Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

Kidney Transplantation in Patients With SARS-CoV-2 Infection: A Case Series Report.

We read the report by Kute et al1 published in Transplantation regarding the safety of live kidney donation in 31 individuals with previous severe acute respiratory syndrome coronovirus-2 (SARS-CoV-2) infection. Liver transplantation (LT) has been severely restricted during the coronavirus disease 2019 (COVID-19) pandemic due to concerns of perioperative SARS-CoV-2 infection in donors and recipients.2,3 Unlike kidney transplantation that can be postponed for an extended duration, there is an element of urgency for patients awaiting LT. While there is general consensus that individuals with symptomatic SARS-CoV-2 infections should not proceed with living donor hepatectomy (LDH), there are no clear recommendations regarding the safety of LDH in individuals with recent asymptomatic infection. We had several instances of asymptomatic donors testing positive on preoperative screening. We set up a protocol of reassessing these donors for LDH if they satisfied the following 4 criteria: asymptomatic infection without abnormal inflammatory markers or liver function tests, have completed 2-wk isolation period, 2 negative real-time polymerase chain reaction (RT-PCR) tests 48 h apart—the second within 48 h of LDLT, and normal preoperative chest computed tomography scan. SARS-nCoV2 antibody levels were not routinely measured. Donors and recipients were managed in a COVID-19 free unit. All donors received perioperative deep venous thrombosis prophylaxis. Postdischarge follow-up visits were minimized and donors were followed by e-consultation with home blood sample collection.4 This is a retrospective report of living donors who tested positive for SARS-nCoV2 infection on routine RT-PCR screening. All clinical procedures were performed in accordance with the principles of the Istanbul Declaration. The study was exempt from ethics board approval as it was a retrospective review of deidentified data. Between July and December 2020, 9 potential living donors tested positive for SARS-nCoV2 infection on routine RT-PCR screening at 3 LT centers in India. There were 3 male and 6 female donors donating to 5 adult and 4 pediatric recipients (Table 1). Six tested positive during donor evaluation, while 3 tested positive during preoperative testing. None had computed tomography chest findings suggestive of SAR-nCoV2 infection. Two potential recipients also had positive testing with no symptoms. LT was postponed in all cases and donors and recipients were managed with strict home isolation for 2 wk. Repeat testing was performed after 2 wk, and donors proceeded with LDH once previously mentioned criteria were satisfied. TABLE 1. - Details of 9 donors who underwent LDH after asymptomatic SARS-CoV-2 infection Center number Donor age/sex Recipient age/sex Cause/MELD (PELD) Donor-patient relationship Graft type Time interval between first positive test and LDH (d) Total RT-PCR tests performed Peak postop serum bilirubin (mg%) Perioperative morbidity Hospital stay (d) Current status of donor Follow-up duration (mo) 1.1 24/M 41/M ALD/12 Uncle LL 92 4 2.1 Nil 7 Good 2.5 1.2 34/F 9/F Wilson’s/11 Mother LL 72 3 1.9 Ileus, NG 5 Good 1 1.3 35/F 47/M ALD/31 Spouse RL 64 3 3.4 Nil 6 Good 2 1.4 29/F 2/F EHBA/18 Mother LLS 53 3 1.6 Nil 6 Good 1 2.1 43/F 48/M ALD/24 Spouse RL 27 5 1.8 Pleural effusion 7 Good 4 2.2 33/F 8/F Wilson’s ACLF/28 Mother LL 15 3 1.3 Nil 7 Good 1 3.1 32/M 12/F BCS with HCC/20 Cousin RL 49 3 3.3 Nil 7 Good 1.5 3.2 30/F 35/M Cryptogenic CLD/22 Spouse RL 22 6 1.7 Nil 8 Good 1 3.3 46/M 3/M Abernathy syndrome Father LLS 87 4 1.0 Nil 7 Good 1 ACLF, acute on chronic liver failure; ALD, alcoholic liver disease; BCS, Budd-Chiari syndrome; CLD, chronic liver disease; EHBA, extrahepatic biliary atresia; F, female, HCC, hepatocellular carcinoma; LDH, living donor hepatectomy; LL, left lobe; LLS, left lateral segment graft; M, male; MELD, Model for End-stage Liver Disease; NG, nasogastric tube; PELD, pediatric end-stage liver disease; RL, right lobe; RT-PCR, real-time polymerase chain reaction; SARS-CoV-2, severe acute respiratory syndrome coronovirus-2. Median interval between the first positive RT-PCR and LDH was 53 d. Three donors had positive RT-PCR tests even 3 wk after the initial positive test necessitating further delays in surgery until 2 consecutive negative tests were obtained. There were no major complications in any of the donors. One recipient needed reoperation for sepsis and developed early allograft dysfunction leading to prolonged hospital stay. All donors and recipients were discharged in stable condition. There were no COVID-19-related complications among the donors or recipients during the perioperative and follow-up period. Our report provides initial evidence for the safety of LDH after previous asymptomatic SARS-nCOV2 infection. Clarity is needed regarding the significance of repeat positive tests beyond 3 wk, role of antibody testing, and the benefit of preoperative vaccination for potential donors with previous asymptomatic SARS-nCOV2 infection.

