[Abstract unavailable

Medical imaging can assess the tumor and its environment in their entirety, which makes it suitable for monitoring the temporal and spatial characteristics of the tumor. Progress in computational methods, especially in artificial intelligence for medical image process and analysis, has converted these images into quantitative and minable data associated with clinical events in oncology management. This concept was first described as radiomics in 2012. Since then, computer scientists, radiologists, and oncologists have gravitated towards this new tool and exploited advanced methodologies to mine the information behind medical images. On the basis of a great quantity of radiographic images and novel computational technologies, researchers developed and validated radiomic models that may improve the accuracy of diagnoses and therapy response assessments. Here, we review the recent methodological developments in radiomics, including data acquisition, tumor segmentation, feature extraction, and modelling, as well as the rapidly developing deep learning technology. Moreover, we outline the main applications of radiomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalized medicine. Finally, we discuss the challenges in the field of radiomics and the scope and clinical applicability of these methods.

Extracellular vesicles (EVs) have stimulated considerable scientific and clinical interest, yet protein profiling and sizing of individual EVs remains challenging due to their small particle size, low abundance of proteins, and overall heterogeneity. Building upon a laboratory-built high-sensitivity flow cytometer (HSFCM), we report here a rapid approach for quantitative multiparameter analysis of single EVs down to 40 nm with an analysis rate up to 10 000 particles per minute. Statistically robust particle size distribution was acquired in minutes with a resolution and profile well matched with those of cryo-TEM measurements. Subpopulations of EVs expressing CD9, CD63, and/or CD81 were quantified upon immunofluorescent staining. When HSFCM was used to analyze blood samples, a significantly elevated level of CD147-positive EVs was identified in colorectal cancer patients compared to healthy controls (P < 0.001). HSFCM provides a sensitive and rapid platform for surface protein profiling and sizing of individual EVs, which could greatly aid the understanding of EV-mediated intercellular communication and the development of advanced diagnostic and therapeutic strategies.

The CRISPR-Cas systems, as exemplified by CRISPR-Cas9, are RNA-guided adaptive immune systems used by bacteria and archaea to defend against viral infection. The CRISPR-Cpf1 system, a new class 2 CRISPR-Cas system, mediates robust DNA interference in human cells. Although functionally conserved, Cpf1 and Cas9 differ in many aspects including their guide RNAs and substrate specificity. Here we report the 2.38 Å crystal structure of the CRISPR RNA (crRNA)-bound Lachnospiraceae bacterium ND2006 Cpf1 (LbCpf1). LbCpf1 has a triangle-shaped architecture with a large positively charged channel at the centre. Recognized by the oligonucleotide-binding domain of LbCpf1, the crRNA adopts a highly distorted conformation stabilized by extensive intramolecular interactions and the (Mg(H2O)6)(2+) ion. The oligonucleotide-binding domain also harbours a looped-out helical domain that is important for LbCpf1 substrate binding. Binding of crRNA or crRNA lacking the guide sequence induces marked conformational changes but no oligomerization of LbCpf1. Our study reveals the crRNA recognition mechanism and provides insight into crRNA-guided substrate binding of LbCpf1, establishing a framework for engineering LbCpf1 to improve its efficiency and specificity for genome editing.

A large body of previous models to predict where people look in natural scenes focused on pixel-level image attributes. To bridge the semantic gap between the predictive power of computational saliency models and human behavior, we propose a new saliency architecture that incorporates information at three layers: pixel-level image attributes, object-level attributes, and semantic-level attributes. Object- and semantic-level information is frequently ignored, or only a few sample object categories are discussed where scaling to a large number of object categories is not feasible nor neurally plausible. To address this problem, this work constructs a principled vocabulary of basic attributes to describe object- and semantic-level information thus not restricting to a limited number of object categories. We build a new dataset of 700 images with eye-tracking data of 15 viewers and annotation data of 5,551 segmented objects with fine contours and 12 semantic attributes (publicly available with the paper). Experimental results demonstrate the importance of the object- and semantic-level information in the prediction of visual attention.

Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven lung cancer analysis. However, the heterogeneity of lung nodules and the presence of similar visual characteristics between nodules and their surroundings make it difficult for robust nodule segmentation. In this study, we propose a data-driven model, termed the Central Focused Convolutional Neural Networks (CF-CNN), to segment lung nodules from heterogeneous CT images. Our approach combines two key insights: 1) the proposed model captures a diverse set of nodule-sensitive features from both 3-D and 2-D CT images simultaneously; 2) when classifying an image voxel, the effects of its neighbor voxels can vary according to their spatial locations. We describe this phenomenon by proposing a novel central pooling layer retaining much information on voxel patch center, followed by a multi-scale patch learning strategy. Moreover, we design a weighted sampling to facilitate the model training, where training samples are selected according to their degree of segmentation difficulty. The proposed method has been extensively evaluated on the public LIDC dataset including 893 nodules and an independent dataset with 74 nodules from Guangdong General Hospital (GDGH). We showed that CF-CNN achieved superior segmentation performance with average dice scores of 82.15% and 80.02% for the two datasets respectively. Moreover, we compared our results with the inter-radiologists consistency on LIDC dataset, showing a difference in average dice score of only 1.98%.

Regeneration of adult tissues depends on somatic stem cells that remain quiescent yet are primed to enter a differentiation program. The molecular pathways that prevent activation of these cells are not well understood. Using mouse skeletal muscle stem cells as a model, we show that a general repression of translation, mediated by the phosphorylation of translation initiation factor eIF2α at serine 51 (P-eIF2α), is required to maintain the quiescent state. Skeletal muscle stem cells unable to phosphorylate eIF2α exit quiescence, activate the myogenic program, and differentiate, but do not self-renew. P-eIF2α ensures in part the robust translational silencing of accumulating mRNAs that is needed to prevent the activation of muscle stem cells. Additionally, P-eIF2α-dependent translation of mRNAs regulated by upstream open reading frames (uORFs) contributes to the molecular signature of stemness. Pharmacological inhibition of eIF2α dephosphorylation enhances skeletal muscle stem cell self-renewal and regenerative capacity.

Epidermal growth factor receptor (EGFR) genotyping is critical for treatment guidelines such as the use of tyrosine kinase inhibitors in lung adenocarcinoma. Conventional identification of EGFR genotype requires biopsy and sequence testing which is invasive and may suffer from the difficulty of accessing tissue samples. Here, we propose a deep learning model to predict EGFR mutation status in lung adenocarcinoma using non-invasive computed tomography (CT).We retrospectively collected data from 844 lung adenocarcinoma patients with pre-operative CT images, EGFR mutation and clinical information from two hospitals. An end-to-end deep learning model was proposed to predict the EGFR mutation status by CT scanning.By training in 14 926 CT images, the deep learning model achieved encouraging predictive performance in both the primary cohort (n=603; AUC 0.85, 95% CI 0.83–0.88) and the independent validation cohort (n=241; AUC 0.81, 95% CI 0.79–0.83), which showed significant improvement over previous studies using hand-crafted CT features or clinical characteristics (p<0.001). The deep learning score demonstrated significant differences in EGFR-mutant and EGFR-wild type tumours (p<0.001).Since CT is routinely used in lung cancer diagnosis, the deep learning model provides a non-invasive and easy-to-use method for EGFR mutation status prediction.