[Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function].

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.

Deep learning-based lung image registration: A review.

Lung image registration can effectively describe the relative motion of lung tissues, thereby helping to solve series problems in clinical applications. Since the lungs are soft and fairly passive organs, they are influenced by respiration and heartbeat, resulting in discontinuity of lung motion and large deformation of anatomic features. This poses great challenges for accurate registration of lung image and its applications. The recent application of deep learning (DL) methods in the field of medical image registration has brought promising results. However, a versatile registration framework has not yet emerged due to diverse challenges of registration for different regions of interest (ROI). DL-based image registration methods used for other ROI cannot achieve satisfactory results in lungs. In addition, there are few review articles available on DL-based lung image registration. In this review, the development of conventional methods for lung image registration is briefly described and a more comprehensive survey of DL-based methods for lung image registration is illustrated. The DL-based methods are classified according to different supervision types, including fully-supervised, weakly-supervised and unsupervised. The contributions of researchers in addressing various challenges are described, as well as the limitations of these approaches. This review also presents a comprehensive statistical analysis of the cited papers in terms of evaluation metrics and loss functions. In addition, publicly available datasets for lung image registration are also summarized. Finally, the remaining challenges and potential trends in DL-based lung image registration are discussed.

Human amniotic fluid stem cells support undifferentiated propagation and pluripotency of human embryonic stem cell without b-FGF in a density dependent manner.

Human embryonic stem cells (hESCs) are pluripotent cells which can give rise to almost all adult cell lineages. Culture system of hESCs is complex, requiring exogenous b-FGF and feeder cell layer. Human mesenchymal stem cells (MSCs) not only synthesize soluble cytokines or factors such as b-FGF, but also provide other mechanism which might play positive role on sustaining hESCs propagation and pluripotency. Human amniotic fluid stem (AFS) cells, which share characteristics of both embryonic and adult stem cells, have been regarded as promising cells for regenerative medicine. Taking advantage by AFS cells, we studied the ability of AFS cells in supporting undifferentiated propagation and pluripotency of Chinese population derived X-01 hESCs. Human AF-type amniotic fluid stem cells (hAF-AFSCs) transcribed genes including Activin A, TGF-ß1, Noggin and b-FGF, which involved in maintaining pluripotency and self-renewal of hESCs. Compared to mouse embryonic fibroblasts (MEFs), hAF-AFSCs secreted higher concentration of b-FGF which was important in hESCs culture (P < 0.05). The hESCs were propagated more than 30 passages on hAF-AFSCs layer with exogenous b-FGF supplementation, keeping undifferentiated status. While exogenous b-FGF was obviated, propagation of hESCs with undifferentiated status was dependent on density of hAF-AFSC feeder layer. Lower density of hAF-AFSCs resulted in rapid decline in undifferentiated clone number, while higher ones hindered the growth of colonies. The most appropriate hAF-AFSCs feeder density to maintain the X-01 hESC line without exogenous b-FGF was 15-20×10(4)/well. To the best of our knowledge, this is the first study demonstrating that hAF-AFSCs could support undifferentiated propagation and pluripotency of Chinese population derived hESCs without exogenous b-FGF supplementation.