Fluorogenic CRISPR for genomic DNA imaging.

Genomic DNA exhibits high heterogeneity in terms of its dynamic within the nucleus, its structure and functional roles. CRISPR-based imaging approaches can image genomic loci in living cells. However, conventional CRISPR-based tools involve expressing constitutively fluorescent proteins, resulting in high background and nonspecific nucleolar signal. Here, we construct fluorogenic CRISPR (fCRISPR) to overcome these issues. fCRISPR is designed with dCas9, an engineered sgRNA, and a fluorogenic protein. Fluorogenic proteins are degraded unless they are bound to specific RNA hairpins. These hairpins are inserted into sgRNA, resulting in dCas9: sgRNA: fluorogenic protein ternary complexes that enable fluorogenic DNA imaging. With fCRISPR, we image various genomic DNA in different human cells with high signal-to-noise ratio and sensitivity. Furthermore, fCRISPR tracks chromosomes dynamics and length. fCRISPR also allows DNA double-strand breaks (DSBs) and repair to be tracked in real time. Taken together, fCRISPR offers a high-contrast and sensitive platform for imaging genomic loci.

Is Intensity Inhomogeneity Correction Useful for Classification of Breast Cancer in Sonograms Using Deep Neural Network?

The sonogram is currently an effective cancer screening and diagnosis way due to the convenience and harmlessness in humans. Traditionally, lesion boundary segmentation is first adopted and then classification is conducted, to reach the judgment of benign or malignant tumor. In addition, sonograms often contain much speckle noise and intensity inhomogeneity. This study proposes a novel benign or malignant tumor classification system, which comprises intensity inhomogeneity correction and stacked denoising autoencoder (SDAE), and it is suitable for small-size dataset. A classifier is established by extracting features in the multilayer training of SDAE; automatic analysis of imaging features by the deep learning algorithm is applied on image classification, thus allowing the system to have high efficiency and robust distinguishing. In this study, two kinds of dataset (private data and public data) are used for deep learning models training. For each dataset, two groups of test images are compared: the original images and the images after intensity inhomogeneity correction, respectively. The results show that when deep learning algorithm is applied on the sonograms after intensity inhomogeneity correction, there is a significant increase of the tumor distinguishing accuracy. This study demonstrated that it is important to use preprocessing to highlight the image features and further give these features for deep learning models. In this way, the classification accuracy will be better to just use the original images for deep learning.