Voxel-wise mapping of DCE-MRI time-intensity-curve profiles enables visualizing and quantifying hemodynamic heterogeneity in breast lesions

OBJECTIVES

To propose a novel model-free data-driven approach based on the voxel-wise mapping of DCE-MRI time-intensity-curve (TIC) profiles for quantifying and visualizing hemodynamic heterogeneity and to validate its potential clinical applications.

MATERIALS AND METHODS

From December 2018 to July 2022, 259 patients with 325 pathologically confirmed breast lesions who underwent breast DCE-MRI were retrospectively enrolled. Based on the manually segmented breast lesions, the TIC of each voxel within the 3D whole lesion was classified into 19 subtypes based on wash-in rate (nonenhanced, slow, medium, and fast), wash-out enhancement (persistent, plateau, and decline), and wash-out stability (steady and unsteady), and the composition ratio of these 19 subtypes for each lesion was calculated as a new feature set (type-19). The three-type TIC classification, semiquantitative parameters, and type-19 features were used to build machine learning models for identifying lesion malignancy and classifying histologic grades, proliferation status, and molecular subtypes.

RESULTS

The type-19 feature-based model significantly outperformed models based on the three-type TIC method and semiquantitative parameters both in distinguishing lesion malignancy (respectively; AUC = 0.875 vs. 0.831, p = 0.01 and 0.875vs. 0.804, p = 0.03), predicting tumor proliferation status (AUC = 0.890 vs. 0.548, p = 0.006 and 0.890 vs. 0.596, p = 0.020), but not in predicting histologic grades (p = 0.820 and 0.970).

CONCLUSION

In addition to conventional methods, the proposed computational approach provides a novel, model-free, data-driven approach to quantify and visualize hemodynamic heterogeneity.

CLINICAL RELEVANCE STATEMENT

Voxel-wise intra-lesion mapping of TIC profiles allows for visualization of hemodynamic heterogeneity and its composition ratio for differentiation of malignant and benign breast lesions.

KEY POINTS

• Voxel-wise TIC profiles were mapped, and their composition ratio was compared between various breast lesions. • The model based on the composition ratio of voxel-wise TIC profiles significantly outperformed the three-type TIC classification model and the semiquantitative parameters model in lesion malignancy differentiation and tumor proliferation status prediction in breast lesions. • This novel, data-driven approach allows the intuitive visualization and quantification of the hemodynamic heterogeneity of breast lesions.

Super-resolution dual-layer CBCT imaging with model-guided deep learning

Objective.This study aims at investigating a novel super resolution CBCT imaging approach with a dual-layer flat panel detector (DL-FPD).Approach.With DL-FPD, the low-energy and high-energy projections acquired from the top and bottom detector layers contain over-sampled spatial information, from which super-resolution CT images can be reconstructed. A simple mathematical model is proposed to explain the signal formation procedure in DL-FPD, and a dedicated recurrent neural network, named suRi-Net, is developed based upon the above imaging model to nonlinearly retrieve the high-resolution dual-energy information. Physical benchtop experiments are conducted to validate the performance of this newly developed super-resolution CBCT imaging method.Main Results.The results demonstrate that the proposed suRi-Net can accurately retrieve high spatial resolution information from the low-energy and high-energy projections of low spatial resolution. Quantitatively, the spatial resolution of the reconstructed CBCT images from the top and bottom detector layers is increased by about 45% and 54%, respectively.Significance.In the future, suRi-Net will provide a new approach to perform high spatial resolution dual-energy imaging in DL-FPD-based CBCT systems.

