Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion.

In laser powder bed fusion processes, keyholes are the gaseous cavities formed where laser interacts with metal, and their morphologies play an important role in defect formation and the final product quality. The in-situ X-ray imaging technique can monitor the keyhole dynamics from the side and capture keyhole shapes in the X-ray image stream. Keyhole shapes in X-ray images are then often labeled by humans for analysis, which increasingly involves attempting to correlate keyhole shapes with defects using machine learning. However, such labeling is tedious, time-consuming, error-prone, and cannot be scaled to large data sets. To use keyhole shapes more readily as the input to machine learning methods, an automatic tool to identify keyhole regions is desirable. In this paper, a deep-learning-based computer vision tool that can automatically segment keyhole shapes out of X-ray images is presented. The pipeline contains a filtering method and an implementation of the BASNet deep learning model to semantically segment the keyhole morphologies out of X-ray images. The presented tool shows promising average accuracy of 91.24% for keyhole area, and 92.81% for boundary shape, for a range of test dataset conditions in Al6061 (and one AliSi10Mg) alloys, with 300 training images/labels and 100 testing images for each trial. Prospective users may apply the presently trained tool or a retrained version following the approach used here to automatically label keyhole shapes in large image sets.

Vicinity Vision Transformer.

Vision transformers have shown great success on numerous computer vision tasks. However, their central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Linear attention was introduced in natural language processing (NLP) which reorders the self-attention mechanism to mitigate a similar issue, but directly applying existing linear attention to vision may not lead to satisfactory results. We investigate this problem and point out that existing linear attention methods ignore an inductive bias in vision tasks, i.e., 2D locality. In this article, we propose Vicinity Attention, which is a type of linear attention that integrates 2D locality. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance from its neighbouring patches. In this case, we achieve 2D locality in a linear complexity where the neighbouring image patches receive stronger attention than far away patches. In addition, we propose a novel Vicinity Attention Block that is comprised of Feature Reduction Attention (FRA) and Feature Preserving Connection (FPC) in order to address the computational bottleneck of linear attention approaches, including our Vicinity Attention, whose complexity grows quadratically with respect to the feature dimension. The Vicinity Attention Block computes attention in a compressed feature space with an extra skip connection to retrieve the original feature distribution. We experimentally validate that the block further reduces computation without degenerating the accuracy. Finally, to validate the proposed methods, we build a linear vision transformer backbone named Vicinity Vision Transformer (VVT). Targeting general vision tasks, we build VVT in a pyramid structure with progressively reduced sequence length. We perform extensive experiments on CIFAR-100, ImageNet-1 k, and ADE20 K datasets to validate the effectiveness of our method. Our method has a slower growth rate in terms of computational overhead than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous approaches.

Synergetic removal of oppositely charged dyes by co-precipitation and amphoteric self-floating capturer: Mechanism investigation by molecular simulation.

The adsorption performances of adsorbents to dyes are hard to maintain in a wide pH range because most of the reactions are pH-dependent, developing a cost-effective strategy to break the pH-limitation is significant. In this study, an amphoteric self-floating adsorbent (Am-SA) was synthesized by hollow silica microsphere surface modification, which was useful to capture anionic acid orange 7 (AO7) and cationic crystal violet (CV) dyes, but the adsorption performances were also greatly affected by pH. Fortunately, a co-precipitation phenomenon was noticed when the AO7 and CV solutions were mixed with a 1:1 molecule ratio. The precise structures of AO7 and CV molecules were constructed and the AO7-CV-H2O mixed system was structured by Materials Studio. Besides, this system was involved in a dynamic simulation to reveal the mechanism of the co-precipitation phenomenon. The simulation results showed H2O molecules dispersed out of the system via thermal motions within 30 ps, but the AO7 and CV molecules aggregated to each other via electrostatic attractions. The energy calculations also demonstrated the electrostatic attraction between AO7 and CV is the dominant factor that induced the aggregation. The aggregation phenomena were also observed in various mixed cationic-anionic dyes systems. The removals of dyes significantly improved in a wide pH range in the mixed systems as the captures of the aggregated dye clusters were much easier than that of independent dye molecules, and both co-precipitation and adsorption contributed to it. Proper utilization of the aggregation behaviors between dyes can be regarded as a prospective strategy in cost-effective treatments.

Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding.

Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information. However, it relies on neighbouring frames which are not always available in the real world. Meanwhile, slight camera shake easily causes heavy motion blur on long-distance-shot low-resolution images. To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images. Motion-blurred images are the accumulation over time during the exposure of cameras, while the proposed BMDSRNet learns the reverse process and uses three-streams to learn Bidirectional spatio-temporal information based on well designed reconstruction loss functions to recover clean high-resolution images. Extensive experiments demonstrate that the proposed BMDSRNet outperforms recent state-of-the-art methods, and has the ability to simultaneously deal with image deblurring and SR.

RNase L facilitates the repair of DNA double-strand breaks through the nonhomologous end-joining pathway.

RNA molecules have been found to play important roles in DNA double-strand break (DSB) repair, but the exact underlying mechanism remains unclear. Here, we aimed to clarify the function of RNase L, an important ribonuclease in the immune system of vertebrates, in DSB repair. Knockdown of RNase L reduces cell survival after induction of DSBs by ionizing radiation or camptothecin and causes a significant decrease in DSB repair, as evidenced by an increase in the extent of phosphorylation of histone H2AX on Ser139 (γH2AX) and γH2AX nuclear foci formation. Thus, our findings indicate that RNase L interacts with the core factors involved in DNA end joining, such as XRCC4 and Lig4, and facilitates DSB repair through the nonhomologous end-joining pathway.

Adversarial Spatio-Temporal Learning for Video Deblurring.

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance.

Identification of lncRNA MEG3 Binding Protein Using MS2-Tagged RNA Affinity Purification and Mass Spectrometry.

Long noncoding RNAs (lncRNAs) are nonprotein coding transcripts longer than 200 nucleotides. Recently in mammals, thousands of long noncoding RNAs have been identified and studied as key molecular players in different biological processes with protein complexes. As a long noncoding RNA, maternally expressed gene 3 (MEG3) plays an important role in many cellular processes. However, the mechanism underlying MEG3 regulatory effects remains enigmatic. By using the specific interaction between MS2 coat protein and MS2 RNA hairpin, we developed a method (MS2-tagged RNA affinity purification and mass spectrometry (MTRAP-MS)) to identify proteins that interact with MEG3. Mass spectrometry and gene ontology (GO) analysis showed that MEG3 binding proteins possess nucleotide binding properties and take part in transport, translation, and other biological processes. In addition, interleukin enhancer binding factor 3 (ILF3) and poly(A) binding protein, cytoplasmic 3 (PABPC3) were validated for their interaction with MEG3. These findings indicate that the newly developed method can effectively enrich lncRNA binding proteins and provides a strong basis for studying MEG3 functions.