RESUMO
Flexible bronchoscopy has revolutionized respiratory disease diagnosis. It offers direct visualization and detection of airway abnormalities, including lung cancer lesions. Accurate identification of airway lesions during flexible bronchoscopy plays an important role in the lung cancer diagnosis. The application of artificial intelligence (AI) aims to support physicians in recognizing anatomical landmarks and lung cancer lesions within bronchoscopic imagery. This work described the development of BM-BronchoLC, a rich bronchoscopy dataset encompassing 106 lung cancer and 102 non-lung cancer patients. The dataset incorporates detailed localization and categorical annotations for both anatomical landmarks and lesions, meticulously conducted by senior doctors at Bach Mai Hospital, Vietnam. To assess the dataset's quality, we evaluate two prevalent AI backbone models, namely UNet++ and ESFPNet, on the image segmentation and classification tasks with single-task and multi-task learning paradigms. We present BM-BronchoLC as a reference dataset in developing AI models to assist diagnostic accuracy for anatomical landmarks and lung cancer lesions in bronchoscopy data.
Assuntos
Broncoscopia , Neoplasias Pulmonares , Humanos , Inteligência Artificial , Neoplasias Pulmonares/diagnóstico por imagem , Tórax/diagnóstico por imagem , Pontos de Referência Anatômicos/diagnóstico por imagemRESUMO
BACKGROUND: As a method to acknowledge the devastating health and economic impacts of tobacco usage worldwide, telephone-based tobacco cessation counseling services have emerged as a potential tool to aid people in their quitting process. This study explores the satisfaction of smokers who use the QUITLINE service and factors associated with their quit attempts and cessation. METHODS: A cross-sectional survey of 110 participants was conducted from June to July 2016 at the Respiratory Center at Bach Mai Hospital, Hanoi, Vietnam. Multivariate logistic regression was used, and it was found that the percentage of people quitting smoking increased after using the service. RESULTS: In total, 65.5% of participants were completely satisfied with the counseling service. The mean score of staff/s capacity/responsiveness, motivation, and service convenience were 4.37 ± 0.78, 4.30 ± 0.81, and 4.27 ± 0.66, respectively. The smoking relapse rate was relatively high at 58.3%, which mainly resulted from cravings and busy work (26.2% and 14.3%, respectively). A higher satisfaction score in "Staffs' capacity and responsiveness" was negatively associated with "ever tried to quit smoking in consecutive 24 h" and actually quit smoking after receiving counseling. Meanwhile, a higher score in the "Motivation" domain was positively associated with both quit attempt indicators as well as actually quitting smoking after receiving counseling (OR = 9.48; 95%CI = 2.27; 39.57). CONCLUSIONS: These results suggest that it is crucial for decision makers to place more focus on countermeasures for smoking relapse and to strengthen the capacity of staff, especially in motivating clients. Interventions should also be maintained throughout a long period of time to prevent relapse.