PEARL: Cascaded Self-supervised Cross-fusion Learning For Parallel MRI Acceleration

Supervised deep learning (SDL) methodology holds promise for accelerated magnetic resonance imaging (AMRI) but is hampered by the reliance on extensive training data. Some self-supervised frameworks, such as deep image prior (DIP), have emerged, eliminating the explicit training procedure but often struggling to remove noise and artifacts under significant degradation. This work introduces a novel self-supervised accelerated parallel MRI approach called PEARL, leveraging a multiple-stream joint deep decoder with two cross-fusion schemes to accurately reconstruct one or more target images from compressively sampled k-space. Each stream comprises cascaded cross-fusion sub-block networks (SBNs) that sequentially perform combined upsampling, 2D convolution, joint attention, ReLU activation and batch normalization (BN). Among them, combined upsampling and joint attention facilitate mutual learning between multiple-stream networks by integrating multi-parameter priors in both additive and multiplicative manners. Long-range unified skip connections within SBNs ensure effective information propagation between distant cross-fusion layers. Additionally, incorporating dual-normalized edge-orientation similarity regularization into the training loss enhances detail reconstruction and prevents overfitting. Experimental results consistently demonstrate that PEARL outperforms the existing state-of-the-art (SOTA) self-supervised AMRI technologies in various MRI cases. Notably, 5-fold  ∼ 6-fold accelerated acquisition yields a 1 %  ∼  2 % improvement in SSIM ROI and a 3 %  ∼  6 % improvement in PSNR ROI, along with a significant 15 %  ∼  20 % reduction in RLNE ROI.

Dynamic Changes of Phenolic Composition, Antioxidant Capacity, and Gene Expression in 'Snow White' Loquat (Eriobotrya japonica Lindl.) Fruit throughout Development and Ripening

The newly released 'Snow White' (SW), a white-fleshed loquat (Eriobotrya japonica Lindl.) cultivar, holds promise for commercial production. However, the specifics of the phenolic composition in white-fleshed loquats, along with the antioxidant substances and their regulatory mechanisms, are not yet fully understood. In this study, we examined the dynamic changes in the phenolic compounds, enzyme activities, antioxidant capacity, and gene expression patterns of SW during the key stages of fruit development and ripening. A total of 18 phenolic compounds were identified in SW, with chlorogenic acid, neochlorogenic acid, and coniferyl alcohol being the most predominant. SW demonstrated a stronger antioxidant capacity in the early stages of development, largely due to total phenolics and flavonoids. Neochlorogenic acid may be the most significant antioxidant contributor in loquat. A decline in enzyme activities corresponded with fruit softening. Different genes within a multigene family played distinct roles in the synthesis of phenolics. C4H1, 4CL2, 4CL9, HCT, CCoAOMT5, F5H, COMT1, CAD6, and POD42 were implicated in the regulation of neochlorogenic acid synthesis and accumulation. Consequently, these findings enhance our understanding of phenolic metabolism and offer fresh perspectives on the development of germplasm resources for white-fleshed loquats.

CMID: Crossmodal Image Denoising via Pixel-Wise Deep Reinforcement Learning

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

Effect of Molecular Weight on the Structural and Emulsifying Characteristics of Bovine Bone Protein Hydrolysate

The emulsifying capacity of bovine bone protein extracted using high-pressure hot water (HBBP) has been determined to be good. Nevertheless, given that HBBP is a blend of peptides with a broad range of molecular weights, the distinction in emulsifying capacity between polypeptide components with high and low molecular weights is unclear. Therefore, in this study, HBBP was separated into three molecular weight components of 10-30 kDa (HBBP 1), 5-10 kDa (HBBP 2), and <5 kDa (HBBP 3) via ultrafiltration, and the differences in their structures and emulsifying properties were investigated. The polypeptide with the highest molecular weight displayed the lowest endogenous fluorescence intensity, the least solubility in an aqueous solution, and the highest surface hydrophobicity index. Analysis using laser confocal Raman spectroscopy showed that with an increase in polypeptide molecular weight, the α-helix and β-sheet contents in the secondary structure of the polypeptide molecule increased significantly. Particle size, rheological characteristics, and laser confocal microscopy were used to characterize the emulsion made from peptides of various molecular weights. High-molecular-weight peptides were able to provide a more robust spatial repulsion and thicker interfacial coating in the emulsion, which would make the emulsion more stable. The above results showed that the high-molecular-weight polypeptide in HBBP effectively improved the emulsion stability when forming an emulsion. This study increased the rate at which bovine bone was utilized and provided a theoretical foundation for the use of bovine bone protein as an emulsifier in the food sector.

