Purpose: This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95. Methods: We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance. Results: MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation. Conclusion MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Nerve growth factor (NGF) is a neurotrophic factor usually involved in the survival, differentiation, and growth of sensory neurons and nociceptive function. Yet, it has been suggested to play a role in the pathogenesis of osteoarthritis (OA). Previous studies suggested a possible relationship between NGF and OA; however, the underlying mechanisms remain unknown. Therefore, we investigated the impact of NGF in chondrogenesis using human induced pluripotent stem cells (hiPSCs)-derived chondrogenic pellets. To investigate how NGF affects the cartilage tissue, hiPSC-derived chondrogenic pellets were treated with NGF on day 3 of differentiation, expression of chondrogenic, hypertrophic, and fibrotic markers was confirmed. Also, inflammatory cytokine arrays were performed using the culture medium of the NGF treated chondrogenic pellets. As a result, NGF treatment decreased the expression of pro-chondrogenic markers by approximately 2∼4 times, and hypertrophic (pro-osteogenic) markers and fibrotic markers were increased by approximately 3-fold or more in the NGF-treated cartilaginous pellets. In addition, angiogenesis was upregulated by approximately 4-fold or more, bone formation by more than 2-fold, and matrix metalloproteinase induction by more than 2-fold. These inflammatory cytokine array were using the NGF-treated chondrogenic pellet cultured medium.Furthermore, it was confirmed by Western blot to be related to the induction of the glycogen synthase kinase-3 beta (GSK3β) pathway by NGF. In Conclusions, these findings provide valuable insights into the multifaceted role of NGF in cartilage hypertrophy and fibrosis, which might play a critical role in OA progression.

Purpose: This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95. Methods: We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance. Results: MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation. Conclusion MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Purpose: This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95. Methods: We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance. Results: MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation. Conclusion MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Nerve growth factor (NGF) is a neurotrophic factor usually involved in the survival, differentiation, and growth of sensory neurons and nociceptive function. Yet, it has been suggested to play a role in the pathogenesis of osteoarthritis (OA). Previous studies suggested a possible relationship between NGF and OA; however, the underlying mechanisms remain unknown. Therefore, we investigated the impact of NGF in chondrogenesis using human induced pluripotent stem cells (hiPSCs)-derived chondrogenic pellets. To investigate how NGF affects the cartilage tissue, hiPSC-derived chondrogenic pellets were treated with NGF on day 3 of differentiation, expression of chondrogenic, hypertrophic, and fibrotic markers was confirmed. Also, inflammatory cytokine arrays were performed using the culture medium of the NGF treated chondrogenic pellets. As a result, NGF treatment decreased the expression of pro-chondrogenic markers by approximately 2∼4 times, and hypertrophic (pro-osteogenic) markers and fibrotic markers were increased by approximately 3-fold or more in the NGF-treated cartilaginous pellets. In addition, angiogenesis was upregulated by approximately 4-fold or more, bone formation by more than 2-fold, and matrix metalloproteinase induction by more than 2-fold. These inflammatory cytokine array were using the NGF-treated chondrogenic pellet cultured medium.Furthermore, it was confirmed by Western blot to be related to the induction of the glycogen synthase kinase-3 beta (GSK3β) pathway by NGF. In Conclusions, these findings provide valuable insights into the multifaceted role of NGF in cartilage hypertrophy and fibrosis, which might play a critical role in OA progression.

Purpose: This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95. Methods: We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance. Results: MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation. Conclusion MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Nerve growth factor (NGF) is a neurotrophic factor usually involved in the survival, differentiation, and growth of sensory neurons and nociceptive function. Yet, it has been suggested to play a role in the pathogenesis of osteoarthritis (OA). Previous studies suggested a possible relationship between NGF and OA; however, the underlying mechanisms remain unknown. Therefore, we investigated the impact of NGF in chondrogenesis using human induced pluripotent stem cells (hiPSCs)-derived chondrogenic pellets. To investigate how NGF affects the cartilage tissue, hiPSC-derived chondrogenic pellets were treated with NGF on day 3 of differentiation, expression of chondrogenic, hypertrophic, and fibrotic markers was confirmed. Also, inflammatory cytokine arrays were performed using the culture medium of the NGF treated chondrogenic pellets. As a result, NGF treatment decreased the expression of pro-chondrogenic markers by approximately 2∼4 times, and hypertrophic (pro-osteogenic) markers and fibrotic markers were increased by approximately 3-fold or more in the NGF-treated cartilaginous pellets. In addition, angiogenesis was upregulated by approximately 4-fold or more, bone formation by more than 2-fold, and matrix metalloproteinase induction by more than 2-fold. These inflammatory cytokine array were using the NGF-treated chondrogenic pellet cultured medium.Furthermore, it was confirmed by Western blot to be related to the induction of the glycogen synthase kinase-3 beta (GSK3β) pathway by NGF. In Conclusions, these findings provide valuable insights into the multifaceted role of NGF in cartilage hypertrophy and fibrosis, which might play a critical role in OA progression.

