Cardiac Segmentation Method Based on Domain Knowledge.

Echocardiography plays an important role in the clinical diagnosis of cardiovascular diseases. Cardiac function assessment by echocardiography is a crucial process in daily cardiology. However, cardiac segmentation in echocardiography is a challenging task due to shadows and speckle noise. The traditional manual segmentation method is a time-consuming process and limited by inter-observer variability. In this paper, we present a fast and accurate echocardiographic automatic segmentation framework based on Convolutional neural networks (CNN). We propose FAUet, a segmentation method serially integrated U-Net with coordinate attention mechanism and domain feature loss from VGG19 pre-trained on the ImageNet dataset. The coordinate attention mechanism can capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other spatial direction. And the domain feature loss is more concerned with the topology of cardiac structures by exploiting their higher-level features. In this research, we use a two-dimensional echocardiogram (2DE) of 88 patients from two devices, Philips Epiq 7C and Mindray Resona 7T, to segment the left ventricle (LV), interventricular septal (IVS), and posterior left ventricular wall (PLVW). We also draw the gradient weighted class activation mapping (Grad-CAM) to improve the interpretability of the segmentation results. Compared with the traditional U-Net, the proposed segmentation method shows better performance. The mean Dice Score Coefficient (Dice) of LV, IVS, and PLVW of FAUet can achieve 0.932, 0.848, and 0.868, and the average Dice of the three objects can achieve 0.883. Statistical analysis showed that there is no significant difference between the segmentation results of the two devices. The proposed method can realize fast and accurate segmentation of 2DE with a low time cost. Combining coordinate attention module and feature loss with the original U-Net framework can significantly increase the performance of the algorithm.

Improved FCOS for Detecting Breast Cancers.

PURPOSE: Breast cancer ranks first among cancers affecting women's health. Our goal is to develop a fast, high-precision, and fully automated breast cancer detection algorithm to improve the early detection rate of breast cancer. METHODS: We compare different object detection algorithms, including anchor-based and anchor-free object detection algorithms for detecting breast lesions. Finally, we find that the fully convolutional onestage object detection (FCOS) showed the best performance in the detection of breast lesions, which is an anchor-free algorithm. 1) Considering that the detection of breast lesions requires the context information of the ultrasound images, we introduce the non-local technique, which models long-range dependency between pixels to the FCOS algorithm, providing the global context information for the detection of the breast lesions. 2) The variety of shapes and sizes of breast lesions makes detection difficult. We propose a new deformable spatial attention (DSA) module and add it to the FCOS algorithm. RESULTS: The detection performance of the original FCOS is that the average precision (AP) for benign lesions is 0.818, and for malignant lesions is 0.888. The FCOS with a non-local module improves the performance of the breast detection; the AP of benign lesions was 0.819, and that of malignant lesions was 0.894. Combining the DSA module with the FCOS improves the performance of breast detection; the AP for benign lesions and malignant lesions is 0.840 and 0.899, respectively. CONCLUSION: We propose two methods to improve the FCOS algorithm from different perspectives to improve its performance in detecting breast lesions. We find that FCOS combined with DSA is beneficial in improving the localization and classification of breast tumors and can provide auxiliary diagnostic advice for ultrasound physicians, which has a certain clinical application value.

Effect of Moxibustion on ß-EP and Dyn Levels of Pain-Related Indicators in Patients with Rheumatoid Arthritis.

BACKGROUND: Rheumatoid arthritis (RA) is a systemic immunodeficiency disease characterized by persistent synovial inflammation, pannus formation, and bone and cartilage destruction, resulting in joint malformations and function decline. OBJECTIVE: The purpose of this study is to evaluate the effect of moxibustion on clinical symptoms and levels of pain-related indicators beta-endorphin (ß-EP) and dynorphin (Dyn) in patients with RA and to explore the potential anti-inflammatory and analgesic mechanisms of moxibustion in RA treatment. METHODS: A total of 64 patients with RA who met the inclusion criteria were randomly and equally classified into the control and treatment groups. The control group received conventional treatment (oral methotrexate, folate, or leflunomide prescribed for a long time). The treatment group was treated with moxibustion at ST36 (Zusanli), BL23 (Shenshu), and Ashi points with respect to the control group. Patients' clinical symptoms and routine inspection indexes (rheumatoid factor [RF], erythrocyte sedimentation rate [ESR], and C-reactive protein [CRP]) were recorded before and after treatment. Serum levels of tumor necrosis factor-α (TNF-α), interleukin-1ß (IL-1ß), ß-EP, and Dyn were determined by enzyme-linked immunosorbent assay (ELISA). The software SPSS24.0 was used for statistical analysis. RESULTS: (1) Compared with the pretreatment result, both of the two groups' clinical symptoms and routine inspection indexes (RF, ESR, and CRP) improved (P < 0.05), and the improvement of clinical symptoms in the treatment group outperformed that in the control group (P < 0.05). (2) TNF-α and IL-1ß levels decreased significantly in the treatment group after treatment (P < 0.01), while no significant difference was observed in the control group (P > 0.05). (3) ß-EP and Dyn levels in the treatment group were significantly increased after treatment (P < 0.01, P < 0.01), but the control group showed no significant difference (P > 0.05, P > 0.05). It is worth mentioning that the serum TNF-α, IL-1ß, ß-EP, and Dyn levels between the two groups were significantly different after 8 weeks of treatment (P < 0.05). (4) Differences in the serum ß-EP and Dyn levels in the patients of the treatment group were correlated with TNF-α and IL-1ß levels after treatment, and the correlation was mainly negative (r < 0). CONCLUSION: Moxibustion can improve joint pain in patients with RA using conventional western medicine. One of the mechanisms may affect the serum ß-EP and Dyn levels by downregulating the inflammatory factors to play an anti-inflammatory and analgesic role.

