(263 days)
The uCT 550 is a computed tomography X-ray system intended to produce crosssectional images of the body by computer reconstruction of X-ray transmission data taken at different angles and planes and indicated for the whole body, including head, neck, cardiac and vascular.
The Computed Tomography X-ray system, uCT 550, is intended to produce crosssectional images of the patient by computer reconstruction of X-ray transmission data taken at different angles and planes. These images may be obtained either with or without contrast. The proposed device consists of CT scan gantry (including high voltage generator, X-ray tube, collimator and detectors), patient table, operating console (including console PC, monitor and Control Box), power supply cabinet (PSC), vital signal monitoring gated control unit (VSM), 3D camera, system software, and accessories.
The provided document describes the uCT 550, a Computed Tomography (CT) X-ray system, and specifically details the performance evaluation of its DELTA (Deep Recon) algorithm.
Here's an analysis of the acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance (DELTA Algorithm)
| Acceptance Criteria (Bench Testing) | Reported Device Performance (Bench Testing) |
|---|---|
| DELTA should pass the General IQ test according to IEC 61223-3-5. | DELTA passed the basic general IQ test, satisfying IEC 61223-3-5 requirements. |
| Compared with FBP, DELTA should have better LCD and noise under same scanning dose, and DELTA can reduce scanning dose keep similar LCD compared with FBP. | DELTA showed better LCD and noise compared with FBP at the same scanning dose AND can reduce scanning dose compared with FBP at the same LCD. |
| Compared with FBP, DELTA should have better high contrast spatial resolution. | DELTA showed better spatial resolution compared with FBP at the same scanning dose. |
| Acceptance Criteria (Clinical Evaluation) | Reported Device Performance (Clinical Evaluation) |
| The mean score of simulated low dose DELTA image is equal or higher than the mean score of normal dose FBP. | Accepted (Results indicate acceptance criteria were met). |
| The mean score of DELTA is better than the mean score of FBP under same dose. | Accepted (Results indicate acceptance criteria were met). |
| DELTA image should satisfy diagnosis requirements. | DELTA images satisfy diagnosis requirements. |
| Overall Conclusion | All study results show that the acceptance criteria were met. |
2. Sample Size Used for the Test Set and Data Provenance
- Clinical Evaluation Test Set:
- Size: 30 cases (10 for abdomen, 10 for chest, 10 for head).
- Data Provenance: Not explicitly stated as retrospective or prospective, nor the country of origin. It mentions "gathering from different scanning doses and a wide range of population" for the overall clinical dataset.
- Clinical Evaluation Validation Set (used to inform the test set, but separate):
- Size: 14 cases (5 for abdomen, 4 for chest, 5 for head).
- Data Provenance: Same as above, not explicitly stated.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- The clinical evaluation mentions that "different board-certified U.S. radiologists" scored the image quality.
- The exact number of radiologists is not specified, but the qualification is "board-certified U.S. radiologists." No experience level (e.g., "10 years of experience") is provided.
4. Adjudication Method for the Test Set
- The document states that the radiologists "perform a five-point scale evaluation of both image sets on three image quality aspects: noise, image structure fidelity and overall image quality."
- It does not specify an adjudication method such as 2+1 or 3+1 for resolving discrepancies among readers. It implies that individual scores were collected and mean scores were calculated.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- A reader study was performed where "different board-certified U.S. radiologists" evaluated image quality. This is inherently a multi-reader study.
- The study compared DELTA images (simulated low dose or same dose) against FBP (normal dose or same dose) to assess improvement in image quality aspects (noise, image structure fidelity, overall image quality).
- Effect Size: The document states that the "mean score of simulated low dose DELTA image is equal or higher than the mean score of normal dose FBP" and "The mean score of DELTA is better than the mean score of FBP under same dose." While it indicates a positive effect (improvement or equivalence with dose reduction), a specific quantifiable effect size (e.g., AUC difference, percentage improvement) is not provided in this summary.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Yes, a standalone study was performed. The "Bench Testing" section (8.1) directly evaluates the DELTA algorithm's image quality metrics (LCD, noise, spatial resolution, HU value, thickness section) using phantoms, comparing it quantitatively to FBP. This is an algorithm-only evaluation.
7. Type of Ground Truth Used (DELTA Algorithm)
- Bench Testing: Phantom-based measurements (MITA CCT189, MITA CCT191, Catphan 700, water phantom) are used, effectively creating a known and reproducible "ground truth" for physical image quality metrics.
- Clinical Evaluation: Expert consensus/opinion from "board-certified U.S. radiologists" through a five-point scale evaluation of image quality aspects (noise, image structure fidelity, overall image quality). It also states that "DELTA image should satisfy diagnosis requirements," implying that clinical utility against diagnostic benchmarks is a component of the ground truth.
8. Sample Size for the Training Set (DELTA Algorithm)
- The document states for the DELTA algorithm: "The dataset was increased to 127 cases compared with the original dataset." This refers to the dataset used for the algorithm's development/training, indicating a training set size of 127 cases.
9. How the Ground Truth for the Training Set Was Established (DELTA Algorithm)
- The document does not explicitly describe how the ground truth for the training set was established. It only states that the dataset size was increased. For deep learning algorithms, ground truth for training data typically involves expert annotations or meticulously prepared reference images, often by comparing with a higher-quality imaging standard or expert-labeled findings. However, this specific detail is not present in the provided text.
§ 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.