for the study (prospective) or selected from an existing archive (retrospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: One.
- Qualifications of Experts: A "board certified radiologist." No further details on years of experience or sub-specialty are provided.
4. Adjudication Method for the Test Set
The document indicates that "Clinical images were acquired and evaluated by a board certified radiologist who concluded the images from the new panel are as good as or better than the images acquired with the predicate panel." This implies a single-reader evaluation against the predicate device, not a multi-reader adjudication process. Therefore, the adjudication method was essentially none in the sense of comparing multiple experts' opinions. The single expert provided the judgment.
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 done.
- AI Improvement Effect Size: Not applicable. This submission is for a digital radiography panel, not an AI software/algorithm intended to assist human readers or provide automated diagnoses. The device being cleared (ATAL 9) is a hardware device for image acquisition.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
- Standalone Performance: No, a standalone performance study as described (algorithm only without human-in-the-loop performance) was not done. The ATAL 9 is a digital X-ray panel, where the "performance" relates to image acquisition and quality, not an algorithm's diagnostic output. The clinical evaluation involved a human radiologist examining the acquired images.
7. The Type of Ground Truth Used
For the clinical evaluation, the "ground truth" was established by the expert opinion/conclusion of a single board-certified radiologist. The radiologist compared images from the new panel against those from the predicate panel. This is a form of expert consensus, albeit from a single expert, comparing image quality.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable/not provided. The ATAL 9 is a hardware device (digital X-ray panel). It is not an AI algorithm that undergoes a "training" phase with a large dataset. The "software" component remains the same as its predicate (K113812), implying no new algorithm training was performed for the ATAL 9.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not applicable. As explained above, this device does not involve an AI algorithm with a training phase requiring a "ground truth" to be established for training data.
Ask a specific question about this device
Page 1 of 1