Self-Supervised monocular depth and ego-Motion estimation in endoscopy: Appearance flow to the rescue.

Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios. One widely adopted assumption of depth and ego-motion self-supervised learning is that the image brightness remains constant within nearby frames. Unfortunately, the endoscopic scene does not meet this assumption because there are severe brightness fluctuations induced by illumination variations, non-Lambertian reflections and interreflections during data collection, and these brightness fluctuations inevitably deteriorate the depth and ego-motion estimation accuracy. In this work, we introduce a novel concept referred to as appearance flow to address the brightness inconsistency problem. The appearance flow takes into consideration any variations in the brightness pattern and enables us to develop a generalized dynamic image constraint. Furthermore, we build a unified self-supervised framework to estimate monocular depth and ego-motion simultaneously in endoscopic scenes, which comprises a structure module, a motion module, an appearance module and a correspondence module, to accurately reconstruct the appearance and calibrate the image brightness. Extensive experiments are conducted on the SCARED dataset and EndoSLAM dataset, and the proposed unified framework exceeds other self-supervised approaches by a large margin. To validate our framework's generalization ability on different patients and cameras, we train our model on SCARED but test it on the SERV-CT and Hamlyn datasets without any fine-tuning, and the superior results reveal its strong generalization ability. Code is available at: https://github.com/ShuweiShao/AF-SfMLearner.

GINS2 attenuates the development of lung cancer by inhibiting the STAT signaling pathway.

GINS complex subunit 2 (GINS2) controls DNA replication. GINS2 expression is upregulated in several kinds of aggressive tumors. However, the effect of GINS2 in lung cancer remains unclear. We performed TCGA database analysis to confirm the clinical significance of GINS2 in lung cancer. After silencing GINS2 in A549 cells, we performed MTT assays, flow cytometry assays, colony formation assays, cell cycle analyses and RNA sequence analysis to elucidate the effect of GINS2 on lung cancer. Moreover, we assessed tumor growth and analyzed body fluorescence in mice as a measure of tumor burden. The TCGA database analysis demonstrated that GINS2 mRNA and protein was highly expressed in three kinds of lung cancer tissues. Subsequently, knockdown of GINS2 inhibited cell proliferation, colony formation, cell cycle arrest and apoptosis in A549 cells. On the other hand, we also investigated the effect of GINS2 on tumor formation in vivo. The analysis of nude mouse tumors showed that the tumor volume and weight of shGINS2 mice were significantly smaller than those of the control mice. To reveal the mechanism of GINS2 in lung cancer, we collected A549 cells with GINS2 knockdown to examine the downstream gene expression changes. The results showed that STAT1 and STAT2 mRNA and protein expression were significantly upregulated after GINS2 knockdown in A549 cells. Our results suggest that GINS2 inhibits the proliferation of lung cancer cells by inhibiting the STAT signaling pathway, which may be a potential biomarker for the diagnosis or prognosis of lung cancer.

Detecting vulnerable plaque with vulnerability index based on convolutional neural networks.

Plaque rupture and subsequent thrombosis are major processes of acute cardiovascular events. The Vulnerability Index is a very important indicator of whether a plaque is ruptured, and these easily ruptured or fragile plaques can be detected early. The higher the general vulnerability index, the higher the instability of the plaque. Therefore, determining a clear vulnerability index classification point can effectively reduce unnecessary interventional therapy. However, the current critical value of the vulnerability index has not been well defined. In this study, we proposed a neural network-based method to determine the critical point of vulnerability index that distinguishes vulnerable plaques from stable ones. Firstly, based on MatConvNet, the intravascular ultrasound images under different vulnerability index labels are classified. Different vulnerability indexes can obtain different accuracy rates for the demarcation points. The corresponding data points are fitted to find the existing relationship to judge the highest classification. In this way, the vulnerability index corresponding to the highest classification accuracy rate is judged. Then the article is based on the same experiment of different components of the aortic artery in the artificial neural network, and finally the vulnerability index corresponding to the highest classification accuracy can be obtained. The results show that the best vulnerability index point is 1.716 when the experiment is based on the intravascular ultrasound image, and the best vulnerability index point is 1.607 when the experiment is based on the aortic artery component data. Moreover, the vulnerability index and classification accuracy rate has a periodic relationship within a certain range, and finally the highest AUC is 0.7143 based on the obtained vulnerability index point on the verification set. In this paper, the convolution neural network is used to find the best vulnerability index classification points. The experimental results show that this method has the guiding significance for the classification and diagnosis of vulnerable plaques, further reduce interventional treatment of cardiovascular disease.

