Prediction of recurrence risk factors in patients with early-stage cervical cancers by nomogram based on MRI handcrafted radiomics features and deep learning features: a dual-center study.

PURPOSE: To establish and validate a deep learning radiomics nomogram (DLRN) based on intratumoral and peritumoral regions of MR images and clinical characteristics to predict recurrence risk factors in early-stage cervical cancer and to clarify whether DLRN could be applied for risk stratification. METHODS: Two hundred and twenty five pathologically confirmed early-stage cervical cancers were enrolled and made up the training cohort and internal validation cohort, and 40 patients from another center were enrolled into the external validation cohort. On the basis of region of interest (ROI) of intratumoral and different peritumoral regions, two sets of features representing deep learning and handcrafted radiomics features were created using combined images of T2-weighted MRI (T2WI) and diffusion-weighted imaging (DWI). The signature subset with the best discriminant features was chosen, and deep learning and handcrafted signatures were created using logistic regression. Integrated with independent clinical factors, a DLRN was built. The discrimination and calibration of DLNR were applied to assess its therapeutic utility. RESULTS: The DLRN demonstrated satisfactory performance for predicting recurrence risk factors, with AUCs of 0.944 (95% confidence interval 0.896-0.992) and 0.885 (95% confidence interval 0.834-0.937) in the internal and external validation cohorts. Furthermore, decision curve analysis revealed that the DLRN outperformed the clinical model, deep learning signature, and radiomics signature in terms of net benefit. CONCLUSION: A DLRN based on intratumoral and peritumoral regions had the potential to predict and stratify recurrence risk factors for early-stage cervical cancers and enhance the value of individualized precision treatment.

Cross-Modality Reference and Feature Mutual-Projection for 3D Brain MRI Image Super-Resolution.

High-resolution (HR) magnetic resonance imaging (MRI) can reveal rich anatomical structures for clinical diagnoses. However, due to hardware and signal-to-noise ratio limitations, MRI images are often collected with low resolution (LR) which is not conducive to diagnosing and analyzing clinical diseases. Recently, deep learning super-resolution (SR) methods have demonstrated great potential in enhancing the resolution of MRI images; however, most of them did not take the cross-modality and internal priors of MR seriously, which hinders the SR performance. In this paper, we propose a cross-modality reference and feature mutual-projection (CRFM) method to enhance the spatial resolution of brain MRI images. Specifically, we feed the gradients of HR MRI images from referenced imaging modality into the SR network to transform true clear textures to LR feature maps. Meanwhile, we design a plug-in feature mutual-projection (FMP) method to capture the cross-scale dependency and cross-modality similarity details of MRI images. Finally, we fuse all feature maps with parallel attentions to produce and refine the HR features adaptively. Extensive experiments on MRI images in the image domain and k-space show that our CRFM method outperforms existing state-of-the-art MRI SR methods.

The study on the spatiotemporal changes in tradeoffs and synergies of ecosystem services and response to land use/land cover changes in the region around Taihu Lake.

Interactions among ecosystem services (ESs) involve tradeoffs and synergies. Quantitatively studying the trade-off and synergistic relationships between land use/land cover change (LULC) and ESs enables the precise identification of the quality status and driving factors of ESs within the region, which is crucial for rational resource allocation and environmental protection. In this study, the spatial and temporal change characteristics of the three ESs of carbon storage (CS), soil retention (SR) and habitat quality (HQ) are explored by using the InVEST model and GIS technology in the region around Taihu Lake, and the tradeoffs and synergies among the three are determined based on the difference comparison. The results indicate that: (1) The study area has a downward trajectory in CS and HQ from 1990 to 2020, while SR experiences some fluctuations. The spatial distribution of the three ESs exhibits high levels in the southwest and low levels in the northeast. (2) The most sensitive regions where tradeoffs and synergies are most pronounced occur primarily in the newly construction land regions and the southwestern mountainous and hilly areas. In newly construction land regions, there are often tradeoffs relationships observed between CS and SR, as well as between HQ and SR. Conversely, a predominantly negative synergy is mainly observed between CS and HQ. In the southwestern hilly terrain, due to changes in landscape patterns, HQ and SR exhibit higher levels of negative synergistic relationships. (3) LULC is a significant driver of spatial and temporal changes in ESs, as well as changes in tradeoffs and synergies in the study area, necessitating integrated research from economic, social and climate change perspectives.

Multi-level feature extraction and reconstruction for 3D MRI image super-resolution.

