Role of chest radiographs in early lung cancer detection

UniChest: Conquer-and-Divide Pre-Training for Multi-Source Chest X-Ray Classification

Vision-Language Pre-training (VLP) that utilizes the multi-modal information to promote the training efficiency and effectiveness, has achieved great success in vision recognition of natural domains and shown promise in medical imaging diagnosis for the Chest X-Rays (CXRs). However, current works mainly pay attention to the exploration on single dataset of CXRs, which locks the potential of this powerful paradigm on larger hybrid of multi-source CXRs datasets. We identify that although blending samples from the diverse sources offers the advantages to improve the model generalization, it is still challenging to maintain the consistent superiority for the task of each source due to the existing heterogeneity among sources. To handle this dilemma, we design a Conquer-and-Divide pre-training framework, termed as UniChest, aiming to make full use of the collaboration benefit of multiple sources of CXRs while reducing the negative influence of the source heterogeneity. Specially, the "Conquer" stage in UniChest encourages the model to sufficiently capture multi-source common patterns, and the "Divide" stage helps squeeze personalized patterns into different small experts (query networks). We conduct thorough experiments on many benchmarks, e.g., ChestX-ray14, CheXpert, Vindr-CXR, Shenzhen, Open-I and SIIM-ACR Pneumothorax, verifying the effectiveness of UniChest over a range of baselines, and release our codes and pre-training models at https://github.com/Elfenreigen/UniChest.

Carboxypeptidase N2 as a Novel Diagnostic and Prognostic Biomarker for Lung Adenocarcinoma

Carboxypeptidase N2 (CPN2) is a plasma metallo-protease that cleaves basic amino acids from the C-terminal of peptides and proteins. Emerging evidence showed that carboxypeptidases perform many diverse functions in the body and play key roles in tumorigenesis. However, the clinical significance and biological functions of CPN2 in lung adenocarcinoma remain unclear. Our study aimed to explore the potential role and functions of CPN2 in lung adenocarcinoma. The results showed that the transcription level of CPN2 was significantly increased in the tumor tissues of lung adenocarcinoma patients compared to the adjacent normal tissues in The Cancer Genome Atlas cohort (P < 0.05). The survival plots showed that the overall survival of patients with a high expression of CPN2 was significantly lower than that of patients with a low expression of CPN2, both in the Kaplan-Meier database and the clinical sample cohort (P < 0.05). The tissue microarray analysis found that CPN2 protein expression was significantly positively correlated with node status and tumor stage as well as tumor malignancy (P < 0.05). Further univariate and multivariate Cox regression analyses showed that CPN2 may act as an independent prognostic factor in patients with lung adenocarcinoma (P < 0.05). In addition, the analysis of co-expression genes from LinkedOmics showed that CPN2 was positively associated with many genes of fibrillar collagen family members and the PI3K-Akt pathway. The gene set enrichment analysis showed that a higher expression of CPN2 may participate in mTOR, TGF-BETA, NOTCH, TOLL-like-receptor, WNT, and MAPK signaling pathway in lung adenocarcinoma. Notably, the knockdown of CPN2 significantly inhibited the ability of cell proliferation, clone formation, invasion, and migration. Our findings suggested that the upregulation of CPN2 is associated with a worse clinical outcome in lung adenocarcinoma and cancer-related pathways, which laid the foundation for further research on CPN2 during carcinogenesis.

Has COVID-19 Affected Cancer Screening Programs? A Systematic Review

Background

Health care services across the world have been enormously affected by the onset of the coronavirus disease 2019 (COVID-19). Services in oncology have been curtailed because medical services have been focused on preventing the spread of the virus and maximizing the number of available hospital beds. The present study was designed to investigate the impact of COVID-19 on cancer screening.

Methods

Databases such as Medline, Web of Science Core Collection (Indexes = SCI-EXPANDED, SSCI, A & HCI Timespan) and Scopus were searched comprehensively for articles published until January 2021. The keywords used were COVID-19 and cancer screening, Articles dealing with cancer screening in the COVID-19 pandemic were included in the review.

Results

The review comprised 17 publications. The impact of COVID-19 was categorized into four dimensions: a significant decline in cancer screening and pathology samples, the cancer diagnosis rate, an increase in advanced cancers, mortality rate and years of life lost (YLLs).

Conclusion

Cancer screening programs have been clearly interrupted since the onset of the COVID-19 disease. The anticipated outcomes include delayed diagnosis and marked increases in the numbers of avoidable cancer deaths. Urgent policy interventions are needed to handle the backlog of routine diagnostic services and minimize the harmful effects of the COVID-19 pandemic on cancer patients.