Image analysis algorithms including machine learning techniques
—
Slope 1.04, Intercept 1.52, R² 0.92
—
—
Method comparison study: 300 semen specimens
—
Total motility
Image analysis algorithms including machine learning techniques
—
Slope 1.02, Intercept -0.01, R² 0.93
—
—
Method comparison study: 300 semen specimens
—
Progressive motility
Image analysis algorithms including machine learning techniques
—
Slope 0.95, Intercept 0.02, R² 0.91
—
—
Method comparison study: 300 semen specimens
—
Sperm morphology
Image analysis algorithms including machine learning techniques
—
Slope 1.10, Intercept 0.00, R² 0.90
—
—
Method comparison study: 300 semen specimens
—
Semen pH
Image analysis algorithms including machine learning techniques
—
Slope 0.99, Intercept 0.05, R² 0.90
—
—
Method comparison study: 300 semen specimens
—
Sperm vitality
Image analysis algorithms including machine learning techniques
—
Slope 1.01, Intercept -0.01, R² 0.90
—
—
Method comparison study: 300 semen specimens
—
Indications for Use
The Seaman PRO Analyzer is an automated, point-of-care, in vitro use-only medical device for semen analysis performed by healthcare professionals. The desktop unit consists of a light source, optical elements, and an image sensor connected to a PC, which records a video of the semen sample and sends it to the cloud compute unit. The cloud compute unit runs software containing algorithms for assessing semen parameters. The product is a software-based medical device powered by ML that enables the user to further assess semen parameters, including concentration, motility, pH, morphology, and vitality. The product is intended for adult male patients to assess sperm quality. The product is not intended to process any of the PHI/PII. Seaman PRO for prescription use only. Seaman PRO used with Imaging Hardware is an optical device for human semen analysis, which provides direct and calculated quantitative measurements for: 1. Sperm concentration (10^6 per ml) 2. Total motility (PR+NP, %) 3. Progressive motility (%) 4. pH value 5. Sperm morphology (normal forms, %) 6. Vitality (%) The Seaman PRO device does not provide a comprehensive evaluation of a male's fertility status. Instead, it analyzes semen parameters which can be used by healthcare professionals as part of a broader assessment of male fertility.
Device Story
Seaman PRO is an automated, point-of-care, in vitro diagnostic system for semen analysis. Input: video recordings of semen samples captured by desktop imaging hardware (light source, optics, USB camera). Processing: image data transferred to PC and processed in a secure cloud compute environment using AI/ML-based image analysis algorithms to quantify sperm parameters. Output: quantitative test report for concentration, motility (total/progressive), morphology, vitality, and pH. Used by healthcare professionals in clinical settings to support fertility assessments. Does not interpret results or diagnose fertility status. Benefits: provides objective, quantitative measurements of sperm quality to assist clinicians in broader fertility evaluations. Does not process PHI/PII.
Clinical Evidence
Clinical method comparison study (N=300 adult male semen samples) compared Seaman PRO against established reference procedures. Results showed strong agreement with correlation coefficients >0.90 and regression slopes between 0.90 and 1.10. Supported by extensive non-clinical bench testing (precision, linearity, LoB/LoD/LoQ, interference, and environmental stability) per CLSI/WHO/ISO standards.
Technological Characteristics
Modular system: desktop optical unit (light source, fixed optics, digital image sensor), PC, and cloud-based software. Uses GoldCyto semen analysis slides. Connectivity: PC to cloud. Software: ML-based image analysis. Sterilization: Not required (reusable hardware cleaned via standard lab procedures; single-use sample carriers).
Indications for Use
Indicated for adult male patients to assess sperm quality via semen analysis performed by healthcare professionals in a point-of-care setting. Not for post-vasectomy confirmation or diagnosis/treatment of disease.
Regulatory Classification
Identification
An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.
Special Controls
*Classification.* Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY AND INSTRUMENT
## I Background Information:
A 510(k) Number
K252228
B Applicant
CheckCells, Inc.
C Proprietary and Established Names
Seaman PRO
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| POV | Class II | 21 CFR 864.5220 - Automated Differential Cell Counter | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission:
Clearance of new device.