ObjectiveTo evaluate the accuracy of chest computed tomography (CT) in patients with suspected severe acute respiratory syndrome-related coronavirus-2 (SARS-CoV-2) infection at a cancer center.Materials and MethodsThis retrospective single-center study selected 91 patients who had chest CT and real-time polymerase chain reaction (RT-PCR) test collected at the same day. CT results were classified in negative, typical, indeterminate or atypical findings. Diagnostic accuracy, sensitivity and specificity were calculated for two different scenarios: in the first, only typical findings on CT were considered positive; in the second, both typical and indeterminate findings were considered positive.ResultsMean patients’ age was 58.2 years, most were male (60.4%) and had prior diagnosis of cancer (85.7%). CT showed typical findings in 28.6%, indeterminate findings in 24.2% and atypical findings in 26.4%. RT-PCR results were positive for SARS-CoV-2 in 27.5%. The sensitivity, specificity and accuracy in the first and second scenarios were respectively 64.0%, 84.8% and 79.1%, and 92.0%, 62.1% and 70.3%.ConclusionCT has a high accuracy for the diagnosis of SARS-CoV-2 infection. Different interpretation criteria can provide either high sensitivity or high specificity. CT should be integrated as a triage test in resource-constrained environments during the pandemic to assist in the optimization of PCR-tests, isolation beds and intensive care units.

Background: Coronavirus Disease 2019 (COVID-19) is associated with an increased risk for acute ischemic stroke but screening for COVID-19 based on clinical criteria or laboratory testing may be difficult in acute stroke evaluation. Chest computed tomographic (CT) scan may be another time-sensitive option for identification. of COVID-19 in such patients. Objective: We report our experience of incorporating chest CT scan in the initial neuroimaging protocol for evaluation of acute stroke patients. Methods: All acute stroke patients underwent chest CT scan concurrent to CT head, CT angiogram of head and neck and CT perfusion for 4 months. We identified patients who had chest CT scan findings that were suggestive of COVID-19 including bilateral, multilobar ground glass opacification with a peripheral or posterior distribution, and/or consolidation (mainly in the lower lobes). All patients subsequently underwent polymerase chain reaction (PCR) testing of nasopharyngeal swab with contact isolation until COVID-19 could be excluded. Results: A total of 224 consecutive patients (mean age 62.12 years±SD; 15.3) underwent acute stroke evaluation with a concurrent chest CT scan. The chest CT identified findings suggestive of COVID-19 in 11 (4.9%) patients. Subsequent PCR testing did not confirm the diagnosis of COVID-19 in any of the patient. Another 99 patients (44%) without any findings suggestive of COVID-19 on chest CT scan underwent PCR testing. PCR testing did not confirm the diagnosis of COVID-19 in any of the patients. Four patients (4.3%) with chest CT scan findings suggestive of COVID-19 were found to have an ischemic stroke while 7 patients (5.9%) with chest CT scan findings suggestive of COVID-19 did not have any ischemic stroke (stroke mimic). Conclusions: We found a very low yield for identifying COVID-19 in acute stroke patients by performing chest CT scan concurrent to standard acute stroke neuroimaging protocol.