Magnetic resonance imaging (MRI) is an essential radiology technique in clinical diagnosis, but its spatial resolution may not suffice to meet the growing need for precise diagnosis due to hardware limitations and thicker slice thickness. Therefore, it is crucial to explore suitable methods to increase the resolution of MRI images. Recently, deep learning has yielded many impressive results in MRI image super-resolution (SR) reconstruction. However, current SR networks mainly use convolutions to extract relatively single image features, which may not be optimal for further enhancing the quality of image reconstruction. In this work, we propose a multi-level feature extraction and reconstruction (MFER) method to restore the degraded high-resolution details of MRI images. Specifically, to comprehensively extract different types of features, we design the triple-mixed convolution by leveraging the strengths and uniqueness of different filter operations. For the features of each level, we then apply deconvolutions to upsample them separately at the tail of the network, followed by the feature calibration of spatial and channel attention. Besides, we also use a soft cross-scale residual operation to improve the effectiveness of parameter optimization. Experiments on lesion-free and glioma datasets indicate that our method obtains superior quantitative performance and visual effects when compared with state-of-the-art MRI image SR methods.

MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images.

Aim: The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that uses a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesion contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results. Patients: The X-ray dataset from Qatar University which contains 3379 cases for light, normal and heavy COVID-19 lung infection. The CT dataset contains the scans of 10 patient cases with COVID-19, a total of 1562 CT axial slices. The BAA dataset is obtained from the hospital and includes 387 original images. The ISIC 2018 dataset is from the International Skin Imaging Collaborative (ISIC) containing 2594 original images. Results: The proposed MS-DCANet achieved evaluation metrics (MIOU) of 73.86, 97.26, 89.54, and 79.54 on the four datasets, respectively, far exceeding other current state-of-the art baselines. Conclusion: The proposed MS-DCANet can help clinicians to automate the diagnosis of COVID-19 patients with different symptoms.

Knockdown of hnRNPAB reduces the stem cell properties and enhances the chemosensitivity of human colorectal cancer stem cells.

Heterogeneous ribonucleoprotein AB (hnRNPAB) is one of the main members of the nuclear heterogeneous ribonucleoprotein family and plays a crucial role in the occurrence and development of tumours. A previous study by the authors demonstrated that hnRNPAB was highly expressed in colorectal cancer tissues and was closely associated with a poor prognosis of patients. However, the contribution of hnRNPAB to the tumorigenesis and drug resistance of colorectal cancer (CRC) stem cells (CSCs) remains elusive. The aim of the present study was thus to examine whether hnRNPAB can enhance the characteristics of colorectal CSCs and chemotherapeutic drug resistance by altering the cell cycle and the apoptosis of colorectal CSCs. The results revealed that the expression of hnRNPAB in colorectal CSCs was increased compared with that in their parental cells. The knockdown of hnRNPAB reduced the sphere formation of and the levels of CSC markers in colorectal CSCs, enhanced sensitivity to 5­fluorouracil and oxaliplatin chemotherapy and increased apoptosis. Taken together, these data indicate the role of hnRNPAB in maintaining CSC properties and provide a novel therapeutic target for the treatment of CRC and particularly, drug resistance.

Application of Robust Zero-Watermarking Scheme Based on Federated Learning for Securing the Healthcare Data.

The privacy protection and data security problems existing in the healthcare framework based on the Internet of Medical Things (IoMT) have always attracted much attention and need to be solved urgently. In the teledermatology healthcare framework, the smartphone can acquire dermatology medical images for remote diagnosis. The dermatology medical image is vulnerable to attacks during transmission, resulting in malicious tampering or privacy data disclosure. Therefore, there is an urgent need for a watermarking scheme that doesn't tamper with the dermatology medical image and doesn't disclose the dermatology healthcare data. Federated learning is a distributed machine learning framework with privacy protection and secure encryption technology. Therefore, this paper presents a robust zero-watermarking scheme based on federated learning to solve the privacy and security issues of the teledermatology healthcare framework. This scheme trains the sparse autoencoder network by federated learning. The trained sparse autoencoder network is applied to extract image features from the dermatology medical image. Image features are undergone to two-dimensional Discrete Cosine Transform (2D-DCT) in order to select low-frequency transform coefficients for creating zero-watermarking. Experimental results show that the proposed scheme has more robustness to the conventional attack and geometric attack and achieves superior performance when compared with other zero-watermarking schemes. The proposed scheme is suitable for the specific requirements of medical images, which neither changes the important information contained in medical images nor divulges privacy data.