B Measurand:
Sperm concentration (M/mL), total motility (%), progressive motility (%), morphology (%), pH, and Vitality (%)
C Type of Test:
Analysis of Semen Parameters
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K252228 - Page 2 of 13
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
The Seaman PRO Analyzer is an automated, point-of-care, in vitro use-only medical device for semen analysis performed by healthcare professionals. The desktop unit consists of a light source, optical elements, and an image sensor connected to a PC, which records a video of the semen sample and sends it to the cloud compute unit. The cloud compute unit runs software containing algorithms for assessing semen parameters. The product is a software-based medical device powered by ML that enables the user to further assess semen parameters, including concentration, motility, pH, morphology, and vitality. The product is intended for adult male patients to assess sperm quality. The product is not intended to process any of the PHI/PII. Seaman PRO for prescription use only.
Seaman PRO used with Imaging Hardware is an optical device for human semen analysis, which provides direct and calculated quantitative measurements for:
1. Sperm concentration (10^6 per ml)
2. Total motility (PR+NP, %)
3. Progressive motility (%)
4. pH value
5. Sperm morphology (normal forms, %)
6. Vitality (%)
The Seaman PRO device does not provide a comprehensive evaluation of a male's fertility status. Instead, it analyzes semen parameters that healthcare professionals use as part of a broader assessment of male fertility.
### C Special Conditions for Use Statement(s):
Rx Only
### D Special Instrument Requirements:
Seaman PRO System
## IV Device/System Characteristics:
### A Device Description:
The Seaman PRO System is an automated in vitro diagnostic device for human semen analysis consisting of imaging hardware and software components designed for use in the point-of-care setting. The devices are intended for use in adult male individuals and are not to be used for post-vasectomy confirmation or in the diagnosis or treatment of disease. The device is intended for
{2}
multiple uses and does not require patient-contact reprocessing. Only single-use sample carriers come into direct contact with the biological material. The reusable imaging hardware does not require sterilization and is cleaned using standard laboratory procedures. The Seaman PRO kit includes the following components for analysis: Imaging Hardware (for precise camera positioning, sample illumination and image capturing), Power cable (for light source), Camera cable (for image recognition), Cartridge for pH strip, and scale (informational purposes only).
## B Principle of Operation:
For both the Seaman and Seaman PRO Systems, the imaging hardware includes a desktop optical unit composed of a light source, fixed optical elements, and a digital image sensor. The unit captures video recordings of semen samples prepared on sperm counting microscopic slides. The acquired image data is transferred to a connected PC and processed in a secure cloud compute environment. The software component is a Software as a Medical Device (SaMD) that uses image analysis algorithms, including machine learning (ML) techniques, to quantify semen parameters, including:
- Sperm concentration (10⁶/mL),
- Total Motility (%),
- Progressive Motility (%),
- Sperm morphology (% normal forms),
- pH value,
- Vitality (%).
Analysis of semen parameters require minimal sample manipulation. However, Vitality (%) is determined using WHO laboratory manual for the examination and processing of human semen, 6ᵗʰ edition Eosin-Nigrosin Stain procedure. A smear is prepared on a glass slide from fresh liquefied semen samples mixed with equal volume of eosin-nigrosin staining solution. Once dry, the stained slides are immediately analyzed on the Seaman PRO System.
The device provides quantitative outputs based on video analysis of sperm. The software does not interpret results or diagnose fertility status. It is intended to support healthcare professionals in assessing semen quality. The device does not process, store, or transmit any Protected Health Information (PHI) or Personally Identifiable Information (PII).
## C Instrument Description Information:
1. Instrument Name:
Seaman PRO System
2. Specimen Identification:
Manual Data Entry
K252228 - Page 3 of 13
{3}
K252228 - Page 4 of 13
3. Specimen Sampling and Handling:
The semen specimen should be collected via masturbation directly into a sterile, wide-mouthed, non-toxic, and appropriately labeled container made of polypropylene or polystyrene, in accordance with WHO laboratory manual recommendations. No lubricants or spermicidal agents should be used. The entire ejaculate should be collected, ensuring the first portion (rich in spermatozoa) is not lost. After collection, the sample must rest undisturbed at room temperature for approximately 15-30 minutes to allow for natural liquefaction. Incomplete liquefaction may affect analysis accuracy. The sample should be analyzed within 60 minutes of ejaculation for optimal accuracy. Delays in analysis beyond 60 minutes may result in decreased motility and alterations in morphology or pH. Samples should not be refrigerated or frozen prior to analysis.
4. Calibration:
User calibration is not required.
5. Quality Control:
The quality control of the device should be performed regularly and at least once a month. The quality can be controlled on a hardware level and on a software level.
