-
PloS One 2024In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and...
BACKGROUND
In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and advance disease classification. Among established preprocessing techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving segmentation algorithms across various modalities, such as X-rays and CT. However, there remains a demand for improved contrast enhancement methods considering the heterogeneity of datasets and the various contrasts across different anatomic structures.
METHOD
This study proposes a novel preprocessing technique, ps-KDE, to investigate its impact on deep learning algorithms to segment major organs in posterior-anterior chest X-rays. Ps-KDE augments image contrast by substituting pixel values based on their normalized frequency across all images. We evaluate our approach on a U-Net architecture with ResNet34 backbone pre-trained on ImageNet. Five separate models are trained to segment the heart, left lung, right lung, left clavicle, and right clavicle.
RESULTS
The model trained to segment the left lung using ps-KDE achieved a Dice score of 0.780 (SD = 0.13), while that of trained on CLAHE achieved a Dice score of 0.717 (SD = 0.19), p<0.01. ps-KDE also appears to be more robust as CLAHE-based models misclassified right lungs in select test images for the left lung model. The algorithm for performing ps-KDE is available at https://github.com/wyc79/ps-KDE.
DISCUSSION
Our results suggest that ps-KDE offers advantages over current preprocessing techniques when segmenting certain lung regions. This could be beneficial in subsequent analyses such as disease classification and risk stratification.
Topics: Humans; Lung; Algorithms; Deep Learning; Semantics; Radiography, Thoracic; Tomography, X-Ray Computed; Image Processing, Computer-Assisted; Clavicle
PubMed: 38913621
DOI: 10.1371/journal.pone.0299623 -
Resuscitation Plus Sep 2024Emergency Medical Service (EMS) providers are essential for out-of-hospital cardiac arrest (OHCA) survival, however implementing high-performance CPR guidelines in...
INTRODUCTION
Emergency Medical Service (EMS) providers are essential for out-of-hospital cardiac arrest (OHCA) survival, however implementing high-performance CPR guidelines in developing EMS settings presents challenges. This study assessed the impact of Continuous Quality Improvement (CQI) initiatives on OHCA outcomes in a hospital-based EMS agency in Bangkok, Thailand.
METHODS
A before-and-after study design was utilized, utilizing data from a prospective OHCA registry spanning 2019 to 2023. CQI interventions included low-dose high-frequency training in advanced airway management, high-performance CPR, and post-debriefing with video recording (VDO). Data collection encompassed patient characteristics, EMS management, and survival outcomes. Quality CPR metrics were assessed using the mobile defibrillator and CPR code review software. Statistical analyses compared outcomes between the pre-intervention period in 2019 and the post-full CQI implementation period in 2023.
RESULTS
Among enrolled OHCA patients, with 88 cases occurring in 2019 and 91 cases in 2023. The bystander CPR rate was similar between both groups (47.73% in 2023 vs 53.85%, = 0.413). In 2023, there was a significantly higher rate of prehospital intubation (93.40% vs 70.45%, < 0.001) compared to 2019. Prehospital return of spontaneous circulation (ROSC) improved from 30.68% to 49.45% ( = 0.012), with an adjusted odds ratio (aOR) of 2.16 (95% CI: 1.14-4.07). Survival to discharge increased significantly from 2.27% in 2019 to 7.69% in 2023 ( = 0.27), with an aOR of 3.81 (95% CI: 0.46-31.79).
CONCLUSION
Tailored CQI initiatives in a developing EMS setting were significantly associated with improved prehospital ROSC but showed an insignificant increase in survival to discharge.
PubMed: 38912534
DOI: 10.1016/j.resplu.2024.100683 -
Frontiers in Public Health 2024Pre-frailty represents an ideal window of opportunity to potentially prevent frailty and disability. Early and effective interventions to delay or reverse pre-frailty... (Randomized Controlled Trial)
Randomized Controlled Trial
Effectiveness of a mHealth platform-based lifestyle integrated multicomponent exercise () program to reverse pre-frailty in community-dwelling older adults: a randomized controlled trial study protocol.
