CACCT: An Automated Tool of Detecting Complicated Cardiac Malformations in Mouse Models

Chu, Qing; Jiang, Haobin; Zhang, Libo; Zhu, Dekun; Yin, Qianqian; Zhang, Hao; Zhou, Bin; Zhou, Wangming; Zhang, Yue; Hong, Lan; Liu, Lihui; Nie, Yu; Hu, Shengshou

doi:10.1002/advs.201903592

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Histology and immunohistochemistry were performed as described previously ( Chu et al, 2020 ). Briefly, mouse embryos were dissected in PBS and fixed in 4% PFA overnight at 4°C.…”

Section: Methodsmentioning

confidence: 99%

EZH2 controls epicardial cell migration during heart development

et al. 2023

Self Cite

View full text Add to dashboard Cite

Enhancer of zeste homolog 2 (EZH2) is an important transcriptional regulator in development that catalyzes H3K27me3. The role of EZH2 in epicardial development is still unknown. In this study, we show that EZH2 is expressed in epicardial cells during both human and mouse heart development.Ezh2epicardial deletion resulted in impaired epicardial cell migration, myocardial hypoplasia, and defective coronary plexus development, leading to embryonic lethality. By using RNA sequencing, we identified that EZH2 controls the transcription of tissue inhibitor of metalloproteinase 3 (TIMP3) in epicardial cells during heart development. Loss-of-function studies revealed that EZH2 promotes epicardial cell migration by suppressing TIMP3 expression. We also found that epicardialEzh2deficiency–induced TIMP3 up-regulation leads to extracellular matrix reconstruction in the embryonic myocardium by mass spectrometry. In conclusion, our results demonstrate that EZH2 is required for epicardial cell migration because it blocksTimp3transcription, which is vital for heart development. Our study provides new insight into the function of EZH2 in cell migration and epicardial development.

show abstract

“…Histology and immunohistochemistry were performed as described previously ( Chu et al, 2020 ). Briefly, mouse embryos were dissected in PBS and fixed in 4% PFA overnight at 4°C.…”

Section: Methodsmentioning

confidence: 99%

EZH2 controls epicardial cell migration during heart development

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although there are previous reports of automated segmentation and classification of CHD in mice [12][13][14][15][16] , they have several limitations. First, segmentation and analysis algorithms, when publicly available, typically require coding skills to be used, and hence call for user-friendly alternatives 14,15 .…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based detection of murine congenital heart defects from µCT scans

Nguyen,

Desgrange,

Ochandorena-Saa

et al. 2024

Preprint

View full text Add to dashboard Cite

Congenital heart defects (CHD) result in high morbidity and mortality rates, but their origins are poorly understood. Mouse models of heart morphogenesis are required to study the pathological mechanisms of heart development compared to normal. In mouse fetuses, CHD can be observed and detected in 3D images obtained by thoracic micro-computed tomography (μCT). However, diagnosis of CHD from μCT scans is a time-consuming process that requires the experience of senior experts. An automated alternative would thus save time, empower less experienced investigators and could broaden analysis to larger numbers of samples. Here, we describe and validate an approach based on deep learning to automatically segment the heart and screen normal from malformed hearts in mouse μCT scans. In an initial cohort, we collected 139 μCT scans from thorax and abdomen of control and mutant perinatal mice. We trained a self-configurating neural network (nnU-Net) to segment hearts from body μCT scans and validated its performance on expert segmentations, achieving a Dice coefficient of 96%. To identify malformed hearts, we developed and trained a 3D convolutional neural network (CNN) that uses segmented μCT scans as inputs. Despite the relatively small training data size, our diagnosis model achieved a sensitivity, specificity (for a 0.5 threshold), and area under the curve (AUC) of 92%, 96%, and 97% respectively, as determined by 5-fold cross-validation. As further validation, we analyzed two additional cohorts that were collected after the model was trained: a 'prospective' cohort, using the same experimental protocol as the initial cohort, and containing a subset of its genotypes, and a 'divergent' cohort in which mice were subjected to a different treatment for heart arrest (cardioplegia) and that contained a new mouse line. Performance on the prospective cohort was excellent, with a sensitivity of 92%, a specificity of 100%, and an AUC of 100%. Performance on the divergent cohort was moderate (sensitivity: 69%, specificity: 80% and AUC: 81%), but was much improved when the model was finetuned on (a subset of) the cohort (sensitivity: 79%, specificity: 88% and AUC: 91%). These results showcase our model's robustness and adaptability to technical and biological differences in the data, highlighting its usefulness for practical applications. In order to facilitate the adoption, adaptation and further improvement of these methods, we built a user-friendly Napari plugin (available at napari-hub.org/plugins/mousechd-napari) that allows users without programming skills to utilize the segmentation and diagnosis models and re-train the latter on their own data and resources. The plugin also highlights the cardiac regions used for the diagnosis. Our automatic and retrainable pipeline, which can be employed in high-throughput genetic screening, will accelerate diagnosis of heart anomalies in mice and facilitate studies of the mechanisms of CHD.