Hamilton Thorne Accu-beads: three concentration levels (low, medium, high) of silicone beads, similar in size to human sperm, suspended in an aqueous solution.
Fertility Solutions Semen Test Recordings: control material represented by a set of microscopic recordings of human semen with three levels (low, medium, high) of motility, morphology, and vitality.
V Substantial Equivalence Information:
A Predicate Device Name(s):
LensHooke X1 Pro Semen Quality Analyzer
B Predicate 510(k) Number(s):
K180343
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K252228 | K180343 |
| --- | --- | --- |
| Device Trade Name | Seaman PRO System | LensHooke X1 Pro Semen Quality Analyzer |
{4}
K252228 - Page 5 of 13
| General Device Characteristic Similarities | | |
| --- | --- | --- |
| Intended Use/Indications For Use | The Seaman PRO Analyzer is an automated, point-of-care, in vitro use-only medical device for semen analysis performed by healthcare professionals. The desktop unit consists of a light source, optical elements, and an image sensor connected to a PC, which records a video of the semen sample and sends it to the cloud compute unit. The cloud compute unit runs software containing algorithms for assessing semen parameters. The product is a software-based medical device powered by ML that enables the user to further assess semen parameters, including concentration, motility, pH, morphology, and vitality. The product is intended for adult male patients to assess sperm quality. The product is not intended to process any of the PHI/PII. Seaman PRO for prescription use only.
Seaman PRO used with Imaging Hardware is an optical device for human semen analysis, which provides direct and calculated quantitative measurements for: | The LensHooke X1 PRO Semen Quality Analyzer used with LensHooke Semen Test Cassette is an optical device for human semen analysis which provides direct and calculated quantitative measurements for:
(1) Sperm concentration (10^{6} per ml)
(2) Total motility (PR+NP, %)
• Progressive motility (%)
• Non-Progressive motility (%)
(3) Sperm morphology (normal forms, %)
(4) pH value.
The LensHooke X1 PRO Semen Quality Analyzer does not provide a comprehensive evaluation of a male’s fertility status. It is an in-vitro diagnostic system intended for human semen analysis of individuals in healthcare professional setting to evaluate male fertility. |
{5}
K252228 - Page 6 of 13
| | 1. Sperm concentration (10^6 per ml)
2. Total motility (PR+NP, %)
3. Progressive motility (%)
4. pH value
5. Sperm morphology (normal forms, %)
6. Vitality (%).
The Seaman PRO device does not provide a comprehensive evaluation of a male's fertility status. Instead, it analyzes semen parameters that healthcare professionals use as part of a broader assessment of male fertility. | |
| --- | --- | --- |
| Regulation (product code) | 21 CFR 864.5220 (POV) | Same |
| Sample Type | Human Semen | Same |