BACKGROUND
Pre-frailty represents an ideal window of opportunity to potentially prevent frailty and disability. Early and effective interventions to delay or reverse pre-frailty are public health imperative. The present trial aims to evaluate the effectiveness and underlying mechanisms of mobile health (mHealth) platform-supported lifestyle-integrated multicomponent exercise () to reverse pre-frailty in community-dwelling older adults.
METHODS
This is an open-label, prospective, two-arm parallel randomized controlled trial with allocation concealment and outcome assessment blinding. We aim to recruit 140 pre-frail community-dwelling older adults who will be randomized into two groups. The control group will receive a health education program, while the intervention group will receive training as planned for 1 year. The proportion of pre-frailty, functional performance (muscular strength, aerobic capacity, flexibility, and balance), body composition, and physical activity will be measured at pre-intervention, post-intervention, and 12-month follow-up. Inflammatory biomarkers will also be collected to explore the underlying mechanisms.
DISCUSSION
This is the first study to evaluate the effects of a novel digital lifestyle-integrated multicomponent exercise for pre-frail older people. The results of this trial will provide much-needed information on the short-and long-term effects of based on functional performance and body composition. Meanwhile, inflammatory biomarkers and physical activity levels will be used to elucidate the underlying mechanisms of . The findings from this trial will provide evidence for the effectiveness of lifestyle multicomponent exercise intervention supported by the mHealth platform that may reverse or even halt the onset of frailty.
CLINICAL TRIAL REGISTRATION
https://www.chictr.org.cn/showproj.html?proj=176477, identifier ChiCTR2200063431.
Topics: Humans; Aged; Independent Living; Male; Female; Telemedicine; Prospective Studies; Exercise; Frailty; Frail Elderly; Life Style; Exercise Therapy; Aged, 80 and over
PubMed: 38912262
DOI: 10.3389/fpubh.2024.1389297 -
Perspectives on Medical Education 2024Medical education has acknowledged the impact of structural societal factors on health, prompting the need for curricula seeking to eliminate health inequities upstream...
PROBLEM & BACKGROUND
Medical education has acknowledged the impact of structural societal factors on health, prompting the need for curricula seeking to eliminate health inequities upstream while simultaneously caring for downstream effects of existing inequities. The Keck School of Medicine of USC (KSOM) implemented one such comprehensive curriculum, Health Justice and Systems of Care (HJSC), integrating health systems science, structural competency, and service-learning in a required course spanning the pre-clerkship and clerkship phases with an optional post clerkship elective.
APPROACH
The HJSC course addresses topics including racism in medicine, health inequities, and health systems science. Using transformative learning theory, it fosters critical consciousness and structural competency. Assessments include case analyses, reflections, team-based learning sessions, and group projects related to social justice in healthcare. The program aims to instill cultural humility and practical application, fostering a holistic approach to medical education that implores physicians to become advocates for health justice.
OUTCOMES OF THE INNOVATION
Feedback from students indicated generally positive perceptions of the curriculum. Students provided overall positive comments about discussions with guest speakers. However, students expressed a desire for more concrete examples of how health inequities can be remedied. Some found small-group activities less engaging. Other challenges included providing students of different readiness levels with tailored experiences and seamlessly integrating HJSC content within basic and clinical sciences courses.
CRITICAL REFLECTION
Next steps include continuing to integrate content into the science curriculum and clerkships, improving opportunities for meaningful student interactions, and enhancing faculty development to address health justice concerns in clinical settings.
Topics: Humans; Curriculum; Social Justice; Students, Medical; Delivery of Health Care; Clinical Clerkship
PubMed: 38912167
DOI: 10.5334/pme.1325 -
Psychology Research and Behavior... 2024Resilience is considered as a protective factor that can assist individuals to reduce post-traumatic stress reactions. In recent years, armies in many countries have... (Review)
Review
PURPOSE
Resilience is considered as a protective factor that can assist individuals to reduce post-traumatic stress reactions. In recent years, armies in many countries have widely implemented resilience training programs before deployment to prevent or reduce post-deployment combat stress reactions. Therefore, this study aims to review what is known about resilience interventions for military personnel in pre deployment.
