Adaptive Cross-Feature Fusion Network With Inconsistency Guidance for Multi-Modal Brain Tumor Segmentation.

In the context of contemporary artificial intelligence, increasing deep learning (DL) based segmentation methods have been recently proposed for brain tumor segmentation (BraTS) via analysis of multi-modal MRI. However, known DL-based works usually directly fuse the information of different modalities at multiple stages without considering the gap between modalities, leaving much room for performance improvement. In this paper, we introduce a novel deep neural network, termed ACFNet, for accurately segmenting brain tumor in multi-modal MRI. Specifically, ACFNet has a parallel structure with three encoder-decoder streams. The upper and lower streams generate coarse predictions from individual modality, while the middle stream integrates the complementary knowledge of different modalities and bridges the gap between them to yield fine prediction. To effectively integrate the complementary information, we propose an adaptive cross-feature fusion (ACF) module at the encoder that first explores the correlation information between the feature representations from upper and lower streams and then refines the fused correlation information. To bridge the gap between the information from multi-modal data, we propose a prediction inconsistency guidance (PIG) module at the decoder that helps the network focus more on error-prone regions through a guidance strategy when incorporating the features from the encoder. The guidance is obtained by calculating the prediction inconsistency between upper and lower streams and highlights the gap between multi-modal data. Extensive experiments on the BraTS 2020 dataset show that ACFNet is competent for the BraTS task with promising results and outperforms six mainstream competing methods.

Towards Transparent Deep Image Aesthetics Assessment with Tag-based Content Descriptors.

Deep learning approaches for Image Aesthetics Assessment (IAA) have shown promising results in recent years, but the internal mechanisms of these models remain unclear. Previous studies have demonstrated that image aesthetics can be predicted using semantic features, such as pre-trained object classification features. However, these semantic features are learned implicitly, and therefore, previous works have not elucidated what the semantic features are representing. In this work, we aim to create a more transparent deep learning framework for IAA by introducing explainable semantic features. To achieve this, we propose Tag-based Content Descriptors (TCDs), where each value in a TCD describes the relevance of an image to a human-readable tag that refers to a specific type of image content. This allows us to build IAA models from explicit descriptions of image contents. We first propose the explicit matching process to produce TCDs that adopt predefined tags to describe image contents. We show that a simple MLP-based IAA model with TCDs only based on predefined tags can achieve an SRCC of 0.767, which is comparable to most state-of-the-art methods. However, predefined tags may not be sufficient to describe all possible image contents that the model may encounter. Therefore, we further propose the implicit matching process to describe image contents that cannot be described by predefined tags. By integrating components obtained from the implicit matching process into TCDs, the IAA model further achieves an SRCC of 0.817, which significantly outperforms existing IAA methods. Both the explicit matching process and the implicit matching process are realized by the proposed TCD generator. To evaluate the performance of the proposed TCD generator in matching images with predefined tags, we also labeled 5101 images with photography-related tags to form a validation set. And experimental results show that the proposed TCD generator can meaningfully assign photography-related tags to images.

Benchmarking Polyp Segmentation Methods in Narrow-Band Imaging Colonoscopy Images.

In recent years, there has been significant progress in polyp segmentation in white-light imaging (WLI) colonoscopy images, particularly with methods based on deep learning (DL). However, little attention has been paid to the reliability of these methods in narrow-band imaging (NBI) data. NBI improves visibility of blood vessels and helps physicians observe complex polyps more easily than WLI, but NBI images often include polyps with small/flat appearances, background interference, and camouflage properties, making polyp segmentation a challenging task. This paper proposes a new polyp segmentation dataset (PS-NBI2K) consisting of 2,000 NBI colonoscopy images with pixel-wise annotations, and presents benchmarking results and analyses for 24 recently reported DL-based polyp segmentation methods on PS-NBI2K. The results show that existing methods struggle to locate polyps with smaller sizes and stronger interference, and that extracting both local and global features improves performance. There is also a trade-off between effectiveness and efficiency, and most methods cannot achieve the best results in both areas simultaneously. This work highlights potential directions for designing DL-based polyp segmentation methods in NBI colonoscopy images, and the release of PS-NBI2K aims to drive further development in this field.