| Parameters | Sperm concentration, motility (total, progressive), morphology, pH | Same |
| Test Principles | Optical design and Image processing method, Image analysis | Same |
| Software Algorithm | Custom image analysis with AI | Similar |
| Test Locale | POC | Same |
| **General Device Characteristic Differences** | | |
| Standard/ Guidance Document | WHO 6th edition guidelines | WHO 5th edition guidelines |
| Consumables | GoldCyto semen analysis slides | Semen Test Cassette (CS0, CS1) |
| Hardware Configuration | Camera + optics + PC with AI software (modular) | Integrated desktop analyzer |
| Different Parameters | % Vitality, Semen | Nonprogressive |
{6}
| | Volume, Total Sperm Count | Motility |
| --- | --- | --- |
| Testing requiring additional reagents / slide from end-user (not provided) | % Vitality procedure | None |
| Control Material | Hamilton Thorne Accu-beads | X QC Beads, X QC Reticle |
| | Fertility Solutions Semen Test Recordings | LensHooke X QC Video (For Semen) |
# VI Standards/Guidance Documents Referenced:
WHO Laboratory Manual for the Examination and Processing of Human Semen 6th Edition (2021)
CLSI EP05-A3 (2014): Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline - Third Edition
CLSI EP06-A2 (2020): Evaluation of the Linearity of Quantitative Measurement Procedures; Approved Guideline - Second Edition
CLSI EP07 (2018): Interference Testing in Clinical Chemistry; Approved Guideline - Third Edition
CLSI EP25-A2 (2023): Evaluation of Stability of In Vitro Diagnostic Reagents; Approved Guideline - Second edition
CLSI EP09-c (2018): Measurement Procedure Comparison and Bias Estimation Using Patient Samples; Approved Guideline - Third Edition
CLSI EP17-A2 (2012): Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline - Second edition
CLSI EP21 (2016): Evaluation of Total Analytical Error for Quantitative Medical Laboratory Measurement Procedures; Approved Guideline - second edition
CLSI EP15-A3 (2019): Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline - Second Edition
# VII Performance Characteristics (if/when applicable):
# A Analytical Performance:
K252228 - Page 7 of 13
{7}
# 1. Precision/Reproducibility:
# Repeatability
A precision study was conducted evaluating sperm concentration, motility, progressive motility, morphology, pH, and vitality using fourteen native semen samples covering low, medium, and high ranges for all parameters. Some samples were only utilized for certain parameters (i.e. pH and vitality) due to limited sample stability, but at least seven samples were used for each parameter evaluation. The analysis was carried out at one POC site over the course of one day by two POC operators using three lots, and three analyzers. Due to the limited stability of semen samples, each "day" in the statistical analysis represents different times of the one day. The study included two replicates per run with 2 runs per 20 "days" (all over one actual day) (20 "days" × two replicates × two runs = 80 data points per level). Data analyses were performed to provide within-run, between-run, between-day, within-laboratory, between-operator, between-instrument, and between-lot repeatability. All results met the predefined acceptance criteria.
