K Number

Device Name

Manufacturer

VYSIS

Date Cleared

2004-12-13

(61 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

N/A

Predicate For

N/A

Intended Use

The Vysis® AutoVysion™ System is an automated scanning microscope and image analysis system. It is intended for in vitro diagnostic use with the Vysis® PathVysion® HER-2 DNA Probe Kit to aid in the detection and enumeration of FISH signals in interphase nuclei. and to determine the LSI® HER-2 to CEP® 17 signal ratio of the HER-2/neu gene via FISH in formalinfixed, paraffin-embedded human breast cancer tissue specimens. The AutoVysion System is intended to reduce overall hands-on time by performing automated enumeration. For a small percentage of samples (less than 7%) manual enumeration may be required.

The Vysis® AutoVysion™ System is an adjunctive computer-assisted methodology to assist in the acquisition and measurement of images from microscope slides of formalin-fixed, paraffin-embedded breast cancer tissue sections for the presence of amplified HER-2/neu gene. The Vysis® AutoVysion™ System is intended for use as aid in determining HER-2/neu amplification status. in coniunction with optional manual visualization directly through the fluorescence microscope.

When used with the Vysis® PathVysion® HER-2 DNA Probe Kit, the Vysis® AutoVysion™ System is indicated for use as
a) an adjunct to existing clinical and pathologic information currently used as prognostic factors in stage II, node-positive breast cancer patients
b) an aid to predict disease-free and overall survival in patients with stage II. node positive breast cancer treated with adjuvant cyclophosphamide, doxorubicin and 5-fluorouracil (CAF) chemotherapy; and,
c) aid in the assessment of patients for whom HERCEPTIN® (Trastuzumab) treatment is being considered (see HERCEPTIN package insert).

Device Description

The Vysis® AutoVysion™ System consists of an automated fluorescence microscope with motorized scanning stage, a large-format monochrome CCD camera, computer and scanning and assay specific analysis software. The microscope is equipped with a mercury arc lamp for fluorescence epi-illumination; three single-pass fluorescence filter sets for DAPI, SpectrumGreen™ (SG) and SpectrumOrange™ (SO) and a triple-pass fluorescence filter set for DAPI/SG/SQ, all mounted in a motorized filter turret; 10x and 40x objectives in a motorized objective turret; 10x eyepieces; a CCD camera; and a motorized scanning stage that holds up to 8 slides. Images of single fluorescence colors are captured by the CCD camera and transferred to the computer. All functions are controlled by the System software.

AI/ML Overview

Here is a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria Category	Specific Metric	Acceptance Criteria (Implicit)	Reported Device Performance
Reproducibility	Day-to-day LSI HER-2/neu to CEP 17 ratio variability	No statistically significant differences in variance across study days (p-value > 0.05 for Levene's test).	All p-values for Levene's test (testing homogeneity of day-to-day variances) were > 0.05, indicating no statistically significant differences. CVs ranged from 5.12% to 29.34%. (Note: For one data point, SD and %CV were "NR" - Not Reported).
Reproducibility	Inter-site LSI HER-2/neu to CEP 17 ratio variability	No statistically significant differences in variance across study sites.	All p-values for inter-site reproducibility were > 0.05, indicating no statistically significant differences. CVs ranged from 1.02% to 31.23%. (Note: For one data point, SD and %CV were "NR" - Not Reported).
Method Comparison	Overall Concordance with Manual Enumeration	High agreement with manual enumeration. (Specific numerical threshold not explicitly stated but implied by "correctly classified").	92.5% (196/212) overall agreement for all informative results. If equivocal range (1.5-3.0) excluded, total agreement was 98.8% (169/171).
Method Comparison	Positive Agreement with Manual Enumeration	High positive agreement.	96.0% positive agreement for all informative results. If equivocal range excluded, 100% positive agreement.
Method Comparison	Negative Agreement with Manual Enumeration	High negative agreement.	89.2% negative agreement for all informative results. If equivocal range excluded, 97.5% negative agreement.
Method Comparison	Bias relative to Manual Enumeration (1.18-4.49 ratio)	Average bias within ±15% of the average manual enumeration ratio in this range (as per NCCLS guideline EP9-A2).	Average bias was 0.472 (SD = 1.24), which is 11.7% of the average manual enumeration ratio (4.05). This met the acceptable error of ±15%.
Re-tests of Discrepancies	Consistency for initial "false positives"	Repeat tests should demonstrate consistency, indicating the initial discrepancy might be due to variability rather than systematic error.	Two "false positive" results by AutoVysion™ were re-tested six times manually and by the scanner. Both methods (manual and scanner) gave positive results in five of the six repeats for these two samples, suggesting consistency on re-testing.

