Fundus tessellation segmentation and quantization based on the deep convolution neural network / 中华眼底病杂志

Objective:To propose automatic measurement of global and local tessellation density on color fundus images based on a deep convolutional neural network (DCNN) method.Methods:An applied study. An artificial intelligence (AI) database was constructed, which contained 1 005 color fundus images captured from 1 024 eyes of 514 myopic patients in the Northern Hospital of Qingdao Eye Hospital from May to July, 2021. The images were preprocessed by using RGB color channel re-calibration method (CCR algorithm), CLAHE algorithm based on Lab color space, Retinex algorithm for multiple iterative illumination estimation, and multi-scale Retinex algorithm. The effects on the segmentation of tessellation by adopting the abovemetioned image enhancement methods and utilizing the Dice, Edge Overlap Rate and clDice loss were compared and observed. The tessellation segmentation model for extracting the tessellated region in the full fundus image as well as the tissue detection model for locating the optic disc and macular fovea were built up. Then, the fundus tessellation density (FTD), macular tessellation density (MTD) and peripapillary tessellation density (PTD) were calculated automatically.Results:When applying CCR algorithm for image preprocessing and the training losses combination strategy, the Dice coefficient, accuracy, sensitivity, specificity and Jordan index for fundus tessellation segmentation were 0.723 4, 94.25%, 74.03%, 96.00% and 70.03%, respectively. Compared with the manual annotations, the mean absolute errors and root mean square errors of FTD, MTD, PTD automatically measured by the model were 0.014 3, 0.020 7, 0.026 7 and 0.017 8, 0.032 3, 0.036 5, respectively.Conclusion:The DCNN-based segmentation and detection method can automatically measure the tessellation density in the global and local regions of the fundus of myopia patients, which can more accurately assist clinical monitoring and evaluation of the impact of fundus tessellation changes on the development of myopia.

ALeRT-COVID: Attentive Lockdown-awaRe Transfer Learning for Predicting COVID-19 Pandemics in Different Countries

Countries across the world are in different stages of COVID-19 trajectory, among which many have implemented the lockdown measures to prevent its spread. Although the lockdown is effective in such prevention, it may put the economy into a depression. Predicting the epidemic progression with government switching the lockdown on or off is critical. We propose a transfer learning approach called ALeRT-COVID using attention-based recurrent neural network (RNN) architecture to predict the epidemic trends for different countries. A source model was trained on the pre-defined source countries and then transferred to each target country. The lockdown measure was introduced to our model as a predictor and the attention mechanism was utilized to learn the different contributions of the confirmed cases in the past days to the future trend. Results demonstrated that the transfer learning strategy is helpful especially for early-stage countries. By introducing the lockdown predictor and the attention mechanism, ALeRT-COVID showed a significant improvement on the prediction performance. We predicted the confirmed cases in one week when extending and easing lockdown separately. Results showed the lockdown measures is still necessary for a number of countries. We expect our research can help different countries to make better decisions on the lockdown measures.

Exploring transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images.

The success of Convolutional Neural Network (CNN) is attributed to their ability to learn rich midlevel image representations as opposed to hand-crafted low-level features used in many natural image classification methods. Learning CNN, however, amounts to estimating millions of parameters and requires a very large number of annotated image samples. In this paper, we explored transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images, and showed how image representations learned with CNN on large-scale annotated datasets can be efficiently transferred to other tasks with limited amount of training data. We first transferred pre-trained Inception V3 model trained on the ImageNet dataset to compute mid-level image representation, and then fine-tuned the trained model with labeled endoscopy images, and resumed training from already learned weights. Additionally, we introduce both data augmentation and image resampling to increase the size of the training database and the positive sample rate to perform the Transfer Learning. Our results showed that our transfer learning method produces the best performance on AUC (the area under the receiver operating curve), Precision, Recall and Accuracy as compared to both the hand-crafted feature based method and training CNN model from-scratch method.