Purpose: This study compares 3 deep learning models (UNet, TransUNet, and MIST) for left atrium (LA) segmentation of cardiac computed tomography (CT) images from patients with congenital heart disease (CHD). It investigates how architectural variations in the MIST model, such as spatial squeeze-and-excitation attention, impact Dice score and HD95. Methods: We analyzed 108 publicly available, de-identified CT volumes from the ImageCHD dataset. Volumes underwent resampling, intensity normalization, and data augmentation. UNet, TransUNet, and MIST models were trained using 80% of 97 cases, with the remaining 20% employed for validation. Eleven cases were reserved for testing. Performance was evaluated using the Dice score (measuring overlap accuracy) and HD95 (reflecting boundary accuracy). Statistical comparisons were performed via one-way repeated measures analysis of variance. Results: MIST achieved the highest mean Dice score (0.74; 95% confidence interval, 0.67–0.81), significantly outperforming TransUNet (0.53; P<0.001) and UNet (0.49; P<0.001). Regarding HD95, TransUNet (9.09 mm) and MIST (5.77 mm) similarly outperformed UNet (27.49 mm; P<0.0001). In ablation experiments, the inclusion of spatial attention did not further enhance the MIST model’s performance, suggesting redundancy with existing attention mechanisms. However, the integration of multi-scale features and refined skip connections consistently improved segmentation accuracy and boundary delineation. Conclusion MIST demonstrated superior LA segmentation, highlighting the benefits of its integrated multi-scale features and optimized architecture. Nevertheless, its computational overhead complicates practical clinical deployment. Our findings underscore the value of advanced hybrid models in cardiac imaging, providing improved reliability for CHD evaluation. Future studies should balance segmentation accuracy with feasible clinical implementation.

Background/Aims: We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user’s experience and polyp characteristics. Methods: We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed. Results: The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively). Conclusions CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user’s experience, particularly for challenging lesions.

Background/Aims: Smoking is considered a risk factor for the development of nonalcoholic fatty liver disease (NAFLD). However, the association of a weight change after a change in smoking status and the risk of NAFLD remains undetermined. Methods: This study used the Korean National Health Insurance Service-National Sample Cohort. Based on the first (2009 to 2010) and second (2011 to 2012) health examination periods, 139,180 adults aged at least 40 years were divided into nonsmoking, smoking cessation, smoking relapse, and sustained smoking groups. NAFLD was operationally defined using the fatty liver index. The adjusted odds ratio (aOR) and 95% confidence interval (CI) were calculated using multivariable-adjusted logistic regression. Results: Compared to nonsmoking with no body mass index (BMI) change, the risk of NAFLD was significantly increased among subjects with BMI gain and nonsmoking (aOR, 4.07; 95% CI, 3.77 to 4.39), smoking cessation (aOR, 5.52; 95% CI, 4.12 to 7.40), smoking relapse (aOR, 7.51; 95% CI, 4.81 to 11.72), and sustained smoking (aOR, 6.65; 95% CI, 5.33 to 8.29), whereas the risk of NAFLD was reduced among participants with BMI loss in all smoking status groups. In addition, smoking cessation (aOR, 1.76; 95% CI, 1.35 to 2.29) and sustained smoking (aOR, 1.64; 95% CI, 1.39 to 1.94) were associated with higher risk of NAFLD among participants with no BMI change.The liver enzyme levels were higher among participants with smoking cessation and BMI gain. Conclusions Monitoring and management of weight change after a change in smoking status may be a promising approach to reducing NAFLD.