BACKGROUND: In the realm of in vitro fertilization (IVF), artificial intelligence (AI) models serve as invaluable tools for clinicians, offering predictive insights into ovarian stimulation outcomes. Predicting and understanding a patient\'s response to ovarian stimulation can help in personalizing doses of drugs, preventing adverse outcomes (eg, hyperstimulation), and improving the likelihood of successful fertilization and pregnancy. Given the pivotal role of accurate predictions in IVF procedures, it becomes important to investigate the landscape of AI models that are being used to predict the outcomes of ovarian stimulation.
OBJECTIVE: The objective of this review is to comprehensively examine the literature to explore the characteristics of AI models used for predicting ovarian stimulation outcomes in the context of IVF.
METHODS: A total of 6 electronic databases were searched for peer-reviewed literature published before August 2023, using the concepts of IVF and AI, along with their related terms. Records were independently screened by 2 reviewers against the eligibility criteria. The extracted data were then consolidated and presented through narrative synthesis.
RESULTS: Upon reviewing 1348 articles, 30 met the predetermined inclusion criteria. The literature primarily focused on the number of oocytes retrieved as the main predicted outcome. Microscopy images stood out as the primary ground truth reference. The reviewed studies also highlighted that the most frequently adopted stimulation protocol was the gonadotropin-releasing hormone (GnRH) antagonist. In terms of using trigger medication, human chorionic gonadotropin (hCG) was the most commonly selected option. Among the machine learning techniques, the favored choice was the support vector machine. As for the validation of AI algorithms, the hold-out cross-validation method was the most prevalent. The area under the curve was highlighted as the primary evaluation metric. The literature exhibited a wide variation in the number of features used for AI algorithm development, ranging from 2 to 28,054 features. Data were mostly sourced from patient demographics, followed by laboratory data, specifically hormonal levels. Notably, the vast majority of studies were restricted to a single infertility clinic and exclusively relied on nonpublic data sets.
CONCLUSIONS: These insights highlight an urgent need to diversify data sources and explore varied AI techniques for improved prediction accuracy and generalizability of AI models for the prediction of ovarian stimulation outcomes. Future research should prioritize multiclinic collaborations and consider leveraging public data sets, aiming for more precise AI-driven predictions that ultimately boost patient care and IVF success rates.

Thyroid hormones(THs) are essential for the proper functioning of the ovaries, and multiple studies have shown that thyroid abnormalities, especially during adolescence and reproductive age, can lead to lifelong ovarian dysfunction. Autoimmune thyroid disease (AITD), one of the most common organ specific autoimmune diseases, is mainly mediated by cellular autoimmune reactions, and has strong inflammatory infiltration and immune active cells, including chemokines and cytokines, which are important components of ovarian aging. This suggests that autoimmune and inflammatory molecular processes may play a role in the emergence of ovarian dysfunction. The purpose of this review is to summarize recent in vivo and in vitro evidence of a complex relationship between AITD and ovarian dysfunction. AITD is closely related to the decline of ovarian function from the perspective of antibody, cytokine, oxidative stress, and genetic factors. Finally, some of the currently known treatments for AITD and hypo ovarian disease are summarized.

Ovarian cancer is usually confined intraperitoneally. Distant metastases at presentation is unusual. Its spread via lymphatics is uncommon, and metastasis to axillary lymph nodes is very rare. We report two cases with presentation of axillary lymphadenopathy without breast involvement. Computed tomography scan identified the ovarian masses. Both had elevated Serum Ca 125. The first case had a Grade 2 ovarian endometrioid carcinoma. The second case had a high-grade serous ovarian carcinoma. These cases illustrate the rarity of axillary lymphadenopathy from ovarian cancer. It is important to identify the primary ovarian carcinoma in order to offer appropriate management. Despite surgery and chemotherapy, both succumbed within 3 years from diagnosis.

UNASSIGNED: Ovarian cystadenofibroma is a relatively rare benign tumor (Groutz et al., 1994) that develops from the ovarian epithelium and stroma. This tumor can be solid, cystic, or semi-solid, depending on the fraction of epithelium and stroma it contains and the secretory activity of the epithelium that composes it.
METHODS: We report the case of a 58-year-old multiparous patient who consulted for pelvic pain and for whom an MRI was requested, objectifying the presence of a mass of ovarian origin. The patient had been menopausal since the age of 51 and was not taking hormone replacement therapy. She had comorbid hypertension for 4 years under treatment. Preoperative ultrasound showed an ovarian-appearing, finely echogenic mass, site of endocystic vegetation, measuring 8.48 mm × 7.30 mm long axis.
UNASSIGNED: The mechanism underlying this hyperestrogenism is considered to be hypersecretion of the hormone by the tumor itself.
CONCLUSIONS: cystadenofibromas had morphologic imaging features of malignancy on CT or MR images. On histology, solid components in the cystic tumors were correlated with fibrous stromas that occasionally made a false positive result for malignancy on imaging.

UNASSIGNED: Adnexal torsion is an uncommon but urgent surgical situation more frequently observed during the reproductive years and rarely in postmenopausal women.
METHODS: This case report describes a postmenopausal woman with a large left ovarian cyst measuring 18 × 20 × 22 cm who experienced adnexal torsion, which is a rare occurrence in this age group. To avoid the potential requirement for additional surgical procedures in case of cyst recurrence in the remaining ovary or the development of uterine diseases a total abdominal hysterectomy and bilateral salpingo-oophorectomy with cystectomy were performed. Histopathological analysis of the cyst confirmed that it was a benign serous cystadenoma of the ovary.
UNASSIGNED: Adnexal torsion can happen at any age but is less likely to occur after menopause. Moreover, giant ovarian cysts (>10 cm) are uncommon, making adnexal torsion on these cysts a rare event. While laparotomy remains the gold standard surgical intervention, laparoscopy is beginning to play a role in management of giant cyst.
CONCLUSIONS: This report documenting a rare case of adnexal torsion in a postmenopausal woman following a serous giant cystadenoma emphasizes that this surgical emergency can occur at any age. In addition, the report highlights that the presence of an ovarian mass or cyst increases the risk of adnexal torsion, regardless of age.

