Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

Computer Decision Support System for Skin Cancer Localization and Classification

In this work,we propose a new,fully automated system for multiclass skin lesion localization and classification using deep learning.The main challenge is to address the problem of imbalanced data classes,found in HAM10000,ISBI2018,and ISBI2019 datasets.Initially,we consider a pretrained deep neural network model,DarkeNet19,and fine-tune the parameters of third convolutional layer to generate the image gradients.All the visualized images are fused using a High-Frequency approach along with Multilayered Feed-Forward Neural Network(HFaFFNN).The resultant image is further enhanced by employing a log-opening based activation function to generate a localized binary image.Later,two pre-trained deep models,Darknet-53 and NasNet-mobile,are employed and fine-tuned according to the selected datasets.The concept of transfer learning is later explored to train both models,where the input feed is the generated localized lesion images.In the subsequent step,the extracted features are fused using parallel max entropy correlation(PMEC)technique.To avoid the problem of overfitting and to select the most discriminant feature information,we implement a hybrid optimization algorithm called entropy-kurtosis controlled whale optimization(EKWO)algorithm.The selected features are finally passed to the softmax classifier for the final classification.Three datasets are used for the experimental process,such as HAM10000,ISBI2018,and ISBI2019 to achieve an accuracy of 95.8%,97.1%,and 85.35%,respectively.

A Rapid DNA Mini-prep Method for Large-Scale Rice Mutant Screening

A high throughput rice DNA mini-preparation method was developed. The method is suitable for large-scale mutant bank screening as well as large mapping populations with characteristics of maintaining relatively high level of DNA purity and concentration. The extracted DNA was tested and suitable for regular PCR amplification （SSR） and for Targeting Induced Local Lesion in Genome （TILLING） analysis.

High-resolution melting-based TILLING of γ ray-induced mutations in rice

Targeting Induced Local Lesions IN Genomes （TILLING） is a reverse genetics strategy for the high-throughput screening of induced mutations.γ, radiation, which often induces both insertion/deletion （Indel） and point mutations, has been widely used in mutation induction and crop breeding. The present study aimed to develop a simple, high-throughput TILLING system for screening γ ray-induced mutations using high-resolution melting （HRM） analysis. Pooled rice （Oryza sativa） samples mixed at a 1：7 ratio of Indel mutant to wild-type DNA could be distinguished from the wild-type controls by HRM analysis. Thus, an HRM-TILLING system that analyzes pooled samples of four M2 plants is recommended for screening γ, ray-induced mutants in rice. For demonstration, a γ, ray-mutagenized M2 rice population （n=4560） was screened for mutations in two genes, OsLCT1 and SPDT, using this HRM-TILLING system. Mutations including one single nucleotide substitution （G→A） and one single nucleotide insertion （A） were identified in OsLCT1, and one tdnucleotide （TTC） deletion was identified in SPDT. These mutants can be used in rice breeding and genetic studies, and the findings are of importance for the application of γ, ray mutagenesis to the breeding of rice and other seed crops.