We propose a conceptually simple framework for fast COVID-19 screening in 3D chest CT images. The framework can efficiently predict whether or not a CT scan contains pneumonia while simultaneously identifying pneumonia types between COVID-19 and Interstitial Lung Disease (ILD) caused by other viruses. In the proposed method, two 3D-ResNets are coupled together into a single model for the two above-mentioned tasks via a novel prior-attention strategy. We extend residual learning with the proposed prior-attention mechanism and design a new so-called prior-attention residual learning (PARL) block. The model can be easily built by stacking the PARL blocks and trained end-to-end using multi-task losses. More specifically, one 3D-ResNet branch is trained as a binary classifier using lung images with and without pneumonia so that it can highlight the lesion areas within the lungs. Simultaneously, inside the PARL blocks, prior-attention maps are generated from this branch and used to guide another branch to learn more discriminative representations for the pneumonia-type classification. Experimental results demonstrate that the proposed framework can significantly improve the performance of COVID-19 screening. Compared to other methods, it achieves a state-of-the-art result. Moreover, the proposed method can be easily extended to other similar clinical applications such as computer-aided detection and diagnosis of pulmonary nodules in CT images, glaucoma lesions in Retina fundus images, etc.

Objective: Many common eye diseases and cardiovascular diseases can be diagnosed through retinal imaging. However, due to uneven illumination, image blurring, and low contrast, retinal images with poor quality are not useful for diagnosis, especially in automated image analyzing systems. Here, we propose a new image enhancement method to improve color retinal image luminosity and contrast. Methods: A luminance gain matrix, which is obtained by gamma correction of the value channel in the HSV (hue, saturation, and value) color space, is used to enhance the R, G, and B (red, green and blue) channels, respectively. Contrast is then enhanced in the luminosity channel of L ^* a ^* b ^* color space by CLAHE (contrast-limited adaptive histogram equalization). Image enhancement by the proposed method is compared to other methods by evaluating quality scores of the enhanced images. Results: The performance of the method is mainly validated on a dataset of 961 poor-quality retinal images. Quality assessment (range 0-1) of image enhancement of this poor dataset indicated that our method improved color retinal image quality from an average of 0.0404 (standard deviation 0.0291) up to an average of 0.4565 (standard deviation 0.1000). Conclusion: The proposed method is shown to achieve superior image enhancement compared to contrast enhancement in other color spaces or by other related methods, while simultaneously preserving image naturalness. Significance: This method of color retinal image enhancement may be employed to assist ophthalmologists in more efficient screening of retinal diseases and in development of improved automated image analysis for clinical diagnosis.

Background: One of the major challenges in precision medicine is accurate prediction of individual patient’s response to drugs. A great number of computational methods have been developed to predict compounds activity using genomic profiles or chemical structures, but more exploration is yet to be done to combine genetic mutation, gene expression, and cheminformatics in one machine learning model.Results: We presented here a novel deep-learning model that integrates gene expression, genetic mutation, and chemical structure of compounds in a multi-task convolutional architecture. We applied our model to the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) datasets. We selected relevant cancer-related genes based on oncology genetics database and L1000 landmark genes, and used their expression and mutations as genomic features in model training. We obtain the cheminformatics features for compounds from PubChem or ChEMBL. Our finding is that combining gene expression, genetic mutation, and cheminformatics features greatly enhances the predictive performance.Conclusion: We implemented an extended Graph Neural Network for molecular graphs and Convolutional Neural Network for gene features. With the employment of multi-tasking and self-attention functions to monitor the similarity between compounds, our model outperforms recently published methods using the same training and testing datasets.