Energy resolving dark-field imaging with dual phase grating interferometer

X-ray dark-filed imaging is a powerful approach to quantify the dimension of micro-structures of the object. Often, a series of dark-filed signals have to be measured under various correlation lengths. For instance, this is often achieved by adjusting the sample positions by multiple times in Talbot-Lau interferometer. Moreover, such multiple measurements can also be collected via adjustments of the inter-space between the phase gratings in dual phase grating interferometer. In this study, the energy resolving capability of the dual phase grating interferometer is explored with the aim to accelerate the data acquisition speed of dark-filed imaging. To do so, both theoretical analyses and numerical simulations are investigated. Specifically, the responses of the dual phase grating interferometer at varied X-ray beam energies are studied. Compared with the mechanical position translation approach, the combination of such energy resolving capability helps to greatly shorten the total dark-field imaging time in dual phase grating interferometer.

Burden of type 1 and type 2 diabetes and high fasting plasma glucose in Europe, 1990-2019: a comprehensive analysis from the global burden of disease study 2019

Introduction

With population aging rampant globally, Europe faces unique challenges and achievements in chronic disease prevention. Despite this, comprehensive studies examining the diabetes burden remain absent. We investigated the burden of type 1 and type 2 diabetes, alongside high fasting plasma glucose (HFPG), in Europe from 1990-2019, to provide evidence for global diabetes strategies.

Methods

Disease burden estimates due to type 1 and type 2 diabetes and HFPG were extracted from the GBD 2019 across Eastern, Central, and Western Europe. We analyzed trends from 1990 to 2019 by Joinpoint regression, examined correlations between diabetes burden and Socio-demographic indices (SDI), healthcare access quality (HAQ), and prevalence using linear regression models. The Population Attributable Fraction (PAF) was used to described diabetes risks.

Results

In Europe, diabetes accounted for 596 age-standardized disability-adjusted life years (DALYs) per 100,000 people in 2019, lower than globally. The disease burden from type 1 and type 2 diabetes was markedly higher in males and escalated with increasing age. Most DALYs were due to type 2 diabetes, showing regional inconsistency, highest in Central Europe. From 1990-2019, age-standardized DALYs attributable to type 2 diabetes rose faster in Eastern and Central Europe, slower in Western Europe. HFPG led to 2794 crude DALYs per 100,000 people in 2019. Type 1 and type 2 diabetes burdens correlated positively with diabetes prevalence and negatively with SDI and HAQ. High BMI (PAF 60.1%) and dietary risks (PAF 34.6%) were significant risk factors.

Conclusion

Europe's diabetes burden was lower than the global average, but substantial from type 2 diabetes, reflecting regional heterogeneity. Altered DALYs composition suggested increased YLDs. Addressing the heavy burden of high fasting plasma glucose and the increasing burden of both types diabetes necessitate region-specific interventions to reduce type 2 diabetes risk, improve healthcare systems, and offer cost-effective care.

A future for digital public goods for monitoring SDG indicators

Digital public goods (DPGs), if implemented with effective policies, can facilitate the realization of the United Nations Sustainable Development Goals (SDGs). However, there are ongoing deliberations on how to define DPGs and assure that society can extract the maximum benefit from the growing number of digital resources. The International Research Center of Big Data for Sustainable Development Goals (CBAS) sees DPGs as an important mechanism to facilitate information-driven policy and decision-making processes for the SDGs. This article presents the results of a CBAS survey of 51 respondents from around the world spanning multiple scientific fields, who shared their expert opinions on DPGs and their thoughts about challenges related to their practical implementation in supporting the SDGs. Based on the survey results, the paper presents core principles in a proposed strategy, including establishment of international standards, adherence to open science and open data principles, and scalability in monitoring SDG indicators. A community-driven strategy to develop DPGs is proposed to accelerate DPG production in service of the SDGs while adhering to the core principles identified in the survey.

