SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning.

Coronavirus disease (COVID-19) broke out at the end of 2019, and has resulted in an ongoing global pandemic. Segmentation of pneumonia infections from chest computed tomography (CT) scans of COVID-19 patients is significant for accurate diagnosis and quantitative analysis. Deep learning-based methods can be developed for automatic segmentation and offer a great potential to strengthen timely quarantine and medical treatment. Unfortunately, due to the urgent nature of the COVID-19 pandemic, a systematic collection of CT data sets for deep neural network training is quite difficult, especially high-quality annotations of multi-category infections are limited. In addition, it is still a challenge to segment the infected areas from CT slices because of the irregular shapes and fuzzy boundaries. To solve these issues, we propose a novel COVID-19 pneumonia lesion segmentation network, called Spatial Self-Attention network (SSA-Net), to identify infected regions from chest CT images automatically. In our SSA-Net, a self-attention mechanism is utilized to expand the receptive field and enhance the representation learning by distilling useful contextual information from deeper layers without extra training time, and spatial convolution is introduced to strengthen the network and accelerate the training convergence. Furthermore, to alleviate the insufficiency of labeled multi-class data and the long-tailed distribution of training data, we present a semi-supervised few-shot iterative segmentation framework based on re-weighting the loss and selecting prediction values with high confidence, which can accurately classify different kinds of infections with a small number of labeled image data. Experimental results show that SSA-Net outperforms state-of-the-art medical image segmentation networks and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage. Meanwhile, our semi-supervised iterative segmentation model can improve the learning ability in small and unbalanced training set and can achieve higher performance.

Modified lung ultrasound scoring system to evaluate the feasibility of pregnant women with COVID-19 pneumonia.

OBJECTIVE: To investigate whether physicians with short-term training can use a modified lung ultrasound scoring system for coronavirus disease 2019 (COVID-19) pneumonia to assess lung damage in pregnant women. METHODS: Sixteen consecutively hospitalized third-trimester pregnant women with pregnancy-induced hypertension, preeclampsia, rheumatoid arthritis or connective tissue disease were selected as the study subjects for the simulation of COVID-19 pneumonia. Two physicians (imaging and internal medicine) without ultrasonic experience performed lung examinations on pregnant women after six days of lung ultrasound training, and their consistency with examinations by the expert was assessed. In addition, 54 healthy third-trimester pregnant women and 54 healthy nonpregnant women of the same age who were continuously treated in the outpatient clinic of this hospital were selected for comparisons of abnormalities on lung ultrasound. RESULTS: (1) Third trimester pregnant women with pregnancy-induced hypertension, preeclampsia, rheumatoid arthritis or connective tissue disease had the same lung ultrasound patterns as those associated with COVID-19 pneumonia. (2) There was no statistically significant difference between the scores of the two trained doctors and the expert when the modified ultrasound scoring system was used (p > .05). (3) The evaluations of the two trained doctors and the expert showed good consistency (kappa value = 0.833-0.957). (4) The incidence of abnormal ultrasound manifestations of the pleura and lung parenchyma was higher among healthy third-trimester pregnant women than among healthy women of the same age (p < .001). CONCLUSIONS: After receiving short-term training, imaging and internal medicine physicians can use the modified lung ultrasound scoring system to evaluate pregnant women's pulmonary damage, but caution is needed to avoid false-positive results among pregnant women with suspected COVID-19 pneumonia.

Quality evaluation of online courses during COVID-19 pandemic based on integrated FCE-AHP method

After sudden outbreak of COVID-19 pandemic, the university campuses were closed and millions of university teachers and students had to shift teaching and learning activities from the classrooms to online courses in China. The COVID-19 pandemic undoubtedly brought significant negative effects to university education activities. How does COVID-19 influenced teaching quality and the degree of influences have been studied by many researches. However, the online course quality which is influences by COVID-19 pandemic was commonly evaluated qualitatively rather than quantitatively. In order to obtain quantitative evaluation results of online course quality during the pandemic period, the integrated FCE-AHP evaluation was applied. Based on real case of online courses, the influence factors of online course quality were divided into four first-level indicators and further subdivided into 14 second level indicators. The weight vectors of evaluation indicators were determined based on experts’ comments from the Teaching Affairs Committee and the fuzzy evaluation memberships were calculated based on questionnaire results of 2021 students. The evaluation results revealed that the integral performance of online courses is acceptable and the performances of students and hardware are relative weaker. Finally, some improvement measures were conducted to deal with difficulties encountered in online courses during COVID-19 pandemic period. [ABSTRACT FROM AUTHOR] Copyright of Journal of Intelligent & Fuzzy Systems is the property of IOS Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Use of Lung Ultrasound to Differentiate Coronavirus Disease 2019 (COVID-19) Pneumonia From Community-Acquired Pneumonia.

To investigate the feasibility of lung ultrasound in evaluating coronavirus disease 2019 (COVID-19) and distinguish the sonographic features between COVID-19 and community-acquired pneumonia (CAP), a total of 12 COVID-19 patients and 20 CAP patients were selected and underwent lung ultrasound. The modified Buda scoring system for interstitial lung disease was used to evaluate the severity and treatment effect of COVID-19 on ultrasonography. The differences between modified lung ultrasound (MLUS) score and high-resolution computed tomography (HRCT) Warrick score were analyzed to evaluate their correlation. COVID-19 showed the following sonographic features: thickening (12/12), blurred (9/12), discontinuous (6/12) pleural line; rocket sign (4/12), partially diffused B-line (12/12), completely diffused B-line (10/12), waterfall sign (4/12); C-line sign (5/12); pleural effusion (1/12) and pulmonary balloon (Am line, 1/12). The last two features were rarely seen. Differences of ultrasonic features, including lesion range, lung signs and pneumonia-related complications, between COVID-19 and CAP were statistically significant (p˂ 0.05 or 0.001). MLUS scores (p = 0.006) and HRCT Warrick scores (p = 0.015) increased as the severity of COVID-19 increased. The differences between moderate (29.00 [25.75-37.50]) and severe (43.00 [38.75-47.25]) (p = 0.022) or between moderate and critical (47.50 [44.25-50.00]) (p = 0.002) type COVID-19 were statistically significant, compared with those between severe and critical types. Correlation between MLUS scores and HRCT Warrick scores was positive (r = 0.54, p = 0.048). MLUS scores (Z = 2.61, p = 0.009) and HRCT Warrick scores (Z = 2.63, p = 0.009) of five severe or critical COVID-19 patients significantly decreased as their conditions improved after treatment. The differences of sonographic features between COVID-19 and CAP patients were notable. The MLUS scoring system could be used to evaluate the severity and treatment effect of COVID-19.