Causes of Death Following Nonmetastatic Colorectal Cancer Diagnosis in the U.S.: A Population-Based Analysis.

INTRODUCTION: Because of the improved colorectal cancer (CRC) survival in the U.S., patients may live long enough after CRC diagnosis to the point where non-cancer-related comorbidities may considerably impact their overall survival. In this study, we perform a long-term analysis of causes of death (CODs) following nonmetastatic CRC with respect to different demographic and tumor-related criteria. MATERIALS AND METHODS: We gained access to the Surveillance, Epidemiology, and End Results data to review patients diagnosed with nonmetastatic CRC during 2000-2015. We calculated standardized mortality ratios (SMRs) for each COD following CRC. SMRs represented the change of risk of a specific COD following CRC diagnoses when compared with the risk in the general U.S. RESULTS: We reviewed 302,345 patients, of whom 112,008 died during the study period. More deaths (68.3%) occurred within 5 years following nonmetastatic CRC diagnosis, with 76,486 deaths. CRC was the most common COD (51.4%) within 5 years of diagnosis followed by heart disease (15.2%) and other cancers (8.4%). As time passed after diagnosis, the number of CRC deaths decreased, and other noncancer causes increased to the point that after 10 years only 10.4% of deaths were attributed to CRC, 15.3% were attributed to other cancers, and 34.2% were secondary to heart disease. CONCLUSION: Following nonmetastatic CRC diagnosis, most deaths remain secondary to CRC. Other causes, including other cancers and cardiovascular disease, represent a significant number of deaths, especially in the 5 years following initial CRC diagnosis. Our findings help guide counseling patients with CRC regarding future health risks. IMPLICATIONS FOR PRACTICE: Most common causes of death following nonmetastatic colorectal cancer (CRC) are heart diseases, other cancers, chronic obstructive pulmonary disease, and cerebrovascular diseases. Physicians should counsel patients regarding survivorship with cancer screening and focus on prevention of noncancer deaths. These findings should be considered by physicians who give care for survivors of nonmetastatic CRC.

Structured crowdsourcing enables convolutional segmentation of histology images.

MOTIVATION: While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. RESULTS: We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. AVAILABILITY AND IMPLEMENTATION: Dataset is freely available at: https://goo.gl/cNM4EL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Outcome disparities in colorectal cancer: a SEER-based comparative analysis of racial subgroups.

PURPOSE: Previous studies of ethnic disparities in colorectal cancer (CRC) have focused mainly on patients of Caucasian and African-American descent. We aimed to evaluate outcomes for a range of races, representing a broader demographic of the US population. METHODS: The Surveillance, Epidemiology, and End Results database was queried to identify patients with CRC diagnosed between 1994 and 2014. We performed unadjusted Kaplan-Meier test and multivariable covariate-adjusted Cox models to calculate the overall and CRC-specific survival of patients according to their race. RESULTS: We identified 401,723 patients diagnosed with CRC between 1994 and 2014. Overall survival (OS) and CRC-specific survival were compared across different races stratified by age, sex, marital status, disease stage and grade, and undergoing surgery as a treatment. Overall, Asian/Pacific Islanders and Hispanics had improved CRC-specific survival compared to Whites (HR = 0.873, 95%CI 0.853-0.893, P < .001, and HR = 0.958, 95%CI 0.937-0.979, P < .001, respectively). Blacks had the worst CRC-specific survival outcomes when compared to Whites (HR = 1.215, 95%CI 1.192-1.238, P < .001). Racial disparity persisted when looking at two different time periods (1994-2003 and 2004-2014). CONCLUSIONS: Asians/Pacific Islanders have improved outcomes from CRC compared to other races. Multifactorial, including genetic, environmental, and socioeconomic factors appear to influence outcomes and need to be addressed separately in order to reduce racial disparities among patients with CRC.

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.

Epidemiology of Cholangiocarcinoma; United States Incidence and Mortality Trends.

BACKGROUND: Cholangiocarcinoma is an aggressive malignancy with few available studies assessing incidence and mortality. In this study, we aim to investigate trends of incidence and mortality in a large nation-wide epidemiologic study. METHODS: We used SEER 18 database to study cholangiocarcinoma cases in the US during 2000-2015. Incidence and mortality rates of cholangiocarcinoma were calculated by race and were expressed by 1,000,000 person-years. Annual percent change (APC) was calculated using joinpoint regression software. RESULTS: We reviewed 16,189 patients with cholangiocarcinoma, of which 64.4% were intrahepatic. Most patients were whites (78.4%), males (51.3%), and older than 65 years (63%). A total of 13,121 patients died of cholangiocarcinoma during the study period. Cholangiocarcinoma incidence and mortality were 11.977 and 10.295 and were both higher among Asians, males, and individuals older than 65 years. Incidence rates have significantly increased over the study period (APC=5.063%, P<.001), while mortality increased significantly over the study period (APC=5.964%, P<.001), but decreased after 2013 (APC=-25.029, P<.001). CONCLUSION: The incidence and mortality of cholangiocarcinoma were increasing in the study period with significant observed disparities based on race and gender.

Trends in Renal-Cell Carcinoma Incidence and Mortality in the United States in the Last 2 Decades: A SEER-Based Study.

BACKGROUND: Renal-cell carcinoma (RCC) is one of the common malignancies in the United States. RCC incidence and mortality have been changing for many reasons. We performed a thorough investigation of incidence and mortality trends of RCC in the United States using the cell Surveillance, Epidemiology, and End Results (SEER) database. PATIENTS AND METHODS: The 13 SEER registries were accessed for RCC cases diagnosed between 1992 and 2015. Incidence and mortality were calculated by demographic and tumor characteristics. We calculated annual percentage changes of these rates. Rates were expressed as 100,000 person-years. RESULTS: A total of 104,584 RCC cases were reviewed, with 47,561 deaths. The overall incidence was 11.281 per 100,000 person-years. Incidence increased by 2.421% per year (95% confidence interval, 2.096, 2.747; P < .001) but later became stable since 2008. However, the incidence of clear-cell subtype continued to increase (1.449%; 95% confidence interval, 0.216, 2.697; P = .024). RCC overall mortality rates have been declining since 2001. However, mortality associated with distant RCC only started to decrease in 2012, with an annual percentage change of 18.270% (95% confidence interval, -28.775, -6.215; P = .006). CONCLUSION: Despite an overall increase in the incidence of RCC, there has been a recent plateau in RCC incidence rates with a significant decrease in mortality.