Methylation of AcGST1 Is Associated with Anthocyanin Accumulation in the Kiwifruit Outer Pericarp

Most red-fleshed kiwifruit cultivars, such as Hongyang, only accumulate anthocyanins in the inner pericarp; the trait of full red flesh becomes the goal pursued by breeders. In this study, we identified a mutant "H-16" showing a red color in both the inner and outer pericarps, and the underlying mechanism was explored. Through transcriptome analysis, a key differentially expressed gene AcGST1 was screened out, which was positively correlated with anthocyanin accumulation in the outer pericarp. The result of McrBC-PCR and bisulfite sequencing revealed that the SG3 region (-292 to -597 bp) of AcGST1 promoter in "H-16" had a significantly lower CHH cytosine methylation level than that in Hongyang, accompanied by low expression of methyltransferase genes (MET1 and CMT2) and high expression of demethylase genes (ROS1 and DML1). Transient calli transformation confirmed that demethylase gene DML1 can activate transcription of AcGST1 to enhance its expression. Overexpression of AcGST1 enhanced the anthocyanin accumulation in the fruit flesh and leaves of the transgenic lines. These results suggested that a decrease in the methylation level of the AcGST1 promoter may contribute to accumulation of anthocyanin in the outer pericarp of "H-16".

Acceleration of high-quality Raman imaging via a locality enhanced transformer network

Raman imaging (RI) is an outstanding technique that enables molecular-level medical diagnostics and therapy assessment by providing characteristic fingerprint and morphological information about molecules. However, obtaining high-quality Raman images generally requires a long acquisition time, up to hours, which is prohibitive for RI applications of timely cytopathology and histopathology analyses. To address this issue, image super-resolution (SR) based on deep learning, including convolutional neural networks and transformers, has been widely recognized as an effective solution to reduce the time required for achieving high-quality RI. In this study, a locality enhanced transformer network (LETNet) is proposed to perform Raman image SR. Specifically, the general architecture of the transformer is adopted with the replacement of self-attention by convolution to generate high-fidelity and detailed SR images. Additionally, the convolution in the LETNet is further optimized by utilizing depth-wise convolution to improve the computational efficiency of the model. Experiments on hyperspectral Raman images of breast cancer cells and Raman images of a few channels of brain tumor tissues demonstrate that the LETNet achieves superior 2×, 4×, and 8× SR with fewer parameters compared with other SR methods. Consequently, high-quality Raman images can be obtained with a significant reduction in time, ranging from 4 to 64 times. Overall, the proposed method provides a novel, efficient, and reliable solution to expedite high-quality RI and promote its application in real-time diagnosis and therapy.

Accelerated submillimeter wave-encoded magnetic resonance imaging via deep untrained neural network

BACKGROUND

Wave gradient encoding can adequately utilize coil sensitivity profiles to facilitate higher accelerations in parallel magnetic resonance imaging (pMRI). However, there are limitations in mainstream pMRI and a few deep learning (DL) methods for recovering missing data under wave encoding framework: the former is prone to introduce errors from the auto-calibration signals (ACS) signal acquisition and is time-consuming, while the latter requires a large amount of training data.

PURPOSE

To tackle the above issues, an untrained neural network (UNN) model incorporating wave-encoded physical properties and deep generative model, named WDGM, was proposed with additional ACS- and training data-free.