Doctor of Public Health-Crisis Management and COVID-19 Prevention and Control: A Case Study in China.

In the fields of public health policy and public health care, advanced educational programs are an important strategy in dealing with public health crises. The COVID-19 pandemic has exposed the global need for skilled public health leaders and managers to address complex public health challenges, which requires the strengthening of public health education at the highest levels. This paper is a qualitative case study of a special educational program for doctors of public health in China. The program's educational objectives are in line with epidemic prevention and control. With the goal of developing the world's leading national public health management system, the Chinese government established an advanced academic program for public health crisis management. The program offers doctoral students a multidisciplinary degree based upon the theoretical knowledge of crisis management, supported by advanced training in the foundational concepts, theories, and practices of public health, and the study of basic medicine which provides the theoretical support for developing essential clinical skills. Program graduates develop the theoretical, practical, and leadership-related capabilities required for the management of national emergencies. The program introduced in this paper meets current epidemic prevention and control needs and should be considered by public health policy makers, leaders, and scholars in the discussion of advanced public health policy and health care education in China, including the development of an internationally recognized Doctor of Public Health program.

Expression of CYP107Z13 in Streptomyces lividans TK54 catalyzes the oxidation of avermectin to 4″-oxo-avermectin.

Streptomyces ahygroscopicus ZB01 has strong catalytic activity for the regiospecific oxidation of 4″-OH of avermectin to form 4″-oxo-avermectin. A cytochrome P450 gene from S. ahygroscopicus ZB01, cyp107z13, was cloned into pKC1139 to generate pKCZ1 and was transformed into Streptomyces lividans TK54, which does not have the ability to catalyze the conversion of avermectin. CYP107Z13, under the control of an ermE* promoter, was actively expressed in the TK54 recombinant strain as determined by a reduced CO difference spectrum analysis of the crude protein. Analysis of whole-cell biocatalytic activity by high-performance liquid chromatography revealed the recombinant to be able to oxidize avermectin regiospecifically to 4″-oxo-avermectin and CYP107Z13 to be a regioselective oxidase of avermectin. In addition, the whole-cell reaction conditions of the recombinant were optimized. Growth on medium ISP-2 at pH 6 was more conducive for the expression of CYP107Z13 than on medium PYG1 or at pH 7, and active cells of the recombinant strain had higher biocatalytic activity than resting cells.

[Cloning and prokaryotic expression of cyp107z gene from Streptomyces ahygroscopicus ZB01].

OBJECTIVE: We cloned and expressed a cytochrome P450 gene cyp107z from Streptomyces ahygroscopicus ZB01, and determined the kinetic parameters of the recombinant enzyme in vitro. METHOD: Degenerate primers were designed by the conserved sequence of cyp genes and were used to amplify partial sequence of cyp107z gene from Streptomyces ahygroscopicus ZB01 genome. The full-length cyp107z gene sequence was obtained by genome walking, and linked with pET28a to construct pET-cyp1O7z13 expressing vector which was then transferred into Escherichia coli, and the expressed recombinant protein was purified by Ni-NTA affinity chromatography. The catalysis system of the recombinant protein was constructed with avermectin as substrate, and the kinetic parameters of the recombinant protein were determined by monitoring the consumption of NADPH in the system in vitro. RESULTS: A cyp107z homologous gene named cyp107z13 was cloned from Streptomyces ahygroscopicus ZB01 genome, which was 1290 bp in length encoding 429 amino acid residues. The Km of purified recombinant protein of CYP107Z13 expressed in E. coli was 1.4 micromol/L, the Vmax was 0.041 micromol/min x mg and the k(cat), was 0.033 s(-1) in a reaction system with avermectin as substrate. CONCLUSION: A cyp10z3 gene from Streptomyces ahygroscopicus ZB01 was cloned, the heterologous expressed recombinant protein can catalyze the oxidizing reaction with avermectin as substrate.