Coupled Gold Nanoparticles with Aptamers Colorimetry for Detection of Amoxicillin in Human Breast Milk Based on Image Preprocessing and BP-ANN.

Antibiotic residues in breast milk can have an impact on the intestinal flora and health of babies. Amoxicillin, as one of the most used antibiotics, affects the abundance of some intestinal bacteria. In this study, we developed a convenient and rapid process that used a combination of colorimetric methods and artificial intelligence image preprocessing, and back propagation-artificial neural network (BP-ANN) analysis to detect amoxicillin in breast milk. The colorimetric method derived from the reaction of gold nanoparticles (AuNPs) was coupled to aptamers (ssDNA) with different concentrations of amoxicillin to produce different color results. The color image was captured by a portable image acquisition device, and image preprocessing was implemented in three steps: segmentation, filtering, and cropping. We decided on a range of detection from 0 µM to 3.9 µM based on the physiological concentration of amoxicillin in breast milk and the detection effect. The segmentation and filtering steps were conducted by Hough circle detection and Gaussian filtering, respectively. The segmented results were analyzed by linear regression and BP-ANN, and good linear correlations between the colorimetric image value and concentration of target amoxicillin were obtained. The R2 and MSE of the training set were 0.9551 and 0.0696, respectively, and those of the test set were 0.9276 and 0.1142, respectively. In prepared breast milk sample detection, the recoveries were 111.00%, 98.00%, and 100.20%, and RSDs were 6.42%, 4.27%, and 1.11%. The result suggests that the colorimetric process combined with artificial intelligence image preprocessing and BP-ANN provides an accurate, rapid, and convenient way to achieve the detection of amoxicillin in breast milk.

Mass spectrometry of the photolysis of sulfonylurea herbicides in Prairie waters.

This review of mass spectrometry of sulfonylurea herbicides includes a focus on studies relevant to Canadian Prairie waters. Emphasis is given to data gaps in the literature for the rates of photolysis of selected sulfonylurea herbicides in different water matrices. Specifically, results are evaluated for positive ion electrospray tandem mass spectrometry with liquid chromatography separation for the study of the photolysis of chlorsulfuron, tribenuron-methyl, thifensulfuron-methyl, metsulfuron-methyl, and ethametsulfuron-methyl. LC-MS/MS is shown to be the method of choice for the quantification of sulfonylurea herbicides with instrumental detection limits ranging from 1.3 to 7.2 pg (on-column). Tandem mass spectrometry coupled with the use of authentic standards likewise has proven to be well suited for the identification of transformation products. To date, however, the power of time-of-flight MS and ultrahigh resolution MS has not been exploited fully for the identification of unknown photolysis products. Dissipation of the herbicides under natural sunlight fit pseudo-first-order kinetics with half-life values ranging from 4.4 to 99 days. For simulated sunlight, radiation wavelengths shorter than 400 nm are required to induce significant photolytic reactions. The correlation between field dissipation studies and laboratory photolysis experiments suggests that photolysis is a major pathway for the dissipation of some sulfonylurea herbicides in natural Prairie waters.

Zero-Watermarking Algorithm for Medical Image Based on VGG19 Deep Convolution Neural Network.

Aiming at the security issues in the storage and transmission of medical images in the medical information system, combined with the special requirements of medical images for the protection of lesion areas, this paper proposes a robust zero-watermarking algorithm for medical images' security based on VGG19. First, the pretrained VGG19 is used to extract deep feature maps of medical images, which are fused into the feature image. Second, the feature image is transformed by Fourier transform, and low-frequency coefficients of the Fourier transform are selected to construct the feature matrix of the medical image. Then, based on the low-frequency part of the feature matrix of the medical image, the mean-perceptual hashing algorithm is used to achieve a set of 64-bit binary perceptual hashing values, which can effectively resist local nonlinear geometric attacks. Finally, the algorithm adopts a watermarking image after scrambling and the 64-bit binary perceptual hashing value to obtain robust zero-watermarking. At the same time, the proposed algorithm utilizes Hermite chaotic neural network to scramble the watermarking image for secondary protection, which enhances the security of the algorithm. Compared with the existing related works, the proposed algorithm is simple to implement and can effectively resist local nonlinear geometric attacks, with good robustness, security, and invisibility.

Impacts of land use at multiple buffer scales on seasonal water quality in a reticular river network area.

