A New DCT Image Compression Algorithm Using Block Visual Activities

A new image compression algorithm is proposed based on local visual activity classification and the investigation of the histograms of the small non-overlapping blocks of the differential and angle image. Histograms of the differential blocks are classified according to their visual activities as Unimodal, Bimodal and Multimodal blocks. According to the histogram shape of the differential block and the mean angle of the same block an optimized quantization table with special coding is applied by taking the advantages of the local visual activities within the block. A considerable compression ratio and visual output improvement compared with the DCT compression algorithm are gained.

Altered intrinsic functional connectivity of the primary visual cortex in youth patients with comitant exotropia: a resting state fMRI study

AIM： To evaluate the differences in the functional connectivity（FC） of the primary visual cortex（V1） between the youth comitant exotropia（CE） patients and health subjects using resting functional magnetic resonance imaging（f MRI） data.METHODS： Totally, 32 CEs（25 males and 7 females） and 32 healthy control subjects（HCs）（25 males and 7 females） were enrolled in the study and underwent the MRI scanning. Two-sample t-test was used to examine differences in FC maps between the CE patients and HCs. RESULTS： The CE patients showed significantly less FC between the left brodmann area（BA17） and left lingual gyrus/cerebellum posterior lobe, right middle occipital gyrus, left precentral gyrus/postcentral gyrus and right inferior parietal lobule/postcentral gyrus. Meanwhile, CE patients showed significantly less FC between right BA17 and right middle occipital gyrus（BA19, 37）.CONCLUSION： Our findings show that CE involves abnormal FC in primary visual cortex in many regions, which may underlie the pathologic mechanism of impaired fusion and stereoscopic vision in CEs.

Deep Stacked Ensemble Learning Model for COVID-19 Classification

COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.