BACKGROUND: Angiosarcoma (AS) is a rare and highly aggressive soft tissue disease that most commonly arises in deep soft tissues. There are only a few reported cases of AS involving the ovary and even fewer reports of the underlying molecular abnormalities. Here, we briefly review two cases of primary ovarian AS (oAS) with specific molecular events and immune checkpoints. The clinical features and prognosis of the disease, diagnosis, differential diagnosis, and new treatment approaches are discussed based on a literature review.
METHODS: Case 1: A 51-year-old female patient was admitted with right lower limb pain for 5 mo, and lower abdominal pain with hematuria for 1 mo. Partial removal of rectus abdominis muscle and fascia, partial hysterectomy, bilateral salpingo-oophorectomy, and inguinal and pelvic lymphadenectomy were performed. Pathology revealed primary oAS. Fluorescence in situ hybridization revealed c-MYC gene amplification. MESNA + ADM + IFO + DTIC (MAID) regimen was administered, but stable disease was achieved. The patient died 1 mo later. Case 2: A 41-year-old female patient presented with fatigue, nausea, decreased appetite, and diffuse abdominal pain. On physical examination, the abdomen was distended and a complex cystic mass was palpable in the right pelvic cavity. Pathology revealed primary oAS. MAID chemotherapy was administered and programmed death ligand 1 (PD-L1) staining was performed on the tumor samples. The patient benefited from anti-PD-1 immunotherapy and is alive without any evidence of disease 27 mo off therapy in follow-up.
CONCLUSIONS: Long-term survival benefit for primary oAS can be achieved by alternative therapeutic strategies using pathological indicators to inform treatment.

•We report a case of a patient with acute myeloid leukemia (AML) presenting as myeloid sarcoma.•This patient with bilateral adnexal masses was managed via total robotic hysterectomy with bilateral salpingo-oophorectomy.•There are a limited number of reports of bilateral ovarian occurrences that exist in the literature.•Myeloid sarcoma of the ovaries may present with vaginal bleeding to dysmenorrhea, dysuria, and palpable abdominal mass.

Background: Epithelial ovarian cancer (EOC) is the most common type of ovarian cancer. About 90% of ovary tumors are epithelial. The current treatment for EOC involves surgical debulking of the tumors followed by a combination of chemotherapy. While most patients achieve complete remission, many EOCs will recur and develop chemoresistance. The cancer cells can adapt to several stress stimuli, becoming resistant. Therefore, new ways to fight resistant cells during the disease are being studied. Recently, exosomes, which reflect cell behavior in normal and pathological conditions such as epithelial ovarian cancer, are of academic interest as new biomarkers for diagnosis and therapy. Consequently, the current study aimed to investigate the research output of exosomes in EOC. Method: A bibliometric method was used for analyzing publications on exosome and epithelial ovarian cancer from the beginning to 15 October 2022 by searching keywords in Scopus, PubMed and Google scholar. Annual scientific publications, authors, citations, journals, co-authorships, and keywords co-occurrence were analyzed and plotted using Microsoft Office Excel and VOS viewer. 39 original journal articles and 3 reviews have been published since 2015 up to 15 October 2022. Results: The findings showed that China is the top country in research output, international collaborations, organization, author, and sponsorship. The top journals were the Journal of Ovarian Research, Oncotarget, and Tumor Biology, all in the United States. The top institution was Shanghai Jiao Tong University in China. The top author was Xipeng Wang. Co-occurrence analysis showed that academics\' interest is toward:1) 1) Exosomes as prognostic biomarkers of EOC as well as their role in the proliferation and migration of cells. 2) The role of exosomes in metastasis through different mechanisms; 3) The role of exosomes in epithelial-mesenchymal transition of ovarian cancer cells; 4) The diagnostic role of EVs in EOC; and 5) Conferring chemoresistance in EOC through the exosomal transfer of miRNAs. Conclusion: Research on the exosome and EOC has an increasing trend, and China is much more involved than other countries in research, financial support, and international cooperation. These findings could aid researcher in understanding novel ideas and subjects interested by sponsors in this field.

There is an unmet biomedical need for ex vivo tumour models that would predict drug responses and in turn help determine treatment regimens and potentially predict resistance before clinical studies. Research has shown that three dimensional models of ovarian cancer (OvCa) are more realistic than two dimensional in vitro systems as they are able to capture patient in vivo conditions in more accurate manner. The vast majority of studies aiming to recapitulate the ovarian tumour morphology, behaviors, and study chemotherapy responses have been using ovarian cancer cell lines. However, despite the advantages of utilising cancer cell lines to set up a platform, they are not as informative as systems applying patient derived cells, as cell lines are not able to recapitulate differences between each individual patient characteristics. In this review we discussed the most recent advances in the creation of 3D ovarian cancer models that have used patient derived material, the challenges to overcome and future applications.

Pure primary ovarian squamous cell carcinoma (oSCC) is very rare, with about 42 cases have been reported in the literature. Lacking effective treatment guidelines, the prognosis of oSCC is extremely poor. Here, we report a 52-year-old postmenopausal woman diagnosed with pure primary oSCC in our center. The patient received debulking surgery followed by chemotherapy with carboplatin, paclitaxel, and bevacizumab. The patient survived 11 months after surgery and died of tumor progression and multiple organ failure. We also present a review of the literature.