The assessment and prediction of regional water quality are fundamental inputs to environmental planning and watershed ecological management. This paper explored spatiotemporal changes in the correlation of water quality parameters (WQPs) and land-use types (LUTs) in a reticular river network area. Water samples of 44 sampling sites were collected every quarter from 2016 to 2018 and evaluated for dissolved oxygen (DO), total phosphorus (TP), ammonia nitrogen (NH3-N), and permanganate index (CODMn). A redundancy analysis (RDA) and stepwise multiple linear regression (SMLR) were applied to analyze the land-use type impacts on seasonal WQPs at five buffer scales (100, 200, 500, 800, and 1000 m). The Kruskal-Wallis test results revealed significant seasonal differences in NH3-N, TP, CODMn, and DO. The area percentages of farmland, water area and built-up land in the study area were 38.96%, 22.75% and16.20%, respectively, for a combined total area percentage of nearly 80%. Our study showed that orchard land had an especially favorable influence on WQPs. Land-use type impacts on WQPs were more significant during the dry season than the wet season. The total variation explained by LUTs regarding WQPs at the 1 km buffer scale was slightly stronger than at smaller buffer scales. Built-up land had a negative effect on WQPs, but orchard and forest-grassland had a positive effect on WQPs. The effects of water area and farmland on WQPs were complex on different buffer scales. These findings are helpful for improving regional water resource management and environmental planning.

3D dense convolutional neural network for fast and accurate single MR image super-resolution.

Super-resolution (SR) MR image reconstruction has shown to be a very promising direction to improve the spatial resolution of low-resolution (LR) MR images. In this paper, we presented a novel MR image SR method based on a dense convolutional neural network (DDSR), and its enhanced version called EDDSR. There are three major innovations: first, we re-designed dense modules to extract hierarchical features directly from LR images and propagate the extracted feature maps through dense connections. Therefore, unlike other CNN-based SR MR techniques that upsample LR patches in the initial phase, our methods take the original LR images or patches as input. This effectively reduces computational complexity and speeds up SR reconstruction. Second, a final deconvolution filter in our model automatically learns filters to fuse and upscale all hierarchical feature maps to generate HR MR images. Using this, EDDSR can perform SR reconstructions at different upscale factors using a single model with one stride fixed deconvolution operation. Third, to further improve SR reconstruction accuracy, we exploited a geometric self-ensemble strategy. Experimental results on three benchmark datasets demonstrate that our methods, DDSR and EDDSR, achieved superior performance compared to state-of-the-art MR image SR methods with less computational load and memory usage.

Dissipation of naphthenic acids mixtures by lake biofilms.

The dissipation (combined sorption and biodegradation) of naphthenic acids (C(n)H(2n+z)O(2)) by lake biofilms with no previous adaptation to oil sands acids was investigated using rotating annular bioreactors. The dissipation by the biofilm was dependent on the chemical composition of the naphthenic acids mixture. There were 2 distinct groups of Fluka naphthenic acids which dissipated with pseudo first order kinetics: (a) t(1/2)= 7 days, r(2)= 0.984 and (b) components which were less readily dissipated with t(1/2)= 134 days, r(2)= 0.618. In contrast to the results observed for Fluka naphthenic acids, no dissipation was evident for lake biofilm exposed to Athabasca oil sands naphthenic acids. The differences in dissipation observed for the systems investigated are attributed to the combination of 3 key factors: (i) molecular structure and (ii) molecular mass of the naphthenic acids; along with (iii) inhibition by some components (containing elements of S and/or N acids). The later are more prevalent in oil sands naphthenic acids compared to Fluka naphthenic acids.

3D dense connectivity network with atrous convolutional feature pyramid for brain tumor segmentation in magnetic resonance imaging of human heads.

The existing deep convolutional neural networks (DCNNs) based methods have achieved significant progress regarding automatic glioma segmentation in magnetic resonance imaging (MRI) data. However, there are two main problems affecting the performance of traditional DCNNs constructed by simply stacking convolutional layers, namely, exploding/vanishing gradients and limitations to the feature computations. To address these challenges, we propose a novel framework to automatically segment brain tumors. First, a three-dimensional (3D) dense connectivity architecture is used to build the backbone for feature reuse. Second, we design a new feature pyramid module using 3D atrous convolutional layers and add this module to the end of the backbone to fuse multiscale contexts. Finally, a 3D deep supervision mechanism is equipped with the network to promote training. On the multimodal brain tumor image segmentation benchmark (BRATS) datasets, our method achieves Dice similarity coefficient values of 0.87, 0.72, and 0.70 on the BRATS 2013 Challenge, 0.84, 0.70, and 0.61 on the BRATS 2013 LeaderBoard, 0.83, 0.70, and 0.62 on the BRATS 2015 Testing, 0.8642, 0.7738, and 0.7525 on the BRATS 2018 Validation in terms of whole tumors, tumor cores, and enhancing cores, respectively. Compared to the published state-of-the-art methods, the proposed method achieves promising accuracy and fast processing, demonstrating good potential for clinical medicine.

