Leveraging Multimodal Deep Learning Architecture with Retina Lesion Information to Detect Diabetic Retinopathy.

Purpose: To improve disease severity classification from fundus images using a hybrid architecture with symptom awareness for diabetic retinopathy (DR). Methods: We used 26,699 fundus images of 17,834 diabetic patients from three Taiwanese hospitals collected in 2007 to 2018 for DR severity classification. Thirty-seven ophthalmologists verified the images using lesion annotation and severity classification as the ground truth. Two deep learning fusion architectures were proposed: late fusion, which combines lesion and severity classification models in parallel using a postprocessing procedure, and two-stage early fusion, which combines lesion detection and classification models sequentially and mimics the decision-making process of ophthalmologists. Messidor-2 was used with 1748 images to evaluate and benchmark the performance of the architecture. The primary evaluation metrics were classification accuracy, weighted κ statistic, and area under the receiver operating characteristic curve (AUC). Results: For hospital data, a hybrid architecture achieved a good detection rate, with accuracy and weighted κ of 84.29% and 84.01%, respectively, for five-class DR grading. It also classified the images of early stage DR more accurately than conventional algorithms. The Messidor-2 model achieved an AUC of 97.09% in referral DR detection compared to AUC of 85% to 99% for state-of-the-art algorithms that learned from a larger database. Conclusions: Our hybrid architectures strengthened and extracted characteristics from DR images, while improving the performance of DR grading, thereby increasing the robustness and confidence of the architectures for general use. Translational Relevance: The proposed fusion architectures can enable faster and more accurate diagnosis of various DR pathologies than that obtained in current manual clinical practice.

[Characteristics and Influencing Factors of Stable Hydrogen and Oxygen Isotopes in Groundwater in the Permafrost Region of the Source Region of the Yangtze River].

We use 84 rainfall samples collected during June to September 2017 from the Dongkemadi basin, source region of the Yangtze River, China, to analyze the characteristics and influencing factors of stable isotopes in groundwater, and further discuss the groundwater recharge sources. The results showed that the range of groundwater δ18 O values in this permafrost region varied from -15.3‰ to -12.5‰ (mean -14.0‰). The range of δD values in groundwater varied from -108.9‰ to -91.7‰ (mean -100.2‰). Compared with local atmospheric precipitation, groundwater isotopes were relatively enriched. The slope and intercept of the groundwater line (GL) in the study area were both lower than of those of the global and local meteoric water lines (GMWL and LMWL), thus indicating that groundwater in the study area was subjected to evaporation during rainfall recharge of groundwater. The d-excess values of groundwater varied from 4.9‰ to 25.0‰ (mean 11.6‰), which was close to the average d-excess value determined for global average rainfall (10‰), but lower than that of rainfall in the study area (15.1‰). The influencing factors on the composition and variation of groundwater isotopes were different in different periods. The permafrost active layer was relatively thin during periods of increasing air temperature, and groundwater isotopes were significantly affected by air temperature. A temperature decrease during the latter part of the sampling period, when the thickness of the permafrost active layer was still increasing, further increased the retention time of infiltrating rainfall in the soil, thereby eventually leading to evaporation that strengthened the enrichment of heavy isotopes in the groundwater. According to the topographic characteristics of the Dongkemadi basin, the isotopic characteristics of the groundwater, and the factors influencing the isotopic composition, we conclude that rainfall was the main source of groundwater recharge. The results of this study provide a scientific basis for studying water cycle processes in the permafrost regions of the source region of the Yangtze River.