The DiffMaster Octavia™ is an automated cell locating device. DiffMaster Octavia automatically locates and presents images of blood cells on peripheral blood specimens. The operator identifies and verifies the suggested classification of each cell according to type. DiffMaster Octavia is intended to be used by skilled operators, trained in the use of the instrument and in recognition of leukocyte classes.

Device Description

The DiffMaster-Octavia™ is an automated cell locating device for differential count of white blood cells and characterization of red morphology. It is based on a CellaVision AB developed software system Cytologica. DiffMaster Octavia™consists of a commercially available positioning system for the slides, a commercially available microscope, a commercially available camera and the software system.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the DiffMaster Octavia™ Automatic Hematology Analyzer, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly list acceptance criteria in a table format with specific thresholds. Instead, it states that the device demonstrated equivalence to the predicate method. The "results equal to the reference method" is the primary performance claim used for substantial equivalence.

Acceptance Criteria Category	Reported Device Performance
Overall Performance	Results equal to the reference method (Romanowski (MGG)-Stain manual light microscopic process for cell classification) for:
– Accuracy of suggested classification	The accuracy of the suggested classification for each cell type (DiffMaster Octavia™ results compared to the light microscope manual diff count results) was demonstrated to be equivalent to the reference method.
– Precision (location & display)	The precision for location and display of the cells found was demonstrated to be equivalent to the reference method.
– Precision (reproducibility)	The precision of the instrument (reproducibility) was demonstrated to be equivalent to the reference method.
– Sensitivity	The sensitivity of the instrument (false positive found) was demonstrated to be equivalent to the reference method.
– Specificity	The specificity of the instrument (false negatives found) was demonstrated to be equivalent to the reference method.

2. Sample Size and Data Provenance for the Test Set

Sample Size: The document does not specify the exact sample size (number of cases or cells) used in the clinical trials. It merely states "Two clinical trials have been performed."
Data Provenance: Not explicitly stated. The document indicates the studies "have been performed according to the approved standard, NCCLS, vol. 23, no 1, document H-20A, March 1992: Reference Leukocyte Differential Count (proportional) and Evaluation of Instrumental Method." It does not mention the country of origin or if the data was retrospective or prospective.

3. Number of Experts and Qualifications for Ground Truth Establishment (Test Set)

Number of Experts: Not specified.
Qualifications of Experts: The ground truth was established by the "manual reference method results," implying experienced laboratory technologists. The description of the intended use states the device is "intended to be used by skilled operators, trained in the use of the instrument and in recognition of leukocyte classes," which suggests the benchmark manual method would also be performed by similarly qualified individuals.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1). The "manual reference method" implies a standard, accepted process for manual differential counting, which typically involves a single trained operator's assessment or potentially a consensus if discrepancies arise in real-world lab settings, but this is not detailed in the provided text.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a MRMC comparative effectiveness study, as typically understood for AI-assisted workflows, was not explicitly mentioned. The studies compared the device's suggested classifications (which are then verified by a human) against the manual reference method. This is a comparison of the automated system's output (with human verification) against the traditional human-only method, rather than specifically measuring human reader improvement with AI assistance versus without AI assistance. The device's intended use is for human operators to verify/modify the AI's suggestions, so it inherently involves human-in-the-loop.
Effect Size of Human Improvement with AI vs. without AI: Not reported, as this type of study was not described.

6. Standalone (Algorithm Only) Performance Study

Not explicitly described as a standalone study in the traditional sense. The "accuracy of the suggested classification for each cell type (DiffMaster Octavia™ results compared to the light microscope manual diff count results)" implies that the algorithm's initial suggestion was compared to the ground truth. However, the device's intended use is always with a human verifying these suggestions. Therefore, while the algorithm's raw suggestion accuracy was likely evaluated internally, the reported clinical performance encompasses the complete human-in-the-loop workflow.

7. Type of Ground Truth Used

Expert Consensus / Expert Reference Method: The ground truth was established by the "manual reference method results," which means the classifications assigned by skilled human operators using the traditional Romanowski (MGG)-Stain light microscopic process for cell classification.

8. Sample Size for the Training Set

Not provided. The document states that the software uses "deterministic artificial neural networks (ANN's) trained to distinguish between classes of white blood cells," but does not specify the size of the dataset used for this training.

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

Not explicitly stated for the training set ground truth. Similar to the test set, it can be inferred that the training data would have also been labeled based on expert classification (e.g., manual differential counts by skilled technologists) to train the artificial neural networks on correct cell classifications.

