BACKGROUND: Accurate preoperative identification of ovarian tumour subtypes is imperative for patients as it enables physicians to custom-tailor precise and individualized management strategies. So, we have developed an ultrasound (US)-based multiclass prediction algorithm for differentiating between benign, borderline, and malignant ovarian tumours.
METHODS: We randomised data from 849 patients with ovarian tumours into training and testing sets in a ratio of 8:2. The regions of interest on the US images were segmented and handcrafted radiomics features were extracted and screened. We applied the one-versus-rest method in multiclass classification. We inputted the best features into machine learning (ML) models and constructed a radiomic signature (Rad_Sig). US images of the maximum trimmed ovarian tumour sections were inputted into a pre-trained convolutional neural network (CNN) model. After internal enhancement and complex algorithms, each sample\'s predicted probability, known as the deep transfer learning signature (DTL_Sig), was generated. Clinical baseline data were analysed. Statistically significant clinical parameters and US semantic features in the training set were used to construct clinical signatures (Clinic_Sig). The prediction results of Rad_Sig, DTL_Sig, and Clinic_Sig for each sample were fused as new feature sets, to build the combined model, namely, the deep learning radiomic signature (DLR_Sig). We used the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) to estimate the performance of the multiclass classification model.
RESULTS: The training set included 440 benign, 44 borderline, and 196 malignant ovarian tumours. The testing set included 109 benign, 11 borderline, and 49 malignant ovarian tumours. DLR_Sig three-class prediction model had the best overall and class-specific classification performance, with micro- and macro-average AUC of 0.90 and 0.84, respectively, on the testing set. Categories of identification AUC were 0.84, 0.85, and 0.83 for benign, borderline, and malignant ovarian tumours, respectively. In the confusion matrix, the classifier models of Clinic_Sig and Rad_Sig could not recognise borderline ovarian tumours. However, the proportions of borderline and malignant ovarian tumours identified by DLR_Sig were the highest at 54.55% and 63.27%, respectively.
CONCLUSIONS: The three-class prediction model of US-based DLR_Sig can discriminate between benign, borderline, and malignant ovarian tumours. Therefore, it may guide clinicians in determining the differential management of patients with ovarian tumours.

BACKGROUND: The timely identification and management of ovarian cancer are critical determinants of patient prognosis. In this study, we developed and validated a deep learning radiomics nomogram (DLR_Nomogram) based on ultrasound (US) imaging to accurately predict the malignant risk of ovarian tumours and compared the diagnostic performance of the DLR_Nomogram to that of the ovarian-adnexal reporting and data system (O-RADS).
METHODS: This study encompasses two research tasks. Patients were randomly divided into training and testing sets in an 8:2 ratio for both tasks. In task 1, we assessed the malignancy risk of 849 patients with ovarian tumours. In task 2, we evaluated the malignancy risk of 391 patients with O-RADS 4 and O-RADS 5 ovarian neoplasms. Three models were developed and validated to predict the risk of malignancy in ovarian tumours. The predicted outcomes of the models for each sample were merged to form a new feature set that was utilised as an input for the logistic regression (LR) model for constructing a combined model, visualised as the DLR_Nomogram. Then, the diagnostic performance of these models was evaluated by the receiver operating characteristic curve (ROC).
RESULTS: The DLR_Nomogram demonstrated superior predictive performance in predicting the malignant risk of ovarian tumours, as evidenced by area under the ROC curve (AUC) values of 0.985 and 0.928 for the training and testing sets of task 1, respectively. The AUC value of its testing set was lower than that of the O-RADS; however, the difference was not statistically significant. The DLR_Nomogram exhibited the highest AUC values of 0.955 and 0.869 in the training and testing sets of task 2, respectively. The DLR_Nomogram showed satisfactory fitting performance for both tasks in Hosmer-Lemeshow testing. Decision curve analysis demonstrated that the DLR_Nomogram yielded greater net clinical benefits for predicting malignant ovarian tumours within a specific range of threshold values.
CONCLUSIONS: The US-based DLR_Nomogram has shown the capability to accurately predict the malignant risk of ovarian tumours, exhibiting a predictive efficacy comparable to that of O-RADS.