2. Sample Size Used for the Test Set and the Data Provenance

Reproducibility Test Set: 36 specimen slides prepared from four human breast tissue specimens (one normal, one borderline, one moderate, one high amplification). Each site received three of each specimen randomized over three days.
Method Comparison Test Set: 234 clinical slides from 39 tumors with varying levels of HER-2/neu copy number.
Data Provenance: Not explicitly stated, but it conducted at "3 clinical sites" and refers to "clinical slides from 39 tumors," implying a source from a clinical setting. It is a retrospective analysis in the sense that the slides were prepared "prior to shipment to the study sites" and then retrospectively analyzed using both methods. However, the exact country of origin or broader demographic information is not provided.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts

For the reproducibility and method comparison studies, the "ground truth" or reference method was conventional manual microscopy performed in accordance with Vysis® PathVysion® HER-2 DNA Probe Kit.
The study states: "A qualified user visually inspects the tumor regions...identifies areas of tumor invasion...and records the coordinates." and "Final review and reporting of sample results is performed by a qualified user."
It also states that the predicate method was "manual microscopy performed in accordance with Vysis® PathVysion® HER-2 DNA Probe Kit." This implies that the standard manual reading by trained personnel using the established kit constitutes the reference.
The number of experts/manual readers for the comparison is not explicitly given, but it implies standard clinical practice where at least one "qualified user" would perform the manual enumeration. For the "two false positive results," the "manual" repetition implies multiple manual reads.
Qualifications of experts: Described as "qualified user" or standard manual enumeration. Specific qualifications (e.g., "radiologist with 10 years of experience") are not provided.

4. Adjudication Method for the Test Set

No formal adjudication method (e.g., 2+1, 3+1) is explicitly described for the initial ground truth establishment. The "ground truth" is defined by the results of "conventional manual microscopy performed in accordance with Vysis® PathVysion® HER-2 DNA Probe Kit." This suggests a single or standard manual read serves as the reference.
For the two "false positive" discrepancies, a re-testing protocol was used where samples were "repeated six times manually and by the scanner," which could be considered a form of informal adjudication/re-evaluation for specific discrepant 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

No, a MRMC comparative effectiveness study was not performed in the context of human readers improving with AI vs without AI assistance.
This study is a standalone performance study that compares the automated system's performance directly against the manual enumeration (the gold standard at the time).
The device is described as an "adjunctive computer-assisted methodology to assist in the acquisition and measurement of images...in conjunction with optional manual visualization directly through the fluorescence microscope." However, the study presented compares the automated system's result to manual enumeration rather than measuring how human performance changes when using the system as an aid.

6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done

Yes, a standalone performance study was done. The "Method comparison" section directly compares the "Vysis® AutoVysion™ System produced HER-2 to CEP 17 signal ratio" to "manually enumerated... HER-2 to CEP 17 signal ratio."
The system operates "fully automatically" once target areas are identified by a user, then "hybridization signals in each area are detected and enumerated automatically." Final review and reporting are performed by a qualified user, but the core enumeration is automated. The performance metrics reported (concordance, agreement, bias) are for this standalone automated enumeration process compared to manual.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The ground truth used was expert manual enumeration (or "conventional manual microscopy") following the Vysis® PathVysion® HER-2 DNA Probe Kit protocol. This is considered the established clinical method for determining HER-2/neu amplification status at the time.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set for the AutoVysion™ System. It only describes the test sets used for analytical performance evaluations.

9. How the Ground Truth for the Training Set Was Established

The document does not describe how the ground truth for any potential training set was established. It focuses solely on the validation/performance evaluation of the already developed system.

Summary

{0}------------------------------------------------

510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY

A. 510(k) Number: K041875

B. Purpose for Submission: New device

C. Analyte:

Her2/neu gene copy number on formalin-fixed paraffin-embedded breast cancer specimens

D. Type of Test:

Computer-assisted image analyzer for fluorescence in situ hybridization (FISH)

E. Applicant:

Vysis, Inc.

