No abstract

Background This study aimed to establish a deep learning system for detecting the active and inactive phases of thyroid-associated ophthalmopathy (TAO) using magnetic resonance imaging (MRI). This system could provide faster, more accurate, and more objective assessments across populations. Methods A total of 160 MRI images of patients with TAO, who visited the Ophthalmology Clinic of the Ninth People’s Hospital, were retrospectively obtained for this study. Of these, 80% were used for training and validation, and 20% were used for testing. The deep learning system, based on deep convolutional neural network, was established to distinguish patients with active phase from those with inactive phase. The accuracy, precision, sensitivity, specificity, F1 score and area under the receiver operating characteristic curve were analyzed. Besides, visualization method was applied to explain the operation of the networks. Results Network A inherited from Visual Geometry Group network. The accuracy, specificity and sensitivity were 0.863±0.055, 0.896±0.042 and 0.750±0.136 respectively. Due to the recurring phenomenon of vanishing gradient during the training process of network A, we added parts of Residual Neural Network to build network B. After modification, network B improved the sensitivity (0.821±0.021) while maintaining a good accuracy (0.855±0.018) and a good specificity (0.865±0.021). Conclusions The deep convolutional neural network could automatically detect the activity of TAO from MRI images with strong robustness, less subjective judgment, and less measurement error. This system could standardize the diagnostic process and speed up the treatment decision making for TAO.

Efficient exciton diffusion and charge transport play a vital role in advancing the power conversion efficiency (PCE) of organic solar cells (OSCs). Here, a facile strategy is presented to simultaneously enhance exciton/charge transport of the widely studied PM6:Y6‐based OSCs by employing highly emissive trans‐bis(dimesitylboron)stilbene (BBS) as a solid additive. BBS transforms the emissive sites from a more H‐type aggregate into a more J‐type aggregate, which benefits the resonance energy transfer for PM6 exciton diffusion and energy transfer from PM6 to Y6. Transient gated photoluminescence spectroscopy measurements indicate that addition of BBS improves the exciton diffusion coefficient of PM6 and the dissociation of PM6 excitons in the PM6:Y6:BBS film. Transient absorption spectroscopy measurements confirm faster charge generation in PM6:Y6:BBS. Moreover, BBS helps improve Y6 crystallization, and current‐sensing atomic force microscopy characterization reveals an improved charge‐carrier diffusion length in PM6:Y6:BBS. Owing to the enhanced exciton diffusion, exciton dissociation, charge generation, and charge transport, as well as reduced charge recombination and energy loss, a higher PCE of 17.6% with simultaneously improved open‐circuit voltage, short‐circuit current density, and fill factor is achieved for the PM6:Y6:BBS devices compared to the devices without BBS (16.2%).