MiR-29c reduces the cisplatin resistance of non-small cell lung cancer cells by negatively regulating the PI3K/Akt pathway.

In previous studies, miR-29s showed tumor suppressor properties against lung cancer, which improved the survival of patients upon the administration of chemotherapy via an unknown mechanism. Here, we investigated the regulatory effects of miR-29s on the cisplatin resistance of NSCLC cells. The expression of miR-29s was assessed in 130 clinical patients and in cisplatin-treated NSCLS cell lines. MiR-29c expression was decreased in 77% of NSCLC patients. Cisplatin treatment increased the expression of miR-29c and decreased the expression of its oncogenic target AKT2 in NSCLC cell lines. A Kaplan-Meier survival analysis indicated that higher miR-29c levels led to a longer disease-free survival. In particular, patients who experienced cancer recurrences after cisplatin chemotherapy exhibited a lower level of miR-29c expression, suggesting that miR-29c activation may contribute to the chemotherapeutic efficiency of cisplatin. The enforced expression of miR-29c enhanced the cisplatin sensitivity of NSCLC cells, while the knocking down of miR-29c led to cisplatin resistance. MiR-29c amplified the therapeutic effects of cisplatin in vivo. Rescue experiments suggested that miR-29c regulates the cisplatin resistance of NSCLS cells by negatively regulating the PI3K/Akt pathway. Overall, our results demonstrated that miR-29c enhances the sensitivity of NSCLC cells to cisplatin by targeting the PI3K/Akt pathway.

Impaired myocardium energetics associated with the risk for new-onset atrial fibrillation after isolated coronary artery bypass graft surgery.

BACKGROUND: New-onset postoperative atrial fibrillation (POAF) is one of the most common complications occurring in 10-40% of patients after coronary artery bypass graft (CABG) surgery. Recent studies suggest that dysmetabolism may contribute to the pathogenesis of atrial fibrillation; however, the putative mechanism in patients undergoing CABG surgery is unknown. Peroxisome proliferator-activated receptor γ coactivator-1α (PGC-1α) has been demonstrated as a master regulator of myocardial energy metabolism, and glucose transporter 3 (GLUT3) has both a higher affinity for glucose and a much greater transport capacity compared with GLUT1, GLUT2, and GLUT4. We sought to evaluate the role of energy metabolism, especially the glucose metabolism, on patients after isolated CABG surgery. METHODS AND RESULTS: Right atrial appendages were obtained from 79 patients who were in normal sinus rhythm and undergoing isolated CABG; those who exhibited new-onset POAF (n=22) or remained in sinus rhythm (n=57) were prospectively matched on the basis of preoperative, intraoperative, and postoperative characteristics. POAF was assessed by electrocardiogram and must have required the initiation of antiarrhythmic therapy or anticoagulation. Local PGC-1α and GLUT3 concentrations were quantified by enzyme-linked immunosorbent assay in tissue homogenates. The comparison of mRNA expression was tested by quantitative real-time PCR. PGC-1α and GLUT3 levels and the related protein mRNA expression were significantly reduced in POAF patients compared with controls (P<0.05). This selective reduction in PGC-1α was associated with the presence of diabetes mellitus (P<0.05). CONCLUSION: Patients who have low PGC-1α and GLUT3 levels are at increased risk for new-onset POAF. The myofibrillar energetic impairment may be important in the pathogenesis of atrial fibrillation.