Development and Validation of an Algorithm Model for Predicting Heat Sink Effects during Pulmonary Thermal Ablation

AIMS: The aim of this study was to develop an algorithm model to predict the heat sink effect during thermal ablation of lung tumors and to assist doctors in the formulation and adjustment of surgical protocols. BACKGROUND: The heat sink effect is an important factor affecting the therapeutic effect of tumor thermal ablation. At present, there is no algorithm model to predict the intraoperative heat sink effect automatically, which needs to be measured manually, which lacks accuracy and consumes time. OBJECTIVE: To construct a segmentation model based on a convolutional neural network that can automatically identify and segment pulmonary nodules and vascular structure and measure the distance between the nodule and vascular. METHODS: First, the classical Faster RCNN model was used as the nodule detection network. After obtaining the bounding box of pulmonary nodules, the VSPP-NET model was used to segment nodules in the bounding box. The distance from the nodule to the vasculature was measured after the surrounding vasculature was segmented by the VSPP-NET model. The lung CT images of 392 patients with pulmonary nodules were used as the training data for the algorithm. 68 cases were used as algorithm validation data, 29 as nodule algorithm test data, and 80 as vascular algorithm test data. We compared the heat sink effect of 29 cases of data with the results of the algorithm model and expert segmentation and compared the difference between the two results. RESULTS: In pulmonary CT image vasculature segmentation, the recall and precision of the algorithm model reached >0.88 and >0.78, respectively. The average time for automatic segmentation of each image model is 29 seconds, and the average time for manual segmentation is 158 seconds. The output image of the model shows that the results of nodule segmentation and nodule distance measurement are satisfactory. In terms of heat sink effect prediction, the positive rate of the algorithm group was 28.3%, and that of the expert group was 32.1%, with no significant difference between the two groups (p=0.687). CONCLUSION: The algorithm model developed in this study shows good performance in predicting the heat sink effect during pulmonary thermal ablation. It can improve the speed and accuracy of nodule and vessel segmentation, save ablation planning time, reduce the interference of human factors, and provide more reference information for surgeons to make ablation plans to improve the ablation effect.

Bidirectional cross-modality unsupervised domain adaptation using generative adversarial networks for cardiac image segmentation.

BACKGROUND: A novel Generative Adversarial Networks (GAN) based bidirectional cross-modality unsupervised domain adaptation (GBCUDA) framework is developed for cardiac image segmentation, which can effectively tackle the problem of network's segmentation performance degradation when adapting to the target domain without ground truth labels. METHOD: GBCUDA uses GAN for image alignment, applies adversarial learning to extract image features, and gradually enhances the domain invariance of extracted features. The shared encoder performs an end-to-end learning task in which features that differ between the two domains complement each other. The self-attention mechanism is incorporated to the GAN network, which can generate details based on the prompts of all feature positions. Furthermore, spectrum normalization is implemented to stabilize the training of GAN, and knowledge distillation loss is introduced to process high-level feature-maps in order to better complete the cross-mode segmentation task. RESULTS: The effectiveness of our proposed unsupervised domain adaptation framework is tested over the Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge 2017 dataset. The proposed method is able to improve the average Dice from 74.1% to 81.5% for the four cardiac substructures, and reduce the average symmetric surface distance (ASD) from 7.0 to 5.8 over CT images. For MRI images, our proposed framework trained on CT images gives the average Dice of 59.2% and reduces the average ASD from 5.7 to 4.9. CONCLUSIONS: The evaluation results demonstrate our method's effectiveness on domain adaptation and the superiority to the current state-of-the-art domain adaptation methods.

Multiscale attention guided U-Net architecture for cardiac segmentation in short-axis MRI images.

BACKGROUND AND OBJECTIVE: Automatic cardiac segmentation plays an utmost role in the diagnosis and quantification of cardiovascular diseases. METHODS: This paper proposes a new cardiac segmentation method in short-axis Magnetic Resonance Imaging (MRI) images, called attention U-Net architecture with input image pyramid and deep supervised output layers (AID), which can fully-automatically learn to pay attention to target structures of various sizes and shapes. During each training process, the model continues to learn how to emphasize the desired features and suppress irrelevant areas in the original images, effectively improving the accuracy of cardiac segmentation. At the same time, we introduce the Focal Tversky Loss (FTL), which can effectively solve the problem of high imbalance in the amount of data between the target class and the background class during cardiac image segmentation. In order to obtain a better representation of intermediate features, we add a multi-scale input pyramid to the attention network. RESULTS: The proposed cardiac segmentation technique is tested on the public Left Ventricle Segmentation Challenge (LVSC) dataset, which is shown to achieve 0.75, 0.87 and 0.92 for Jaccard Index, Sensitivity and Specificity, respectively. Experimental results demonstrate that the proposed method is able to improve the segmentation accuracy compared with the standard U-Net, and achieves comparable performance to the most advanced fully-automated methods. CONCLUSIONS: Given its effectiveness and advantages, the proposed method can facilitate cardiac segmentation in short-axis MRI images in clinical practice.

Prevalence and risk factors of cardiac events in different ethnic groups in Xinjiang region / 中华健康管理学杂志

Objective:To explore the prevalence and risk factors of cardiac events in different ethnic groups in Xinjiang region.Methods:This retrospective cohort study was based on big data from the health checkup population. A total of 7 899 cases were included from the Physical Examination Center of Xinjiang Uygur Autonomous Region People′s Hospital form 2015 January 1 to December 31, 2017.The population were divided into Uyghur group (2 630 cases), Kazak group (2 636 cases), and the Han nationality group (2 633 cases). Telephone follow-up was conducted once a month after the health checkup, the preset follow-up time for all personnel was 2 years, with the occurrence of cardiac events as the end point. Once cardiac events occurred, the follow-up would be stopped. The risk factors of cardiac events in different ethnic groups were evaluated by statistical analysis.Results:The median follow-up time of the 7 899 included healthy examinees was 1.27 years, and 200 cases of cardiac events occurred, with an incidence rate of 2.53%. The values of body mass index (BMI), the levels of triglyceride (TG), total cholesterol (TC), high density lipoprotein cholesterol (HDL-C) and low density lipoprotein cholesterol (LDL-C) of Uyghur and Kazak were higher than those of Han (all P<0.05). The cardiac events in Uyghur, Kazak and Han group were 75 cases (2.85%), 85 cases (3.22%) and 40 cases (1.52%). There was no significantly statistical difference between Uyghur group and Kazak group in the incidence of cardiac events, while it was significantly lower in the Han group than the other two groups (both P<0.05). Univariate analysis showed that BMI, TC, TG, HDL-C and LDL-C were the risk factors of cardiac events; multivariate Cox regression analysis showed that ethnic groups ( HR=4.34, 95% CI: 1.14―8.13); HDL-C ( HR=3.32, 95% CI: 1.89―5.74) and LDL-C ( HR=2.47, 95% CI: 1.21―7.45) were independent risk factors for cardiac events. Conclusions:Ethnic factor is one of the independent risk factors for the occurrence of cardiac events in Xinjiang, and Uyghur and Kazak have a higher incidence of cardiac events. HDL-C and LDL-C are also important risk factors for cardiac events.