Regional assessment of LV wall in infarcted heart using tagged MRI and cardiac modelling

Fully Automatic Left Ventricle Segmentation Using Bilateral Lightweight Deep Neural Network

The segmentation of the left ventricle (LV) is one of the fundamental procedures that must be performed to obtain quantitative measures of the heart, such as its volume, area, and ejection fraction. In clinical practice, the delineation of LV is still often conducted semi-automatically, leaving it open to operator subjectivity. The automatic LV segmentation from echocardiography images is a challenging task due to poorly defined boundaries and operator dependency. Recent research has demonstrated that deep learning has the capability to employ the segmentation process automatically. However, the well-known state-of-the-art segmentation models still lack in terms of accuracy and speed. This study aims to develop a single-stage lightweight segmentation model that precisely and rapidly segments the LV from 2D echocardiography images. In this research, a backbone network is used to acquire both low-level and high-level features. Two parallel blocks, known as the spatial feature unit and the channel feature unit, are employed for the enhancement and improvement of these features. The refined features are merged by an integrated unit to segment the LV. The performance of the model and the time taken to segment the LV are compared to other established segmentation models, DeepLab, FCN, and Mask RCNN. The model achieved the highest values of the dice similarity index (0.9446), intersection over union (0.8445), and accuracy (0.9742). The evaluation metrics and processing time demonstrate that the proposed model not only provides superior quantitative results but also trains and segments the LV in less time, indicating its improved performance over competing segmentation models.

An Intelligent Mental Health Identification Method for College Students: A Mixed-Method Study

PURPOSE

Mental health assessments that combine patients' facial expressions and behaviors have been proven effective, but screening large-scale student populations for mental health problems is time-consuming and labor-intensive. This study aims to provide an efficient and accurate intelligent method for further psychological diagnosis and treatment, which combines artificial intelligence technologies to assist in evaluating the mental health problems of college students.

MATERIALS AND METHODS

We propose a mixed-method study of mental health assessment that combines psychological questionnaires with facial emotion analysis to comprehensively evaluate the mental health of students on a large scale. The Depression Anxiety and Stress Scale-21(DASS-21) is used for the psychological questionnaire. The facial emotion recognition model is implemented by transfer learning based on neural networks, and the model is pre-trained using FER2013 and CFEE datasets. Among them, the FER2013 dataset consists of 48 × 48-pixel face gray images, a total of 35,887 face images. The CFEE dataset contains 950,000 facial images with annotated action units (au). Using a random sampling strategy, we sent online questionnaires to 400 college students and received 374 responses, and the response rate was 93.5%. After pre-processing, 350 results were available, including 187 male and 153 female students. First, the facial emotion data of students were collected in an online questionnaire test. Then, a pre-trained model was used for emotion recognition. Finally, the online psychological questionnaire scores and the facial emotion recognition model scores were collated to give a comprehensive psychological evaluation score.

RESULTS

The experimental results of the facial emotion recognition model proposed to show that its classification results are broadly consistent with the mental health survey results. This model can be used to improve efficiency. In particular, the accuracy of the facial emotion recognition model proposed in this paper is higher than that of the general mental health model, which only uses the traditional single questionnaire. Furthermore, the absolute errors of this study in the three symptoms of depression, anxiety, and stress are lower than other mental health survey results and are only 0.8%, 8.1%, 3.5%, and 1.8%, respectively.

CONCLUSION

The mixed method combining intelligent methods and scales for mental health assessment has high recognition accuracy. Therefore, it can support efficient large-scale screening of students' psychological problems.

Comparative studies of deep learning segmentation models for left ventricle segmentation

One of the primary factors contributing to death across all age groups is cardiovascular disease. In the analysis of heart function, analyzing the left ventricle (LV) from 2D echocardiographic images is a common medical procedure for heart patients. Consistent and accurate segmentation of the LV exerts significant impact on the understanding of the normal anatomy of the heart, as well as the ability to distinguish the aberrant or diseased structure of the heart. Therefore, LV segmentation is an important and critical task in medical practice, and automated LV segmentation is a pressing need. The deep learning models have been utilized in research for automatic LV segmentation. In this work, three cutting-edge convolutional neural network architectures (SegNet, Fully Convolutional Network, and Mask R-CNN) are designed and implemented to segment the LV. In addition, an echocardiography image dataset is generated, and the amount of training data is gradually increased to measure segmentation performance using evaluation metrics. The pixel's accuracy, precision, recall, specificity, Jaccard index, and dice similarity coefficients are applied to evaluate the three models. The Mask R-CNN model outperformed the other two models in these evaluation metrics. As a result, the Mask R-CNN model is used in this study to examine the effect of training data. For 4,000 images, the network achieved 92.21% DSC value, 85.55% Jaccard index, 98.76% mean accuracy, 96.81% recall, 93.15% precision, and 96.58% specificity value. Relatively, the Mask R-CNN outperformed other architectures, and the performance achieves stability when the model is trained using more than 4,000 training images.

