AI-algorithm training and validation for endometrial CD138+ cells in infertility-associated conditions; polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF)

Abstract

AbstractImmunohistochemical analysis of CD138+ plasma cells has been applied for detecting endometrial inflammation, especially chronic endometritis (CE). In this study, we developed for the first time an artificial intelligence (AI) algorithm, AITAH, to identify CD138+ plasma cells within endometrial tissue, focusing on two infertility-related conditions: polycystic ovary syndrome (PCOS) and recurrent implantation failure (RIF). We obtained 193 endometrial tissues from healthy controls (n=73), women with PCOS (n=91), and RIF patients (n=29) and compared CD138+ cell percentages across cycle phases, ovulation status, and endometrial receptivity. We trained AITAH with CD138 stained tissue images, and experienced pathologists validated the training and performance of AITAH. AITAH, with high accuracy in detecting CD138+ cells (88.57%), revealed higher CD138+ cell percentages in the proliferative phase than in the secretory phase or in the anovulatory PCOS endometrium, irrespective of PCOS diagnosis. Interestingly, CD138+ percentages differed according to PCOS phenotype in the proliferative phase (p=0.01). Different receptivity statuses had no impact on the cell percentages in RIF samples. In summary, the AI-enabled analysis is a rapid and accurate tool to examine endometrial tissues, potentially aiding clinical decision-making. Here, the AI analysis demonstrated cycle-phase differences in CD138+ aggregations pattern, but no major alterations in PCOS or RIF samples.