Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography images

As a powerful diagnostic tool, optical coherence tomography (OCT) has been widely used in various clinical setting. However, OCT images are susceptible to inherent speckle noise that may contaminate subtle structure information, due to low-coherence interferometric imaging procedure. Many supervised learning-based models have achieved impressive performance in reducing speckle noise of OCT images trained with a large number of noisy-clean paired OCT images, which are not commonly feasible in clinical practice. In this article, we conducted a comparative study to investigate the denoising performance of OCT images over different deep neural networks through an unsupervised Noise2Noise (N2N) strategy, which only trained with noisy OCT samples. Four representative network architectures including U-shaped model, multi-information stream model, straight-information stream model and GAN-based model were investigated on an OCT image dataset acquired from healthy human eyes. The results demonstrated all four unsupervised N2N models offered denoised OCT images with a performance comparable with that of supervised learning models, illustrating the effectiveness of unsupervised N2N models in denoising OCT images. Furthermore, U-shaped models and GAN-based models using UNet network as generator are two preferred and suitable architectures for reducing speckle noise of OCT images and preserving fine structure information of retinal layers under unsupervised N2N circumstances.     

Functionalization of liposomes: microscopical methods for preformulative screening

Abstract

The development of smart delivery systems able to deliver and target a drug to the site of action is one of the major challenges in the field of pharmaceutical technology. The surface modification of nanocarriers, such as liposomes, is widely investigated either for increasing the blood circulation time (by pegylation) or for interacting with specific tissues or cells (by conjugation of a selective ligand as a monoclonal antibody, mAb). Microscopical analysis thereby is a useful approach to evaluate the morphology and the size owing to resolution and versatility in defining either surface modification or the architecture and the internal structure of liposomes. This contribution aims to connect the outputs obtained by transmission electron (TEM) and atomic force (AFM) microscopical techniques for identifying the modifications on the liposomal surface. To reach this objective, we prepared liposomes applying two different pegylation technologies and further modifying the surface by mAb conjugation. This work demonstrates the feasibility to apply the combined approach (TEM and AFM analysis) in the evaluation of the efficacy of a surface engineering process.     

基于无人机的昆明海口林场宽地坝林区植物群落建群种格局研究

建群种是植物群落优势层中的主要物种,对群落环境有显著控制作用。空间格局是植物种群的基本特征之一,探讨建群种的空间格局是理解生物与生境之间关系和认识群落生态过程的有效途径。空间格局特征包括种群空间关联性及其空间分布型。利用无人机技术,获取昆明海口林场半湿润常绿阔叶林和落叶栎类林的多光谱遥感影像,采用ArcGIS Pro软件进行遥感影像分类并提取滇青冈(Cyclobalanopsis glaucoides)、光叶石栎(Lithocarpus mairei)、滇石栎(L.dealbatus)、栓皮栎(Quercus variabilis)、槲栎(Q.aliena)植株树冠中心点空间坐标。在Programita Febrero 2014软件中进点格局分析。结果表明:各物种10m以下呈均匀分布或随机,随尺度增加,渐渐表现为聚集分布。光叶石栎种群和滇石栎种群空间关联性表现为负相关。     

Validation of low-dose lung cancer PET-CT protocol and PET image improvement using machine learning

PurposeTo conduct a simplified lesion-detection task of a low-dose (LD) PET-CT protocol for frequent lung screening using 30% of the effective PETCT dose and to investigate the feasibility of increasing clinical value of low-statistics scans using machine learning.MethodsWe acquired 33 SD PET images, of which 13 had actual LD (ALD) PET, and simulated LD (SLD) PET images at seven different count levels from the SD PET scans. We employed image quality transfer (IQT), a machine learning algorithm that performs patch-regression to map parameters from low-quality to high-quality images. At each count level, patches extracted from 23 pairs of SD/SLD PET images were used to train three IQT models – global linear, single tree, and random forest regressions with cubic patch sizes of 3 and 5 voxels. The models were then used to estimate SD images from LD images at each count level for 10 unseen subjects. Lesion-detection task was carried out on matched lesion-present and lesion-absent images.ResultsLD PET-CT protocol yielded lesion detectability with sensitivity of 0.98 and specificity of 1. Random forest algorithm with cubic patch size of 5 allowed further 11.7% reduction in the effective PETCT dose without compromising lesion detectability, but underestimated SUV by 30%.ConclusionLD PET-CT protocol was validated for lesion detection using ALD PET scans. Substantial image quality improvement or additional dose reduction while preserving clinical values can be achieved using machine learning methods though SUV quantification may be biased and adjustment of our research protocol is required for clinical use.