Infertility: AI Finds Sperm Faster and Better Than Doctors

Artificial intelligence really is that tool of the 21st century. From being a doctor’s assistant to assisting diagnosis of cancers, dental problems, and now finding sperm in a man’s semen. Artificial intelligence really has the power to transform healthcare and is getting there real quick. In comparison to the hours it takes scientists, a new artificial intelligence (AI) technology can identify sperm in severely infertile men in seconds. This is according to the results presented at the 39th annual meeting of the European Society of Human Reproduction and Embryology (ESHRE) (1^✔ ✔Trusted Source
Algorithm finds sperm in infertile men faster and more accurately than doctors

Go to source).

Cumbersome Process of Finding Sperm in Semen Made Easy with AI

The algorithm that the study's authors devised, they claim, gives hope to men who desire biological children but lack sperm in their semen.

To help them become fathers, these individuals currently have to have a treatment where a piece of their testicles is removed. This biopsy sample is manually processed by embryologists to get sperm for intracytoplasmic sperm injection (ICSI) treatment, which fertilizes the partner's eggs. The process of finding and isolating sperm in human tissue can take up to six hours, which may impair the embryologist's capacity to recognize sperm due to physical and mental exhaustion.

The results of this recent study by Australian scientists demonstrate that trained AI can relieve practitioners of this laborious task.

SpermSearch: The AI Tool that Recognizes Sperm Faster than a Doctor

Findings reveal that SpermSearch, a tool that quickly recognizes sperm, leaves it up to the embryologist to determine whether sperm is actually there and whether it is viable enough for ICSI. According to the results, the algorithm is also more precise than a skilled physician.

Lead author, Mr. Dale Goss, from the University of Technology Sydney, said: “This tool has the ability to give patients who have very little chance of fathering their own biological children an increased chance.

“The algorithm improves antiquated approaches that have not been updated in decades. It will ensure the rapid identification of sperm in samples, which will not only increase the chance of a couple conceiving their own biological children but also reduce stress on sperm and increase efficiency in the laboratory.”

Non-obstructive azoospermia (NOA), the most severe type of infertility, affects about one percent of all males and is characterized by no sperm in the semen. Five percent of couples seeking reproductive treatment are affected by the disorder.

Embryologists partially rip tissue samples and tear them apart with forceps or small needles to separate the sperm for ICSI. The remaining sperm are then released into a liquid that has been specifically prepared and placed on a Petri plate.

The doctor examines little portions of these liquid droplets one at a time using a microscope. This is difficult due to contamination from other cells and objects, though. The patient's chances of becoming a parent are reduced if the embryologist misses the sperm, and the longer it takes, the higher the likelihood that the sperm won't be viable.

How can AI Identify Sperm?

The study's objective was to determine whether AI could accelerate this procedure. Using AI software installed on a computer, the study was conducted over the course of five months in two rounds at an IVF clinic in Sydney. The algorithm was first taught by the researchers after being shown hundreds of still images taken using a microscope. Although there were numerous other cells and pieces of detritus present in these photos, only the sperm was highlighted.

Through this mentoring, the AI tool was eventually able to recognize what sperm looked like through image analysis utilizing its own performance evaluation system.

Healthy sperm and samples of testicular tissue from seven people, ranging in age from 36 to 55, were first used by Mr. Goss and his team. All had received an NOA diagnosis and had already had sperm retrieval surgery at the facility.

The males gave tissue that was prepped for sperm retrieval but was not required following treatment and was left over.

AI Vs Doctor: Who Found Sperm Quicker and Better?

The algorithm was then put to the test alongside an embryologist whose accuracy was deemed to be 100%. The amount of accuracy and the amount of time it took to identify sperm were compared by the researchers.

Although some sperm were only discovered by the embryologist and some by AI alone, the results showed that the AI found more sperm overall.

The embryologist discovered 560 sperm, and the AI discovered 611, for a combined total of 688. In less than a tenth of the time needed by an embryologist, the algorithm detected sperm for each location of the droplet that it examined.

Additionally, the AI tool detected 60 more sperm and was 5% more accurate than the embryologist per visible droplet area when it came to sperm identification.

The authors emphasize in their conference presentation that a clinical trial is necessary because the study is predicated on a proof-of-concept test. This serves as evidence that the method works as intended and effectively detects sperm.

They emphasize that men who are undergoing additional surgical procedures, such as sperm harvests from various testicular regions, and who have other types of severe infertility should also be included in this investigation.

Previously AI has also helped improve sperm selection (2^✔ ✔Trusted Source
Artificial intelligence for sperm selection-a systematic review

Go to source). There are also studies that have shown the success of AI with in vitro fertilization (IVF) (3^✔ ✔Trusted Source
Does artificial intelligence have a role in the IVF clinic?

Go to source).

The chair of ESHRE, Professor Carlos Calhaz-Jorge from the Northern Lisbon Hospital Centre and the Hospital de Santa Maria in Lisbon (Portugal), said: "For men diagnosed with non-obstructive azoospermia, ICSI with sperm retrieved from the testicles is the only realistic chance of having biological children. This is a preliminary study on the use of AI for finding healthy sperm in men experiencing this type of infertility.

"Finding healthy sperm under the microscope in fragments of testicular biopsies can be an arduous process. The prospect of using AI to make the process quicker and more accurate is very interesting. We need to see more research to build on these results."

References:

1. Algorithm finds sperm in infertile men faster and more accurately than doctors - (https://www.eshre.eu/ESHRE2023/Media/2023-Press-releases/Goss)
2. Artificial intelligence for sperm selection-a systematic review - (https://www.fertstert.org/article/S0015-0282(23)00533-2/pdf)
3. Does artificial intelligence have a role in the IVF clinic? - (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8801019/)

Source-Medindia