| Concentration [M/mL] | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 1 | 131.3 | 80 | 6.5 | 1.1 | 5.8 | 1.0 | 3.9 | 0.7 | 8.4 | 1.4 | 1.3 | 0.2 | 1.8 | 0.3 | 1.3 | 1.7 |
| 2 | 12.9 | 80 | 7.2 | 5.9 | 5.0 | 4.1 | 2.9 | 2.4 | 8.2 | 6.7 | 1.8 | 1.4 | 1.4 | 1.2 | 1.2 | 0.2 |
| 3 | 51.8 | 80 | 3.9 | 2.5 | 5.2 | 3.4 | 3.4 | 2.2 | 6.2 | 4.0 | 1.6 | 1.1 | 2.0 | 1.3 | 0.5 | 0.3 |
| 4 | 7.0 | 80 | 5.6 | 3.9 | 4.8 | 3.4 | 3.8 | 2.7 | 6.9 | 4.9 | 0.7 | 0.5 | 0.6 | 0.5 | 1.3 | 0.1 |
| 5 | 36.9 | 80 | 6.0 | 5.3 | 5.4 | 4.8 | 3.4 | 3.0 | 7.4 | 6.5 | 1.6 | 1.4 | 1.1 | 1.0 | 3.3 | 1.2 |
| 6 | 179.3 | 80 | 6.5 | 2.4 | 5.8 | 2.1 | 3.0 | 1.1 | 8.0 | 3.0 | 1.1 | 0.4 | 0.3 | 0.1 | 0.2 | 0.4 |
| 7 | 95.2 | 80 | 5.3 | 3.0 | 4.9 | 2.8 | 3.3 | 1.9 | 7.0 | 4.0 | 2.1 | 1.2 | 2.0 | 1.2 | 2.4 | 2.3 |
| Total Motility [%] | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 1 | 53.9 | 80 | 6.1 | 3.3 | 5.2 | 2.8 | 3.5 | 1.9 | 7.5 | 4.1 | 0.9 | 0.5 | 0.9 | 0.5 | 1.4 | 0.8 |
| 2 | 30.5 | 80 | 6.4 | 2.0 | 5.1 | 1.5 | 3.9 | 1.2 | 7.6 | 2.3 | 0.1 | 0.0 | 1.4 | 0.4 | 0.6 | 0.2 |
| 3 | 73.1 | 80 | 5.9 | 4.3 | 5.8 | 4.3 | 4.3 | 3.1 | 7.7 | 5.7 | 1.4 | 1.0 | 3.2 | 2.4 | 1.7 | 1.3 |
| 4 | 61.1 | 80 | 5.6 | 3.4 | 6.1 | 3.7 | 4.7 | 2.8 | 7.7 | 4.7 | 0.5 | 0.3 | 1.0 | 0.6 | 1.7 | 1.1 |
| 5 | 24.1 | 80 | 6.6 | 1.6 | 6.6 | 1.6 | 5.7 | 1.4 | 8.6 | 2.1 | 0.9 | 0.2 | 1.7 | 0.4 | 2.8 | 0.7 |
| 6 | 84.5 | 80 | 4.9 | 4.1 | 4.3 | 3.6 | 2.8 | 2.4 | 6.3 | 5.3 | 0.6 | 0.5 | 0.2 | 0.2 | 2.5 | 2.1 |
| 7 | 47.4 | 80 | 5.9 | 2.8 | 5.2 | 2.5 | 3.1 | 1.5 | 7.5 | 3.5 | 1.6 | 0.7 | 1.8 | 0.9 | 1.2 | 0.6 |
| Progressive Motility [%] | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 1 | 48.4 | 80 | 7.3 | 3.6 | 6.2 | 3.0 | 3.7 | 1.8 | 8.8 | 4.2 | 0.1 | 0.1 | 1.6 | 0.8 | 1.1 | 0.6 |
| 2 | 24.6 | 80 | 8.1 | 2.0 | 6.5 | 1.6 | 4.9 | 1.2 | 9.3 | 2.3 | 0.1 | 0.0 | 1.6 | 0.4 | 0.4 | 0.1 |
| 3 | 62.3 | 80 | 6.9 | 4.3 | 6.6 | 4.1 | 4.6 | 2.9 | 9.2 | 5.7 | 1.4 | 0.9 | 3.5 | 2.2 | 1.2 | 0.7 |
| 4 | 52.1 | 80 | 7.0 | 3.7 | 6.0 | 3.1 | 4.8 | 2.5 | 8.5 | 4.4 | 0.5 | 0.3 | 1.2 | 0.6 | 2.1 | 1.1 |
| 5 | 20.5 | 80 | 8.4 | 1.7 | 6.4 | 1.3 | 5.2 | 1.1 | 9.4 | 1.9 | 1.3 | 0.3 | 2.2 | 0.4 | 2.3 | 0.5 |
| 6 | 71.3 | 80 | 5.8 | 4.2 | 5.9 | 4.2 | 4.1 | 2.9 | 7.9 | 5.6 | 0.5 | 0.4 | 0.8 | 0.5 | 2.8 | 2.0 |
| 7 | 40.8 | 80 | 6.4 | 2.6 | 5.9 | 2.4 | 3.6 | 1.5 | 8.1 | 3.3 | 0.8 | 0.3 | 2.0 | 0.8 | 1.7 | 0.7 |
K252228 - Page 8 of 13
{8}
| Morphology [%] | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 1 | 2.7 | 80 | 6.4 | 0.2 | 6.4 | 0.2 | 3.6 | 0.1 | 8.6 | 0.2 | 3.5 | 0.09 | 1.0 | 0.03 | 1.3 | 0.03 |
| 2 | 4.3 | 80 | 6.6 | 0.3 | 5.1 | 0.2 | 3.8 | 0.2 | 7.6 | 0.3 | 0.0 | 0.00 | 1.4 | 0.06 | 2.2 | 0.09 |