Construction of a Diagnostic Model for Lymph Node Metastasis of the Papillary Thyroid Carcinoma Using Preoperative Ultrasound Features and Imaging Omics

In this paper, we mainly adopted 337 patients who had undergone the surgery on lymph node metastasis of papillary thyroid carcinoma (PTC) as the sample population. In order to provide clinical reference for the intelligent decision-making in treatment plan and improvement of prognosis, we utilized ultrasound features and imaging features to construct five early diagnosis models for patients based on the ultrasound features, imaging features, and combined features. The model integrated with broad learning system (BLS) showed the best performance, with the area under the curve (AUC) of 0.857 (95% confidence interval (CI): 0.811–0.902)) and the accuracy of 0.805 (95% CI: 0.759–0.850). For demographic and clinical features, the prediction effect was also good, with the AUC more than 0.700.

COVID-19 Detection Using Deep Learning Algorithm on Chest X-ray Images

COVID-19, regarded as the deadliest virus of the 21st century, has claimed the lives of millions of people around the globe in less than two years. Since the virus initially affects the lungs of patients, X-ray imaging of the chest is helpful for effective diagnosis. Any method for automatic, reliable, and accurate screening of COVID-19 infection would be beneficial for rapid detection and reducing medical or healthcare professional exposure to the virus. In the past, Convolutional Neural Networks (CNNs) proved to be quite successful in the classification of medical images. In this study, an automatic deep learning classification method for detecting COVID-19 from chest X-ray images is suggested using a CNN. A dataset consisting of 3616 COVID-19 chest X-ray images and 10,192 healthy chest X-ray images was used. The original data were then augmented to increase the data sample to 26,000 COVID-19 and 26,000 healthy X-ray images. The dataset was enhanced using histogram equalization, spectrum, grays, cyan and normalized with NCLAHE before being applied to CNN models. Initially using the dataset, the symptoms of COVID-19 were detected by employing eleven existing CNN models; VGG16, VGG19, MobileNetV2, InceptionV3, NFNet, ResNet50, ResNet101, DenseNet, EfficientNetB7, AlexNet, and GoogLeNet. From the models, MobileNetV2 was selected for further modification to obtain a higher accuracy of COVID-19 detection. Performance evaluation of the models was demonstrated using a confusion matrix. It was observed that the modified MobileNetV2 model proposed in the study gave the highest accuracy of 98% in classifying COVID-19 and healthy chest X-rays among all the implemented CNN models. The second-best performance was achieved from the pre-trained MobileNetV2 with an accuracy of 97%, followed by VGG19 and ResNet101 with 95% accuracy for both the models. The study compares the compilation time of the models. The proposed model required the least compilation time with 2 h, 50 min and 21 s. Finally, the Wilcoxon signed-rank test was performed to test the statistical significance. The results suggest that the proposed method can efficiently identify the symptoms of infection from chest X-ray images better than existing methods.

Development and External Validation of a Nomogram for Predicting Overall Survival in Stomach Cancer: A Population-Based Study

Objective

The study was to develop and externally validate a prognostic nomogram to effectively predict the overall survival of patients with stomach cancer.

Methods

Demographic and clinical variables of patients with stomach cancer in the Surveillance, Epidemiology, and End Results (SEER) database from 2007–2016 were retrospectively collected. Patients were then divided into the Training Group (n = 4,456) for model development and the Testing Group (n = 4,541) for external validation. Univariate and multivariate Cox regressions were used to explore prognostic factors. The concordance index (C-index) and the Kolmogorov–Smirnov (KS) value were used to measure the discrimination, and the calibration curve was used to assess the calibration of the nomogram.

Results

Prognostic factors including age, race, marital status, TNM stage, surgery, chemotherapy, grade, and the number of regional nodes positive were used to construct a nomogram. The C-index was 0.790 and the KS value was 0.45 for the Training Group, and the C-index was 0.789 for the Testing Group, all suggesting the good performance of the nomogram.

