Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans.

BACKGROUND: The coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically distinguishing between them is crucial. METHODS: A deep learning method for distinguishing COVID-19 from CAP is developed using maximum intensity projection (MIP) images from CT scans. LinkNet is employed for lung segmentation of chest CT images. MIP images are produced by superposing the maximum gray of intrapulmonary CT values. The MIP images are input into a capsule network for patient-level pred iction and diagnosis of COVID-19. The network is trained using 333 CT scans (168 COVID-19/165 CAP) and validated on three external datasets containing 3581 CT scans (2110 COVID-19/1471 CAP). RESULTS: LinkNet achieves the highest Dice coefficient of 0.983 for lung segmentation. For the classification of COVID-19 and CAP, the capsule network with the DenseNet-121 feature extractor outperforms ResNet-50 and Inception-V3, achieving an accuracy of 0.970 on the training dataset. Without MIP or the capsule network, the accuracy decreases to 0.857 and 0.818, respectively. Accuracy scores of 0.961, 0.997, and 0.949 are achieved on the external validation datasets. The proposed method has higher or comparable sensitivity compared with ten state-of-the-art methods. CONCLUSIONS: The proposed method illustrates the feasibility of applying MIP images from CT scans to distinguish COVID-19 from CAP using capsule networks. MIP images provide conspicuous benefits when exploiting deep learning to detect COVID-19 lesions from CT scans and the capsule network improves COVID-19 diagnosis.

Experimental study on the monotonic mechanical behavior of completely decomposed granite soil reinforced by disposable face-mask chips.

In response to the global outbreak of the coronavirus pandemic (COVID-19), a staggering amount of personal protective equipment, such as disposable face masks, has been used, leading to the urgent environmental issue. This study evaluates the feasibility of mask chips for the soil reinforcement, through triaxial tests on samples mixed with complete decomposed granite (CDG) and mask chips (0%, 0.3%, 0.5%, 1%, 5% by volume). The experimental results show that adding a moderate volumetric amount of mask chips (0.3%-1%) improves the soil strength, especially under high confining pressure. The optimum volumetric content of mask chips obtained by this study is 0.5%, raising the peak shear strength up to 22.3% under the confining stress of 120 kPa. When the volumetric content of mask chips exceeds the optimum value, the peak shear strength decreases accordingly. A limited amount of mask chips also increases the elastic modulus and makes the volumetric response more dilative. By contrast, excessive mask chips create additional voids and shift the strong soil-mask contacts to weak mask-mask contacts. The laser scanning microscope (LSM) and scanning electron microscope (SEM) images on the typical samples demonstrate the microstructure of mask fibers interlocking with soil particles, highly supporting the macro-scale mechanical behavior.

Fully automatic pipeline of convolutional neural networks and capsule networks to distinguish COVID-19 from community-acquired pneumonia via CT images.

BACKGROUND: Chest computed tomography (CT) is crucial in the diagnosis of coronavirus disease 2019 (COVID-19). However, the persistent pandemic and similar CT manifestations between COVID-19 and community-acquired pneumonia (CAP) raise methodological requirements. METHODS: A fully automatic pipeline of deep learning is proposed for distinguishing COVID-19 from CAP using CT images. Inspired by the diagnostic process of radiologists, the pipeline comprises four connected modules for lung segmentation, selection of slices with lesions, slice-level prediction, and patient-level prediction. The roles of the first and second modules and the effectiveness of the capsule network for slice-level prediction were investigated. A dataset of 326 CT scans was collected to train and test the pipeline. Another public dataset of 110 patients was used to evaluate the generalization capability. RESULTS: LinkNet exhibited the largest intersection over union (0.967) and Dice coefficient (0.983) for lung segmentation. For the selection of slices with lesions, the capsule network with the ResNet50 block achieved an accuracy of 92.5% and an area under the curve (AUC) of 0.933. The capsule network using the DenseNet121 block demonstrated better performance for slice-level prediction, with an accuracy of 97.1% and AUC of 0.992. For both datasets, the prediction accuracy of our pipeline was 100% at the patient level. CONCLUSIONS: The proposed fully automatic deep learning pipeline of deep learning can distinguish COVID-19 from CAP via CT images rapidly and accurately, thereby accelerating diagnosis and augmenting the performance of radiologists. This pipeline is convenient for use by radiologists and provides explainable predictions.

Pathologic Diagnosis of Nonalcoholic Fatty Liver Disease.

CONTEXT.­: Nonalcoholic fatty liver disease (NAFLD) encompasses steatosis and steatohepatitis. The cause may be multifactorial, and diagnosis requires correlation with clinical information and laboratory results. OBJECTIVE.­: To provide an overview of the status of histology diagnosis of steatosis, steatohepatitis, and associated conditions. DATA SOURCES.­: A literature search was performed using the PubMed search engine. The terms ''steatosis,'' ''steatohepatitis,'' ''nonalcoholic fatty liver disease (NAFLD),'' ''nonalcoholic steatohepatitis (NASH),'' "alcoholic steatohepatitis (ASH)," ''type 2 diabetes (T2DM),'' "cryptogenic cirrhosis," "drug-induced liver injury (DILI)," "immune checkpoint inhibitor therapy," and "COVID-19 and liver" were used. CONCLUSIONS.­: Nonalcoholic fatty liver disease has become the most common chronic liver disease in the United States. NASH is the progressive form of nonalcoholic fatty liver disease. The hallmarks of steatohepatitis are steatosis, ballooned hepatocytes, and lobular inflammation. NASH and alcoholic steatohepatitis share similar histologic features, but some subtle differences may help their distinction. NASH is commonly seen in patients with metabolic dysfunction but can also be caused by other etiologies. Examples are medications including newly developed immune checkpoint inhibitors and viral infections such as coronavirus disease 2019 (COVID-19). NASH is also a common cause of cryptogenic cirrhosis but can be reversed. The results from recent clinical trials for NASH treatment are promising in reducing the severity of steatosis, ballooning, and fibrosis.

DR-MIL: deep represented multiple instance learning distinguishes COVID-19 from community-acquired pneumonia in CT images.

BACKGROUND AND OBJECTIVE: Given that the novel coronavirus disease 2019 (COVID-19) has become a pandemic, a method to accurately distinguish COVID-19 from community-acquired pneumonia (CAP) is urgently needed. However, the spatial uncertainty and morphological diversity of COVID-19 lesions in the lungs, and subtle differences with respect to CAP, make differential diagnosis non-trivial. METHODS: We propose a deep represented multiple instance learning (DR-MIL) method to fulfill this task. A 3D volumetric CT scan of one patient is treated as one bag and ten CT slices are selected as the initial instances. For each instance, deep features are extracted from the pre-trained ResNet-50 with fine-tuning and represented as one deep represented instance score (DRIS). Each bag with a DRIS for each initial instance is then input into a citation k-nearest neighbor search to generate the final prediction. A total of 141 COVID-19 and 100 CAP CT scans were used. The performance of DR-MIL is compared with other potential strategies and state-of-the-art models. RESULTS: DR-MIL displayed an accuracy of 95% and an area under curve of 0.943, which were superior to those observed for comparable methods. COVID-19 and CAP exhibited significant differences in both the DRIS and the spatial pattern of lesions (p<0.001). As a means of content-based image retrieval, DR-MIL can identify images used as key instances, references, and citers for visual interpretation. CONCLUSIONS: DR-MIL can effectively represent the deep characteristics of COVID-19 lesions in CT images and accurately distinguish COVID-19 from CAP in a weakly supervised manner. The resulting DRIS is a useful supplement to visual interpretation of the spatial pattern of lesions when screening for COVID-19.