Momentum contrast transformer for COVID-19 diagnosis with knowledge distillation.

Intelligent diagnosis has been widely studied in diagnosing novel corona virus disease (COVID-19). Existing deep models typically do not make full use of the global features such as large areas of ground glass opacities, and the local features such as local bronchiolectasis from the COVID-19 chest CT images, leading to unsatisfying recognition accuracy. To address this challenge, this paper proposes a novel method to diagnose COVID-19 using momentum contrast and knowledge distillation, termed MCT-KD. Our method takes advantage of Vision Transformer to design a momentum contrastive learning task to effectively extract global features from COVID-19 chest CT images. Moreover, in transfer and fine-tuning process, we integrate the locality of convolution into Vision Transformer via special knowledge distillation. These strategies enable the final Vision Transformer simultaneously focuses on global and local features from COVID-19 chest CT images. In addition, momentum contrastive learning is self-supervised learning, solving the problem that Vision Transformer is challenging to train on small datasets. Extensive experiments confirm the effectiveness of the proposed MCT-KD. In particular, our MCT-KD is able to achieve 87.43% and 96.94% accuracy on two publicly available datasets, respectively.

Dental health and treatment needs in people with leprosy in China.

OBJECTIVES: To evaluate the dental health status and treatment needs of people affected by leprosy in China, and provide a basis for the development of national or regional dental health programmes to cover the treatment needs of this population. DESIGN: A cross-sectional study with 613 former leprosy patients was carried out in six leprosy villages, in three provinces in China (Nanjing, Taixing and Jiangyan in Jiangsu Province, Hanzhong and Shangluo in Shanxi Province and Yongzhou in Hunan Province). A questionnaire about demographic and clinical data was used. The World Health Organization's (WHO) basic methods were used to determine the tooth-based treatment needs. Periodontal status was determined by using the Community Periodontal Index of Treatment Needs (CPITN). In addition, prosthetic normative needs were assessed. RESULTS: Among the 613 people affected by leprosy, there were 472 people (77%) who had never visited a dentist and 172 people (28.1%) had never brushed their teeth; 302 (49.3%) brushed their teeth once a day. However, there were 267 people (43.6%) who thought their dental health was at an average level and 108 (17.6%) thought they had good dental health. 55.6% of the subjects required dental fillings, 32.7% required pulp care and restoration, and 71.1% required extraction. On CPITN, 23.2% of the subjects scored 2, 28.6% scored three and 48.0% scored four, showing that these people required systematic periodontal treatment. In addition, 84.5% of the subjects needed normative prosthetic treatment. CONCLUSIONS: Most of the subjects with leprosy in this study lacked self-care knowledge on dental health, and especially self-awareness of dental conditions. Normative treatment needs of people affected by leprosy were very high. This result calls for improved oral health education and oral health care in people with leprosy. Oral health education might preferably be integrated into already existing leprosy rehabilitation programs.

Latent feature representation learning for Alzheimer's disease classification.

Early detection and treatment of Alzheimer's Disease (AD) are significant. Recently, multi-modality imaging data have promoted the development of the automatic diagnosis of AD. This paper proposes a method based on latent feature fusion to make full use of multi-modality image data information. Specifically, we learn a specific projection matrix for each modality by introducing a binary label matrix and local geometry constraints and then project the original features of each modality into a low-dimensional target space. In this space, we fuse latent feature representations of different modalities for AD classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative database demonstrate the proposed methods effectiveness in classifying AD.