Introduction: The loss of nigrosome-1, which is also referred to as the swallow tail sign (STS) in T2^*-weighted iron-sensitive magnetic resonance imaging (MRI), has recently emerged as a new biomarker for idiopathic Parkinson's disease (IPD). However, consistent recognition of the STS is difficult due to individual variations and different imaging parameters. Radiomics might have the potential to overcome these shortcomings. Therefore, we chose to explore whether radiomic features of nigrosome-1 of substantia nigra (SN) based on quantitative susceptibility mapping (QSM) could help to differentiate IPD patients from healthy controls (HCs). Methods: Three-dimensional multi-echo gradient-recalled echo images (0.86 × 0.86 × 1.00 mm³) were obtained at 3.0-T MRI for QSM in 87 IPD patients and 77 HCs. Regions of interest (ROIs) of the SN below the red nucleus were manually drawn on both sides, and subsequently, volumes of interest (VOIs) were segmented (these ROIs included four 1-mm slices). Then, 105 radiomic features (including 18 first-order features, 13 shape features, and 74 texture features) of bilateral VOIs in the two groups were extracted. Forty features were selected according to the ensemble feature selection method, which combined analysis of variance, random forest, and recursive feature elimination. The selected features were further utilized to distinguish IPD patients from HC using the SVM classifier with 10 rounds of 3-fold cross-validation. Finally, the representative features were analyzed using an unpaired t-test with Bonferroni correction and correlated with the UPDRS-III scores. Results: The classification results from SVM were as follows: area under curve (AUC): 0.96 ± 0.02; accuracy: 0.88 ± 0.03; sensitivity: 0.89 ± 0.06; and specificity: 0.87 ± 0.07. Five representative features were selected to show their detailed difference between IPD patients and HCs: 10th percentile and median in IPD patients were higher than those in HCs (all p < 0.00125), while Gray Level Run Length Matrix (GLRLM)-Long Run Low Gray Level Emphasis, Gray Level Size Zone Matrix (GLSZM)–Gray Level Non-Uniformity, and volume (all p < 0.00125) in IPD patients were lower than those in HCs. The 10th percentile was positively correlated with UPDRS-III score (r = 0.35, p = 0.001). Conclusion: Radiomic features of the nigrosome-1 region of SN based on QSM could be useful in the diagnosis of IPD and could serve as a surrogate marker for the STS.

Person re-identification (ReID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data [ 9 ], which benefits from the popularity of the synthetic data engine, has attracted great attention from the public. However, existing datasets are limited in quantity, diversity, and realisticity, and cannot be efficiently used for the ReID problem. To address this challenge, we manually construct a large-scale person dataset named FineGPR with fine-grained attribute annotations. Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST based on the traditional machine learning algorithm, which dynamically learns attribute distribution in a real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios. Experiments conducted on benchmarks demonstrate that FineGPR with AOST outperforms (or is on par with) existing real and synthetic datasets, which suggests its feasibility for the ReID task and proves the proverbial less-is-more principle. Our synthetic FineGPR dataset is publicly available at https://github.com/JeremyXSC/FineGPR .

Segmentation of hepatic vessels from 3D CT images is necessary for accurate diagnosis and preoperative planning for liver cancer. However, due to the low contrast and high noises of CT images, automatic hepatic vessel segmentation is a challenging task. Hepatic vessels are connected branches containing thick and thin blood vessels, showing an important structural characteristic or a prior: the connectivity of blood vessels. However, this is rarely applied in existing methods. In this paper, we segment hepatic vessels from 3D CT images by utilizing the connectivity prior. To this end, a graph neural network (GNN) used to describe the connectivity prior of hepatic vessels is integrated into a general convolutional neural network (CNN). Specifically, a graph attention network (GAT) is first used to model the graphical connectivity information of hepatic vessels, which can be trained with the vascular connectivity graph constructed directly from the ground truths. Second, the GAT is integrated with a lightweight 3D U-Net by an efficient mechanism called the plug-in mode, in which the GAT is incorporated into the U-Net as a multi-task branch and is only used to supervise the training procedure of the U-Net with the connectivity prior. The GAT will not be used in the inference stage, and thus will not increase the hardware and time costs of the inference stage compared with the U-Net. Therefore, hepatic vessel segmentation can be well improved in an efficient mode. Extensive experiments on two public datasets show that the proposed method is superior to related works in accuracy and connectivity of hepatic vessel segmentation.