Exploiting both RGB (2D appearance) and Depth (3D geometry) information can improve the performance of semantic segmentation. However, due to the inherent difference between the RGB and Depth information, it remains a challenging problem in how to integrate RGB-D features effectively. In this letter, to address this issue, we propose a Non-local Aggregation Network (NANet), with a well-designed Multi-modality Non-local Aggregation Module (MNAM), to better exploit the non-local context of RGB-D features at multi-stage. Compared with most existing RGB-D semantic segmentation schemes, which only exploit local RGB-D features, the MNAM enables the aggregation of non-local RGB-D information along both spatial and channel dimensions. The proposed NANet achieves comparable performances with state-of-the-art methods on popular RGB-D benchmarks, NYUDv2 and SUN-RGBD.

Deep learning-based intelligent electrocardiogram (ECG) diagnosis algorithms heavily rely on large annotated datasets. Unfortunately, in the context of ECG diagnosis, privacy issues and the high cost of data annotations lead to a shortage of ECG datasets which severely limits the performance of the state-of-the-art ECG diagnosis algorithms. In this paper, we propose a novel instance-level contrastive learning scheme for ECG signals, namely CLECG, to mine effective information from unlabeled data. During the pre-training, CLECG encourages the representations of different augmented views of the same signal (positive samples) to be similar and increases the distance between representations of augmented views from the different signals (negative samples). The whole pre-training process does not require any form of labeling. Experimental results show that the proposed CLECG strategy outperforms other self-supervised methods and supervised transfer learning strategies.

Primary cardiac sarcomas are exceedingly rare, and they commonly result in nonspecific constitutional symptoms such as shortness of breath, weight loss, and anaemia-related fatigue and malaise. However, thrombocytopenia has very rarely been reported in association with cardiac tumours, either benign or malignant. We report one case of primary cardiac synovial sarcoma continuous with the mitral valve, which was accompanied by severe thrombocytopenia, and the platelet counts returned rapidly to a normal range early after tumour excision and without any special therapies. A 52-year-old male diagnosed with atrial myxoma with severe thrombocytopenia was admitted to our hospital. Blood analysis showed severe thrombocytopenia, whereas erythrocyte and leucocyte counts were within the normal range. A 50 × 35 mm mobile mass continuous with the mitral valve was found to be present in the left atrium upon echocardiography. Bone marrow aspiration and related examinations excluded thrombocytopenia caused by haematologic malignancies. The patient received a platelet transfusion, but platelet counts decreased quickly. Glucocorticoid therapy and immunoglobulin transfusion were also used, but were ineffective. Although the operation risk was high, tumour resection was performed via a median sternotomy with a cardiopulmonary bypass system. The postoperative pathological diagnosis was biphasic cardiac synovial sarcoma. Surprisingly, the platelet counts returned rapidly to a normal range early after tumour excision without any special therapies. The disappearance of the tumour from the annular region was confirmed on transthoracic echocardiography 6 days after surgery, and an FDG-PET scan performed 8 days after surgery showed no abnormal accumulation. Unfortunately, the patient died suddenly 6 months later without unknown cause. We report that a rare primary cardiac synovial sarcoma case continuous with the mitral valve caused severe thrombocytopenia; this provides further support for the awareness and diagnosis of primary cardiac synovial sarcoma. We also highlight that thrombocytopenia might be one rare symptom of a solid cardiac tumour but need more cases for support.

Owing to the high patency, the use of the left internal mammary artery (LIMA) for left anterior descending artery (LAD) grafting has been a cornerstone of coronary artery bypass grafting surgery (CABG). However, for some patients whose LIMA cannot be used, surgeons have to choose other conduit materials to revascularize the LAD. The purpose of this study was to explore the differences in different conduit materials used for LAD in terms of parameters measured by transit-time flow measurement (TTFM) and the early graft patency detected by computed tomography angiography. We retrospectively collected the data of 410 patients who underwent isolated primary OPCAB with intraoperative TTFM data. According to the strategy of the LAD revascularization, 410 patients were assigned to three groups: a left internal mammal artery (LIMA) group (n = 333), a right IMA (RIMA) group (n = 34) and a great saphenous vein (SVG) group (n = 43). The baseline and perioperative blood parameters were compared for the three groups, as well as the early graft patency rates. Compared with the LIMA-LAD group, the SVG-LAD group had a significantly higher mean graft flow volume (MGF) (37.15 ± 23.29 vs 29.71 ± 20.94 ml/min, P = 0.036), however, had a lower value of pulse index (PI) (2.07 ± 0.62 vs 2.65 ± 1.01, P0.05). Compared with the RIMA-LAD group, the SVG-LAD group just had a lower value of PI (2.07 ± 0.62 vs 2.56 ± 0.96, P = 0.029). However, there was no significant difference between the two groups in terms of MGF and DF (P>0.05). Compared with the LIMA-LAD group, the RIMA-LAD group had a slightly lower value of DF (70.76 ± 11.87 vs 74.06 ± 7.09, P = 0.018), while there was no difference in terms of MGF and PI between the two groups (P>0.05). The patency rate of the LIMA-LAD group was 98.72% (309/313), that of RIMA-LAD group was 97.06% (33/34), and that of SVG-LAD group was 100%. There was no difference among the three groups in patency rate (P = 0.405). SVG-LAD has a higher intraoperative MGF and a lower value of the PI than both LIMA-LAD and RIMA-LAD. RIMA has a higher preoperative blood flow and a lower value of the PI than LIMA; however, there were no significant difference between RIMA grafted to LAD and LIMA grafted to LAD in terms of MGF, PI and DF. In situ skeletonized RIMA did not increase blood flow compared to pedicled LIMA.

A 66‐year‐old Asian female diagnosed with an occupied mass of the inferior vena cava (IVC) case with extension to the right atrium, bilateral renal vasculature, and venae iliaca communis, which caused severe thrombocytopenia and severe liver and kidney dysfunction. The postoperative pathological diagnosis was high‐grade undifferentiated intimal sarcoma. There have been less than 10 cases of venous undifferentiated intimal sarcomas reported in the literature, three of which occurred in the IVC. Unfortunately, the patient died of multiple organ failure in the intensive care unit postoperatively.

Background: This is an experimental study performed on 15 adult cadavers. In this cadaveric study, we designed and evaluated a novel methodology for determining the optimal trajectory for the placement of thoracic pedicle screws. The accuracy of thoracic pedicle screw placement is critical to the spinal surgery. The concept, implement method, and significance of the optimal thoracic pedicle trajectory have not been reported. Methods: The experimental study was performed on 15 adult cadavers. The Mimics software was used to design optimal trajectory through the pedicle central axis. Using three-dimensional (3D) printing, a navigation module with a locating facet and a stabilizing facet was developed. The thoracic pedicle screws were inserted with the help of the navigation module. The three-dimensional coordinates for the entry and the exit points of the screws were compared between the planned trajectories and the postoperative trajectories. The differences in coordinates were analyzed to evaluate the precision of the screw placement. Results: The trajectories through the pedicle central axis showed an excellent symmetry between the single segments and for all thoracic vertebrae. Out of a total of 358 screws that were inserted, 15 (4.2%) screws breached the pedicle cortex with a breach distance of 0.05). Conclusions: The optimal trajectory was obtained through the pedicle central axis, which significantly reduced the risk of cortex breach. A high degree of precision was obtained for the entry and the exit points of the screws when the postoperative trajectory was compared with the designed trajectory.