METHODS
Based on Arskey and O'Malley's framework, a scoping review was completed. This review was performed through searching databases including PubMed, Embase, Web of Science, Medline and the Cochrane Library, and screening literature to extract data, finally summarizing the findings.
RESULTS
A total of 25 studies focusing on resilience interventions for military personnel in pre deployment were involved and analyzed using intervention approaches, outcome measures, intervention effects, and so on.
CONCLUSION
Based on the existing evidence in this review, it is cautiously believed that the resilience intervention program for military personnel before deployment is effective. However, there is no single effective best method even the same type intervention can make different effects in different situations and populations. Therefore, the population differences and context should be fully considered in constructing and implementing program to build military personnel resilience.
PubMed: 38912160
DOI: 10.2147/PRBM.S459220 -
Frontiers in Oncology 2024
PubMed: 38912056
DOI: 10.3389/fonc.2024.1436077 -
Physics and Imaging in Radiation... Apr 2024Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL)...
BACKGROUND AND PURPOSE
Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features.
METHODS AND MATERIALS
We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient and . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing.
RESULTS
Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC ( ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16, =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( =0) on the test cohort. Failure detection could generate precision ( ), recall ( ), F1-score ( ), and accuracy ( ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values.
CONCLUSIONS
Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.
PubMed: 38912007
DOI: 10.1016/j.phro.2024.100578 -
Revista Brasileira de Ortopedia Jun 2024Complex regional pain syndrome (CRPS) requires further understanding. Thus, the present study aimed to analyze if pre- and intraoperative factors may be related to...
Complex regional pain syndrome (CRPS) requires further understanding. Thus, the present study aimed to analyze if pre- and intraoperative factors may be related to the development of CRPS in the postoperative period. We reviewed 1,183 medical records of patients undergoing forearm and hand surgeries from 2015 to 2021. The data of interest, that is, diagnosis, incisions, synthesis material, and anesthesia, were collected, tabulated, and statistically analyzed, with subsequent calculation of the odds ratios. Most patients were female, aged between 30 and 59 years, and sought the service electively (67% of the cases). The diagnoses included soft tissue trauma (43%), bone trauma (31.6%), and compressive syndromes (25.5%). During this period, 45 (3.8%) subjects developed CRPS. The statistical analysis showed that the chance of developing CRPS is twice as high in patients with compressive syndrome, especially carpal tunnel syndrome (CTS), which represented most surgeries performed in our service (24%). Two or more incisions occurred in 7.6% of the cases, which tripled the chance of developing postoperative CRPS. Gender, age, use pf synthetic material, type of anesthesia type did not statistically increase the risk of developing postoperative CRPS. In short, the incidence of CRPS is low; however, it is critical to know and recognize the risk factors for prevention and active screening in the postoperative period.
PubMed: 38911893
DOI: 10.1055/s-0044-1785659 -
Frontiers in Immunology 2024Anti-rods and rings (anti-RR) antibodies have recently been described as a cytoplasmic pattern in IIF-based screening of autoantibodies on HEp-2 cells and ICAP has named...
INTRODUCTION
Anti-rods and rings (anti-RR) antibodies have recently been described as a cytoplasmic pattern in IIF-based screening of autoantibodies on HEp-2 cells and ICAP has named it as AC-23. It is most frequently related to drug-induced antibody generation. This study aimed to investigate the clinical significance of AC-23 positivity and its relevance to the diagnosis and/or follow-up of the associated diseases and/or drug use.
METHODS
A multicenter retrospective study was conducted among 10 hospitals from six different provinces in Türkiye from January 2017 to December 2021. The laboratory data and clinical information of 600 patients with positive anti-RR antibodies out of 547.558 HEp-2 IIF ANA samples were analyzed.
