Lung Parenchymal and Endobronchial Metastases From Ovarian Carcinoma

A Machine Learning Approach Using XGBoost Predicts Lung Metastasis in Patients with Ovarian Cancer

Background

Liver metastasis (LM) is an independent risk factor that affects the prognosis of patients with ovarian cancer; however, there is still a lack of prediction. This study developed a limit gradient enhancement (XGBoost) to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer, thereby improving prediction efficiency. Patients and Methods. Data of patients diagnosed with ovarian cancer in the Surveillance, Epidemiology, and Final Results (SEER) database from 2010 to 2015 were retrospectively collected. The XGBoost algorithm was used to establish a lung metastasis model for patients with ovarian cancer. The performance of the predictive model was tested by the area under the curve (AUC) of the receiver operating characteristic curve (ROC).

Results

The results of the XGBoost algorithm showed that the top five important factors were age, laterality, histological type, grade, and marital status. XGBoost showed good discriminative ability, with an AUC of 0.843. Accuracy, sensitivity, and specificity were 0.982, 1.000, and 0.686, respectively.

Conclusion

This study is the first to develop a machine-learning-based prediction model for lung metastasis in patients with ovarian cancer. The prediction model based on the XGBoost algorithm has a higher accuracy rate than traditional logistic regression and can be used to predict the risk of lung metastasis in newly diagnosed patients with ovarian cancer.

Carcinoma male breast with tracheal and endobronchial metastasis, masquerading as nonsmall-cell lung cancer, presenting with superior vena cava obstruction - A rare case report

Cancer male breast is not very common. It comprises <1% of all breast cancers. Primary sites of metastasis are bone, brain, lung, and liver. Endobronchial and tracheal metastasis is very rare. To the best of our information, this is the first case of male breast carcinoma with upfront tracheal and endobronchial metastasis which presented as Superior vena cava obstruction (SVCO), initially evaluated on the lines of metastatic nonsmall-cell lung cancer. A 60-year-old gentleman presented with shortness of breath and features of SVCO. On primary evaluation, he was thought to be a case of nonsmall-cell lung cancer. Later on, it was confirmed to be carcinoma male breast with endobronchial and tracheal metastasis, which was reconfirmed with biopsy. The case we came across had symptoms associated with endobronchial metastases from primary extrapulmonary tumor and which was later found out to be breast. Treatment options are very different from lung primary and thus, we should be aware of the unusual disease presentation.

Development and validation of a nomogram to predict synchronous lung metastases in patients with ovarian cancer: a large cohort study

Purpose: Lung metastasis is an independent risk factor affecting the prognosis of ovarian cancer patients. We developed and validated a nomogram to predict the risk of synchronous lung metastases in newly diagnosed ovarian cancer patients.

Methods: Data of ovarian cancer patients from the Surveillance, Epidemiology, and Final Results (SEER) database between 2010 and 2015 were retrospectively collected. The model nomogram was built on the basis of logistic regression. The consistency index (C-index) was used to evaluate the discernment of the synchronous lung metastasis nomogram. Calibration plots were drawn to analyze the consistency between the observed probability and predicted probability of synchronous lung metastases. The Kaplan–Meier method was used to estimate overall survival rate, and influencing factors were included in multivariate Cox regression analysis (P<0.05) to determine the independent prognostic factors of synchronous lung metastases.

Results: Overall, 16059 eligible patients were randomly divided into training (n=11242) and validation cohorts (n=4817). AJCC T, N stage, bone metastases, brain metastases, and liver metastases were evaluated as predictors of synchronous lung metastases. Finally, a nomogram was constructed. The nomogram based on independent predictors was calibrated and showed good discriminative ability. Mixed histological types, chemotherapy, and primary site surgery were factors affecting the overall survival of patients with synchronous lung metastases.

Conclusion: The clinical prediction model has high accuracy and can be used to predict lung metastasis risk in newly diagnosed ovarian cancer patients, which can guide the treatment of patients with synchronous lung metastases.

Endobronchial metastasis of ovarian cancer rescued by tumor ablation and a self-expanding hybrid stent: A case report and review of the literature

Tracheal stenosis caused by malignancy is a life-threatening complication. Herein, we performed tumor ablation and airway stenting using a hybrid stent on a patient with upper tracheal stenosis caused by endobronchial metastasis of ovarian cancer. To date, only 9 cases of endobronchial metastasis of ovarian cancer have been reported. This is the first reported case of endobronchial metastasis in the upper part of the trachea, which had a favorable outcome after tumor ablation as a sequential treatment and use of a hybrid stent. In addition, 10 cases of endobronchial metastasis of ovarian cancer, including ours and other case reports, were reviewed.

Rare Distant Metastatic Disease of Ovarian and Peritoneal Carcinomatosis: A Review of the Literature

Background: Although metastases of ovarian and peritoneal carcinomatosis are most commonly found within the peritoneal cavity, there is a number of other rare distant sites that have been reported. Our goal is to provide an evidence-based summary of the available literature considering the rare distant metastatic sites of ovarian and peritoneal carcinomatosis. Methods: A comprehensive search of the literature was conducted, with Medline/PubMed being searched for cases of rare metastatic disease originated from primary ovarian and peritoneal cancer with related articles up to 2019 including terms such as "ovarian cancer", "metastases", "peritoneal" and others. Results: The most common mechanism of ovarian cancer metastases consists of primarily dissemination within the peritoneal cavity, while, rare and distant sites can either occur at the beginning or during the course of the disease and they are usually associated with hematogenous route and lymphatic invasion, having poor prognosis, with the least common sites being skin, bone, CNS, eye, placenta, central airways, rare lymph nodes, intra-abdominal organs, heart and breast. Conclusions: The occurrence of metastatic sites described in this review represents the most common rare distant metastatic sites, and even though their patterns of metastases are still not fully clarified due to the rarity of the reports, they offer valuable information considering the pathophysiology of the disease.

Sixty-four-year-old man with non-productive cough and lung mass

A 64-year-old manpresented with non-productive cough and dyspnoea and was evaluated and diagnosed to have a left lung mass on CT of the chest. A transthoracic needle biopsy under CT guidance revealed necrotic tissue on histopathology and was inconclusive. Positron emission tomography scan revealed a fluoro-deoxyglucose-avid left lung mass with a left upper lobe luminal cut-off. A flexible video bronchoscopy was performed and revealed left upper lobe complete obstruction with an endoluminal plug which was removed in piecemeal fashion, and deeper biopsies were taken from the lingula. Histopathology revealed underlying adenocarcinoma colonised by aspergillosis. This case serves to remind us of the possibility of missing underlying malignancy when taking superficial biopsies of clearly visualised endobronchial necrotic tissue and the need for debulking it to a reasonable extent and to take deeper biopsies in order to not miss a possible underlying malignancy.