Purpose: Deep learning–based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. Methods: The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. Results: The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. Conclusion S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Purpose: Smoking is causally related to alcohol use disorder. Although polycyclic aromatic hydrocarbons (PAHs) are major neurotoxic pollutants in tobacco smoke, evidence is lacking on the role of PAHs in the relationship between smoking and alcohol use disorder. This study investigated the types of PAHs associated with smoking and whether exposure to those PAHs mediated the effect of smoking on alcohol use disorder. Materials and Methods: A total of 968 male firefighters were analyzed. Smoking history and cumulative pack-years were obtained using self-reported questionnaires. Alcohol use disorder was defined using the Alcohol Use Disorder Identification Test.PAH exposure was assessed by urinary metabolites. Regression analyses were performed between exposure (smoking), outcome (alcohol use disorder), and mediator (PAH metabolites) variables. A mediation analysis was performed to test the indirect effect of PAH metabolites on the association between smoking and alcohol use disorder. All analyses were repeated for 770 participants who were followed up after 2 years, while alcohol use disorder was redefined from follow-up data ensuring the temporal sequence of the variables. Results: Both 2-naphthol [β=0.78, 95% confidence interval (CI): 0.59–0.98] and 2-hydroxyfluorene (β=0.69, 95% CI: 0.56–0.82) were associated with smoking history. Furthermore, 2-naphthol and 2-hydroxyfluorene mediated the associations of smoking history (proportion mediated: 14.2%, 23.6% respectively) or cumulative pack-years (proportion mediated: 14.4%, 25.4% respectively) with alcohol use disorder. The results were consistent in longitudinal settings. Conclusion Exposure to PAHs mediated the association between tobacco smoking and alcohol use disorder. PAH exposure from tobacco may increase the risk of addictive disorders.

Purpose: Deep learning–based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. Methods: The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. Results: The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. Conclusion S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Purpose: Smoking is causally related to alcohol use disorder. Although polycyclic aromatic hydrocarbons (PAHs) are major neurotoxic pollutants in tobacco smoke, evidence is lacking on the role of PAHs in the relationship between smoking and alcohol use disorder. This study investigated the types of PAHs associated with smoking and whether exposure to those PAHs mediated the effect of smoking on alcohol use disorder. Materials and Methods: A total of 968 male firefighters were analyzed. Smoking history and cumulative pack-years were obtained using self-reported questionnaires. Alcohol use disorder was defined using the Alcohol Use Disorder Identification Test.PAH exposure was assessed by urinary metabolites. Regression analyses were performed between exposure (smoking), outcome (alcohol use disorder), and mediator (PAH metabolites) variables. A mediation analysis was performed to test the indirect effect of PAH metabolites on the association between smoking and alcohol use disorder. All analyses were repeated for 770 participants who were followed up after 2 years, while alcohol use disorder was redefined from follow-up data ensuring the temporal sequence of the variables. Results: Both 2-naphthol [β=0.78, 95% confidence interval (CI): 0.59–0.98] and 2-hydroxyfluorene (β=0.69, 95% CI: 0.56–0.82) were associated with smoking history. Furthermore, 2-naphthol and 2-hydroxyfluorene mediated the associations of smoking history (proportion mediated: 14.2%, 23.6% respectively) or cumulative pack-years (proportion mediated: 14.4%, 25.4% respectively) with alcohol use disorder. The results were consistent in longitudinal settings. Conclusion Exposure to PAHs mediated the association between tobacco smoking and alcohol use disorder. PAH exposure from tobacco may increase the risk of addictive disorders.

Purpose: Deep learning–based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. Methods: The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. Results: The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. Conclusion S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Purpose: Smoking is causally related to alcohol use disorder. Although polycyclic aromatic hydrocarbons (PAHs) are major neurotoxic pollutants in tobacco smoke, evidence is lacking on the role of PAHs in the relationship between smoking and alcohol use disorder. This study investigated the types of PAHs associated with smoking and whether exposure to those PAHs mediated the effect of smoking on alcohol use disorder. Materials and Methods: A total of 968 male firefighters were analyzed. Smoking history and cumulative pack-years were obtained using self-reported questionnaires. Alcohol use disorder was defined using the Alcohol Use Disorder Identification Test.PAH exposure was assessed by urinary metabolites. Regression analyses were performed between exposure (smoking), outcome (alcohol use disorder), and mediator (PAH metabolites) variables. A mediation analysis was performed to test the indirect effect of PAH metabolites on the association between smoking and alcohol use disorder. All analyses were repeated for 770 participants who were followed up after 2 years, while alcohol use disorder was redefined from follow-up data ensuring the temporal sequence of the variables. Results: Both 2-naphthol [β=0.78, 95% confidence interval (CI): 0.59–0.98] and 2-hydroxyfluorene (β=0.69, 95% CI: 0.56–0.82) were associated with smoking history. Furthermore, 2-naphthol and 2-hydroxyfluorene mediated the associations of smoking history (proportion mediated: 14.2%, 23.6% respectively) or cumulative pack-years (proportion mediated: 14.4%, 25.4% respectively) with alcohol use disorder. The results were consistent in longitudinal settings. Conclusion Exposure to PAHs mediated the association between tobacco smoking and alcohol use disorder. PAH exposure from tobacco may increase the risk of addictive disorders.