| 3 | 8.6 | 80 | 4.9 | 0.4 | 4.5 | 0.4 | 2.7 | 0.2 | 6.3 | 0.5 | 0.6 | 0.05 | 1.7 | 0.14 | 1.2 | 0.11 |
| 4 | 2.5 | 80 | 7.3 | 0.2 | 5.3 | 0.1 | 4.2 | 0.1 | 8.1 | 0.2 | 1.1 | 0.03 | 2.1 | 0.05 | 1.2 | 0.03 |
| 5 | 14.2 | 80 | 4.2 | 0.6 | 4.2 | 0.6 | 2.9 | 0.4 | 5.6 | 0.8 | 1.1 | 0.15 | 1.1 | 0.15 | 0.6 | 0.09 |
| 6 | 3.5 | 80 | 8.2 | 0.3 | 4.9 | 0.2 | 3.2 | 0.1 | 8.2 | 0.3 | 1.6 | 0.06 | 0.7 | 0.03 | 1.5 | 0.05 |
| 7 | 4.6 | 80 | 6.4 | 0.3 | 5.6 | 0.3 | 4.3 | 0.2 | 7.9 | 0.4 | 0.0 | 0.00 | 0.7 | 0.03 | 2.3 | 0.11 |
| Vitality [%] | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 8 | 17.2 | 80 | 6.5 | 1.1 | 5.8 | 1.0 | 3.9 | 0.7 | 8.4 | 1.4 | 1.3 | 0.2 | 1.8 | 0.3 | 0.6 | 0.1 |
| 9 | 81.8 | 80 | 7.2 | 5.9 | 5.0 | 4.1 | 2.9 | 2.4 | 8.2 | 6.7 | 1.8 | 1.4 | 1.4 | 1.2 | 0.5 | 0.4 |
| 10 | 65.6 | 80 | 3.9 | 2.5 | 5.2 | 3.4 | 3.4 | 2.2 | 6.2 | 4.0 | 1.6 | 1.1 | 2.0 | 1.3 | 1.8 | 1.2 |
| 11 | 70.9 | 80 | 5.6 | 3.9 | 4.8 | 3.4 | 3.8 | 2.7 | 6.9 | 4.9 | 0.7 | 0.5 | 0.6 | 0.5 | 0.7 | 0.5 |
| 12 | 88.7 | 80 | 6.0 | 5.3 | 5.4 | 4.8 | 3.4 | 3.0 | 7.4 | 6.5 | 1.6 | 1.4 | 1.1 | 1.0 | 0.4 | 0.4 |
| 13 | 37.0 | 80 | 6.5 | 2.4 | 5.8 | 2.1 | 3.0 | 1.1 | 8.0 | 3.0 | 1.1 | 0.4 | 0.3 | 0.1 | 1.0 | 0.4 |
| 14 | 57.4 | 80 | 5.3 | 3.0 | 4.9 | 2.8 | 3.3 | 1.9 | 7.0 | 4.0 | 2.1 | 1.2 | 2.0 | 1.2 | 0.9 | 0.5 |
| pH | | | | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ID | Mean Value | n | Within-Run | | Between-Run | | Between-Day | | Within-Laboratory | | Between Operator | | Between Instrument | | Between Lot | |
| | | | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| 8 | 7.8 | 80 | 7.6 | 0.6 | 5.8 | 0.5 | 3.6 | 0.3 | 8.9 | 0.7 | 0.4 | 0.0 | 1.4 | 0.1 | 1.2 | 0.1 |
| 9 | 8.4 | 80 | 4.8 | 0.4 | 4.2 | 0.4 | 3.4 | 0.3 | 6.2 | 0.5 | 1.4 | 0.1 | 0.6 | 0.1 | 1.7 | 0.1 |
| 10 | 7.8 | 80 | 5.1 | 0.4 | 4.3 | 0.3 | 2.8 | 0.2 | 6.4 | 0.5 | 0.7 | 0.1 | 1.2 | 0.1 | 0.8 | 0.1 |
| 11 | 6.8 | 80 | 5.6 | 0.4 | 6.3 | 0.4 | 5.1 | 0.3 | 7.9 | 0.5 | 0.9 | 0.1 | 0.9 | 0.1 | 1.1 | 0.1 |
| 12 | 8.3 | 80 | 4.5 | 0.4 | 4.9 | 0.4 | 3.6 | 0.3 | 6.3 | 0.5 | 1.2 | 0.1 | 1.1 | 0.1 | 1.4 | 0.1 |
| 13 | 7.4 | 80 | 5.9 | 0.4 | 5.6 | 0.4 | 4.1 | 0.3 | 7.7 | 0.6 | 1.8 | 0.1 | 1.7 | 0.1 | 2.3 | 0.2 |
| 14 | 8.6 | 80 | 8.0 | 0.7 | 4.7 | 0.4 | 3.6 | 0.3 | 8.2 | 0.7 | 0.5 | 0.0 | 1.7 | 0.1 | 0.3 | 0.0 |
## Reproducibility
To evaluate the reproducibility performance of the Seaman PRO System, a precision study was conducted at three sites (two US, one OUS) with six POC operators. For sperm concentration and vitality, three levels of QC control solution or slides (low negative, low positive, high positive) were evaluated. For the pH evaluation, three potassium/sodium phosphate buffer levels were utilized. The studies included three sites × five replicates × five days, totaling 75 data points per level. Data analyses were performed for each site and overall to provide within-day repeatability, between-day, between-Operator, between-site, and total reproducibility. All results met the predefined acceptance criteria.