Summary

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

K003301

SECTION 2. SUMMARY AND CERTIFICATION

A. 510(K) SUMMARY

Summary of Safety and Effectiveness

In accordance with 21 CFR 807.92, the following information constitutes the 510(k) summary for the DiffMaster Octavia™.

SUBMITTER'S NAME:	CellaVision AB
ADDRESS:	Ideon Research Park, 223 70 Lund, Sweden
CONTACT PERSON:	Constance G. Bundy
TELEPHONE NUMBER:	612-574-1976
FAX NUMBER:	612-571-2437
DATE OF SUBMISSION:	October 19, 2000

Identification of device 1.

Proprietary Name: DiffMaster Octavia™ Automatic Hematology Analyzer Common Name: DiffMaster Octavia™ Classification Status: Class II per regulations 864-5260 Product Codes: JOY

Equivalent devices 2.

CellaVision AB believes the DiffMaster Octavia™is substantially equivalent to the Romanowski (MGG)-Stain manual light microscopic process for cell classification and the IMI MICRO21 with WBC Diff (White blood cell Differential, 510(k) number K925670/A).

3. Description of the Device

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

Intended use 4.

The DiffMaster Octavia™ is an automated cell locating device.

DiffMaster Octavia automatically locates and presents images of blood cells on peripheral blood specimens. The operator identifies and verifies the suggested classification of each cell according to type.

DiffMaster Octavia is intended to be used by skilled operators, trained in the use of the instrument and in recognition of leukocyte classes.

Technological characteristics, comparison to predicate device 5.

Like the predicate device, the DiffMaster Octavia™ instrument locates WBCs, stores digital images of the cells and displays the images in an organized manner and suggests a cell class for each cell to aid technologists in performing the WBC differential procedure. A competent technologist is required to confirm or modify the suggested classification of each cell. It is intended to be used by skilled operators, trained in the use of the instrument and in recognition of leukocyte classes.

Brief Discussion of Non clinical factors supporting a determination of substantial equivalence:

The method involves a competent human observer to examine the microscopic images of the cells as does the predicate method and device. See attached substantial equivalence comparisons.

Brief discussion of clinical tests supporting a determination of substantial equivalence: Two clinical trials have been performed to confirm equivalence with the predicate method Romanowski (MGG)-Stain manual light microscopic process for cell classification. The studies have been performed according to the approved standard, NCCLS, vol. 23, no 1, document H-20A, March 1992: Reference Leukocyte Differential Count (proportional) and Evaluation of Instrumental Method. Complementary nonclinical tests have been performed to confirm cell location and display of found cells.

Conclusions drawn from clinical tests:

The following information was obtained from the clinical tests comparing the DiffMaster Octavia™ cell classification results to the manual reference method results:

the accuracy of the suggested classification for each cell type (DiffMaster Octavia™ . results compared to the light microscope manual diff count results)
the precision for location and display of the cells found .
the precision of the instrument (reproducibility) ●
the sensitivity and the specificity of the instrument (false positive and false negatives ● found)

Results equal to the reference method was provided by use of the DiffMaster Octavia™ instrument.

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

Comparative features of the DiffMaster Octavia compared with the predicate device and method

Characteristic	IMI Micro21	Manual light microscopic process	DiffMaster Octavia™
Intended use	Automated cell location device for cell location and identification, for in-vitro use. Verification of results by human observer	Manual method for cell location and identification, for in-vitro use. Verification of results by human observer	Automated cell locating device for cell location, and identification, for in-vitro use. Verification of results by human observer
Sample type	Bloodfilm on glass slides of peripheral whole blood, stained	Bloodfilm on glass slides of peripheral whole blood, stained	Bloodfilm on glass slides of peripheral whole blood, stained
Sample preparation	Wright, Wright Giemsa, May Grünwald stain	May Grünwald Giemsa stain (MGG)	May Grünwald Giemsa stain (MGG)
Analysis technique	Cells are located using the NCCLS scanning procedure. Cell images are analyzed using standard mathematical methods, including deterministic artificial neural networks (ANN's) trained to distinguish between classes of white blood cells		Cells are located using the NCCLS scanning procedure. Cell images are analyzed using standard mathematical methods, including deterministic artificial neural networks (ANN's) trained to distinguish between classes of white blood cells

・

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

Discussion of performance testing. ર.

Discussion of performance testing.
An extensive collection of tests has been conducted and successfully completed, including tests to ensure safety, effectiveness, and compliance with product requirements.

The following tests were conducted as prototype tests and successfully completed: a) Evaluation of:

a) Draianon on of ...