Effect of Moxibustion on the Serum Levels of MMP-1, MMP-3, and VEGF in Patients with Rheumatoid Arthritis.

BACKGROUND: Rheumatoid arthritis (RA) is a chronic inflammatory autoimmune disease, which will eventually lead to joints deformity and functional damage. The aim of this research is to evaluate the effect of moxibustion on the serum indicators related to bone and cartilage metabolism, matrix metalloproteinase 1 (MMP-1), matrix metalloproteinase 3 (MMP-3), and vascular endothelial growth factor (VEGF) in patients with RA and to explore the mechanism of moxibustion in the treatment of RA. METHODS: We recruited 70 RA patients who met the inclusion criteria, and they were randomly divided into two groups, a treatment group and a control group in equal ratio. The control group took methotrexate, folate, or leflunomide orally, while the treatment group received methotrexate, folate, or leflunomide orally and moxibustion at ST36 (Zusanli), BL23 (Shen shu), and Ashi points. We compared the clinical symptoms, RA serological disease markers and serum contents of interleukin-1ß (IL-1ß), tumor necrosis factor-α (TNF-α), MMP-1, MMP-3, and VEGF of RA patients before and after treatment. RESULTS: (1) The clinical symptoms and RA serological disease markers of the two groups improved after treatment (P < 0.05), while the clinical symptoms of the treatment group were significantly improved in comparison with the control group (P < 0.05). (2) The levels of IL-1ß, TNF-α, and VEGF decreased in both groups after treatment (P < 0.05), but the treatment group was significantly decreased compared with the control group (P < 0.05). (3) There were significant differences in MMP-1 and MMP-3 contents after treatment in the treatment group (P < 0.05, P < 0.05), while there were no significant differences in the control group (P > 0.05, P > 0.05). Above all, the contents of IL-1ß, TNF-α, MMP-1, MMP-3, and VEGF in the treatment group decreased more significantly than those in the control group (P < 0.05). CONCLUSION: The improvement effect of moxibustion on the clinical symptoms of RA patients may be related to influence on the contents of IL-1ß, TNF-α, MMP-1, MMP-3, and VEGF, and moxibustion may play a potential role in bone protection.

Effect of Moxibustion on HIF-1α and VEGF Levels in Patients with Rheumatoid Arthritis.

Background: Moxibustion has a therapeutic effect of reducing swelling and relieving pain in patients with rheumatoid arthritis (RA) but its mechanism is uncertain. Objective: To evaluate the effect of moxibustion on serum levels of hypoxia-inducible factor-1α (HIF-1α) and vascular endothelial growth factor (VEGF) in patients with RA and to explore the possible mechanism of moxibustion. Methods: This study involved 46 RA patients who had fulfilled the inclusion criteria and were randomly assigned to a treatment group and a control group in an equal ratio. The control group was treated with methotrexate or leflunomide, while the treatment group received methotrexate or leflunomide and moxibustion at ST 36 (Zusanli), BL 23 (Shenshu), and Ashi points. Patients' clinical symptoms, RA-associated serum markers, and serum levels of TNF-α, IL-1ß, HIF-1α, and VEGF were compared in the two groups before and after intervention. Statistical analysis was performed using SPSS 21.0 statistical software. Results: 37 of 46 RA patients eventually completed the whole treatment course. Compared with the control group, the treatment group significantly improved the clinical symptoms (P < 0.05) but with no significant differences in RA-associated serum markers (P > 0.05). There were significant differences in TNF-α and IL-1ß among the groups after 8 weeks of treatment (P < 0.05). HIF-1α and VEGF were decreased in the treatment group after therapy (P < 0.05). VEGF was reduced in the control group (P < 0.05), while HIF-1α was not significantly improved (P > 0.05). The reductions of HIF-1α and VEGF in the treatment group were superior to the control group (P < 0.05). Conclusions: Moxibustion enhanced the anti-inflammatory and analgesic effects of conventional medicine and can enhance the effect of conventional medicine, downregulating HIF-1α/VEGF contents to inhibit angiogenesis.