K252228 - Page 9 of 13
{9}
| Reproducibility | | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Parameter [units] | Level | N | Mean | Within-Day | | Between-Day | | Between Site | | Between Operator | | Reproducibility | |
| | | | | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% |
| Conc [M/mL] | 3 | 75 | 3.2 | 0.2 | 6.4 | 0.1 | 4.5 | 0.1 | 2.1 | 0.1 | 2.4 | 0.3 | 7.9 |
| | 18 | 75 | 17.8 | 1.1 | 6.0 | 0.5 | 3.0 | 0.2 | 1.3 | 0.2 | 1.4 | 1.1 | 6.4 |
| | 35 | 75 | 36.1 | 1.7 | 4.6 | 0.8 | 2.3 | 0.5 | 1.5 | 0.7 | 1.8 | 1.8 | 4.9 |
| pH | 7.0 | 75 | 7.1 | 0.6 | 8.3 | 0.3 | 4.0 | 0.1 | 1.4 | 0.2 | 2.6 | 0.6 | 8.8 |
| | 8.0 | 75 | 8.0 | 0.5 | 6.1 | 0.2 | 2.7 | 0.1 | 1.5 | 0.1 | 1.6 | 0.5 | 6.7 |
| | 9.0 | 75 | 8.9 | 0.5 | 5.5 | 0.3 | 3.9 | 0.1 | 1.3 | 0.2 | 1.9 | 0.6 | 6.4 |
| Vitality [%] | 16 | 75 | 16.3 | 1.5 | 9.2 | 0.7 | 4.5 | 0.3 | 1.9 | 0.6 | 3.4 | 1.6 | 9.8 |
| | 70 | 75 | 71.6 | 4.3 | 6.0 | 1.9 | 2.7 | 0.7 | 1.0 | 1.1 | 1.5 | 4.6 | 6.4 |
| | 81 | 75 | 79.3 | 5.4 | 6.8 | 2.6 | 3.3 | 0.3 | 0.4 | 1.1 | 1.4 | 5.7 | 7.1 |
2. Linearity:
Linearity for sperm concentration, pH, and vitality were evaluated using one analyzer to measure semen samples prepared at nine levels. Sperm concentrations, prepared via concentration or dilution of fresh semen samples, ranged from 2.1–387.1 M/mL (n=3), verified using manual microscope. Sperm pH ranged from 6.0–9.0 (n=3), verified using manual pH strip. The different levels of pH were created by mixing different levels of semen with phosphate buffer (pH 5.0 and pH 9.0). For Vitality, commercial Sperm Viability Quality Control stained slides, with known vitality levels were utilized. For all parameters, the mean and SD of results were calculated; and Weighted Least Squares Regression analysis was used to verify the linear range. Sperm concentration was demonstrated to be linear from 2.1–387.1 M/mL, Sperm pH was demonstrated to be linear from 6.0–9.0, and sperm vitality was demonstrated to be linear from 5–81 %.
3. Analytical Specificity/Interference:
The potential interference of various substances on Seaman PRO results were evaluated by using two sperm concentration levels (< 50 M/mL and > 50 M/mL). The following 11 interfering substances were tested in the study: vitamin B, testosterone, yeast, E. Coli, RBC, WBC, urine, saliva, agglutination of semen sample, D-norgestrel, and β-estradiol. Samples were tested in five replicates on one analyzer using one lot of test slides. Results of test group were compared to the control group. Study results showed that all tested interfering substances met the acceptance criteria, and no significant interference was caused by the tested substances.
4. Detection Limit and Assay Reportable Range:
Detection Limit:
A study was conducted to determine the detection limits of the Seaman PRO System. Semen samples were taken from volunteers. For the limit of blank (LoB), semen was centrifuged to obtain sperm-free seminal plasma to a concentration of ~0 M/mL (blank sample) as verified by manual microscope. For assessing limit of detection (LoD), samples were prepared by diluting semen with seminal plasma to four samples with concentration of ~2-8 M/mL. Blank and low-level samples were divided into four aliquots and tested in five replicates once a day for three days, using one analyzer. For assessing LoQ, samples were prepared by diluting semen with seminal plasma to four samples with concentration of approximately ~2 M/mL.
K252228 - Page 10 of 13
{10}
The four LoQ low-level samples were tested in three replicates once a day for three days, using one analyzer and two lots of sperm counting slides.
Results were calculated, and the detection limits were determined to be:
Limit of Blank (LoB) = 0.0 M/mL
Limit of Detection (LoD) = 1.9 M/mL
Limit of Quantitation (LoQ) = 2.1 M/mL.
