A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images.

PURPOSE: Infiltration of activated dendritic cells and inflammatory cells in cornea represents an important marker for defining corneal inflammation. Deep transfer learning has presented a promising potential and is gaining more importance in computer assisted diagnosis. This study aimed to develop deep transfer learning models for automatic detection of activated dendritic cells and inflammatory cells using in vivo confocal microscopy images. METHODS: A total of 3453 images was used to train the models. External validation was performed on an independent test set of 558 images. A ground-truth label was assigned to each image by a panel of cornea specialists. We constructed a deep transfer learning network that consisted of a pre-trained network and an adaptation layer. In this work, five pre-trained networks were considered, namely VGG-16, ResNet-101, Inception V3, Xception, and Inception-ResNet V2. The performance of each transfer network was evaluated by calculating the area under the curve (AUC) of receiver operating characteristic, accuracy, sensitivity, specificity, and G mean. RESULTS: The best performance was achieved by Inception-ResNet V2 transfer model. In the validation set, the best transfer system achieved an AUC of 0.9646 (P<0.001) in identifying activated dendritic cells (accuracy, 0.9319; sensitivity, 0.8171; specificity, 0.9517; and G mean, 0.8872), and 0.9901 (P<0.001) in identifying inflammatory cells (accuracy, 0.9767; sensitivity, 0.9174; specificity, 0.9931; and G mean, 0.9545). CONCLUSIONS: The deep transfer learning models provide a completely automated analysis of corneal inflammatory cellular components with high accuracy. The implementation of such models would greatly benefit the management of corneal diseases and reduce workloads for ophthalmologists.

Economic burden and its associated factors of hospitalized patients infected with A (H7N9) virus: a retrospective study in Eastern China, 2013-2014.

BACKGROUND: H7N9 continues to cause human infections and remains a pandemic concern. Understanding the economic impacts of this novel disease is important for making decisions on health resource allocation, including infectious disease prevention and control investment. However, there are limited data on such impacts. METHODS: Hospitalized laboratory-confirmed H7N9 patients or their families in Jiangsu Province of China were interviewed. Patients' direct medical costs of hospitalization were derived from their hospital bills. A generalized linear model was employed to estimate the mean direct medical costs of patients with different characteristics. RESULTS: The mean direct cost of hospitalization for H7N9 was estimated to be ¥ 71 060 (95 % CI, 48 180-104 820), i.e., US$ 10 996 (95 % CI, 7 455-16 220), and was ¥12 060 (US$ 1 861), ¥136 120 (US$ 21 001) and ¥218 610 (US$ 33 728) for those who had mild or severe symptoms or who died, respectively. The principal components of the total fees differed among patients with different disease severity, although medication fees were always the largest contributors. Disease severity, proportion of reimbursement and family member monthly average income were identified as the key factors that contributed to a patient's direct medical cost of hospitalization. CONCLUSIONS: The direct medical costs of hospitalized patients with H7N9 are significant, and far surpass the annual per capita income of Jiangsu Province, China. The influencing factors identified should be taken into account when developing related health insurance policies and making health resource allocation. TRIAL REGISTRATION: Not applicable. This is a survey study with no health care intervention implemented on human participants.