No abstract

Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

No abstract

No abstract

No abstract

No abstract

No abstract

The memristor was first theorized as an electrical element, which provided the missing link between the charge and the flux. Due to the advantages of nano-scale size, multiple interconnected memristors have demonstrated unique overall characteristics, which are ideal for the utilization in neuromorphic systems. However, compared with the individual memristor circuit, a little work is explored about the overall behavior of the multiple memristive systems. In particular, the lack of a fault diagnosis approach for composite memristive network structures makes all the corresponding applications unstable and shaky. In this paper, the extraordinary properties of multiple memristor circuits are further investigated with comprehensive formula derivation and scientific computer simulations. Furthermore, a special feedback-control doublet generator is designed for implementing the fuzzy-based parametric fault diagnosis of multiple memristor circuits, which offers huge benefits in terms of accuracy and time consumption. Finally, the entire scheme is validated by an illustrative example. INDEX TERMSMultiple memristor circuits, parametric fault diagnosis, feedback-control, doublet generator, fuzzy-based.