End-to-End Train Horn Detection for Railway Transit Safety.

The train horn sound is an active audible warning signal used for warning commuters and railway employees of the oncoming train(s), assuring a smooth operation and traffic safety, especially at barrier-free crossings. This work studies deep learning-based approaches to develop a system providing the early detection of train arrival based on the recognition of train horn sounds from the traffic soundscape. A custom dataset of train horn sounds, car horn sounds, and traffic noises is developed to conduct experiments and analysis. We propose a novel two-stream end-to-end CNN model (i.e., THD-RawNet), which combines two approaches of feature extraction from raw audio waveforms, for audio classification in train horn detection (THD). Besides a stream with a sequential one-dimensional CNN (1D-CNN) as in existing sound classification works, we propose to utilize multiple 1D-CNN branches to process raw waves in different temporal resolutions to extract an image-like representation for the 2D-CNN classification part. Our experiment results and comparative analysis have proved the effectiveness of the proposed two-stream network and the method of combining features extracted in multiple temporal resolutions. The THD-RawNet obtained better accuracies and robustness compared to those of baseline models trained on either raw audio or handcrafted features, in which at the input size of one second the network yielded an accuracy of 95.11% for testing data in normal traffic conditions and remained above a 93% accuracy for the considerable noisy condition of-10 dB SNR. The proposed THD system can be integrated into the smart railway crossing systems, private cars, and self-driving cars to improve railway transit safety.

Pathogenic Variant Profile of Hereditary Cancer Syndromes in a Vietnamese Cohort.

BACKGROUND: Hereditary cancer syndromes (HCS) are responsible for 5-10% of cancer cases. Genetic testing to identify pathogenic variants associated with cancer predisposition has not been routinely available in Vietnam. Consequently, the prevalence and genetic landscape of HCS remain unknown. METHODS: 1165 Vietnamese individuals enrolled in genetic testing at our laboratory in 2020. We performed analysis of germline mutations in 17 high- and moderate- penetrance genes associated with HCS by next generation sequencing. RESULTS: A total of 41 pathogenic variants in 11 genes were detected in 3.2% individuals. The carrier frequency was 4.2% in people with family or personal history of cancer and 2.6% in those without history. The percentage of mutation carriers for hereditary colorectal cancer syndromes was 1.3% and for hereditary breast and ovarian cancer syndrome was 1.6%. BRCA1 and BRCA2 mutations were the most prevalent with the positive rate of 1.3% in the general cohort and 5.1% in breast or ovarian cancer patients. Most of BRCA1 mutations located at the BRCA C-terminus domains and the top recurrent mutation was NM_007294.3:c.5251C>T (p.Arg1751Ter). One novel variant NM_000038.6(APC):c.6665C>A (p.Pro2222His) was found in a breast cancer patient with a strong family history of cancer. A case study of hereditary cancer syndrome was illustrated to highlight the importance of genetic testing. CONCLUSION: This is the first largest analysis of carrier frequency and mutation spectrum of HCS in Vietnam. The findings demonstrate the clinical significance of multigene panel testing to identify carriers and their at-risk relatives for better cancer surveillance and management strategies.

Estimating the incidence of malignant mesothelioma in Vietnam: a pilot descriptive cancer registration study.

INTRODUCTION: Global asbestos consumption has shifted toward lower income countries, particularly in the Asian region including Vietnam where asbestos and asbestos-containing products have been imported since the late 1960s. METHODS: This pilot descriptive epidemiological study aimed to provide contemporary estimates of malignant mesothelioma incidence (histological subtype M9050/3; ICD-O-3) by gender and age group as recorded across nine cancer registries in Vietnam. RESULTS: We identified 148 incident cases of malignant mesothelioma during 1987-2013. The majority of cases were recorded in the Hanoi region (n = 93) and were aged 55 years or older (n = 96). DISCUSSION: By carefully reviewing existing cancer registry records in Vietnam, we identified a larger number of malignant mesothelioma cases than previously estimated. We recommend the use of cancer registry data in tracking future asbestos-related disease in Vietnam.