F. Proprietary and Established Names: Vysis® AutoVysion™ System for PathVysion HER-2 DNA Kit

G. Regulatory Information:

1. Regulation section: 21 CFR 866.4700, Automated Fluorescent in situ Hybridization (FISH) Enumeration Systems
1. Classification: II
1. Product Code:

NTH, System, Automated Scanning Microscope and Image Analysis for fluorescence in situ hybridization (FISH) assays

1. Panel:
  Immunology 82

H. Intended Use:

1. Intended Use:
  The Vysis® AutoVysion™ System is an automated scanning microscope and image analysis system. It is intended for in vitro diagnostic use with the Vysis® PathVysion® HER-2 DNA Probe Kit to aid in the detection and enumeration of FISH signals in interphase nuclei. and to determine the LSI® HER-2 to CEP® 17 signal ratio of the HER-2/neu gene via FISH in formalinfixed, paraffin-embedded human breast cancer tissue specimens. The AutoVysion System is intended to reduce overall hands-on time by performing automated enumeration. For a small percentage of samples (less than 7%) manual enumeration may be required.

1. Indication(s) for use:

{1}------------------------------------------------

When used with the Vysis® PathVysion® HER-2 DNA Probe Kit, the Vysis® AutoVysion™ System is indicated for use as

a) an adjunct to existing clinical and pathologic information currently used as prognostic factors in stage II, node-positive breast cancer patients
b) an aid to predict disease-free and overall survival in patients with stage II. node positive breast cancer treated with adjuvant cyclophosphamide, doxorubicin and 5-fluorouracil (CAF) chemotherapy; and,
c) aid in the assessment of patients for whom HERCEPTIN® (Trastuzumab) treatment is being considered (see HERCEPTIN package insert).
1. Special condition for use statement(s): For prescription use.
1. Special instrument Requirements:
- Vysis® AutoVysion™ System

I. Device Description:

J. Substantial Equivalence Information:

1. Predicate device name(s) None
1. Predicate K number(s): None
1. Comparison with predicate: Not applicable

K. Standard/Guidance Document Referenced (if applicable):

FDA guidance documents on software validation and off-the shelf Software use and NCCLS- EP9-A2

L. Test Principle:

A qualified user visually inspects the tumor regions of the slide, previously identified by a pathologist, identifies areas of tumor invasion with acceptable hybridization quality and records the coordinates of those areas for analysis through a point and click interface. Once the target areas have been identified, the AutoVysion™ System enters a fully automatic process, capturing extended-focus images of the marked areas at 40x magnification in each color: DAPI. SpectrumGreen and SpectrumOrange. All image data is saved to disk. The hybridization signals in each area are detected and enumerated automatically. The slide is also assessed for appropriate hybridization quality requirements that, if not satisfied, the sample may be rejected for automatic

{2}------------------------------------------------

analysis. Final review and reporting of sample results is performed by a qualified user.

The system uses a "targeted tiles" method for sampling the tumor. In this method, each field of view (FOV) in the area selected for analysis is sampled by placing a set of non-overlapping square "tiles" of equal size on the image. Each tile is comparable in size to the area of a tumor cell nucleus. The tiles are placed one by one in a way that maximizes the DAPI fluorescence contained in each tile, so that the set of tiles covers much of the nuclear material in the FOV. The spot count of a particular tile comprises the total spot count of the cell nuclei that are wholly or partly incorporated in the tile randomly reduced by truncation by tile boundary and microtome slicing. The method used to analyze the observed distribution of per-tile spot counts is the Expectation Maximization Algorithm (EM). EM is used to fit a mixture of two distributions to the observed two dimensional spot count distribution. The goodness of fit of the two-distribution model is compared with the goodness of fit of a single distribution to ensure that truly homogeneous samples are not erroneously fitted by two separate distributions. The HER-2/CEP 17 ratio is obtained directly from the parameters of the fitted distribution(s).

M. Performance Characteristics (if/when applicable):

1. Analytical performance:
- a. Precision/Reproducibility:

The Vysis® AutoVysion™ System was evaluated for inter-site and day-to-day reproducibility at 3 clinical sites. The study consisted of a total of 36 specimen slides prepared from four human breast tissue specimens with varving levels of HER-2/neu gene amplification (one normal, one borderline, one moderate and one high amplification). Each site received three of each of the specimens randomized over three days. The optimal number of fields of view (FOV) was determined using 5, 7 and 10 fields of view. All three numbers of FOVs gave similar results. The ten FOVs were selected to be used for all precision studies.

Day-to-day reproducibility was determined by calculating the mean observed ratio of LSI HER-2/neu to CEP 17. standard deviation (SD) and percent coefficient of variation (%CV) generated from 10 fields of view for each specimen across the three study days. The p-values associated with the Levene test statistics were calculated to test the homogeneity of day-to-day variances, with a 0.05 significance level. Results showed no statistically significant differences (see table below).