Purpose: Deep learning–based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. Methods: The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. Results: The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. Conclusion S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Purpose: Smoking is causally related to alcohol use disorder. Although polycyclic aromatic hydrocarbons (PAHs) are major neurotoxic pollutants in tobacco smoke, evidence is lacking on the role of PAHs in the relationship between smoking and alcohol use disorder. This study investigated the types of PAHs associated with smoking and whether exposure to those PAHs mediated the effect of smoking on alcohol use disorder. Materials and Methods: A total of 968 male firefighters were analyzed. Smoking history and cumulative pack-years were obtained using self-reported questionnaires. Alcohol use disorder was defined using the Alcohol Use Disorder Identification Test.PAH exposure was assessed by urinary metabolites. Regression analyses were performed between exposure (smoking), outcome (alcohol use disorder), and mediator (PAH metabolites) variables. A mediation analysis was performed to test the indirect effect of PAH metabolites on the association between smoking and alcohol use disorder. All analyses were repeated for 770 participants who were followed up after 2 years, while alcohol use disorder was redefined from follow-up data ensuring the temporal sequence of the variables. Results: Both 2-naphthol [β=0.78, 95% confidence interval (CI): 0.59–0.98] and 2-hydroxyfluorene (β=0.69, 95% CI: 0.56–0.82) were associated with smoking history. Furthermore, 2-naphthol and 2-hydroxyfluorene mediated the associations of smoking history (proportion mediated: 14.2%, 23.6% respectively) or cumulative pack-years (proportion mediated: 14.4%, 25.4% respectively) with alcohol use disorder. The results were consistent in longitudinal settings. Conclusion Exposure to PAHs mediated the association between tobacco smoking and alcohol use disorder. PAH exposure from tobacco may increase the risk of addictive disorders.

Purpose: Deep learning–based image enhancement has significant potential in the field of ultrasound image processing, as it can accurately model complicated nonlinear artifacts and noise, such as ultrasonic speckle patterns. However, training deep learning networks to acquire reference images that are clean and free of noise presents significant challenges. This study introduces an unsupervised deep learning framework, termed speckle-to-speckle (S2S), designed for speckle and noise suppression. This framework can complete its training without the need for clean (speckle-free) reference images. Methods: The proposed network leverages statistical reasoning for the mutual training of two in vivo images, each with distinct speckle patterns and noise. It then infers speckle- and noise-free images without needing clean reference images. This approach significantly reduces the time, cost, and effort experts need to invest in annotating reference images manually. Results: The experimental results demonstrated that the proposed approach outperformed existing techniques in terms of the signal-to-noise ratio, contrast-to-noise ratio, structural similarity index, edge preservation index, and processing time (up to 86 times faster). It also performed excellently on images obtained from ultrasound scanners other than the ones used in this work. Conclusion S2S demonstrates the potential of employing an unsupervised learning-based technique in medical imaging applications, where acquiring a ground truth reference is challenging.

Purpose: Smoking is causally related to alcohol use disorder. Although polycyclic aromatic hydrocarbons (PAHs) are major neurotoxic pollutants in tobacco smoke, evidence is lacking on the role of PAHs in the relationship between smoking and alcohol use disorder. This study investigated the types of PAHs associated with smoking and whether exposure to those PAHs mediated the effect of smoking on alcohol use disorder. Materials and Methods: A total of 968 male firefighters were analyzed. Smoking history and cumulative pack-years were obtained using self-reported questionnaires. Alcohol use disorder was defined using the Alcohol Use Disorder Identification Test.PAH exposure was assessed by urinary metabolites. Regression analyses were performed between exposure (smoking), outcome (alcohol use disorder), and mediator (PAH metabolites) variables. A mediation analysis was performed to test the indirect effect of PAH metabolites on the association between smoking and alcohol use disorder. All analyses were repeated for 770 participants who were followed up after 2 years, while alcohol use disorder was redefined from follow-up data ensuring the temporal sequence of the variables. Results: Both 2-naphthol [β=0.78, 95% confidence interval (CI): 0.59–0.98] and 2-hydroxyfluorene (β=0.69, 95% CI: 0.56–0.82) were associated with smoking history. Furthermore, 2-naphthol and 2-hydroxyfluorene mediated the associations of smoking history (proportion mediated: 14.2%, 23.6% respectively) or cumulative pack-years (proportion mediated: 14.4%, 25.4% respectively) with alcohol use disorder. The results were consistent in longitudinal settings. Conclusion Exposure to PAHs mediated the association between tobacco smoking and alcohol use disorder. PAH exposure from tobacco may increase the risk of addictive disorders.