An Anthropomorphic Diagnosis System of Pulmonary Nodules using Weak Annotation-Based Deep Learning.

Purpose: To develop an anthropomorphic diagnosis system of pulmonary nodules (PN) based on Deep learning (DL) that is trained by weak annotation data and has comparable performance to full-annotation based diagnosis systems. Methods: The proposed system uses deep learning (DL) models to classify PNs (benign vs. malignant) with weak annotations, which eliminates the need for time-consuming and labor-intensive manual annotations of PNs. Moreover, the PN classification networks, augmented with handcrafted shape features acquired through the ball-scale transform technique, demonstrate capability to differentiate PNs with diverse labels, including pure ground-glass opacities, part-solid nodules, and solid nodules. Results: The experiments were conducted on two lung CT datasets: (1) public LIDC-IDRI dataset with 1,018 subjects, (2) In-house dataset with 2740 subjects. Through 5-fold cross-validation on two datasets, the system achieved the following results: (1) an Area Under Curve (AUC) of 0.938 for PN localization and an AUC of 0.912 for PN differential diagnosis on the LIDC-IDRI dataset of 814 testing cases, (2) an AUC of 0.943 for PN localization and an AUC of 0.815 for PN differential diagnosis on the in-house dataset of 822 testing cases. These results demonstrate comparable performance to full annotation-based diagnosis systems. Conclusions: Our system can efficiently localize and differentially diagnose PNs even in resource-limited environments with good robustness across different grade and morphology sub-groups in the presence of deviations due to the size, shape, and texture of the nodule, indicating its potential for future clinical translation. Summary: An anthropomorphic diagnosis system of pulmonary nodules (PN) based on deep learning and weak annotation was found to achieve comparable performance to full-annotation dataset-based diagnosis systems, significantly reducing the time and the cost associated with the annotation. Key Points: A fully automatic system for the diagnosis of PN in CT scans using a suitable deep learning model and weak annotations was developed to achieve comparable performance (AUC = 0.938 for PN localization, AUC = 0.912 for PN differential diagnosis) with the full-annotation based deep learning models, reducing around 30%∼80% of annotation time for the experts.The integration of the hand-crafted feature acquired from human experts (natural intelligence) into the deep learning networks and the fusion of the classification results of multi-scale networks can efficiently improve the PN classification performance across different diameters and sub-groups of the nodule.

Does Tweeting Improve Citations? One-Year Results From the TSSMN Prospective Randomized Trial.

BACKGROUND: The Thoracic Surgery Social Media Network (TSSMN) is a collaborative effort of leading journals in cardiothoracic surgery to highlight publications via social media. This study aims to evaluate the 1-year results of a prospective randomized social media trial to determine the effect of tweeting on subsequent citations and nontraditional bibliometrics. METHODS: A total of 112 representative original articles were randomized 1:1 to be tweeted via TSSMN or a control (non-tweeted) group. Measured endpoints included citations at 1 year compared with baseline, as well as article-level metrics (Altmetric score) and Twitter analytics. Independent predictors of citations were identified through univariable and multivariable regression analyses. RESULTS: When compared with control articles, tweeted articles achieved significantly greater increase in Altmetric scores (Tweeted 9.4 ± 5.8 vs Non-tweeted 1.0 ± 1.8, P < .001), Altmetric score percentiles relative to articles of similar age from each respective journal (Tweeted 76.0 ± 9.1 percentile vs Non-tweeted 13.8 ± 22.7 percentile, P < .001), with greater change in citations at 1 year (Tweeted +3.1 ± 2.4 vs Non-Tweeted +0.7 ± 1.3, P < .001). Multivariable analysis showed that independent predictors of citations were randomization to tweeting (odds ratio [OR] 9.50; 95% confidence interval [CI] 3.30-27.35, P < .001), Altmetric score (OR 1.32; 95% CI 1.15-1.50, P < .001), open-access status (OR 1.56; 95% CI 1.21-1.78, P < .001), and exposure to a larger number of Twitter followers as quantified by impressions (OR 1.30, 95% CI 1.10-1.49, P < .001). CONCLUSIONS: One-year follow-up of this TSSMN prospective randomized trial importantly demonstrates that tweeting results in significantly more article citations over time, highlighting the durable scholarly impact of social media activity.

Social Media Improves Cardiothoracic Surgery Literature Dissemination: Results of a Randomized Trial.

