Consistent and effective method to define the mouse estrous cycle stage by a deep learning-based model.

The mouse estrous cycle is divided into four stages: proestrus (P), estrus (E), metestrus (M), and diestrus (D). The estrous cycle affects reproductive hormone levels in a wide variety of tissues. Therefore, to obtain reliable results from female mice, it is important to know the estrous cycle stage during sampling. The stage can be analyzed from a vaginal smear under a microscope. However, it is time-consuming, and the results vary between evaluators. Here, we present an accurate and reproducible method for staging the mouse estrous cycle in digital whole-slide images (WSIs) of vaginal smears. We developed a model using a deep convolutional neural network (CNN) in a cloud-based platform, Aiforia Create. The CNN was trained by supervised pixel-level multiclass semantic segmentation of image features from 171 hematoxylin-stained samples. The model was validated by comparing the results obtained by CNN with those of four independent researchers. The validation data included three separate studies comprising altogether 148 slides. The total agreement attested by the Fleiss kappa value between the validators and the CNN was excellent (0.75), and when D, E, and P were analyzed separately, the kappa values were 0.89, 0.79, and 0.74, respectively. The M stage is short and not well defined by the researchers. Thus, identification of the M stage by the CNN was challenging due to the lack of proper ground truth, and the kappa value was 0.26. We conclude that our model is reliable and effective for classifying the estrous cycle stages in female mice.

Secreted frizzled-related protein 2 (SFRP2) expression promotes lesion proliferation via canonical WNT signaling and indicates lesion borders in extraovarian endometriosis.

STUDY QUESTION: What is the role of SFRP2 in endometriosis? SUMMARY ANSWER: SFRP2 acts as a canonical WNT/CTNNB1 signaling agonist in endometriosis, regulating endometriosis lesion growth and indicating endometriosis lesion borders together with CTNNB1 (also known as beta catenin). WHAT IS KNOWN ALREADY: Endometriosis is a common, chronic disease that affects women of reproductive age, causing pain and infertility, and has significant economic impact on national health systems. Despite extensive research, the pathogenesis of endometriosis is poorly understood, and targeted medical treatments are lacking. WNT signaling is dysregulated in various human diseases, but its role in extraovarian endometriosis has not been fully elucidated. STUDY DESIGN, SIZE, DURATION: We evaluated the significance of WNT signaling, and especially secreted frizzled-related protein 2 (SFRP2), in extraovarian endometriosis, including peritoneal and deep lesions. The study design was based on a cohort of clinical samples collected by laparoscopy or curettage and questionnaire data from healthy controls and endometriosis patients. PARTICIPANTS/MATERIALS, SETTING, METHODS: Global gene expression analysis in human endometrium (n = 104) and endometriosis (n = 177) specimens from 47 healthy controls and 103 endometriosis patients was followed by bioinformatics and supportive qPCR analyses. Immunohistochemistry, Western blotting, primary cell culture and siRNA knockdown approaches were used to validate the findings. MAIN RESULTS AND THE ROLE OF CHANCE: Among the 220 WNT signaling and CTNNB1 target genes analysed, 184 genes showed differential expression in extraovarian endometriosis (P < 0.05) compared with endometrium tissue, including SFRP2 and CTNNB1. Menstrual cycle-dependent regulation of WNT genes observed in the endometrium was lost in endometriosis lesions, as shown by hierarchical clustering. Immunohistochemical analysis indicated that SFRP2 and CTNNB1 are novel endometriosis lesion border markers, complementing immunostaining for the known marker CD10 (also known as MME). SFRP2 and CTNNB1 localized similarly in both the epithelium and stroma of extraovarian endometriosis tissue, and interestingly, both also indicated an additional distant lesion border, suggesting that WNT signaling is altered in the endometriosis stroma beyond the primary border indicated by the known marker CD10. SFRP2 expression was positively associated with pain symptoms experienced by patients (P < 0.05), and functional loss of SFRP2 in extraovarian endometriosis primary cell cultures resulted in decreased cell proliferation (P < 0.05) associated with reduced CTNNB1 protein expression (P = 0.05). LIMITATIONS REASONS FOR CAUTION: SFRP2 and CTNNB1 improved extraovarian endometriosis lesion border detection in a relatively small cohort (n = 20), although larger studies with different endometriosis subtypes in variable cycle phases and under hormonal medication are required. WIDER IMPLICATIONS OF THE FINDINGS: The highly expressed SFRP2 and CTNNB1 improve endometriosis lesion border detection, which can have clinical implications for better visualization of endometriosis lesions over CD10. Furthermore, SFRP2 acts as a canonical WNT/CTNNB1 signaling agonist in endometriosis and positively regulates endometriosis lesion growth, suggesting that the WNT pathway may be an important therapeutic target for endometriosis. STUDY FUNDING/COMPETING INTEREST(S): This study was funded by the Academy of Finland and by Tekes: Finnish Funding Agency for Innovation. The authors have no conflict of interest to declare.