Left ventricular pseudoaneurysm as a rare catastrophic complication to surgical repair of mitral valve endocarditis.

INTRODUCTION: Left ventricular pseudoaneurysm (LVPA) is rarely described in the medical literature, as a complication of mitral valve repair after infective endocarditis (IE) and only a few cases have been published until now. CASE PRESENTATION: We reported a case of a woman in her forties without past medical history who underwent a successful surgical repair of mycotic pseudoaneurysm at the apex of the left ventricular after two months of mitral mechanical prosthetic valve replacement due to infective endocarditis. DISCUSSION: Infective endocarditis (IE) remains a rare condition with high associated morbidity and mortality. The rapid and accurate diagnosis with optimal medical therapy in cases of suspected IE is a central challenge of the disease. Delayed diagnosis and initiation of treatment lead to complications and worse clinical outcomes. Fatal cardiac structural complications occur when the infection spreads to the heart and the infection tends to spread through the weakest annular structures, leading to the formation of a paravalvular abscess, fistula, and pseudoaneurysm. CONCLUSION: The danger in this condition lies in causing a sudden hemodynamic collapse, which is difficult to treat without emergent surgical intervention. Result in a catastrophic condition and consequences. Therefore, early and rapid diagnosis remains the cornerstone of management.

NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer.

BACKGROUND: Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists. RESULTS: This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes. CONCLUSIONS: This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.

Characteristics, survival and incidence rates and trends of primary cardiac malignancies in the United States.

BACKGROUND: The available literature on the incidence, management and prognosis of primary malignant cardiac tumors [PMCTs] is limited to single-center studies, prone to small sample size and referral bias. We used data from the Surveillance, Epidemiology, and End Results [SEER]-18 registry (between 2000 and 2014) to investigate the distribution, incidence trends and the survival rates of PMCTs. METHODS: We used SEER*Stat (version 8.3.4) and the National Cancer Institute's Joinpoint Regression software (version 4.5.0.1) to calculate the incidence rates and annual percentage changes [APC] of PMCTs, respectively. We later used SPSS software (version 23) to perform Kaplan-Meier survival tests and covariate-adjusted Cox models. RESULTS: We identified 497 patients with PMCTs, including angiosarcomas (27.3%) and Non-Hodgkin's lymphomas [NHL] (26.9%). Unlike the incidence rate of NHL (0.108 per 106 person-years) that increased significantly (APC=3.56%, 95% CI, [1.445 to 5.725], P=.003) over the study period, we detected no significant change (APC=1.73%, 95% CI [-3.354 to 7.081], P=.483) in the incidence of cardiac angiosarcomas (0.107 per 106 person-years). Moreover, our analysis showed that the overall survival of NHL is significantly better than angiosarcomas (P<.001). In addition, surgical treatment was associated with a significant improvement (P=.027) in the overall survival of PMCTs. CONCLUSION: Our analysis showed a significant increase in the incidence of cardiac-NHL over the past 14 years with a significantly better survival than angiosarcomas. To further characterize these rare tumors, future studies should report data on the medical history and diagnostic and treatment modalities in these patients.