BACKGROUND: The Thoracic Surgery Social Media Network (TSSMN) represents a collaborative effort of leading journals in cardiothoracic surgery to highlight publications via social media, specifically Twitter. We conducted a prospective randomized trial to determine the effect of scheduled tweeting on nontraditional bibliometrics of dissemination. METHODS: A total of 112 representative original articles (2017-2018) were selected and randomized 1:1 to an intervention group to be tweeted via TSSMN or a control (non-tweeted) group. Four articles per day were tweeted by TSSMN delegates for 14 days. Primary endpoints included change in article-level metrics (Altmetric) score pre-tweet and post-tweet compared with the control group. Secondary endpoints included change in Twitter analytics day 1 post-tweet and day 7 post-tweet for each article compared with baseline. RESULTS: Tweeting via TSSMN significantly improved article Altmetric scores (pre-tweet 1 vs post-tweet 8; P < .001), Mendeley reads (pre-tweet 1 vs post-tweet 3; P < .001), and Twitter impressions (day 1 post-tweet 1599 vs day 7 post-tweet 2296; P < .001). Subgroup analysis demonstrates that incorporating photos into the tweets trended toward increased link clicks to the full-text article (P = .08) whereas tweeting at 1 pm Eastern Standard Time and 9 pm Eastern Standard Time generated the highest and lowest audience reach (P = .022), respectively. Articles published in adult cardiac surgery achieved the highest change in Altmetric score (P = .028) and Mendeley reads (P = .028), and were more likely to be retweeted (P = .042) than were those published on education, general thoracic surgery, and congenital surgery. CONCLUSIONS: Social media highlights of scholarly literature via TSSMN Twitter activity improves article Altmetric scores, Mendeley reads, and Twitter analytics, with dissemination to a greater audience.

Gender-Specific Molecular and Clinical Features Underlie Malignant Pleural Mesothelioma.

Malignant pleural mesothelioma (MPM) is an aggressive cancer that occurs more frequently in men, but is associated with longer survival in women. Insight into the survival advantage of female patients may advance the molecular understanding of MPM and identify therapeutic interventions that will improve the prognosis for all MPM patients. In this study, we performed whole-genome sequencing of tumor specimens from 10 MPM patients and matched control samples to identify potential driver mutations underlying MPM. We identified molecular differences associated with gender and histology. Specifically, single-nucleotide variants of BAP1 were observed in 21% of cases, with lower mutation rates observed in sarcomatoid MPM (P < 0.001). Chromosome 22q loss was more frequently associated with the epithelioid than that nonepitheliod histology (P = 0.037), whereas CDKN2A deletions occurred more frequently in nonepithelioid subtypes among men (P = 0.021) and were correlated with shorter overall survival for the entire cohort (P = 0.002) and for men (P = 0.012). Furthermore, women were more likely to harbor TP53 mutations (P = 0.004). Novel mutations were found in genes associated with the integrin-linked kinase pathway, including MYH9 and RHOA. Moreover, expression levels of BAP1, MYH9, and RHOA were significantly higher in nonepithelioid tumors, and were associated with significant reduction in survival of the entire cohort and across gender subgroups. Collectively, our findings indicate that diverse mechanisms highly related to gender and histology appear to drive MPM.

Validation of a molecular and pathological model for five-year mortality risk in patients with early stage lung adenocarcinoma.

INTRODUCTION: The aim of this study was to validate a molecular expression signature [cell cycle progression (CCP) score] that identifies patients with a higher risk of cancer-related death after surgical resection of early stage (I-II) lung adenocarcinoma in a large patient cohort and evaluate the effectiveness of combining CCP score and pathological stage for predicting lung cancer mortality. METHODS: Formalin-fixed paraffin-embedded surgical tumor samples from 650 patients diagnosed with stage I and II adenocarcinoma who underwent definitive surgical treatment without adjuvant chemotherapy were analyzed for 31 proliferation genes by quantitative real-time polymerase chain reaction. The prognostic discrimination of the expression score was assessed by Cox proportional hazards analysis using 5-year lung cancer-specific death as primary outcome. RESULTS: The CCP score was a significant predictor of lung cancer-specific mortality above clinical covariates [hazard ratio (HR) = 1.46 per interquartile range (95% confidence interval = 1.12-1.90; p = 0.0050)]. The prognostic score, a combination of CCP score and pathological stage, was a more significant indicator of lung cancer mortality risk than pathological stage in the full cohort (HR = 2.01; p = 2.8 × 10) and in stage I patients (HR = 1.67; p = 0.00027). Using the 85th percentile of the prognostic score as a threshold, there was a significant difference in lung cancer survival between low-risk and high-risk patient groups (p = 3.8 × 10). CONCLUSIONS: This study validates the CCP score and the prognostic score as independent predictors of lung cancer death in patients with early stage lung adenocarcinoma treated with surgery alone. Patients with resected stage I lung adenocarcinoma and a high prognostic score may be candidates for adjuvant therapy to reduce cancer-related mortality.