Development of the first conventional and real-time polymerase chain reaction (PCR) tests for the diagnoses of duck circovirus (DuCV) infections is described. Both tests amplified a 230 bp fragment specific to the DuCV Rep gene. Although both tests had the same detection limit (13 x 10(3) target DNA/ml) when the target DNA was diluted in water, the detection limit of the real-time test (13 x 10(4) target DNA/ml) was 10-fold less than the conventional test (13 x 10(5) target DNA/ml) when the amplifications were performed in the presence of cellular DNA. Using the conventional PCR test, DuCV DNA was detected in 85 (84%) of 101 bursa of Fabricius samples from dead or sick ducks, aged between 1 and 12 weeks, and in samples from 35 (94%) of 37 flocks. Application of the SYBR Green-based real-time PCR test to 54 selected bursa of Fabricius samples indicated that more samples were positive by real-time PCR than by conventional PCR, allowed the numbers of genome copies to be estimated and showed that some bursa of Fabricius samples contained over 10(13) genome copies/g tissue. Although DuCV infections were detected in birds aged from 1 to 12 weeks, higher virus DNA levels were detected in ducks aged older than 5 weeks than in ducks younger than 5 weeks. An in situ hybridization method for the detection of DuCV in histological samples was also developed. Additional work is required to determine the clinicopathological significance of DuCV infections.

In response to the increasing number of genetically modified (GM) events released on the market, control laboratories explore various strategies to simplify and reduce the number of tests needed to characterise the content in genetically modified organism (GMO) of a given sample. Lastly, multiplexing is considered as one of the possible ways to decrease the time and cost of analysis. Here, we report the development of four duplex polymerase chain reaction (PCR) tests for the identification and the quantification of four maize transformation events from which commercial lines have been authorised in Europe namely, Bt11 and Bt176 (Syngenta, DE, USA), Mon810 MaisGard™ (Monsanto, MO, USA) and T25 Liberty Link™ (Bayer CropScience, Monheim, Germany). The duplex PCR tests combine a maize-specific PCR test hybridising in the Adh1 locus with an event-specific detection system designed on a junction fragment for each of these four GM maize. Real-time PCR tests, suitable to comply with the European regulation, were designed by using Taqman® chemistry.

The excellent feature extraction ability of deep convolutional neural networks (DCNNs) has been demonstrated in many image processing tasks, by which image classification can achieve high accuracy with only raw input images. However, the specific image features that influence the classification results are not readily determinable and what lies behind the predictions is unclear. This study proposes a method combining the Sobel and Canny operators and an Inception module for ship classification. The Sobel and Canny operators obtain enhanced edge features from the input images. A convolutional layer is replaced with the Inception module, which can automatically select the proper convolution kernel for ship objects in different image regions. The principle is that the high-level features abstracted by the DCNN, and the features obtained by multi-convolution concatenation of the Inception module must ultimately derive from the edge information of the preprocessing input images. This indicates that the classification results are based on the input edge features, which indirectly interpret the classification results to some extent. Experimental results show that the combination of the edge features and the Inception module improves DCNN ship classification performance. The original model with the raw dataset has an average accuracy of 88.72%, while when using enhanced edge features as input, it achieves the best performance of 90.54% among all models. The model that replaces the fifth convolutional layer with the Inception module has the best performance of 89.50%. It performs close to VGG-16 on the raw dataset and is significantly better than other deep neural networks. The results validate the functionality and feasibility of the idea posited.

Preoperative COVID-19 CT screening in renal transplant recipients

Estimates of individual patient risk, and epidemiologic studies assessing potential late effects, must use patient size–specific dose estimates—they cannot use only scanner output (volume CT dose index or dose-length product).