This article reports a case of an ovarian collision tumour consisting of an ovarian fibroma and a serous cystadenoma. A 60-year-old woman exhibited symptoms of post-menopausal bleeding and abdominal pain persisting for three months. Computerized tomography identified a solid mass with a cystic component in the right adnexa, and the patient underwent staging laparotomy. Gross examination of the right ovary revealed a cystic tumour with adjacent solid mass. The histopathological analysis identified a cystic mass that matched the characteristics of a serous cystadenoma, with an adjacent solid mass that matched the characteristics of a sex-cord stromal tumour, both located in the right ovary. Additionally, a small cyst that matched the characteristics of a serous cystadenoma was found in the left ovary. There have been only seven previously reported examples of this specific mix of ovarian tumours. Mostly affecting patients above 60 years of age, although tumour markers levels are normal, such cases may present with a complex clinical scenario, as in this case, and demand a comprehensive diagnostic and therapeutic approach.

Mounting evidence has highlighted the multifunctional characteristics of glutamine metabolism (GM) in cancer initiation, progression and therapeutic regimens. However, the overall role of GM in the tumour microenvironment (TME), clinical stratification and therapeutic efficacy in patients with ovarian cancer (OC) has not been fully elucidated. Here, three distinct GM clusters were identified and exhibited different prognostic values, biological functions and immune infiltration in TME. Subsequently, glutamine metabolism prognostic index (GMPI) was constructed as a new scoring model to quantify the GM subtypes and was verified as an independent predictor of OC. Patients with low-GMPI exhibited favourable survival outcomes, lower enrichment of several oncogenic pathways, less immunosuppressive cell infiltration and better immunotherapy responses. Single-cell sequencing analysis revealed a unique evolutionary trajectory of OC cells from high-GMPI to low-GMPI, and OC cells with different GMPI might communicate with distinct cell populations through ligand-receptor interactions. Critically, the therapeutic efficacy of several drug candidates was validated based on patient-derived organoids (PDOs). The proposed GMPI could serve as a reliable signature for predicting patient prognosis and contribute to optimising therapeutic strategies for OC.

Sertoli-Leydig cell tumours (SLCTs) are rare, mixed sex-cord stromal tumours composed of varying proportions of both Sertoli and Leydig cells, which account for <0.5% of all ovarian tumours. The cytomorphologic features of SLCTs are not well described in literature. Herein, we describe the cytomorphologic features of an SLCT at an uncommon metastatic site in a young female. Sertoli-Leydig cell tumours (SLCTs) are rare, mixed sex-cord stromal tumours composed of varying proportions of both Sertoli and Leydig cells, which account for <0.5% of all ovarian tumours. The cytomorphologic features of SLCTs are not well described in literature. Herein, we describe the cytomorphologic features of an SLCT at an uncommon metastatic site in a young female.

Angiogenic inhibitors have been demonstrated to inhibit tumour cells in ovarian carcinoma, but the initial data are not accurate enough to indicate the influence of these drugs on the post-therapy wound healing. In order to assess the effect of angiogenic inhibitors on the treatment of wound healing in ovarian carcinoma, we performed a meta-analysis of related literature. For this meta-analysis, we looked up the data from 4 databases: PubMed, EMBASE, Web of Science and the Cochrane Library. All literature searches were performed up to October 2023. The ROBINS-I tool was applied to evaluate the risk of bias in the inclusion trials, and statistical analysis was performed with RevMan 5.3. In this research, 971 related research were chosen, and 9 of them were selected. These studies were published between 2013 and 2023. In all 9 trials, a total of 3902 patients were enrolled. There was a significant reduction in the risk of wound infection in the control group than in those who received angiogenesis inhibitors (OR, 0.66; 95% CI, 0.49-0.89 p = 0.007). The risk of developing an abscess was not significantly different from that of those who received angiogenesis inhibitors (OR, 0.80; 95% CI, 0.20-3.12 p = 0.74). The risk of perforation in the control group was smaller than that in those receiving angiogenic inhibitors (OR, 0.25; 95% CI, 0.11-0.56 p = 0.0006). There was a significant increase in the risk of injury and GI perforation in women who received angiogenic inhibitors than in the control group. But the incidence of abscess did not differ significantly among the two groups.

