Mix-and-Interpolate: A Training Strategy to Deal With Source-Biased Medical Data.

Till March 31st, 2021, the coronavirus disease 2019 (COVID-19) had reportedly infected more than 127 million people and caused over 2.5 million deaths worldwide. Timely diagnosis of COVID-19 is crucial for management of individual patients as well as containment of the highly contagious disease. Having realized the clinical value of non-contrast chest computed tomography (CT) for diagnosis of COVID-19, deep learning (DL) based automated methods have been proposed to aid the radiologists in reading the huge quantities of CT exams as a result of the pandemic. In this work, we address an overlooked problem for training deep convolutional neural networks for COVID-19 classification using real-world multi-source data, namely, the data source bias problem. The data source bias problem refers to the situation in which certain sources of data comprise only a single class of data, and training with such source-biased data may make the DL models learn to distinguish data sources instead of COVID-19. To overcome this problem, we propose MIx-aNd-Interpolate (MINI), a conceptually simple, easy-to-implement, efficient yet effective training strategy. The proposed MINI approach generates volumes of the absent class by combining the samples collected from different hospitals, which enlarges the sample space of the original source-biased dataset. Experimental results on a large collection of real patient data (1,221 COVID-19 and 1,520 negative CT images, and the latter consisting of 786 community acquired pneumonia and 734 non-pneumonia) from eight hospitals and health institutions show that: 1) MINI can improve COVID-19 classification performance upon the baseline (which does not deal with the source bias), and 2) MINI is superior to competing methods in terms of the extent of improvement.

Accurate and efficient pulmonary CT imaging workflow for COVID-19 patients by the combination of intelligent guided robot and automatic positioning technology.

BACKGROUND: The ongoing coronavirus disease 2019 (COVID-19) pandemic has put radiologists at a higher risk of infection during the computer tomography (CT) examination for the patients. To help settling these problems, we adopted a remote-enabled and automated contactless imaging workflow for CT examination by the combination of intelligent guided robot and automatic positioning technology to reduce the potential exposure of radiologists to 2019 novel coronavirus (2019-nCoV) infection and to increase the examination efficiency, patient scanning accuracy and better image quality in chest CT imaging . METHODS: From February 10 to April 12, 2020, adult COVID-19 patients underwent chest CT examinations on a CT scanner using the same scan protocol except with the conventional imaging workflow (CW group) or an automatic contactless imaging workflow (AW group) in Wuhan Leishenshan Hospital (China) were retrospectively and prospectively enrolled in this study. The total examination time in two groups was recorded and compared. The patient compliance of breath holding, positioning accuracy, image noise and signal-to-noise ratio (SNR) were assessed by three experienced radiologists and compared between the two groups. RESULTS: Compared with the CW group, the total positioning time of the AW group was reduced ((118.0 ± 20.0) s vs. (129.0 ± 29.0) s, P = 0.001), the proportion of scanning accuracy was higher (98% vs. 93%), and the lung length had a significant difference ((0.90±1.24) cm vs. (1.16±1.49) cm, P = 0.009). For the lesions located in the pulmonary centrilobular and subpleural regions, the image noise in the AW group was significantly lower than that in the CW group (centrilobular region: (140.4 ± 78.6) HU vs. (153.8 ± 72.7) HU, P = 0.028; subpleural region: (140.6 ± 80.8) HU vs. (159.4 ± 82.7) HU, P = 0.010). For the lesions located in the peripheral, centrilobular and subpleural regions, SNR was significantly higher in the AW group than in the CW group (centrilobular region: 6.6 ± 4.3 vs. 4.9 ± 3.7, P = 0.006; subpleural region: 6.4 ± 4.4 vs. 4.8 ± 4.0, P < 0.001). CONCLUSIONS: The automatic contactless imaging workflow using intelligent guided robot and automatic positioning technology allows for reducing the examination time and improving the patient's compliance of breath holding, positioning accuracy and image quality in chest CT imaging.

A comparison between manual and artificial intelligence-based automatic positioning in CT imaging for COVID-19 patients.

