Search

Diabetic retinopathy (DR) is a complication of diabetes, and one of the major causes of vision impairment in the global population. As the early-stage manifestation of DR is usually very mild and hard to detect, an accurate diagnosis via eye-screening is clinically important to prevent vision loss at later stages. In this work, we propose an ensemble method to automatically grade DR using ultra-wide optical coherence tomography angiography (UW-OCTA) images available from Diabetic Retinopathy Analysis Challenge (DRAC) 2022. First, we adopt the state-of-the-art classification networks, i.e., ResNet, DenseNet, EfficientNet, and VGG, and train them to grade UW-OCTA images with different splits of the available dataset. Ultimately, we obtain 25 models, of which, the top 16 models are selected and ensembled to generate the final predictions. During the training process, we also investigate the multi-task learning strategy, and add an auxiliary classification task, the Image Quality Assessment, to improve the model performance. Our final ensemble model achieved a quadratic weighted kappa (QWK) of 0.9346 and an Area Under Curve (AUC) of 0.9766 on the internal testing dataset, and the QWK of 0.839 and the AUC of 0.8978 on the DRAC challenge testing dataset., 13 pages, 6 figures, 5 tables. To appear in Diabetic Retinopathy Analysis Challenge (DRAC), Bin Sheng et al., MICCAI 2022 Challenge, Lecture Notes in Computer Science, Springer

Camera Image Signal Processing(ISP) pipelines, including deep learning trained versions, can get appealing results in different image signal processing tasks. However, most if not all of these methods tend to apply a single filter that is homogeneous over the entire image. This is also particularly true when an encoder-decoder type deep architecture is trained for the task. However, it is natural to view a camera image as heterogeneous, as the color intensity and the artificial noise are distributed vastly different, even across the two dimensional domain of a single image. Varied Moire ringing, motion-blur, color-bleaching or lens based projection distortions can all potentially lead to a heterogeneous image artifact filtering problem. In this paper, we present a specific patch-based, local subspace deep neural network that improves Camera ISP to be robust to heterogeneous artifacts (especially image denoising). We call our three-fold deep trained model the Patch Subspace Learning Autoencoder (PSL-AE). PSL-AE does not necessarily assume uniform image distortion levels nor repeated nor similar artifact types within the image. Rather, PSL-AE first diagnostically encodes patches extracted from noisy and clean image pairs, with different artifact type and distortion levels, by contrastive learning. Then, each image's patches are encoded into soft-clusters in their appropriate latent sub-space, using a prior mixture model. Lastly, the decoders of the PSL-AE are also trained in an unsupervised manner customized for the image patches in each soft-cluster. Our experimental results demonstrates the flexibility and performance that one can achieve through improved heterogeneous filtering, both from synthesized artifacts but also realistic SIDD image pairs.

[ABSTRACT] Mangroves in China have experienced various changes in different time periods due to anthropogenic disturbances, climate change and national restoration policy. However, few studies quantitatively analyzed these changes. This study detected the changes of mangroves in China from 1985 to 2018 by combing Landsat and ALOS PALSAR images. The results demonstrated that the total areas of China’s mangrove in 1985, 1996, 2007, 2010 and 2018 were 20,086 ha, 18,033 ha, 22,428 ha, 23,639 ha and 24,602 ha respectively. Mangrove area began to increase after 1990s mainly due to the national conservation actions. The causes for mangrove changes are various in different regions and time periods. However, most mangroves gained from aquaculture and lost to built-up. The changes between mangroves and other land covers also caused the biocapacity changes in coastal zone which contributed to around 17,000 gha increase of biocapacity from 1996 to 2018.