Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function / 生物医学工程学杂志

Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.

Research progress in lung parenchyma segmentation based on computed tomography / 生物医学工程学杂志

Lung diseases such as lung cancer and COVID-19 seriously endanger human health and life safety, so early screening and diagnosis are particularly important. computed tomography (CT) technology is one of the important ways to screen lung diseases, among which lung parenchyma segmentation based on CT images is the key step in screening lung diseases, and high-quality lung parenchyma segmentation can effectively improve the level of early diagnosis and treatment of lung diseases. Automatic, fast and accurate segmentation of lung parenchyma based on CT images can effectively compensate for the shortcomings of low efficiency and strong subjectivity of manual segmentation, and has become one of the research hotspots in this field. In this paper, the research progress in lung parenchyma segmentation is reviewed based on the related literatures published at domestic and abroad in recent years. The traditional machine learning methods and deep learning methods are compared and analyzed, and the research progress of improving the network structure of deep learning model is emphatically introduced. Some unsolved problems in lung parenchyma segmentation were discussed, and the development prospect was prospected, providing reference for researchers in related fields.

Current Status and Prospects of Non-Invasive Central Arterial Pressure Measurement / 医用生物力学

Cardiovascular disease is one of the important factors that threaten the health of residents, ranking the first among various causes of death, so the monitoring and diagnosis of human cardiovascular health is particularly important. Compared with traditional brachial artery pressure, central arterial pressure (CAP) has a higher correlation with the occurrence of many cardiovascular events. The measurement of CAP can more accurately reflect the real situation of human blood pressure, and provide an important basis for diagnosis and disease prevention. Therefore, the realization of high-precision, high-generalization ability and low-cost non-invasive measurement of CAP has always been the research focus in this field. This article combines the relevant literature in China and abroad to summarize the current status of CPA measurement, introduces related research progress from two aspects, namely parameter measurement and waveform measurement, and discusses the characteristics of the existing methods and the future development.

Prevention and treatment of fungous infection complications of hematopoietic stem cell transplantation / 中国综合临床

Objective To retrospectively evaluate the incidence and treatment of fungous infection compli-cations after hematopoietic stem cell transplantation. Methods The incidence, pathogenic microorganism, prophy-laxis,treatments of infectious complications in 150 patients, who accepted hematopoietic stem cell transplantation from September 1990 to Martch 2000 in our hospital were analyzed. Results The incidence of infectious complica-tions was 89.3% (134/150) in all 150 cases. Three patients (2%) died of the fungal infection. The incidence of the fungal infections was 32.5% (26/80) in patients who accepted treatment with impenem or/and ceftazidine, and 15.7% (11/70) in other patients without the above treatment (P<0.05). 12 fungal infection cases were treated with small-dosage of amphotericin B(10 mg/d) ,with the healing rate was 100%. Conclusion The strong antibac-terial prophylaxis can't reduce the incidence of infection ,but may increase the risk of fungal infection;small-dosage of amphotericin B is a new effective way to treat fungal infection.

Autologous hematopoietic stem cell transplantation in the treatment of patients with poor-prognosis non-Hodgkin iymphoma / 白血病·淋巴瘤

Objective To observe the therapeutic effectiveness and safety of autologous peripheral blood stem cell transplantation (APBSCT) for poor-risk non-Hodgkin lymphoma (NHL). Methods Ten patients with poor-prognosis NHL were enrolled from October 2003 to October 2008 in our institute. Ten patients were treated by APBSCT with CY+TBI conditioning regimen (Two patients of them were treated by Double-APBSCT with MEC conditioning regimen). Results Hematopoietic reconstitution was observed in all patients.The time of neutrophil count ≥0.5×109L and platelet≥20×109/L were at day 10 (range: 7-14) and day 16 (range: 10-37), respectively. All patients achieved complete remission (CR) after transplantation. Severe toxicity and transplant related mortality were not observed. After a median follow-up of 24 (10-84) months,seven cases were in event-free survival and three cases relapsed. One of three relapsed patients died from progression of disease, the other was still alive after treatment. Conclusion APBSCT in the treatment of patients with poor-prognosis NHL is a safe, convenient and efficient treatment.

Salvia miltiorrhiza combined with dextran to prevent veno-occlusive disease after hematopoietic stem cell transplantation / 白血病·淋巴瘤

Objective To investigate the clinic effect of the Salvia miltiorrhiza combined with dextran to prevent veno-occlusive disease after hematopoietic stem cell transplantation. Methods In the process of the pretreatment of the hematopoietic stem cell transplantation, patients were treated with salvia miltiorrhiza (20 ml/d), dextran(250 ml, twice a day) by venous transfusion and the drugs to protect the liver cell was used in the same time. When the count of platelet dropped to 30×109/L, salvia miltiorrhiza and dextranware stopped applying forever. Results Veno-occlusive disease and hemorrhage has not occurred during 85 times of the hematopoietic stem cell transplantation treated with salvia miltiorrhiza and dextran. Conclusion We conclude that the combined treatment with salvia miltiorrhiza and dextran is safe and effective to prevent veno-occlusive disease after hematopoietic stem cell transplantation.

Clinical Research on Infectious Complications after Hematopoietic Stem Cell Transplantation / 中华医院感染学杂志

OBJECTIVE To evaluate retrospectively the incidence and treatment of infectious complications within the first 60 days after hematopoietic stem cell transplantation,and to find more efficient anti-infective regimens. METHODS To study the incidence,pathogenic microorganism,prophylaxis,treatments of infectious complications in 150 patients accepted hematopoietic stem cell transplantation from April 1984 to March 1998 in our hospital.The results were analyzed statistically.RESULTS Incidence of infectious complications was 89.3% in all 150 cases.Three patients(2%) died of the fungal infection.The incidence of the infections was 32.5% in patients accepted treatment with imipenem or／and ceftazidine,and 15.7% in other patients without the treatment with imipenem or／and ceftazidine(P＜0.02).CONCLUSIONS The strong antibacterial prophylaxis can′t reduce the incidence of infection,and may increase the chance of fungal infection.