OBJECTIVE: To analyze and compare the imaging workflow, radiation dose, and image quality for COVID-19 patients examined using either the conventional manual positioning (MP) method or an AI-based automatic positioning (AP) method. MATERIALS AND METHODS: One hundred twenty-seven adult COVID-19 patients underwent chest CT scans on a CT scanner using the same scan protocol except with the manual positioning (MP group) for the initial scan and an AI-based automatic positioning method (AP group) for the follow-up scan. Radiation dose, patient positioning time, and off-center distance of the two groups were recorded and compared. Image noise and signal-to-noise ratio (SNR) were assessed by three experienced radiologists and were compared between the two groups. RESULTS: The AP operation was successful for all patients in the AP group and reduced the total positioning time by 28% compared with the MP group. Compared with the MP group, the AP group had significantly less patient off-center distance (AP 1.56 cm ± 0.83 vs. MP 4.05 cm ± 2.40, p < 0.001) and higher proportion of positioning accuracy (AP 99% vs. MP 92%), resulting in 16% radiation dose reduction (AP 6.1 mSv ± 1.3 vs. MP 7.3 mSv ± 1.2, p < 0.001) and 9% image noise reduction in erector spinae and lower noise and higher SNR for lesions in the pulmonary peripheral areas. CONCLUSION: The AI-based automatic positioning and centering in CT imaging is a promising new technique for reducing radiation dose and optimizing imaging workflow and image quality in imaging the chest. KEY POINTS: • The AI-based automatic positioning (AP) operation was successful for all patients in our study. • AP method reduced the total positioning time by 28% compared with the manual positioning (MP). • AP method had less patient off-center distance and higher proportion of positioning accuracy than MP method, resulting in 16% radiation dose reduction and 9% image noise reduction in erector spinae.

Features of family clusters of COVID-19 patients: A retrospective study.

BACKGROUND: To investigate and compare the clinical and imaging features among family members infected with COVID-19. METHODS: We retrospectively collected a total of 34 COVID-19 cases (15 male, 19 female, aged 48 ± 16 years, ranging from 10 to 81 years) from 13 families from January 17, 2020 through February 15, 2020. Patients were divided into two groups: Group 1 - part of the family members (first-generation) who had exposure history and others (second-generation) infected through them, and Group 2 - patients from the same family having identical exposure history. We collected clinical symptoms, laboratory findings, and high-resolution computed tomography (HRCT) features for each patient. Comparison tests were performed between the first- and second-generation patients in Group 1. RESULTS: In total there were 21 patients in Group 1 and 20 patients in Group 2. For Group 1, first-generation patients had significantly higher white blood cell count (6.5 × 109/L (interquartile range (IQR): 4.9-9.2 × 109/L) vs 4.5 × 109/L (IQR: 3.7-5.3 × 109/L); P = 0.0265), higher neutrophil count (4.9 × 109/L (IQR: 3.6-7.3 × 109/L) vs 2.9 × 109/L (IQR: 2.1-3.3 × 109/L); P = 0.0111), and higher severity scores on HRCT (3.9 ± 2.4 vs 2.0 ± 1.3, P = 0.0362) than the second-generation patients. Associated underlying diseases (odds ratio, 8.0, 95% confidence interval: 3.4-18.7, P = 0.0013) were significantly correlated with radiologic severity scores in second-generation patients. CONCLUSION: Analysis of the family cluster cases suggests that COVID-19 had no age or sex predominance. Secondarily infected patients in a family tended to develop milder illness, but this was not true for those with existing comorbidities.

A fatal outcome from SARS-CoV-2 infection: One case report of a young man with multiple organ damage.

The coronavirus disease 2019 (COVID-19) first emerged in Wuhan, China on December 2019 and has become a severe public health issue worldwide. A 36-year-old man was presented to the hospital staff with a fever that had already persisted for a three-day period, general weakness and diarrhea. He had no chronic diseases and was tested positive for COVID-19 with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) nucleic acid. During his hospitalization, several abnormal indicators appeared in his laboratory tests, which implied systemic inflammation and multiple organ damage. A series of chest radiographs monitored the dynamic process of lung lesions, which could predict the clinical changes of the patient. His condition deteriorated rapidly, resulting in death due to acute respiratory distress syndrome (ARDS) on hospital day 13. The case indicates that inflammatory response may appear in people infected with SARS-CoV-2 and may lead to multiple organ damage (especially pancreatic damage). When a COVID-19 patient is entering into the critical stage, their condition could rapidly deteriorate.