Conclusion

We have developed an effective nomogram with ten easily acquired prognostic factors. The nomogram could accurately predict the overall survival of patients with stomach cancer and performed well on external validation, which would help improve the individualized survival prediction and decision-making, thereby improving the outcome and survival of stomach cancer.

Assessing regional left ventricular thickening dysfunction and dyssynchrony via personalized modeling and 3D wall thickness measurements for acute myocardial infarction

BACKGROUND

Existing clinical diagnostic and assessment methods could be improved to facilitate early detection and treatment of cardiac dysfunction associated with acute myocardial infarction (AMI) to reduce morbidity and mortality.

PURPOSE

To develop 3D personalized left ventricular (LV) models and thickening assessment framework for assessing regional wall thickening dysfunction and dyssynchrony in AMI patients.

STUDY TYPE

Retrospective study, diagnostic accuracy.

SUBJECTS

Forty-four subjects consisting of 15 healthy subjects and 29 AMI patients.

FIELD STRENGTH/SEQUENCE

1.5T/steady-state free precession cine MRI scans; LGE MRI scans.

ASSESSMENT

Quantitative thickening measurements across all cardiac phases were correlated and validated against clinical evaluation of infarct transmurality by an experienced cardiac radiologist based on the American Heart Association (AHA) 17-segment model.

STATISTICAL TEST

Nonparametric 2-k related sample-based Kruskal-Wallis test; Mann-Whitney U-test; Pearson's correlation coefficient.

RESULTS

Healthy LV wall segments undergo significant wall thickening (P < 0.05) during ejection and have on average a thicker wall (8.73 ± 1.01 mm) compared with infarcted wall segments (2.86 ± 1.11 mm). Myocardium with thick infarct (ie, >50% transmurality) underwent remarkable wall thinning during contraction (thickening index [TI] = 1.46 ± 0.26 mm) as opposed to healthy myocardium (TI = 4.01 ± 1.04 mm). For AMI patients, LV that showed signs of thinning were found to be associated with a significantly higher percentage of dyssynchrony as compared with healthy subjects (dyssynchrony index [DI] = 15.0 ± 5.0% vs. 7.5 ± 2.0%, P < 0.01). Also, a strong correlation was found between our TI and left ventricular ejection fraction (LVEF) (r = 0.892, P < 0.01), and moderate correlation between DI and LVEF (r = 0.494, P < 0.01).

DATA CONCLUSION

The extracted regional wall thickening and DIs are shown to be strongly correlated with infarct severity, therefore suggestive of possible practical clinical utility.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;49:1006-1019.

Magnetic resonance imaging of myocardial strain: A review of current approaches

Contraction of the heart is central to its purpose of pumping blood around the body. While simple global function measures (such as the ejection fraction) are most commonly used in the clinical assessment of cardiac function, MRI also provides a range of approaches for quantitatively characterizing regional cardiac function, including the local deformation (or strain) within the heart wall. While they have been around for some years, these methods are still undergoing further technical development, and they have had relatively little clinical evaluation. However, they can provide potentially useful new ways to assess cardiac function, which may be able to contribute to better classification and treatment of heart disease. This article provides some basic background on the physical and physiological factors that determine the motion of the heart, in health and disease and then reviews some of the ways that MRI methods are being developed to image and quantify strain within the myocardium.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1263-1280.

Identification of left ventricular systolic dysfunction and contraction inhomogeneity in post-infarction patients using a segmental two-parameter empirical deformable model

Various computational models have been developed with an objective to mimic the left ventricular (LV) wall motion and establishing global and regional parameters for evaluating cardiac performance. Recently, a segmental two-parameter empirical deformable model was introduced which performs a non-rigid registration to derive contraction and rotational parameters describing the LV motion. In this work, we assessed the capability of the segmental model in identifying the impairment of the LV contraction in the post-infarction patients. The correlation between the contraction parameter, α/repi defined in this work and the total percentage of infarct was investigated. The temporal pattern of the contraction parameter in each LV segment at the mid ventricular slice was also analyzed throughout the systolic cardiac phases. Our results demonstrated that mean α/repi decreased exponentially with an increase in the infarct percentage. While normal subjects showed synchronous contraction for all LV segments, the presence of infarct regions caused LV dyssynchrony, with the infarcted segments demonstrated abnormal contraction patterns.