Performance (Accuracy and precision, clinical sensitivity, specificity, cell location)
Safety

b) Inspections to verify that all design features are as intended and that all authorized design changes have been accomplished and recorded.

c) Validation of the system (including efficacy of user interface)

7. Conclusion

Based on extensive performance testing and a comparison to the predicate device, it is the conclusion of CellaVision AB that the DiffMaster Octavia™ is substantially equivalent to devices already on the marked (cleared by the 510(k) process) and presents no new concerns about safety and effectiveness.

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

DEPARTMENT OF HEALTH & HUMAN SERVICES

Image /page/4/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo is a circular seal with the words "DEPARTMENT OF HEALTH & HUMAN SERVICES USA" arranged around the perimeter. Inside the circle is a stylized representation of an eagle, with three curved lines forming the body and wings.

MAR 1 5 2001

Food and Drug Administration 2098 Gaither Road Rockville MD 20850

Public Health Service

CellaVision AB c/o Ms. Constance G. Bundy C.G. Bundy Associates, Inc. 6740 Riverview Terrace Minneapolis, Minnesota 55432

Re: K003301

Trade Name: DiffMaster Octavia™ Automatic Hematology Analyzer Regulatory Class: II Product Code: JOY Dated: February 16, 2001 Received: February 20, 2001

Dear Ms. Bundy:

We have reviewed your Section 510(k) notification of intent to market the device referenced We have reviewed your Section 910(x) notifically equivalent (for the indications for use above and we nave determined the actrices marketed predicate devices marketed in interstate commerce stated in the enclosure) to legally maneces processes in the Medical Device Amendments, or to devices that prior to May 26, 1970, the chaouncen and of the Federal Food, Drug, and Cosmetic Act (Act). You may, therefore, market the device, subject to the general controls Cosment Act (Act). Tourmaly, morolors, manov as as f the Act include requirements for annual provisions of the Act. "The general controle practice, labeling, and prohibitions against misbranding and adulteration.

If your device is classified (see above) into either class II (Special Controls) or class III (Premarket Approval), it may be subject to such additional controls. Existing major regulations (Fremarket Approval), it they of sayses in one of Federal Regulations, Title 21, Parts 800 to 895. allecting your device our of tournination assumes compliance with the Current Good A Substantially Cquiralient determinates set forth in the Quality System Regulation (QS) for Manufacturing Fridence required in (21 CFR Part 820) and that, through periodic QS Medical Devices. General regulation (FDA) will verify such assumptions. Failure to Inspections, the Food and Drug Temninesult in regulatory action. In addition, FDA may publish Comply with the GMT Togatator may readeral Register. Please note: this response to your premarket notification submission does not affect any obligation you might Its polise to your premarked noursearch start for devices under the Electronic Product Radiation Control provisions, or other Federal laws or regulations.

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

Page 2

This letter will allow you to begin marketing your device as described in your 510(k) premarket a This letter will allow you to begin marketing your do nee of your device to a legally marketed notification. The FDA Inding of substantial equivalise of your device and thus, permits your device to procced to the market.

If you desire specific advice for your device on our labeling regulation (21 CFF Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at additionally 809.10 for in vitto diagnostions on the promotion and advertising of your device, (301) 594-4588. Additionally, for questions on the predictions of Areas note the regulation please contact the Office of Comphanoo at (301) 37 - 407.97 - 10.07.9 Directed entitled, "Misoranding of telefone to pennation in the Act may be obtained from the Division of Small
information on your responsibilities under the Act may be obtained from information on your responsibilities and its toll-free number (800) 638-2041 or (301) 443-6597 or at its internet address "http://www.fda.gov/cdrh/dsma/dsmamain.html".

Sincerely yours,

Steven Sutman

Steven I. Gutman, M.D., M.B.A. Director Division of Clinical Laboratory Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

B. INDICATIONS FOR USE

510(k) Number_________________________________________________________________________________________________________________________________________________________________

Device Name: DiffMaster Octavia™

Indications for Use:

The DiffMaster Octavia™ is an automated cell locating device.

DiffMaster Octavia automatically locates and presents images of blood cells on Diffiviaster Octavia adtomations focults identifies and verifies the suggested classification of each cell according to type.

DiffMaster Octavia is intended to be used by skilled operators, trained in the use of the instrument and in recognition of leukocyte classes.

J. Roberts

(Division Sign-Off) (Division of Clinical Laboratory Deyices o 3,30 L 510(k) Number -

(Please do not write below this line - continue on another page if needed)

Concurrence of CDRH, Office of Device Evaluation (ODE)

Prescription Use (Per 21 CFR 801.109) ાર

Over the Counter Use _________________________________________________________________________________________________________________________________________________________

Regulation Number and Section

§ 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).