Electron Spin Relaxation in Chromium-Nitrosyl Complexes.

A new method to prepare Cr(NO)(H(2)O)(5)(2+) from dichromate and NH(2)OH is reported. The chromium nitrosyls Cr(NO)(EHBA)(+) and Cr(NO)(EHBA)(2) (EHBA = 2-ethyl-2-hydoxybutyrate) were prepared by a literature reaction and characterized by continuous wave electron paramagnetic resonance and two-pulse electron spin echo spectroscopy at X-band. The g values are characteristic of a single unpaired electron in a predominantly d(xy)() orbital. In fluid and glassy solutions Cr(NO)(EHBA)(2) is a mixture of cis and trans isomers. Rotation of the methyl groups in the EHBA ligands causes an increased rate of spin echo dephasing at temperatures between 40 and 120 K. For the EHBA complexes echo envelope modulation is observed at temperatures below about 40 K that is attributed to inequivalent coupling to protons of the slowly rotating methyl groups. Both the effect of the methyl rotation on spin echo dephasing and the depth of the proton modulation are dependent on the number of ethyl groups in the ligand, and thus the spin echo experiments provide confirmation of the number of EHBA ligands in the complexes. The spin-lattice relaxation rates for the chromium-nitrosyl complexes at temperatures near 100 K are similar to values reported previously for Cr(V) complexes, which also have a single unpaired electron in a predominantly d(xy)() orbital. For Cr(NO)(H(2)O)(5)(2+), Cr(NO)(EHBA)(+), and Cr(NO)(EHBA)(2) the dominant contribution to spin-lattice relaxation between 12 and 150 K is the Raman process with a Debye temperature, theta(D), of 110-120 K. For Cr(NO)(CN)(5)(3)(-) the data are consistent with a Raman process (theta(D) = 135 K) and a contribution from a local mode, which dominates above about 60 K. The formally low-spin d(5) chromium nitrosyl complexes relax about 5 orders of magnitude more slowly than low-spin d(5) Fe(III) porphyrins, which is attributed to the absence of a low-lying excited state.

Electrospray ionization mass spectrometry of the photodegradation of naphthenic acids mixtures irradiated with titanium dioxide.

Electrospray ionization mass spectrometry was used to study the photodegradation of an oil sands naphthenic acid (NA) mixture, a commercial Fluka NA mixture and a candidate NA, 4-Methyl-cyclohexaneaceticic acid (4-MCHAA) irradiated with TiO(2) (P25) suspension under both fluorescent and natural sunlight. Under natural sunlight irradiation over the TiO(2) suspension, approximately 75% of compounds in the NA mixtures and 100% of 4-MCHAA were degraded in 8 h. No degradation was observed under dark conditions, regardless of the presence or absence of TiO(2). The structural formula of the NAs is given by C(n)H(2n + z)O(2), where n represents the carbon number and z specifies a homologous family with 0-6 rings (z = 0 to -12). The degree of degradation was noted to vary among the NA mixtures and the candidate NA compound with more efficient degradation achieved for molecules with -z values from 0 to 6. The difference in the efficacy of the photocatalysis was likely due to the structure and size of the compounds. In the case of -z = 6 to 12, steric constraints are a key factor what hinders photocatalysis.

Evaluation of the apparent phytodegradation of pentachlorophenol by Chlorella pyrenoidosa.

Several factors influencing the apparent phytodegradation of pentachlorophenol (PCP) were investigated under controlled laboratory conditions including photolysis, biodegradation, and direct phytodegradation by the algae, Chlorella pyrenoidosa. PCP was observed to degrade over time in all instances. Degradation occurred both with and without the presence of algae. The degradation of PCP was observed to be dependent primarily on photolysis with pseudo-first-order kinetics and rate constants in the range of 6.4 to 7.7 h(-1). In contrast, phytodegradation due to algal activity was negligible. It is suspected that the algae degradation may have been limited by the cycling of light exposure to simulate day and night periods.