Expected	Observed ratios of LSI HER-2/neu to CEP 17			P-value
	Day 1			Day 2			Day 3
	Mean	SD	%CV	Mean	SD	%CV	Mean	SD	%CV
1.33	1.17	0.33	28.04	1.11	0.14	12.3	1.14	0.06	5.12	0.1152
1.71	2.08	0.61	29.34	2.38	0.64	26.82	2.45	NR	NR	0.9049
8.14	5.70	0.86	15.01	5.55	0.33	5.87	5.47	0.66	12.09	0.2788
12.97	6.42	0.81	12.55	7.42	0.17	2.24	8.01	0.35	4.38	0.1205

NR= No result

{3}------------------------------------------------

Inter-site reproducibility was similarly determined across the three study sites. Results for the three sites were not statistically significant and are summarized in the following table:

Expected	Observed ratios of LSI HER-2/neu to CEP 17			P-value

	Site 1			Site 2			Site 3
	Mean	SD	%CV	Mean	SD	%CV	Mean	SD	%CV
1.33	1.24	0.26	21.09	1.05	0.05	4.52	1.14	0.18	15.97	0.1833
1.71	2.09	0.58	27.84	2.42	NR	NR	2.39	0.75	31.23	0.5436
8.14	5.41	0.58	10.70	5.88	0.06	1.02	5.44	0.88	16.12	0.1612
12.97	6.95	1.32	19.03	7.51	0.81	10.72	7.39	0.30	4.04	0.1665

NR= No result

b. Linearity/assay reportable range: Not applicable.
Traceability (controls, calibrators, or method): C. The analytical traceability of the system depends on the Vysis® PathVysion® HER-2 DNA Probe Kit. The AutoVysion™ System employs ProbeCheck control slides for every run to assess the accuracy of signal enumeration and to monitor the assay performance.
d. Detection limit (functional sensitivity): Not applicable
e. Analytical specificity The specificity of the test result is dependent on the analytical performance of the Vysis® PathVysion® HER-2 DNA Probe Kit
f. Assay cut-off:

The assay cut-off of the test result is dependent on the analytical performance of the Vysis® PathVysion® HER-2 DNA Probe Kit.

1. Comparison studies:
- Method comparison with predicate device: a.

The substantial equivalence studies were based on comparison to conventional manual microscopy performed in accordance with Vysis® PathVysion® HER-2 DNA Probe Kit.

Duplicate slides from each tumor were randomized and assayed with the Vysis® PathVysion® HER-2 DNA Probe Kit according to the package insert instructions prior to shipment to the study sites. The randomized slides were enumerated by the standard and test method at each of the three study sites. Two hundred thirty-four clinical slides from 39 tumors with varying levels of HER-2/neu copy number were used in the study.

Concordance was evaluated as the agreement between manually enumerated and the calculated HER-2 to CEP 17 signal ratio and the Vysis® AutoVysion™ System produced HER-2 to CEP 17 signal ratio. Among all tissue specimens with informative results for both

{4}------------------------------------------------

methods, 92.5% (196/212) were correctly classified. Positive agreement was 96.0% and negative agreement was 89.2%. If samples with results in the equivocal range i.e. HER-2 to CEP 17 signal ratios between 1.5 and 3.0 were excluded from the calculation, total agreement was 98.8% (169/171) with 100% positive agreement and 97.5% negative agreement.

	Manual
Scanner	1.5	1.5-<2.0	2.0-<2.5	2.5-<3.0	3.0-<5.0	5.0-<10	≥10	Total
<1.5	77	2	0	0	0	0	0	79
1.5-<2.0	17	3	3	1	0	0	0	24
2.0-<2.5	7	0	2	1	0	1	0	11
2.5-<3.0	3	0	0	1	0	2	0	6
3.0-<5.0	1	0	0	1	5	19	20	46
5.0-<10	0	1	0	1	5	19	20	46
≥10	0	0	0	0	0	1	3	4
Total	105	6	8	8	21	37	27	212

There were two false positive results by the AutoVysion™ System. When these two samples were repeated six times manually and by the scanner, both methods gave positive results in five of the six repeats.

The average bias for the manual enumeration ratio range of 1.18 to 4.49 was determined according to NCCLS guideline EP9-A2 and found to be 0.472 (SD = 1.24). This bias value was 11.7% of the average manual enumeration ratio of 4.05 which met the acceptable error of ±15%. The bias and % of average increased throughout the range as presented in the following table

Enumeration Ratio Range	Average Bias	% Average Enumeration Ratio
0.19-1.17	0.296	7.29
1.18-4.39	0.472	11.66
4.42-21	-2.98	-73.4
Overall	-0.742	-18.26

b. Matrix comparison: Not applicable
1. Clinical studies:
- Clinical sensitivity: a.

