(113 days)
The OmniTom Elite CT system is intended to be used for x-ray computed tomography applications for anatomy that can be imaged in the 40cm field of view, primarily head and neck.
The CT system is intended to be used for both pediatric and adult imaging and as such has preset dose settings based upon weight and age. The CT images can be obtained either with or without contrast.
The OmniTom Elite is an improved version of OmniTom computed tomography system, providing enhanced functionality. It still has the same high resolution, multi row, 40 cm bore, and 30 cm field of view x-ray computed tomography system. The lightweight translating gantry consists of a rotating disk with a solid state x-ray generator, Gd2O2S detector array, collimator, control computer, communications link, power slip-ring, data acquisition system, reconstruction computer, power system, brushless DC servo drive system (disk rotation) and an internal drive system (translation). The power system consists of batteries which provide system power while unplugged from the charging outlet. The system has the necessary safety features such as the emergency stop switch, x-ray indicators, interlocks, patient alignment laser and 110% x-ray timer. The gantry has omnidirectional wheels that allow for robust diagonal, lateral, and rotational 360-degree movement and electrical drive system so the system can be moved easily to different locations.
The provided text is a 510(k) summary for the OmniTom Elite CT system, which is a medical device. This type of regulatory document focuses on establishing substantial equivalence to a predicate device rather than providing detailed acceptance criteria and a complete study report for a novel AI/software component, particularly for diagnostic performance metrics like those specified in the prompt.
The document primarily discusses comparative technical characteristics and conformance to established standards for computed tomography X-ray systems, rather than an AI or software algorithm's diagnostic performance. Therefore, many of the requested points, especially those related to diagnostic performance study design (test set size, ground truth, experts, MRMC, standalone performance), are not applicable or not present in this document.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't present a formal table of "acceptance criteria" in terms of diagnostic performance metrics (e.g., sensitivity, specificity, AUC) for an AI algorithm. Instead, it compares the technical specifications of the subject device (OmniTom Elite) to its predicate device (OmniTom). The "performance" assessment focuses on image quality metrics measured using phantoms and overall system safety and effectiveness.
| Attribute | Acceptance Criteria (Implicit - at least comparable to predicate) | Reported Device Performance (OmniTom Elite) |
|---|---|---|
| Indications for Use | Same as predicate (x-ray CT for 40cm FOV, primarily head and neck, pediatric and adult imaging, with/without contrast) | Same as predicate |
| Aperture (cm) | 40 | 40 |
| Image Field of View (cm) | 30 | 30 |
| Detector Material | Gadolinium Oxysulfide | Gadolinium Oxysulfide |
| Detector Coverage (mm) | 16 x 0.625 mm | 16 x 0.625 mm |
| Slice Configurations | 16 | 16 |
| Spatial Resolution (Soft tissue kernel) (lp/cm) | Comparable to predicate (6.0 lp/cm) | 6.7 lp/cm (Improved) |
| Spatial Resolution (High resolution kernel) (lp/cm) | Comparable to predicate (14.0 lp/cm) | 14.8 lp/cm (Improved) |
| X-ray Tube Type | Grounded/Fixed Anode/Monoblock | Grounded/Fixed Anode/Monoblock |
| Heat Storage (MHU) | 0.72 | 0.72 |
| Cooling | Water-Glycol | Water-Glycol |
| Tube Current (Ma) | 5 – 45 | 5 – 45 |
| Tube Voltage Range (Kv) | 80, 100, 120 | 80, 100, 120 |
| Rotation time (s) | 1, 2 | 1, 2 |
| Gantry Weight (lbs) | 1700 | 1700 |
| Mobile / Stationary | Mobile | Mobile |
| Battery / Wall power | Lithium Iron Phosphate | Lithium Iron Phosphate |
| Input Voltage | Single Phase 90 – 264 VAC/1300 watts peak | Single Phase 90 – 264 VAC/1300 watts peak |
| Max Input Power (Kva) | 5.4 Kw | 5.4 Kw |
| PACS DICOM 3.1 | Yes | Yes |
| 2D Scout Scan | Yes | Yes |
| Bolus Tracking | No (predicate) | Yes (New feature) |
| Axial Scan | Yes | Yes |
| Helical Scan | Yes | Yes |
| Dynamic Scan | Yes | Yes |
| 2D Viewing | Yes | Yes |
| MPR Viewing | Yes | Yes |
| 3D Viewing | Yes | Yes |
| Max Scan Range (cm) | 40 | 40 |
| Scan Localizer | Laser | Laser |
| Cardiac/Respiratory Gating | No | No |
| Patient Table | No | No |
| Image recon speed max (images per second) | 16 image/s | 16 image/s |
| X-ray Warning Lights | Yes | Yes |
| 110% X-ray Timer | Yes | Yes |
| Emergency Stop | Yes | Yes |
| Operator X-ray On Switch | Yes | Yes |
| Quality Test Phantom | Yes | Yes |
| Quality Test Report | Yes | Yes |
| X-ray Filter | Bowtie | Bowtie |
| Administrator Privileges | Yes | Yes |
| Dose Display | Yes | Yes |
| Dose Report / Audit | Yes | Yes |
| Protocol Override Protection | Yes | Yes |
| Dose Check | Yes | Yes |
| Pediatric Protocols | Yes (By Age/weight) | Yes (By Age/weight) |
| Automatic Exposure Control | Yes | Yes |
| Biocompatibility | N/A (predicate) | Yes (Applicable for subject device) |
| Sterility | N/A | N/A |
