Shaolin Li's research while affiliated with Sun Yat-Sen University and other places

... The severity of COVID-19 depends on many physiological factors of which some are explainable in artificial intelligence (AI)-assisted severity classification. In a study by Liu et al. [15], 78 patients with COVID-19 were categorized as mild, regular, severe, and critical according to clinical conditions. Early triage of these patients could be supported by machine learning with CT-based clinical-radiological features. ...

... Decreased MMF and MTR were observed for cartilage and meniscus in mild and advanced OA as compared to healthy subjects. 93,94 UTE Quantitative Susceptibility Mapping Quantitative susceptibility mapping (QSM) has recently emerged as a promising technique that allows characterization of tissue based on its magnetic susceptibility. 95 QSM can estimate the spatial susceptibility distribution from a measured field perturbance using nonlinear optimization techniques. ...

... The purpose of cartilage imaging is to assess the completeness of cartilage tissue, cartilage thickness, and its relationship to subchondral bone. Ultrashort echo time (UTE) sequences represent a group of clinically compatible techniques that are capable of using echo times <1 ms [11] and has gained attention for the display of osteochondral junctions [10,[12][13][14][15][16][17][18]. Bae et al. imaged the isolated patella using the dual inversion prepared UTE sequence (DIR-UTE) and found a high signal at the osteochondral junction [12], which was not available on conventional sequences; by histological experiments, the source of the high signal at the osteochondral junction was found to be the deepest layer of the non-calcified and calcified cartilage. ...

... Previous models often used elaborate architectures as well as deeper hierarchies to improve their fitting ability and thus give them higher accuracy. While this approach can increase the model's accuracy to some extent, it tends to reduce the generalization ability of the model, and thus the effect of the improvement is on the weak side often [39,40]. Further, excessively sophisticated architecture will lead to slow and less efficient model training, and the hardware demands will likely be high. ...

... İterasyon başına işlenen örnek sayısı, önerilen modelin girdi görüntülerini eş zamanlı olarak seçilmiş değer kadar işlenmesini sağlar ve donanımsal özellikler ile doğrudan alakalıdır [27]. [11] çalışmasına göre avantajı uçtan uca bir yaklaşım önermesidir. Fakat deneysel analizlerin kuantum bilgisayarlar tarafından gerçekleştirilememesi ise bir dezavantaj olarak görülmüştür. ...

... Moreover, the interaction between miR-101-3p and PTGS2 has also been demonstrated in colon cancer, gastric cancer and esophageal squamous cell carcinoma but not in bone remodeling (Strillacci et al., 2009;Wang et al., 2010;Gong et al., 2016). In contrast, miR-186-5p and miRNA-93-5p were reported to be osteogenic differentiation inhibitors via various target genes (Zhang et al., 2017;Xu et al., 2019;Xiao et al., 2020;Li et al., 2021). Interestingly, it was reported that miR-451a induced osteoblast differentiation and mineralization in vitro and significantly reversed ovariectomy-induced bone loss in vivo (Karvande et al., 2018). ...

... After assigning each lung lobe with a score based on the degree of pneumonia, the total chest CT score is calculated as the sum of 5 lobe scores [1,[8][9][10][11]. Studies have showed that semi-quantitative chest CT scores were associated with categorized COVID-19 outcomes, and higher chest CT score was predictive of adverse outcomes [12][13][14][15]. ...

... [5] CRP in severe Covid -19patients increased significantly at the initial stage, and is a signal of lung deterioration and progression. [6] In this study, we examined the relationship between levels of inflammatory markers and CT severity score in patients with SARS-COV-2 pneumonia to prove whether or not there is a correlation between them, and thus to assess the role of CT versus biomarkers as a prognostic value for COVID-19 disease severity and short-term clinical outcome. ...

... CT manifestations of heavy/critical-type infection show consolidation of multiple lesions and interlobular septal thickening. In the paper [44], Bernheim et al. mentioned that the CT image features of COVID-19 are consolidative pulmonary opacities and bilateral and peripheral ground glass. The longer the onset of symptoms, the more findings on CT images. ...

... Two retrospective group of critically ill patients in Italy, reported a median PaO2/FiO2 was 160, with higher values in younger patients (164) than in older patients (156)" [28,29]. "Radiographic features of severe disease imaging modalities are clinically useful in revealing important findings linked to the development of the severe disease" [32]. in this study the classification of the severity of pulmonary engagement detected by X-ray or CT scan imaging was classified as previously described [21] and proved to be a good predictor of the outcome as reported in Figs. 2 and 5b, these results were in good accordance with data from literature [33,34]. ...