P–123 How to develop accurate Computer Assisted Sperm Analysis (CASA) AI in the absence of protocol standardization and abundance of human error when performing semen analyses?

Study question

How can an automation & artificial intelligent tools be developed to perform according to WHO recommendations?

Summary answer

Developing CASA performs at < 20% error margin requires AI trained with high quality datasets and a robotic system adheres to WHO guidelines.

What is known already

A survey of 40 andrology laboratories, in 22 countries, revealed that > 90% had nonconformities in correct use of equipment, standardisation of protocols and quality control, leading to a lack of compliance to WHO protocols. Conventional CASA systems can standardize analysis, but controversy has occurred due to differences between manual and automated analyses stemming from: 1) all cells in a semen sample are detected including debris; 2) protocol variation when compared to top-notch manual analysis. The first point can be addressed by AI. The second point can be addressed by robotics designed to adhere to WHO guidelines.

Study design, size, duration

A mojo AISA (AI-powered semen analysis) system was placed in four clinical laboratories mentioned above capturing images of over 300 samples, one million images were generated over a course of 2 years. Mojo AISA’s AI was trained on data collected from the four clinics using robotic system is developed according to WHO guidelines.

Participants/materials, setting, methods

For an AI to detect sperm accurately, sperm samples were captured using mojo AISA smart microscopy and then the extracted sperm images expertly annotated. To evaluate the system-ability for semen analysis, fresh sample were analysed for concentration and motility by a manual operator and compared to a mojo AISA test.

Main results and the role of chance

To train the sperm detection AI, representative sperm images were carefully captured using mojo AISA and processed according to the following criteria: the number of images and videos to train and to test the model: 50,000 spermatozoon head and tails with various variations the variety of images: data used to train the AI has to be representative of the population that will undergo the analysis: 1) wide concentration ranges from 0 to 300 M/ml, 2) high and low density of debris and cells, 3) Presence of slight aggregations careful and precise annotation: expert andrology scientists annotated sperm images and identify objects to exclude, such as debris in seminal plasma, Mojo AISA is an attempt strictly build CASA AI system to WHO-guidelines. The marriage of AI and robotics automation has shown a promising results to mimic humans when measuring a semen sample and attempt to obtain results comparable to the manual analysis.

mojo AISA’s performance improved three-fold (from 0,85 to 0,95 Pearson sperm count correlation and from >100% means relative error to 25% mean relative error).

Limitations, reasons for caution

Lack of standardization for semen analysis laboratory process globally is a bottleneck towards building a robust multi-center study, on-site CASA testing and generating an actionable data pool for studying the causes behind male fertility declineWider implications of the findings: Key learnings for parties advancing developing AI based on images and videos for application in the fertility space.

Trial registration number

Not applicable

P–111 Development of a flow cytometric assay for membrane lipid oxidation in human sperm

Study question

Is a commercially available lipid peroxidation assay sensitive enough to detect sperm lipid membrane damage and thus provide a novel indicator of male fertility status?

Summary answer

Provisional results demonstrate the novelty of creating a protocol to identify and quantify sperm lipid membrane damage and indicate possible insight into individual male fertility.

What is known already

Cytotoxic lipid aldehydes such as 4-hydroxynonenal (4HNE) created by the damaging effects of reactive oxygen species (ROS) have been studied extensively in sperm, as an indicator of male fertility. This is due to their connection with detrimental effects on sperm function such as morphology, acrosome reactions, motility and fertilization of the oocyte. Although literature states the mechanisms of damage caused to the lipid membrane of the sperm cell, there is no evidence of its quantification or usage as a commercial fertility indicator for human males.

Study design, size, duration

Since the assay is still being developed, there is no formal study size or duration. The goal of this pilot study is to determine whether a commercial lipid peroxidation assay can detect the difference between sperm with high levels of oxidative damage and control sperm cells. We used the remains of sperm samples initially collected for standard semen analysis, which were flash-frozen and then assayed with / without hydrogen peroxide treatment to induce oxidative damage.

Participants/materials, setting, methods

Frozen sperm from consenting donors (n = 21) were washed, optionally treated with hydrogen peroxide to induce oxidative damage, stained with a commercially available lipid peroxidation sensor (LPS, Abcam ab243377), and the resulting fluorescence quantitated by flow cytometry. Assay optimization varied the numbers of sperm input to the protocol, the concentration of the peroxidation sensor, the amount and duration of hydrogen peroxide treatment and the effect of paraformaldehyde (PFA) fixation of samples before or after staining.

Main results and the role of chance

Successful detection of lipid damage in control samples

We observed a significant difference at a p-value < 0.05 between untreated samples and all positive controls with hydrogen peroxide concentrations stronger than 500uM (p < 0.038) . This indicates that we can detect sperm bearing oxidative damage, and establishes the conditions required to make a positive control sample.

Establishment of assay parameters

Results indicate the concentration of sperm input to the protocol is not a significant factor for concentrations below 5 million/ml. Low concentration samples thus do not require further dilution before testing.

Correlation with DNA damage

A significant direct strong positive Pearson correlation coefficient (R = 0.93, p < 0.023) was found between samples with low DNA fragmentation index (DFI (%), measured by flow cytometric staining with acridine orange) and the LPS flow cytometric data (%).

Limitations, reasons for caution

As yet our data only addresses high level lipid damage induced by peroxide treatment. It remains to be established whether it is possible to detect endogenous LPO damage due to oxidative stress in semen. Future work will correlate our data with motility information and oxidative stress data (measured by MiOXSYS).

Wider implications of the findings: If we are able to develop a direct assay for sperm LPO, this will allow an additional avenue for testing patients with unexplained male infertility, which could in turn affect treatment choices and ART methodology. Improved diagnosis and treatment will potentially improve the lives of families with their fertility matters.

Trial registration number

Not applicable