Precision Medicine for Chronic Endometritis: Computer-Aided Diagnosis Using Deep Learning Model

Abstract

Chronic endometritis (CE) is a localized mucosal infectious and inflammatory disorder marked by infiltration of CD138(+) endometrial stromal plasmacytes (ESPC). CE is drawing interest in the field of reproductive medicine because of its association with female infertility of unknown etiology, endometriosis, repeated implantation failure, recurrent pregnancy loss, and multiple maternal/newborn complications. The diagnosis of CE has long relied on somewhat painful endometrial biopsy and histopathologic examinations combined with immunohistochemistry for CD138 (IHC-CD138). With IHC-CD138 only, CE may be potentially over-diagnosed by misidentification of endometrial epithelial cells, which constitutively express CD138, as ESPCs. Fluid hysteroscopy is emerging as an alternative, less-invasive diagnostic tool that can visualize the whole uterine cavity in real-time and enables the detection of several unique mucosal findings associated with CE. The biases in the hysteroscopic diagnosis of CE; however, are the inter-observer and intra-observer disagreements on the interpretation of the endoscopic findings. Additionally, due to the variances in the study designs and adopted diagnostic criteria, there exists some dissociation in the histopathologic and hysteroscopic diagnosis of CE among researchers. To address these questions, novel dual immunohistochemistry for CD138 and another plasmacyte marker multiple myeloma oncogene 1 are currently being tested. Furthermore, computer-aided diagnosis using a deep learning model is being developed for more accurate detection of ESPCs. These approaches have the potential to contribute to the reduction in human errors and biases, the improvement of the diagnostic performance of CE, and the establishment of unified diagnostic criteria and standardized clinical guidelines for the disease.

Chronic endometritis and infertility — in vitro fertilization outcomes: systematic review and meta-analysis

“…Several major factors are currently considered responsible for reproductive dysfunction in CE [20]: this is primarily the abnormal uterine microbiome, as demonstrated by a suffi cient number of microbiological studies [1,[47][48][49][50], the disruption of cytobiochemical and immune processes in the endometrium [28,36,[51][52][53][54], and also confi rmed by the improved fertility following antibacterial therapy in CE patients [34,55,56]. The abnormal uterine microbiome leads to immune deviations primarily affecting the leukocyte pool of immunocompetent cells with a change in the ratio of pro-and anti-infl ammatory cytokines, which results in the reduced implantation capacity of the endometrium and prevents embryo invasion [19,20,22,57].…”

“…Hysteroscopy has suffi cient sensitivity; however, it is highly dependent on the technician [33][34][35]. Therefore, the current gold standard for CE diagnosis is the detection of plasma cells (PCs) in endometrial biopsy material [36][37][38]. The number of PCs required to diagnose CE remains a matter of discussion [38,39].…”

The Role of Plasma Cells as a Marker of Chronic Endometritis: A Systematic Review and Meta-Analysis

“…Fluid hysteroscopy has been recently proposed as a versatile and convenient diagnostic tool that can be utilized in gynecologic practice to detect uterine cavity lesions associated with female infertility, such as endometrial polyps, submucosal leiomyomas, intrauterine adhesions, and uterine septum [ 31 ]. Recent studies have also demonstrated the potential utility of fluid hysteroscopy for the endoscopic diagnosis of chronic endometritis (CE) since it represents a less painful and time-consuming alternative to traditional endometrial biopsy [ 31 , 32 ].…”

“…In this regard, the retrospective study by Cicinelli et al showed that endometrial micropolyposis can easily be detected by fluid hysteroscopy; moreover, histopathologic evidence of plasma cells was less frequently identified in women without hysteroscopic evidence of micropolyposis [ 34 ]. In another retrospective study, the positive and negative predictive values of fluid hysteroscopy detecting the triad of endometrial micropolyposis, stromal edema, and focal/diffuse hyperemia for the presence of histopathologic CE were 98.4% and 94.5%, respectively [ 32 ]. Based on these studies, the detection of endometrial micropolyposis using fluid hysteroscopy may represent a potentially useful diagnostic tool for CE in infertile women.…”

Bridging the Diagnostic Gap between Histopathologic and Hysteroscopic Chronic Endometritis with Deep Learning Models

“…In 2022, we launched the ARCHIPELAGO (ARChival Hysteroscopic Image-based Prediction for histopathologic chronic Endometritis in infertile women using deep LeArninG mOdel) study. The goal of this study is to link the findings of HistoCE with those of HysteroCE using deep learning-based CNN models and establish computer-aided detection/diagnosis systems for the biopsy-free, less invasive, accurate/precise diagnosis of this inflammatory disease that can deteriorate endometrial receptivity [ 65 ]. These approaches could potentially benefit infertile women suffering from CE as well as aid us in establishing diagnostic criteria/clinical guidelines for this yet elusive disease.…”