| Chemical Safety | N/A | N/A |
| EM Emissions | ETL Testing | ETL Testing |
| Electrical Safety (IEC 60601-1) | ETL Testing | ETL Testing |
| Mechanical Safety (IEC 60601-1) | ETL Testing | ETL Testing |
| Where Used | (Mobile) Radiology, ICU, ED, OR, Clinic, Office | (Mobile) Radiology, ICU, ED, OR, Clinic, Office, Ambulance (New location) |
| Metal Artifact Reduction (MAR) | Not explicitly stated for predicate but stated as a new feature for the subject device. Performance assessed by "successfully mitigating the streak artifacts... without raising any new questions of safety or effectiveness." | Performs as indicated, mitigating streak artifacts without new safety/effectiveness concerns. |
| Image Quality (Noise, Slice thickness, Low and High contrast resolution, Radiation metrics, MTF) | Must demonstrate comparable image quality to predicate. | Successfully demonstrated comparable image quality as the predicate and meets all image quality criteria used for testing the OmniTom. |
| Diagnostic Quality of Images | Images reviewed by a board-certified radiologist must be of diagnostic quality. | Images reviewed by a board-certified radiologist were of diagnostic quality. |
Study Proving Acceptance Criteria:
The document states that "internal verification and validation activities and external testing of product safety and EMC / EMI was completed successfully." The "study" mentioned for image quality and diagnostic relevance primarily relies on phantom testing and expert review of those phantom-generated images.
- "Image quality metrics such as noise, slice thickness, low and high contrast resolution, radiation metrics, and modulation transfer function were measured utilizing phantom image quality tests in accordance with the equipment performance standards for diagnostic x-ray systems administered by the FDA. The OmniTom Elite system successfully demonstrated that it has comparable image quality as the predicate device OmniTom (K171183) and meets all the image quality criteria that are used for testing the OmniTom."
- "Clinical performance of the CT system was evaluated using an ACR Phantom was used to measure image metrics, such as CT number linearity, image slice thickness, image noise, low contrast resolution and high contrast resolution. The data provided clinical demonstration of the operation of the device and the images reviewed by a board-certified radiologist were of diagnostic quality."
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not specified in terms of patient cases. The evaluation involved "phantom image quality tests" and an "ACR Phantom."
- Data Provenance: The data appears to be from internal lab testing using phantoms, not human patient data. Therefore, country of origin and retrospective/prospective designations are not applicable.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of Experts: "a board-certified radiologist" (singular, implied one) reviewed the images from the ACR Phantom.
- Qualifications of Experts: "board-certified radiologist." No further details on years of experience or subspecialty are provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: Not applicable/not specified. The review was by a single "board-certified radiologist" for diagnostic quality of phantom images. There's no indication of multiple readers or an adjudication process for a "ground truth" derived from patient cases.
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. This document describes a CT scanner (hardware and basic software functions), not an AI diagnostic algorithm. The "Metal Artifact Reduction (MAR)" is a post-processing algorithm, but its evaluation does not appear to be a comparative effectiveness study involving human readers with and without AI assistance. The focus for MAR was simply demonstrating artifact mitigation without new safety/effectiveness concerns.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Not applicable in the context of diagnostic AI. The document primarily concerns the performance of the CT scanner hardware and integrated software features. While MAR is an algorithm, its "standalone" performance is described in terms of its effect on artifacts in phantom images, not as a diagnostic accuracy measure on patient data.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Ground Truth: For image quality, the ground truth is against expected values and characteristics of reference phantom images. For the diagnostic quality assessment, the "ground truth" for ensuring images were "of diagnostic quality" was the subjective assessment by the board-certified radiologist of the phantom images. This is not a ground truth for a disease state based on patient data.
8. The sample size for the training set
- Training Set Sample Size: Not applicable. This document does not describe the development or validation of a machine learning model that would require a training set. The software updates mentioned are general enhancements and workflow improvements, not an AI algorithm for diagnostic inference.
9. How the ground truth for the training set was established
- Training Set Ground Truth: Not applicable, as there is no described training set for an AI algorithm.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.