The clinical sensitivity of the test system is dependent on the analytical performance of the Vysis® PathVysion® HER-2 DNA Probe Kit.

b. Clinical specificity:
The clinical specificity of the test system is dependent on the analytical performance of the Vysis® PathVysion® HER-2 DNA Probe Kit.
Other clinical supportive data (when a and b are not applicable) C.

{5}------------------------------------------------

Not applicable.

1. Clinical cut-off: The clinical cut-offs of the test result is dependent on the analytical performance of the Vysis® PathVysion® HER-2 DNA Probe Kit.
1. Expected values/Reference range:

Expected values of HER-2/CEP 17 ratio were established on breast cancer tissue specimens from 524 breast cancer patients with the Vysis® PathVysion® HER-2 DNA Probe Kit. Based on a cut-off ratio of 2.0, 433 of the specimens were negative and 91 positive for HER-2/neu gene amplification. The distribution of the HER-2/CEP 17 ratios for the 433 nonamplified specimens is summarized below.

Statistics	Range
	0.1-1.0	1.1-1.5	1.6-1.99
Mean	0.86	1.15	1.72
SD	0.14	0.13	0.11
N	185	226	22

The following table summarizes the distribution of HER-2/CEP 17 ratios for the 91 amplified specimens.

Statistics	2.0-5.0	5.1-10.0	>10.0
Mean	3.35	7.39	12.77
SD	0.95	1.41	1.80
N	33	42	16

N. Instrument Name:

Vysis® AutoVysion™ System

O. System Descriptions:

See (H) Device Description.

Modes of Operation: 1.
Semi-automated computer-assisted interpretation.
1. Software:
  FDA has reviewed applicant's Hazard Analysis and software development processes for this line of product types: Yes
1. Sample Identification: Slide identification is entered manually into the AutoVysion™ System before the slides are loaded into the instrument.
1. Specimen Sampling and Handling:

The microscope slides to be examined are loaded onto the microscope stage of the AutoVysion™ System and the user records the coordinates of those areas for analysis through a point and click interface. Once the target areas have been identified, the AutoVysion™ System automatically captures images of the marked areas in each fluorescence color and enumerates the hybridization

{6}------------------------------------------------

signals in each area. The system also rejects slide that failed hybridization quality requirements for automatic analysis.

న్. Assay Types: Computer-assisted image analysis of fluorescence in situ hybridization signals in interphase nuclei of cells in formalin-fixed paraffin-embedded tissue.
1. Reaction Types: Fluorescent microscopy
1. Calibration:

The AutoVysion™ instrument is factory calibrated. Monthly calibration checks with End Switches and Movements tests should be performed. To assess accuracy of signal enumeration by the instrument, laboratory-stained Vysis ProCheck slides are used for every staining run.

1. Quality Control:
  The accuracy of the system depends on the laboratory following the quality control instructions recommended in the labeling of the fluorescence in situ hybridization (FISH) assay kit associated with the AutoVysion™.

P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "M. Performance Characteristics" Section Of The SE Determination Decision Summary.

None. Q. Conclusion:

The petition for Evaluation of Automatic Class III Designation for this device is accepted. The device is classified as Class II under regulation 21 CFR 866.4700 with special controls. The special control guidance document " Class II Special Controls Guidance Document: Automated Fluorescence in situ Hvbridization (FISH) Enumeration Systems" is available at WWW.fda.gov/cdrh/oivd/guidance/1550.pdf.

Regulation Number and Section

§ 866.4700 Automated fluorescence

in situ hybridization (FISH) enumeration systems.(a)
Identification. An automated FISH enumeration system is a device that consists of an automated scanning microscope, image analysis system, and customized software applications for FISH assays. This device is intended for in vitro diagnostic use with FISH assays as an aid in the detection, counting and classification of cells based on recognition of cellular color, size, and shape, and in the detection and enumeration of FISH signals in interphase nuclei of formalin-fixed, paraffin-embedded human tissue specimens.(b)
Classification. Class II (special controls). The special control is FDA's guidance document entitled “Class II Special Controls Guidance Document: Automated Fluorescencein situ Hybridization (FISH) Enumeration Systems.” See § 866.1(e) for the availability of this guidance document.