No abstract

Objective: Coronavirus disease 2019 (COVID-19) has caused hundreds of thousands of infections and deaths. Efficient diagnostic methods could help curb its global spread. The purpose of this study was to develop and evaluate a method for accurately diagnosing COVID-19 based on computed tomography (CT) scans in real time. Methods: We propose an architecture named "concatenated feature pyramid network" ("Concat-FPN") with an attention mechanism, by concatenating feature maps of multiple. The proposed architecture is then used to form two networks, which we call COVID-CT-GAN and COVID-CT-DenseNet, the former for data augmentation and the latter for data classification. Results: The proposed method is evaluated on 3 different numbers of magnitude of COVID-19 CT datasets. Compared with the method without GANs for data augmentation or the original network auxiliary classifier generative adversarial network, COVID-CT-GAN increases the accuracy by 2% to 3%, the recall by 2% to 4%, the precision by 1% to 3%, the F1-score by 1% to 3%, and the area under the curve by 1% to 4%. Compared with the original network DenseNet-201, COVID-CT-DenseNet increases the accuracy by 1% to 3%, the recall by 4% to 9%, the precision by 1%, the F1-score by 1% to 3%, and the area under the curve by 2%. Conclusion: The experimental results show that our method improves the efficiency of diagnosing COVID-19 on CT images, and helps overcome the problem of limited training data when using deep learning methods to diagnose COVID-19. Significance: Our method can help clinicians build deep learning models using their private datasets to achieve automatic diagnosis of

Purpose Ultrasound image segmentation is a challenging task due to a low signal‐to‐noise ratio and poor image quality. Although several approaches based on the convolutional neural network (CNN) have been applied to ultrasound image segmentation, they have weak generalization ability. We propose an end‐to‐end, multiple‐channel and atrous CNN designed to extract a greater amount of semantic information for segmentation of ultrasound images. Method A multiple‐channel and atrous convolution network is developed, referred to as MA‐Net. Similar to U‐Net, MA‐Net is based on an encoder–decoder architecture and includes five modules: the encoder, atrous convolution, pyramid pooling, decoder, and residual skip pathway modules. In the encoder module, we aim to capture more information with multiple‐channel convolution and use large kernel convolution instead of small filters in each convolution operation. In the last layer, atrous convolution and pyramid pooling are used to extract multi‐scale features. The architecture of the decoder is similar to that of the encoder module, except that up‐sampling is used instead of down‐sampling. Furthermore, the residual skip pathway module connects the subnetworks of the encoder and decoder to optimize learning from the deeper layer and improve the accuracy of segmentation. During the learning process, we adopt multi‐task learning to enhance segmentation performance. Five types of datasets are used in our experiments. Because the original training data are limited, we apply data augmentation (e.g., horizontal and vertical flipping, random rotations, and random scaling) to our training data. We use the Dice score, precision, recall, Hausdorff distance (HD), average symmetric surface distance (ASD), and root mean square symmetric surface distance (RMSD) as the metrics for segmentation evaluation. Meanwhile, Friedman test was performed as the nonparametric statistical analysis to evaluate the algorithms. Results For the datasets of brachia plexus (BP), fetal head, and lymph node segmentations, MA‐Net achieved average Dice scores of 0.776, 0.973, and 0.858, respectively; with average precisions of 0.787, 0.968, and 0.854, respectively; average recalls of 0.788, 0.978, and 0.885, respectively; average HDs (mm) of 13.591, 10.924, and 19.245, respectively; average ASDs (mm) of 4.822, 4.152, and 4.312, respectively; and average RMSDs (mm) of 4.979, 4.161, and 4.930, respectively. Compared with U‐Net, U‐Net++, M‐Net, and Dilated U‐Net, the average performance of the MA‐Net increased by approximately 5.68%, 2.85%, 6.59%, 36.03%, 23.64%, and 31.71% for Dice, precision, recall, HD, ASD, and RMSD, respectively. Moreover, we verified the generalization of MA‐Net segmentation to lower grade brain glioma MRI and lung CT images. In addition, the MA‐Net achieved the highest mean rank in the Friedman test. Conclusion The proposed MA‐Net accurately segments ultrasound images with high generalization, and therefore, it offers a useful tool for diagnostic application in ultrasound images.

Background: Dietary inflammatory potential could impact the presence and severity of chronic adverse treatment effects among patients with head and neck cancer. The objective of this study was to determine whether pretreatment dietary patterns are associated with nutrition impact symptoms (NIS) as self-reported 1 year after diagnosis. Methods: This was a longitudinal study of 336 patients with newly diagnosed head and neck cancer enrolled in the University of Michigan Head and Neck Specialized Program of Research Excellence. Principal component analysis was utilized to derive pretreatment dietary patterns from food frequency questionnaire data. Burden of seven NIS was selfreported 1 year after diagnosis. Associations between pretreatment dietary patterns and individual symptoms and a composite NIS summary score were examined with multivariable logistic regression models. Results: The two dietary patterns that emerged were prudent and Western. After adjusting for age, smoking status, body mass index, tumor site, cancer stage, calories, and human papillomavirus status, significant inverse associations were observed between the prudent pattern and difficulty chewing [OR 0.44; 95% confidence interval (CI), 0.21-0.93; P ¼ 0.03], dysphagia of liquids (OR 0.38; 95% CI, 0.18-0.79; P ¼ 0.009), dysphagia of solid foods (OR 0.46; 95% CI, 0.22-0.96; P ¼ 0.03), mucositis (OR 0.48; 95% CI, 0.24-0.96; P ¼ 0.03), and the NIS summary score (OR 0.45; 95% CI, 0.22-0.94; P ¼ 0.03). No significant associations were observed between the Western pattern and NIS. Conclusions: Consumption of a prudent diet before treatment may help reduce the risk of chronic NIS burden among head and neck cancer survivors. Impact: Dietary interventions are needed to test whether consumption of a prudent dietary pattern before and during head and neck cancer treatment results in reduced NIS burden.

No studies, to date, have examined the relationship between dietary fiber and recurrence or survival after head and neck cancer diagnosis. The aim of this study was to determine whether pretreatment intake of dietary fiber or whole grains predicted recurrence and survival outcomes in newly diagnosed head and neck cancer (HNC) patients. This was a prospective cohort study of 463 participants baring a new head and neck cancer diagnosis who were recruited into the study prior to the initiation of any cancer therapy. Baseline (pre-treatment) dietary and clinical data were measured upon entry into the study cohort. Clinical outcomes were ascertained at annual medical reviews. Cox proportional hazard models were fit to examine the relationships between dietary fiber and whole grain intakes with recurrence and survival. There were 112 recurrence events, 121 deaths, and 77 cancer-related deaths during the study period. Pretreatment dietary fiber intake was inversely associated with risk of all-cause mortality (hazard ratio (HR): 0.37, 95% confidence interval (CI): 0.14–0.95, ptrend = 0.04). No statistically significant associations between whole grains and prognostic outcomes were found. We conclude that higher dietary fiber intake, prior to the initiation of treatment, may prolong survival time, in those with a new HNC diagnosis.