Due to the space inconsistency between benchmark image and segmentation result in many existing semantic segmentation algorithms for abdominal CT images, an improved model based on the basic framework of DeepLab-v3 is proposed, and Pix2pix network is introduced as the generation adversarial model. Our proposed model realizes the segmentation framework combining deep feature with multi-scale semantic feature. In order to improve the generalization ability and training accuracy of the model, this paper proposes a combination of the traditional multi-classification cross-entropy loss function with the content loss function of generator output and the adversarial loss function of discriminator output. A large number of qualitative and quantitative experimental results show that the performance of our proposed semantic segmentation algorithm is better than the existing algorithms, and can improve the segmentation efficiency while ensuring the space consistency of the semantics segmentation for abdominal CT images.
Vestibular migraine (VM) is a multidisciplinary disease under exploration. Multiple temporal patterns of vertigo and migraine make it difficult to diagnose VM, and their effect on the clinical features of VM is still unclear. Here we investigated the clinical features of VM under three temporal patterns. 172 VM patients were enrolled in this study and divided into three groups: 86 patients in group A had an earlier onset of migraine than vertigo, 35 patients in group B had an earlier onset of vertigo than migraine, and 51 patients in group C had concurrent vertigo and migraine. No significant difference was found among three groups regarding types, intensity and accompanying symptoms of the vestibular attack. Patients in group C presented higher frequency and longer duration of vertigo than group A and B, while patients in group A presented lower frequency and shorter duration of headaches than group B and C. Additionally, the frequency, duration, intensity and accompanying symptoms of headache in group A decreased significantly after the onset of vertigo, especially in women around menopause. We hypothesized that vestibular stimulation could inhibit the trigeminal pain pathway, while painful trigeminal stimulation could excite the vestibular system. Our findings may contribute to the clinical identification of VM and further clarification of its pathogenesis.
Cerebral microbleed (CMB) is a serious public health concern. It is associated with dementia, which can be detected with brain magnetic resonance image (MRI). CMBs often appear as tiny round dots on MRIs, and they can be spotted anywhere over brain. Therefore, manual inspection is tedious and lengthy, and the results are often short in reproducible. In this paper, a novel automatic CMB diagnosis method was proposed based on deep learning and optimization algorithms, which used the brain MRI as the input and output the diagnosis results as CMB and non-CMB. Firstly, sliding window processing was employed to generate the dataset from brain MRIs. Then, a pre-trained VGG was employed to obtain the image features from the dataset. Finally, an ELM was trained by Gaussian-map bat algorithm (GBA) for identification. Results showed that the proposed method VGG-ELM-GBA provided better generalization performance than several state-of-the-art approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.