(112 days)
The Ikoniscope® oncoFISH™ Bladder Test System is an automated scanning microscope coupled with image analysis, acquisition and display functions. It is intended for in-vitro diagnosis as an aide to the technologist or pathologist in the detection, classification and enumeration of cells of interest based on particular characteristics such as intensity, size, shape or fluorescence. The Ikoniscope® oncoFISH™ Bladder Test System is intended to detect cells, derived from urine samples, stained by FISH using commercially available direct labeled DNA probes for chromosomes 3, 7, 17 and loss of 9p21 locus. Following identification, a summary report is generated which may provide the basis for a diagnostic determination by the genetics professional and a gallery of the images scanned is presented for review to permit the professional to confirm or deny the diagnosis.
The Ikoniscope® oncoFISH™ Bladder Test system is intended to increase the efficiency of current cell analysis methods, by decreasing the amount of time an operator spends scanning slides in search of the cells of interest. The operator/reader identifies chromosome presence by identifying the colors provided by the Fluorescence in Situ Hybridization ("FISH") probes, and manually counts the number of chromosomes appearing within each cell containing such signals. The Ikoniscope® oncoFISH™ Bladder Test System is an automated scanning microscope system incorporating automated slide loading and handing, low and high magnification scanning to identify targets of interest and digital image acquisition, coupled with an image analysis workstation. Microscope slides, prepared according to the DNA probe manufacturers' specifications, are placed into a multiple slide cassette, and loaded into the Ikoniscope® oncoFISH™ Bladder Test System microscope system. The system unloads each slide, scans each one, and returns it to the cassette automatically. During scanning, images of cells exhibiting the predetermined characteristics for FISH signals are digitally photographed and stored. After all the slides are scanned, the workstation provides an image gallery for each slide that displays the image of each nucleus meeting predetermined characteristics and quantity in scorable categories. The operator/reader can then evaluate the cell nuclei, and make the diagnostic determination accordingly. The Ikonisyscope® oncoFISH™ Imaging System combines elements of existing technologies to perform its function, Fluorescence In-Situ Hybridization (FISH) uses commercially available, . FDA cleared, DNA probes (not supplied with the test system) for marking chromosomes 3. 7. 17. and the loss of 9p21 locus. Automated Cell Locating/Counting using pattern recognition algorithms to identify the signal characteristics of interest and sort them into scorable categories as defined in the Instructions for Use for the Vysis UroVysion™ DNA Probe Kit. The Ikoniscope® software automatically captures an image of each cell containing FISH signals and stores its location on the slide. These images are then presented to the operator, using a computer workstation, for analysis in a gallery that displays cells in scorable categories and stores each image for review by the cytotechnologist, cytogeneticist or pathologist for final diagnostic determination.
Here's a summary of the acceptance criteria and the study that proves the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance:
The document doesn't explicitly state numerical acceptance criteria in a dedicated section. However, it implies performance expectations based on comparison to its predicate device and manual FISH analysis. The primary performance metric reported is concordance.
| Acceptance Criteria Category | Specific Metric (Implied) | Reported Device Performance |
|---|---|---|
| Diagnostic Accuracy | Concordance with manual FISH analysis in terms of diagnostic result | 99% |
| Inter-system Reproducibility | Concordance of diagnostic outcome between two test systems | 98% |
| Intra-system Reproducibility | Variability of results on the same samples using different instruments | No variability of results |
| Nucleus Specific Accuracy | Fish dot counting (comparison to predicate K061392) | Results "similar" to predicate |
2. Sample Sizes and Data Provenance:
-
Test Set (Clinical Comparison):
- Sample Size: 100 patient samples (for comparison with manual analysis).
- Data Provenance: Not explicitly stated, but likely from a clinical setting, presumably in the US. The study is described as a "clinical trial," suggesting prospective data collection for this particular evaluation.
-
Test Set (Inter-system Reproducibility):
- Sample Size: 50 individual patient slides.
- Data Provenance: Not explicitly stated, but likely from a clinical setting, presumably in the US.
-
Test Set (Reproducibility for Predicate K062755):
- Sample Size: 100 samples.
- Data Provenance: Not explicitly stated, but this refers to a prior study for the predicate device.
3. Number of Experts and Qualifications for Ground Truth:
- Number of Experts: The document does not explicitly state the number of experts used to establish the ground truth for the test set. However, it mentions "standard manual analysis to perform the FISH analysis" and "the genetic professional," "cytotechnologist, cytogeneticist or pathologist" as the individuals who would make the final diagnostic determination. This implies that qualified professionals perform the ground truth evaluation.
- Qualifications of Experts: The qualifications are implied to be a "genetics professional," "cytotechnologist, cytogeneticist or pathologist." The specific level of experience (e.g., "10 years of experience") is not provided.
4. Adjudication Method for the Test Set:
The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). The "ground truth" for the clinical trial was established by "standard manual analysis." It is not clear if multiple readers were involved in the manual analysis for each case or how discrepancies, if any, were resolved.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
No explicit MRMC comparative effectiveness study is described where human readers' performance with AI assistance is compared to without AI assistance to measure an effect size. The study compares the system's performance (Ikoniscope® oncoFISH™ Bladder Test System) to standard manual evaluation. The system is intended to "assist the operator" and "increase the efficiency of current cell analysis methods," but a direct comparison of human performance improvement with AI aid is not provided. The system itself essentially performs initial identification and presents images for human review and final diagnostic determination.
6. Standalone (Algorithm Only) Performance:
Yes, a standalone performance evaluation was done implicitly for the "Nucleus Specific Accuracy Test (Fish dot counting)" and the comparison to manual analysis. The device itself performs the "automated cell locating/counting using pattern recognition algorithms to identify the signal characteristics of interest and sort them into scorable categories." The reported 99% concordance reflects the performance of the system's output (which is then reviewed by a human for final diagnosis) against the full manual process.
7. Type of Ground Truth Used:
The ground truth used was expert consensus / manual evaluation. The "standard manual analysis to perform the FISH analysis" by genetics professionals, cytotechnologists, cytogeneticists, or pathologists served as the reference standard.
8. Sample Size for the Training Set:
The document does not provide information regarding the sample size used for the training set of the Ikoniscope® oncoFISH™ Bladder Test System's algorithms.
9. How Ground Truth for the Training Set Was Established:
The document does not provide information on how the ground truth for the training set was established.
§ 864.5260 Automated cell-locating device.
(a)
Identification. An automated cell-locating device is a device used to locate blood cells on a peripheral blood smear, allowing the operator to identify and classify each cell according to type. (Peripheral blood is blood circulating in one of the body's extremities, such as the arm.)(b)
Classification. Class II (performance standards).