**Assay Reportable Range:**
Sperm concentration: 2.1–380 M/mL
Vitality: 1–100%
pH: 6.0–9.0
The assay reportable range was determined by the linearity and detection limit studies and verified in the method comparison study.
5. **Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):**
**Device Stability**
A stability study was conducted to determine the shelf-life of the Seaman PRO System at room temperature. Three semen samples with varying sperm concentrations (low/near cutoff, medium, high) were tested in 80 replicates using three analyzers before and after storage. The evaluation met the acceptance criteria when comparing results from the stressed devices to control analyzers. Study results demonstrated analyzer performance for three years at room temperature conditions.
**Sample Stability**
Stability of semen samples was determined with 42 samples at different concentration levels (half low and half high concentration samples). The semen samples were stored at room temperature. At time zero (0 hour), the samples were tested to establish the baseline. These samples were tested again at various timepoints and for each time point, the results were compared to the baseline results. The results support a 1-hour semen sample stability duration.
6. **Assay Cut-Off:**
See Reference Range study, section VII.D.
**B Comparison Studies:**
1. **Method Comparison with Predicate Device:**
A method comparison study was conducted to evaluate the performance of the Seaman PRO System when used by intended users (i.e. healthcare professionals). The study was performed
K252228 - Page 11 of 13
{11}
at three sites (two US; one OUS site), with a total of three POC operators for semen analysis. Following collection of the specimen, the operators analyzed the sample on the Seaman PRO System. After recording the results, a different operator at the study site performed semen analysis on the sample using either the predicate (i.e., the LensHooke X1 PRO Semen Quality Analyzer for concentration, motility, and morphology) or the reference method (i.e., manual microscope for % vitality analysis as recommended in the WHO 6th edition; and manual pH strip reading for pH analysis). A total of 300 semen specimens spanning the analytical measuring range were analyzed by using the Passing-Bablok regression. All results met the predefined acceptance criteria.
| Seaman PRO vs. LensHooke X1 Pro | | | | | |
| --- | --- | --- | --- | --- | --- |
| Parameter [Units] | N | Result Range | Slope (95% CI) | Intercept (95% CI) | R² (95% CI) |
| Concentration [10^6/mL] | 300 | 3.1 - 391.3 | 1.04 (1.00, 1.07) | 1.52 (-1.11, 4.15) | 0.92 (0.91, 0.94) |
| Total Motility [%] | 300 | 0 - 84 | 1.02 (0.99, 1.05) | -0.01 (-0.02, 0.00) | 0.93 (0.92, 0.95) |
| Progressive Motility [%] | 300 | 0 - 84 | 0.95 (0.92, 0.99) | 0.02 (0.01, 0.04) | 0.91 (0.89, 0.93) |
| Morphology [%] | 300 | 2.7 - 7.2 | 1.10 (1.06, 1.14) | 0.00 (-0.00, 0.00) | 0.90 (0.88, 0.92) |
| pH | 300 | 6.0 - 10.0 | 0.99 (0.96, 1.03) | 0.05 (-0.25, 0.34) | 0.90 (0.88, 0.92) |
| Vitality [%] | 300 | 14 - 100 | 1.01 (0.97, 1.05) | -0.01 (-0.04, 0.02) | 0.90 (0.87, 0.92) |
2. Matrix Comparison:
Not applicable.
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable.
2. Clinical Specificity:
Not applicable.
3. Clinical Cut-Off
Not applicable.
4. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
K252228 - Page 12 of 13
{12}
K252228 - Page 13 of 13
# D Expected Values/Reference Range:
The lower limit of the reference range for parameters Sperm Concentration (M/mL), Total Motility (%), Progressive Motility (%), Morphology (%), and Vitality (%) were directly reported as the 5th percentile in the WHO Laboratory Manual for the Examination and Processing of Human Semen, 6th Edition (Table 8.3). No reference range has been established for pH.
| Semen Parameter | Reference Range | Source |
| --- | --- | --- |
| Sperm Concentration (M/mL) | ≥ 16 | WHO 6th Edition |
| Total Motility (%) | ≥ 42 | |
| Progressive Motility (%) | ≥ 30 | |
| Morphology (%) | ≥ 4 | |
| Vitality (%) | ≥ 54 | |
# E Other Supportive Instrument Performance Characteristics Data:
Electrical safety and electromagnetic compatibility (EMC) testing were performed, and the system was found to be acceptable.
Software and cybersecurity documentation was reviewed and found to be acceptable.
# VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
# IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.