To distinguish benign from malignant pulmonary nodules using CT images is critical for their precise diagnosis and treatment. A new Agile convolutional neural network (CNN) framework is proposed to conquer the challenges of a small-scale medical image database and the small size of the nodules, and it improves the performance of pulmonary nodule classification using CT images. A hybrid CNN of LeNet and AlexNet is constructed through combining the layer settings of LeNet and the parameter settings of AlexNet. A dataset with 743 CT image nodule samples is built up based on the 1018 CT scans of LIDC to train and evaluate the Agile CNN model. Through adjusting the parameters of the kernel size, learning rate, and other factors, the effect of these parameters on the performance of the CNN model is investigated, and an optimized setting of the CNN is obtained finally. After finely optimizing the settings of the CNN, the estimation accuracy and the area under the curve can reach 0.822 and 0.877, respectively. The accuracy of the CNN is significantly dependent on the kernel size, learning rate, training batch size, dropout, and weight initializations. The best performance is achieved when the kernel size is set to [Formula: see text], the learning rate is 0.005, the batch size is 32, and dropout and Gaussian initialization are used. This competitive performance demonstrates that our proposed CNN framework and the optimization strategy of the CNN parameters are suitable for pulmonary nodule classification characterized by small medical datasets and small targets. The classification model might help diagnose and treat pulmonary nodules effectively.

The role of radiology in patients with clinical suspicion of COVID-19 is evolving with scientific evidence, but there are differences in opinion on when and how the technique should be used for clinical diagnosis. To estimate the pre-test and post-test probability that a patient has COVID-19 in the event of a positive and/or negative result from chest X-ray and chest computed tomography (CT) radiological studies, comparing with those of real time polymerase chain reaction (RT-PCR) tests. The literature on the sensitivity and specificity of the chest X-ray, chest CT, and RT-PCR was reviewed. Based on these reported data, the likelihood ratios (LR) were estimated and the pre-test probabilities were related to the post-test probabilities after positive or negative results. The chest X-ray has only a confirmatory value in cases of high suspicion. Chest CT analyses showed that when it is used as a general study, it has almost confirmatory value under high clinical suspicion. A chest CT classified with CO-RADS ≥ 4 has almost a diagnostic certainty of COVID-19 even with moderate or low clinical presumptions, and the CO-RADS 5 classification is almost pathognomonic before any clinical presumption. To rule out COVID-19 completely is only possible in very low clinical assumptions with negative RT-PCR and/or CT. Chest X-ray and especially CT are fast studies that have the capacity to report high probability of COVID-19, being a real contribution to the concept of "probable case" and allowing support to be installed in an early and timely manner.

Cervical cancer is the fourth most prevalent disease among women. Prompt diagnosis and its management can significantly improve patients’ survival rates. Therefore, routine screening for cervical cancer is of paramount importance. Herein, we explore the potential of a deep learning model to automatically distinguish abnormal cells from normal cells. The ThinPrep cytologic test dataset was collected from the fourth central hospital of Baoding city, China. Based on the dataset, four classification models were developed. The first model was a 10-layer convolutional neural network (CNN). The second model was an advancement of the first model equipped with a spatial pyramid pooling (SPP) layer (CNN + SPP) to treat cell images based on their sizes. Based on the first model, the third model replaced the CNN layers with the inception module (CNN + Inception). However, the fourth model incorporated both the SPP layer and the inception module into the first model (CNN + inception + SPP). The performances of the four models are estimated and compared by using the same testing data and evaluation index. The testing results demonstrated that the fourth model yields the best performance. Moreover, the area under the curve (AUC) for module four was 0.997.

Real-time reverse transcription polymerase chain reaction (RT-PCR) tests for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are occasionally repeated when clinicians suspect false-negative results, but the conditions under which repeated RT-PCR testing is warranted remain unclear. We evaluated the practice of repeat RT-PCR testing for SARS-CoV-2 in 45 patients who were retested after an initial negative PCR test. Of these, the diagnosis of coronavirus disease (COVID-19) was confirmed in four patients with typical chest computed tomography (CT) findings and in one patient without typical CT findings in whom the test result was strongly suspected to be false-positive. We recommend repeat RT-PCR testing only for patients with typical CT findings of COVID-19.

Detection of metastasis of mediastinal lymph nodes in lung cancer patients with an artificial intelligence model.

Application of Self-Quenched JH Consensus Primers for Real-Time Quantitative PCR of IGH Gene to Minimal Residual Disease Evaluation in Multiple Myeloma