No abstract

This paper studies brain tumor grading using multiphase MRI images and compares the results with various configurations of deep learning structure and baseline Neural Networks. The MRI images are used directly into the learning machine, with some combination operations between multiphase MRIs. Compared to other researches, which involve additional effort to design and choose feature sets, the approach used in this paper leverages the learning capability of deep learning machine. We present the grading performance on the testing data measured by the sensitivity and specificity. The results show a maximum improvement of 18% on grading performance of Convolutional Neural Networks based on sensitivity and specificity compared to Neural Networks. We also visualize the kernels trained in different layers and display some self-learned features obtained from Convolutional Neural Networks.

Highlights A novel weakly supervised learning framework for COVID-19 severity assessment A multiple instance learning model with virtual bag-based augmentation A novel self-supervised pretext task to aid the learning process

Aim: To investigate the diagnostic performance of shear wave velocity (SWV) using virtual touch tissue quantification (VTQ) of acoustic radiation force impulse imaging (ARFI) technology in differentiating malignant and benign thyroid nodules by conducting a meta-analysis. Material and methods: The Cochrane library, Embase, Pubmed, and Web of Science were searched for relevant studies through December 2014. Studies evaluating the diagnostic accuracy of SWV in the identification of malignant and benign thyroid nodules by using VTQ of ARFI technology were selected. The cytology or histology was used as the reference standard. The pooled sensitivity, specificity, diagnostic odds ratio, likelihood ratio, and the area under the summary receiver operating characteristic (SROC) curve were used to examine the diagnostic accuracy of SWV. Results: A total of 13 cohort studies involving 1617 thyroid nodules from 1451 patients were identified. Of 13 studies, one was a retrospective study and others were prospective studies. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio of SWV in differentiating malignant and benign thyroid nodules were 86.3% (95%CI: 78.2-91.7), 89.5% (95%CI: 83.3-93.6), 7.04 (95%CI: 4.40-11.26), 0.17 (95%CI: 0.10-0.31), and ), respectively. The area under the SROC curve was 94% (95% CI: 92-96). Conclusions: This meta-analysis indicates that VTQ is useful in evaluating the stiffness of thyroid nodules and differentiating between malignant and benign nodules. Due to the high sensitivity, specificity, and diagnostic odds ratio, SWV can be considered as a useful complement for conventional ultrasonography.