Adversarial Attacks on Medical Image Classification.

Due to the growing number of medical images being produced by diverse radiological imaging techniques, radiography examinations with computer-aided diagnoses could greatly assist clinical applications. However, an imaging facility with just a one-pixel inaccuracy will lead to the inaccurate prediction of medical images. Misclassification may lead to the wrong clinical decision.

Identifying Antisense Oligonucleotides to Disrupt Small RNA Regulated Antibiotic Resistance via a Cell-Free Transcription-Translation Platform.

Bacterial small RNAs (sRNAs) regulate many important physiological processes in cells, including antibiotic resistance and virulence genes, through base-pairing interactions with mRNAs. Antisense oligonucleotides (ASOs) have great potential as therapeutics against bacterial pathogens by targeting sRNAs such as MicF, which regulates outer membrane protein OmpF expression and limits the permeability of antibiotics. Here we devised a cell-free transcription-translation (TX-TL) assay to identify ASO designs that sufficiently sequester MicF.

Identifying antisense oligonucleotides to disrupt small RNA regulated antibiotic resistance via a cell-free transcription-translation platform.

Bacterial small RNAs (sRNAs) regulate many important physiological processes in cells including antibiotic resistance and virulence genes through base pairing interactions with mRNAs. Antisense oligonucleotides (ASOs) have great potential as therapeutics against bacterial pathogens by targeting sRNAs such as MicF, which regulates outer membrane protein OmpF expression and limits permeability of antibiotics. Here, we devise a cell-free transcription-translation (TX-TL) assay to identify ASO designs that sufficiently sequester MicF.

Deep Learning Technology Applied to Medical Image Tissue Classification.

Medical image classification is a novel technology that presents a new challenge. It is essential that pathological images are automatically and correctly classified to enable doctors to provide precise treatment. Convolutional neural networks have demonstrated their effectiveness in classifying images in deep learning, which may have dozens or hundreds of layers, to illustrate the relationship between them in terms of their different neural network features.

CONTROLLING ABSOLUTE FREQUENCY OF FEEDBACK IN A SELF-CONTROLLED SITUATION ENHANCES MOTOR LEARNING.

The guidance hypothesis suggested that excessive extrinsic feedback facilitates motor performance but blocks the processing of intrinsic information. The present study tested the tenet of guidance hypothesis in self-controlled feedback by controlling the feedback frequency. The motor learning effect of limiting absolute feedback frequency was examined.