P-075 Artificial intelligence for sperm analysis: A KNIME-Based automated analysis of sperm morphology

Abstract

Abstract Study question To evaluate an automated sperm morphology assessment method using the KNIME Analytics Platform compared to manual sperm morphology analysis performed as per WHO guidelines. Summary answer Our method emphasizes how artificial intelligence technologies have the potential to foster standardization of sperm morphology assessment with comparable precision and reliability. What is known already Manual sperm morphology assessment is considered the most difficult parameter to standardize due to its subjective nature, strongly linked to the operator's level of expertise. Indeed, there is a high degree of inter and intra-laboratory variability. Manual examination is time-consuming and laborious. There were many attempts to automate sperm morphology analysis, especially with CASA (Computer Assisted Sperm Analysis) systems, but their performance is still disputable. One of the difficulties in this field of study is the lack of publicly available datasets. Besides, the available databases are only focused on the sperm head morphology. Study design, size, duration A total of 37 semen samples from men attending our laboratory for infertility investigation were included, over a period of one year. For each sample, semen smears were fixed and stained by the Spermoscan® kit. Participants/materials, setting, methods A total of 1000 images of individual spermatozoa were obtained using the MMC® CASA system. The number of images per sample depended on its quality. Three experts have classified these spermatozoa according to modified David classification for sperm morphology. The results were then processed and an algorithm created using teh KNIME Analytics Platform, trained and tested to classify spermatozoa. This workflow uses CNN (convolutional neural network) to perform image classification on our dataset. Main results and the role of chance Of the 1000 images analyzed, we counted : 116 Normal sperm morphology, 67 abnormal post-acrosomal region, 128 abnormal acrosomes, 8 elongated heads, 6 thin heads,10 microcephalic,7 multiple heads, 27 coiled tails, 7 cytoplasmic residues, 17 angulated tails, 6 short tails, 4 multiple tails, and 697 associated abnormalities. For each image, a notebook file containing sperm abnormalities as assessed by the three experts was created, in addition to sperm head, mid-piece and tail dimensions obtained by the CASA system. Our dataset was randomly partitioned into 2 groups: 80% of data formed the training set, and The remaining 20% formed the fully independent test set. The best performance with the KNIME-Based algorithm was achieved for post-acrosomal abnormalities (97 % True positive rate), and the worst for multiple tail abnormalities (69 % True positive rate). Our machine learning model classifies sperm morphology at high accuracy (99.5 %). The overall process occurs in less than 10 seconds. Limitations, reasons for caution Our database included various head, midpiece and tail anomalies. However, the number of images in each category is unequal due to the limited occurrence of some morphological abnormalities. Thus, it is important to increase the number of images in these categories to obtain better results. Wider implications of the findings Our goal is to expand our modified David’s classification-based database. We aim to improve the performance of our model, and to put it at the service of learning and routine use in laboratories. Trial registration number not applicable