Search

A medical image retrieval method combining attention mechanism is proposed for a series of problems such as poor retrieval performance,low accuracy and lack of interpretability in current medical image retrieval.Based on deep convolutional neural networks and taking Bayesian models as the framework,the proposed algorithm introduces an attention mechanism module guided by semantic features.Local feature descriptors containing semantic information are generated under the guidance of the classification network.Both global features and local features rich in semantic information are used as inputs to the hash network,which enhances the feature representation capability of hash coding by guiding the hash network to pay attention to important feature regions from both global and local perspectives.And the weighted likelihood estimation function is introduced to solve the problem of the unbalanced number of positive and negative sample pairs.MAP and NDCG are used as evaluation metrics,and the ChestX-ray14 dataset is selected for experiments.The proposed algorithm is compared with the current commonly used deep ha-shing methods.Experiment results show that the MAP and NDCG values are much better than the existing deep hashing methods at different code levels of hash coding,which proves the effectiveness of the proposed algorithm.

We aimed to develop and validate a nomogram for preoperatively estimating the risk of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) within the Milan criteria. The clinical data of 312 HCC patients who underwent liver surgery at the xxx from Jan 2017 to Dec 2019 were retrospectively collected. Then, the study population was categorized into the training and validation group based on the date of surgery. To identify risk factors related to MVI, we conducted a series of logistic regression analyses. By combining these risk factors, a nomogram was then established. We further clarified the usability of our model through the area under the ROC curve (AUC), decision curve analysis (DCA), and calibration curve. Pathological examination revealed MVI in 108 patients with HCC (34.6%). Three independent predictors were identified: level of alpha-fetoprotein (AFP) exceeds 194 ng/mL (OR = 2.20, 95% CI: 1.13-4.31, p = 0.021), size of tumor (OR = 1.59; 95% CI: 1.18-2.12; P < 0.001) and number of tumors (OR = 3.37, 95% CI: 1.64-7.28, p < 0.001). A nomogram was subsequently built with an AUC of 0.73 and 0.74 respectively in the training cohort and validation cohort. The calibration curve showed a relatively high consistency between predicted probability and observed outcomes. Besides, the DCA revealed that the model was clinically beneficial for preoperatively predicting MVI in HCC. A model for evaluating the risk of MVI HCC patients was developed and validated. The model could provide clinicians with a relatively reliable basis for optimizing treatment decisions. [ABSTRACT FROM AUTHOR]

The Pearl River Delta (PRD) of China, which has a population of more than 58 million people, is one of the largest agglomerations of cities in the world and had severe PM2:5 pollution at the beginning of this century. Due to the implementation of strong pollution control in recent decades, PM2:5 in the PRD has continuously decreased to relatively lower levels in China. To comprehensively understand the current PM2:5 sources in the PRD to support future air pollution control strategies in similar regions, we performed regional-scale PM2:5 field observations coupled with a state-of-the-art source apportionment model at six sites in four seasons in 2015. The regional annual average PM2:5 concentration based on the 4-month sampling was determined to be 37 µgm-3, which is still more than 3 times the WHO standard, with organic matter (36.9%) and SO2-4 (23.6%) as the most abundant species. A novel multilinear engine (ME-2) model was first applied to a comprehensive PM2:5 chemical dataset to perform source apportionment with predetermined constraints, producing more environmentally meaningful results compared to those obtained using traditional positive matrix factorization (PMF) modeling. The regional annual average PM2:5 source structure in the PRD was retrieved to be secondary sulfate (21%), vehicle emissions (14%), industrial emissions (13%), secondary nitrate (11%), biomass burning (11%), secondary organic aerosol (SOA, 7%), coal burning (6%), fugitive dust (5%), ship emissions (3%) and aged sea salt (2%). Analyzing the spatial distribution of PM2:5 sources under different weather conditions clearly identified the central PRD area as the key emission area for SO2, NOx, coal burning, biomass burning, industrial emissions and vehicle emissions. It was further estimated that under the polluted northerly air flow in winter, local emissions in the central PRD area accounted for approximately 45% of the total PM2:5, with secondary nitrate and biomass burning being most abundant; in contrast, the regional transport from outside the PRD accounted for more than half of PM2:5, with secondary sulfate representing the most abundant transported species. [ABSTRACT FROM AUTHOR]