An improved contrastive learning network for semi-supervised multi-structure segmentation in echocardiography.

Cardiac diseases have high mortality rates and are a significant threat to human health. Echocardiography is a commonly used imaging technique to diagnose cardiac diseases because of its portability, non-invasiveness and low cost. Precise segmentation of basic cardiac structures is crucial for cardiologists to efficiently diagnose cardiac diseases, but this task is challenging due to several reasons, such as: (1) low image contrast, (2) incomplete structures of cardiac, and (3) unclear border between the ventricle and the atrium in some echocardiographic images. In this paper, we applied contrastive learning strategy and proposed a semi-supervised method for echocardiographic images segmentation. This proposed method solved the above challenges effectively and made use of unlabeled data to achieve a great performance, which could help doctors improve the accuracy of CVD diagnosis and screening. We evaluated this method on a public dataset (CAMUS), achieving mean Dice Similarity Coefficient (DSC) of 0.898, 0.911, 0.916 with 1/4, 1/2 and full labeled data on two-chamber (2CH) echocardiography images, and of 0.903, 0.921, 0.928 with 1/4, 1/2 and full labeled data on four-chamber (4CH) echocardiography images. Compared with other existing methods, the proposed method had fewer parameters and better performance. The code and models are available at https://github.com/gpgzy/CL-Cardiac-segmentation.

Landslide spatial modelling using novel bivariate statistical based Naïve Bayes, RBF Classifier, and RBF Network machine learning algorithms.

Landslides are major hazards for human activities often causing great damage to human lives and infrastructure. Therefore, the main aim of the present study is to evaluate and compare three machine learning algorithms (MLAs) including Naïve Bayes (NB), radial basis function (RBF) Classifier, and RBF Network for landslide susceptibility mapping (LSM) at Longhai area in China. A total of 14 landslide conditioning factors were obtained from various data sources, then the frequency ratio (FR) and support vector machine (SVM) methods were used for the correlation and selection the most important factors for modelling process, respectively. Subsequently, the resulting three models were validated and compared using some statistical metrics including area under the receiver operating characteristics (AUROC) curve, and Friedman and Wilcoxon signed-rank tests The results indicated that the RBF Classifier model had the highest goodness-of-fit and performance based on the training and validation datasets. The results concluded that the RBF Classifier model outperformed and outclassed (AUROC = 0.881), the NB (AUROC = 0.872) and the RBF Network (AUROC = 0.854) models. The obtained results pointed out that the RBF Classifier model is a promising method for spatial prediction of landslide over the world.

Up-regulation of mir-10b predicate advanced clinicopathological features and liver metastasis in colorectal cancer.

Given the emerging role of microRNA in tumor disease progression, we investigated the association between miRNA 10b expression, liver metastasis, and clinicopathological of colorectal cancer (CRC). Two hundred and forty-six pairs of samples (including CRC samples and normal adjacent tissues) from CRC patients were collected from May 2004 to May 2009. All samples verified to contain at least 80% tumor cells, and were immediately frozen in liquid nitrogen and stored at -80°C or fixed in 10% formalin for paraffin embedding. The expression of miRNA-10b in CRC tissues was evaluated using a quantitative real-time polymerase chain reaction RT-PCR. Correlation between miR-10b expression and poor clinicopathological of CRC patients were analyzed using Student's t-tests and Chi-square tests. A Kaplan-Meier survival curve was generated following a log-rank test. miR-10b expression was up-regulated in CRC tissues (P < 0.0001) and in patients diagnosed as colorectal liver metastasis (CLM) at initial involvement or during follow-up. When the Tumor Node Metastasis (TNM) stage was taken into consideration, the expression levels of miR-10b were positively correlated with advanced TNM stages. In addition, the miR-10b expression of patients diagnosed as CLM at initial involvement was significantly higher than those without liver metastasis (nCLM). Similarly, those patients developed with CLM during follow-up (FCLM) was also markedly higher than those with nCLM. miR-10b expression was also found correlated with advanced stage (P < 0.0001), lymph node metastasis (P = 0.025), venous infiltration (P = 0.007), poorer differentiation (P = 0.002), and served as an independent prognostic factor of poor overall survival (P < 0.0001). This study demonstrated the expression of miR-10b had strong potential to serve as a noninvasive biomarker for CRC prognosis and predicting liver metastasis.

Do multiple renal arteries in the remnant kidney have a negative influence on kidney donors after kidney donation?

AIM: To investigate whether the presence of multiple renal arteries in the remnant kidney has implications for lower renal function or increased incidence of hypertension. METHODS: We reviewed the intraoperative and follow-up data of 101 live kidney donors who underwent nephrectomies at our institution. Sixty-nine donors (68.3%) had single artery in the remnant kidney (Group A), while 32 donors (31.7%) had multiple renal arteries in the remnant kidney (Group B). We compared the demographic and intraoperative data between the two groups. The follow-up data of donors in each group were divided into three subgroups based on the length of the follow-up period (12-24 months, 24-48 months and ≥48 months). Subgroups were created based on blood pressure and serum creatinine level. The δblood pressure (follow-up blood pressure minus preoperative blood pressure) and δserum creatinine (follow-up serum creatinine minus preoperative serum creatinine) in each subgroup in Group A were compared with the counterparts in Group B. RESULTS: Renal arterial stenosis and calcification of renal arterial wall were not observed in all donors. There were no significant differences in the intraoperative characteristics (e.g. age, body mass index, operative duration and estimated blood loss) between the two groups. In addition, the blood pressure and serum creatinine level among subgroups within each group were similar. Furthermore, significant differences in δblood pressure and δserum creatinine were not observed between subgroups within the same follow-up period. Recipient survival rate and serum creatinine level were similar and acceptable in both groups. CONCLUSIONS: The presence of multiple renal arteries in the remnant kidney does not have additional negative influence on kidney donors after kidney donation.

Retroperitoneoscopic live-donor right nephrectomy: a Chinese single center.

OBJECTIVES: To evaluate our right-retro- peritoneoscopic live-donor nephrectomy by comparing the left side with the right side, and reporting our single-center experience for rightretroperitoneoscopic live-donor nephrectomy. PATIENTS AND METHODS: In China, live-kidney transplant is limited. It is even more essential now, because the deceased-donor kidney has become fewer after enacting the Chinese Regulation on Human Organ Transplantation. Therefore, there is a continued need to use the limited live-donor population. We chose 103 consecutive cases (84 left and 19 right) that underwent retroperitoneoscopic live-donor nephrectomy between December 2005 and December 2009, to compare the intraoperative and postoperative characteristics between the left and right sides, and report our experiences for 19 right-retroperitoneoscopic live-donor nephrectomies. RESULTS: All 84 left and 19 right-retro peritoneoscopic live-donor nephrectomies were accomplished successfully without open conversion and transfusion. No significant differences were observed between the 2 groups regarding operative time, warm ischemia time, estimated blood loss, length of hospital stay, and serum creatinine level at discharge (Table 1). Eight of the donors and 3 of the grafts had minor complications that were all resolved with conservative treatment. The recipient's serum creatinine levels at 1 day and 1 month after surgery were the same in both groups. No acute renal tubule necrosis or delayed graft function was observed in the recipients. CONCLUSIONS: Our right-retroperitoneoscopic live-donor nephrectomy achieves comparable outcomes with the left side and proves to be a feasible, cost-effective, safe, and minimally invasive alternative for live-kidney donation. This maximally uses the innately limited donors and potentially increases the donor pool in China.