Geometric deep learning is increasingly important thanks to the popularity of 3D sensors. Inspired by the recent advances in NLP domain, the self-attention transformer is introduced to consume the point clouds. We develop Point Attention Transformers (PATs), using a parameter-efficient Group Shuffle Attention (GSA) to replace the costly Multi-Head Attention. We demonstrate its ability to process size-varying inputs, and prove its permutation equivariance. Besides, prior work uses heuristics dependence on the input data (e.g., Furthest Point Sampling) to hierarchically select subsets of input points. Thereby, we for the first time propose an end-to-end learnable and taskagnostic sampling operation, named Gumbel Subset Sampling (GSS), to select a representative subset of input points. Equipped with Gumbel-Softmax, it produces a "soft" continuous subset in training phase, and a "hard" discrete subset in test phase. By selecting representative subsets in a hierarchical fashion, the networks learn a stronger representation of the input sets with lower computation cost. Experiments on classification and segmentation benchmarks show the effectiveness and efficiency of our methods. Furthermore, we propose a novel application, to process event camera stream as point clouds, and achieve a state-of-theart performance on DVS128 Gesture Dataset.

X-ray repair cross-complementing group 1 (XRCC1) plays an important role in base excision and single-strand break repair, as a scaffold protein that brings together proteins of the DNA repair complex, and appears to be a candidate for cancer risk. However, studies on the association between polymorphisms in this protein and cancer have yielded conflicting results. We performed a meta-analysis to investigate the association between the breast cancer and the XRCC1 polymorphisms Arg194Trp (9411 cases and 9783 controls), Arg399Gln (22 481 cases and 23 905 controls) and Arg280His (6062 cases and 5864 controls) in different inheritance models. Our analysis suggested that Arg399Gln was associated with a trend of increased breast cancer risk when using both dominant [odds ratio (OR) = 1.06, 95% confidence interval (CI): 1.00-1.13] and recessive models (OR = 1.12, 95% CI: 1.02-1.23) to analyse the data. In ethnic subgroups and using recessive model analysis: Arg399Gln increased breast cancer risk in Asians (OR = 1.26, 95% CI: 0.96-1.64) and Africans (OR = 1.80, 95% CI: 0.97-3.32), and also while only slightly increasing the breast cancer risk in Caucasians (OR = 1.08, 95% CI: 0.95-1.22). However, Arg194Trp (recessive model, OR = 0.95, 95% CI: 0.75-1.20) and Arg280His (recessive model, OR = 1.28, 95% CI: 0.64-2.55) did not appear to be risk factors for breast cancer. Larger scale primary studies are required to further evaluate the interaction of XRCC1 polymorphisms and breast cancer risk in specific populations.

No abstract

No abstract

The computation of image segmentation has become more complicated with the increasing number of thresholds, and the option and application of the thresholds in image thresholding fields have become an NP problem at the same time. The paper puts forward the modified discrete grey wolf optimizer algorithm (MDGWO), which improves on the optimal solution updating mechanism of the search agent by the weights. Taking Kapur's entropy as the optimized function and based on the discreteness of threshold in image segmentation, the paper firstly discretizes the grey wolf optimizer (GWO) and then proposes a new attack strategy by using the weight coefficient to replace the search formula for optimal solution used in the original algorithm. The experimental results show that MDGWO can search out the optimal thresholds efficiently and precisely, which are very close to the result examined by exhaustive searches. In comparison with the electromagnetism optimization (EMO), the differential evolution (DE), the Artifical Bee Colony (ABC), and the classical GWO, it is concluded that MDGWO has advantages over the latter four in terms of image segmentation quality and objective function values and their stability.

No abstract

Thresholding segmentation based on fuzzy entropy and intelligent optimization is one of the most commonly used and direct methods. This paper takes fuzzy Kapur's entropy as the best optimal objective function, with modified quick artificial bee colony algorithm (MQABC) as the tool, performs fuzzy membership initialization operations through Pseudo Trapezoid-Shaped (PTS) membership function, and finally, according to the image's spacial location information, conducts local information aggregation by way of median, average, and iterative average so as to achieve the final segmentation. The experimental results show that the proposed FMQABC (fuzzy based modified quick artificial bee colony algorithm) and FMQABCA (fuzzy based modified quick artificial bee colony and aggregation algorithm) can search out the best optimal threshold very effectively, precisely, and speedily and in particular show exciting efficiency in running time. This paper experimentally compares the proposed method with Kapur's entropy-based Electromagnetism Optimization (EMO) method, standard ABC, and FDE (fuzzy entropy based differential evolution algorithm), respectively, and concludes that MQABCA is far more superior to the rest in terms of segmentation quality, iterations to convergence, and running time.

Radiomics analysis has achieved great success in recent years. However, conventional Radiomics analysis suffers from insufficiently expressive hand-crafted features. Recently, emerging deep learning techniques, e.g., convolutional neural networks (CNNs), dominate recent research in Computer-Aided Diagnosis (CADx). Unfortunately, as blackbox predictors, we argue that CNNs are "diagnosing" voxels (or pixels), rather than lesions; in other words, visual saliency from a trained CNN is not necessarily concentrated on the lesions. On the other hand, classification in clinical applications suffers from inherent ambiguities: radiologists may produce diverse diagnosis on challenging cases. To this end, we propose a controllable and explainable Probabilistic Radiomics framework, by combining the Radiomics analysis and probabilistic deep learning. In our framework, 3D CNN feature is extracted upon lesion region only, then encoded into lesion representation, by a controllable Non-local Shape Analysis Module (NSAM) based on self-attention. Inspired from variational auto-encoders (VAEs), an Ambiguity PriorNet is used to approximate the ambiguity distribution over human experts. The final diagnosis is obtained by combining the ambiguity prior sample and lesion representation, and the whole network named DenseSharp + is end-to-end trainable. We apply the proposed method on lung nodule diagnosis on LIDC-IDRI database to validate its effectiveness.