Peritoneal tuberculosis (TB) is one of the types of extrapulmonary TB that predominantly involves the omentum, liver, intestinal tract, spleen, or female genital tract. It can occasionally result in gynecological-related oncology diagnoses such as advanced ovarian cancer due to its non-specific signs and symptoms, making it very difficult to detect. This report presents a case of a 22-year-old female who presented with the chief complaints of pain and distension of the abdomen for one month with dysuria. Ultrasonography and magnetic resonance imaging was performed that reported a large uni-loculated cystic pelvic abdominal lesion likely to be of ovarian origin and suggestive of neoplastic etiology with bilateral hydroureteronephrosis. To confirm the diagnosis, an exploratory laparotomy was performed which revealed extrapulmonary abdominal TB, and was registered for Directly Observed Treatment Shortcourse (DOTS) following which anti-tubercular drugs were given. In conclusion, this case report highlighted the masquerading behavior of encysted peritoneal TB as an ovarian tumor, and the fact that it should, therefore, should be considered in the differential diagnosis in regions where TB remains endemic, such as in developing countries. Hence, an appropriate diagnosis can prevent the need for unnecessary surgical operations and adequate therapy can save the patient\'s life.

Ovarian mucinous cystic tumours with mural nodules are rare tumours of the ovary that are often missed out during diagnosis. They are classified under the ovarian mucinous surface epithelial-stromal tumours. These mural nodules can be sarcoma-like (benign), anaplastic carcinoma, sarcomas, or mixed malignant (carcinosarcoma). However, very few cases of anaplastic malignant mural nodules have been reported. Here, we present a case of a borderline ovarian mucinous cystadenoma with anaplastic mural nodule that has sarcomatoid differentiation, in a 39-year-old woman who presented with a 1-year history of progressive abdominal swelling and pain. There were intraoperative findings of huge right ovarian cystic tumour with omental and umbilical deposits. Differential diagnosis of possible germ cell tumours, vascular tumours, melanoma, sarcoma and sarcoma-like nodules were ruled out with routine histology (Haematoxylin & Eosin), histochemical (reticulin) and immunohistochemical stains (CK AE1/3+, CD30+, AFP-, HCG-, EMA-, S100 protein-, CD31-, and CD34-) and the final diagnosis of a mural nodule of anaplastic carcinoma with sarcomatoid differentiation in a borderline ovarian mucinous cystadenoma established. Unfortunately, due to the aggressive nature of the tumour and disease progression, the patient passed on a few months after the surgery. This rare tumour, especially the ones with anaplastic carcinoma or mixed tumours, usually has an aggressive clinical course with most patients presenting late when the disease is advanced with poor clinical outcomes as is seen with the index patient. A high index of suspicion of this tumour with early detection and a multidisciplinary approach to its management is advised.

We present the case of a woman in her 20s with an eight-month history of increasing abdominal distention, dyspnea, and night sweats. The patient believed she was pregnant despite being told at another hospital that the pregnancy tests were negative, and no fetus was seen on an abdominal ultrasound. The patient delayed obtaining follow-up because of a distrust of the healthcare system and presented to our hospital at the behest of her mother. On physical examination, the abdomen was distended with a positive fluid wave, and a large mass was palpated in the abdomen. Gynecological examination was limited because of severe abdominal distension but a mass was palpable in the right adnexa. A pregnancy test and fetal ultrasound were performed, and the patient was not pregnant. A CT scan of the abdomen and pelvis revealed a large mass arising from the right adnexa. She underwent right salpingo-oophorectomy, appendectomy, omentectomy, lymph node dissection, and peritoneal implant resection. The biopsy confirmed intestinal-type IIB primary ovarian mucinous adenocarcinoma, expansile type, with peritoneal spread. Chemotherapy was provided for three cycles. A follow-up CT scan of the abdomen showed no evidence of a tumor six months after surgery.

Krukenberg tumours are unusual metastatic tumours of the ovary with primary tumours from the stomach, breast and gastrointestinal malignancies. Krukenberg tumour from pulmonary malignancy represents an extremely rare situation. This is an elaboration of a case of young women with Krukenberg tumour rising from lung adenocarcinoma. A 38-year-old woman presented with progressive abdominal distention for the past 2-years. Computed tomography (CT) of thorax, abdomen and pelvis revealed a huge ovarian mass with left lung nodules and left-sided pleural effusion. A detailed immunohistochemical staining on pleural fluid cytology confirmed the diagnosis of metastatic adenocarcinoma of lung origin. She underwent doublet platinum chemotherapy as molecular testing for oncogenic mutation was negative. The patient responded well to chemotherapy with a significant reduction in ovarian tumour size. Early identification of the primary source of Krukenberg tumour is paramount to avoid invasive diagnostic surgical intervention for ovarian metastasis.