RESULTS
The distribution of AC-23 positive patients by year indicated a steady increase between 2017-2021. Anti-RR prevalence in post-COVID-19 period was significantly higher than that of pre-COVID-19 period (p=0.00). Concomitant ANA positivity was detected in 56.5% of patients, the most common patterns being AC-4 and AC-5 (41.1%). The most frequent pathology among the anti-RR positive patients was an autoimmune disease (19.83%); 28.57% of which had rheumatoid arthritis and 17.65% autoimmune liver disease. Among the 600 patients, 65 (10.83%) were diagnosed as hepatitis C virus (HCV) infection. Available data for 38 of the HCV patients revealed that 71.05% of them had a history of interferon alfa+ribavirin and 28.95% of them had a history of NS3/4/5A/5B polymerase inhibitor or protease inhibitor drug use. Significant increase in the rate of anti-RR positivity was observed in the post-COVID-19 period when compared to pre-COVID-19 period (p:0.00).
DISCUSSION
This is the first multicenter study in Türkiye about the clinical association of anti-RR antibodies which may be ignored during routine HEp-2 IIF testing. Pathologies other than HCV should be taken into consideration in terms of the possible role of anti-RR in autoimmune diseases and other pathologies. The preliminary data obtained in this study suggest that anti-RR antibody development might also be associated to COVID-19, supporting the several previous data related to the potential of viruses triggering the formation of autoantibodies. Large-scale prospective studies should elucidate the clinical significance of RR pattern and determine its role in patient diagnosis and follow-up.
Topics: Humans; Retrospective Studies; Antibodies, Antinuclear; Female; Male; COVID-19; Middle Aged; Fluorescent Antibody Technique, Indirect; Aged; Adult; SARS-CoV-2; Autoimmune Diseases
PubMed: 38911869
DOI: 10.3389/fimmu.2024.1359030 -
Frontiers in Immunology 2024Exacerbations of chronic obstructive pulmonary disease (COPD) increase mortality risk and can lead to accelerated loss of lung function. The increased inflammatory...
INTRODUCTION
Exacerbations of chronic obstructive pulmonary disease (COPD) increase mortality risk and can lead to accelerated loss of lung function. The increased inflammatory response during exacerbations contributes to worsening of airflow limitation, but whether it also impacts epithelial repair is unclear. Therefore, we studied the effect of the soluble factor micro-environment during COPD exacerbations on epithelial repair using an exacerbation cocktail (EC), composed of four factors that are increased in COPD lungs during exacerbations (IL-1β, IL-6, IL-8, TNF-α).
METHODS
Mouse organoids (primary CD31-CD45-Epcam+ cells co-cultured with CCL206 fibroblasts) were used to study epithelial progenitor behavior. Mature epithelial cell responses were evaluated using mouse precision cut lung slices (PCLS). The expression of epithelial supportive factors was assessed in CCL206 fibroblasts and primary human lung fibroblasts.
RESULTS
EC exposure increased the number and size of organoids formed, and upregulated , and expression in day 14 organoids. In PCLS, EC imparted no effect on epithelial marker expression. Pre-treatment of CCL206 fibroblasts with EC was sufficient to increase organoid formation. Additionally, the expression of , and was increased in CCL206 fibroblasts from EC treated organoids, but these factors individually did not affect organoid formation or size. However, TGF-α downregulated expression and upregulated expression in day 14 organoids.
CONCLUSIONS
EC exposure stimulates organoid formation and growth, but it alters epithelial differentiation. EC changes the epithelial progenitor support function of fibroblasts which contributes to observed effects on epithelial progenitors.
Topics: Animals; Pulmonary Disease, Chronic Obstructive; Humans; Mice; Fibroblasts; Epithelial Cells; Organoids; Cytokines; Lung; Cells, Cultured; Disease Progression; Respiratory Mucosa; Mice, Inbred C57BL
PubMed: 38911863
DOI: 10.3389/fimmu.2024.1346491