show abstract

“…Congenital heart disease (CHD) is the most common structural birth defect with an incidence rate of 6-12 per 1,000 newborns (1)(2)(3)(4), and its estimated prevalence is about 19-20 per 1,000 newborns when the bicuspid aortic valve is included (5,6). In China, a national study reported an overall CHD prevalence of 9 per 1,000 newborns (7), and it remains the leading noninfectious cause of death in infancy and childhood despite tremendous progress in surgical therapies (8). CHD imposes a substantial burden on survivors, families, and societies.…”

Section: Introductionmentioning

confidence: 99%

How Parental Predictors Jointly Affect the Risk of Offspring Congenital Heart Disease: A Nationwide Multicenter Study Based on the China Birth Cohort

Zhang

Sun

Zhao

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

ObjectiveCongenital heart disease (CHD) is complex in its etiology. Its genetic causes have been investigated, whereas the non-genetic factor related studies are still limited. We aimed to identify dominant parental predictors and develop a predictive model and nomogram for the risk of offspring CHD.MethodsThis was a retrospective study from November 2017 to December 2021 covering 44,578 participants, of which those from 4 hospitals in eastern China were assigned to the development cohort and those from 5 hospitals in central and western China were used as the external validation cohort. Univariable and multivariable analyses were used to select the dominant predictors of CHD among demographic characteristics, lifestyle behaviors, environmental pollution, maternal disease history, and the current pregnancy information. Multivariable logistic regression analysis was used to construct the model and nomogram using the selected predictors. The predictive model and the nomogram were both validated internally and externally. A web-based nomogram was developed to predict patient-specific probability for CHD.ResultsDominant risk factors for offspring CHD included increased maternal age [odds ratio (OR): 1.14, 95% CI: 1.10–1.19], increased paternal age (1.05, 95% CI: 1.02–1.09), maternal secondhand smoke exposure (2.89, 95% CI: 2.22–3.76), paternal drinking (1.41, 95% CI: 1.08–1.84), maternal pre-pregnancy diabetes (3.39, 95% CI: 1.95–5.87), maternal fever (3.35, 95% CI: 2.49–4.50), assisted reproductive technology (2.89, 95% CI: 2.13–3.94), and environmental pollution (1.61, 95% CI: 1.18–2.20). A higher household annual income (100,000–400,000 CNY: 0.47, 95% CI: 0.34–0.63; > 400,000 CNY: 0.23, 95% CI: 0.15–0.36), higher maternal education level (13–16 years: 0.68, 95% CI: 0.50–0.93; ≥ 17 years: 0.87, 95% CI: 0.55–1.37), maternal folic acid (0.21, 95% CI: 0.16–0.27), and multivitamin supplementation (0.33, 95% CI: 0.26–0.42) were protective factors. The nomogram showed good discrimination in both internal [area under the receiver-operating-characteristic curve (AUC): 0.843] and external validations (development cohort AUC: 0.849, external validation cohort AUC: 0.837). The calibration curves showed good agreement between the nomogram-predicted probability and actual presence of CHD.ConclusionWe revealed dominant parental predictors and presented a web-based nomogram for the risk of offspring CHD, which could be utilized as an effective tool for quantifying the individual risk of CHD and promptly identifying high-risk population.

show abstract

CACCT: An Automated Tool of Detecting Complicated Cardiac Malformations in Mouse Models

Cited by 6 publications

References 21 publications

EZH2 controls epicardial cell migration during heart development

EZH2 controls epicardial cell migration during heart development

Deep learning-based detection of murine congenital heart defects from µCT scans

How Parental Predictors Jointly Affect the Risk of Offspring Congenital Heart Disease: A Nationwide Multicenter Study Based on the China Birth Cohort

Contact Info

Product

Resources

About