METHODS

Generally, the proposed method can provide powerful missing data interpolation capability using the wave physical encoding framework and designed UNN to characterize the MR image (k-space data) priors. Specifically, the MRI reconstruction combining physical wave encoding and elaborate UNN is modeled as a generalized minimization problem. The designation of UNN is driven by the coil sensitivity maps (CSM) smoothness and k-space linear predictability. And then, the iterative paradigm to recover the full k-space signal is determined by the projected gradient descent, and the complex computation is unrolled to the network with optimized parameters by the optimizer. Simulated wave encoding and in vivo experiments are exploited to demonstrate the feasibility of the proposed method. The best quantitative metrics RMSE/SSIM/PSNR of 0.0413, 0.9514, and 37.4862 gave competitive results in all experiments with at least six-fold acceleration, respectively.

RESULTS

In vivo experiments of human brains and knees showed that the proposed method can achieve comparable reconstruction quality and even has superiority relative to the comparison, especially at a high resolution of 0.67 mm and fewer ACS. In addition, the proposed method has a higher computational efficiency achieving a computation time of 9.6 s/per slice.

CONCLUSIONS

The model proposed in this work addresses two limitations of MRI reconstruction in the wave encoding framework. The first is to eliminate the need for ACS signal acquisition to perform the time-consuming calibration process and to avoid errors such as motion during the acquisition procedure. Furthermore, the proposed method has clinical application friendly without the need to prepare large training datasets, which is difficult in the clinical. All results of the proposed method demonstrate more confidence in both quantitative and qualitative metrics. In addition, the proposed method can achieve higher computational efficiency.

Lignan constituents with α-amylase and α-glucosidase inhibitory activities from the fruits of Viburnum urceolatum

Eleven previously undescribed lignan constituents, including five 8-O-4' type neolignans, viburnurcosides A-E (1-5), three benzofuran type neolignans, viburnurcosides F-H (6-8), and three tetrahydrofuran type lignans, viburnurcosides I-K (9-11), were isolated from the fruits of Viburnum urceolatum. The structures of all isolates were elucidated by an extensive analysis of the NMR and HRESIMS data. The absolute configurations of these compounds were determined by quantum-chemical electronic circular dichroism calculation and comparison. The sugar units of viburnurcosides A-K were identified by acid hydrolysis and HPLC analysis of the chiral derivatives of monosaccharides. The in vitro enzyme inhibition assay exhibited that viburnurcoside J (10) had the most potent inhibitory activity against α-amylase and α-glucosidase with the IC50 values of 19.75 and 9.14 μM, respectively, which were stronger than those of the positive control acarbose (37.31 and 26.75 μM, respectively). The potential binding modes of viburnurcoside J (10) with α-amylase and α-glucosidase were also analyzed by molecular modeling.

The role of SLC12A family of cation-chloride cotransporters and drug discovery methodologies

The solute carrier family 12 (SLC12) of cation-chloride cotransporters (CCCs) comprises potassium chloride cotransporters (KCCs, e.g. KCC1, KCC2, KCC3, and KCC4)-mediated Cl- extrusion, and sodium potassium chloride cotransporters (N[K]CCs, NKCC1, NKCC2, and NCC)-mediated Cl- loading. The CCCs play vital roles in cell volume regulation and ion homeostasis. Gain-of-function or loss-of-function of these ion transporters can cause diseases in many tissues. In recent years, there have been considerable advances in our understanding of CCCs' control mechanisms in cell volume regulations, with many techniques developed in studying the functions and activities of CCCs. Classic approaches to directly measure CCC activity involve assays that measure the transport of potassium substitutes through the CCCs. These techniques include the ammonium pulse technique, radioactive or nonradioactive rubidium ion uptake-assay, and thallium ion-uptake assay. CCCs' activity can also be indirectly observed by measuring γ-aminobutyric acid (GABA) activity with patch-clamp electrophysiology and intracellular chloride concentration with sensitive microelectrodes, radiotracer 36Cl-, and fluorescent dyes. Other techniques include directly looking at kinase regulatory sites phosphorylation, flame photometry, 22Na+ uptake assay, structural biology, molecular modeling, and high-throughput drug screening. This review summarizes the role of CCCs in genetic disorders and cell volume regulation, current methods applied in studying CCCs biology, and compounds developed that directly or indirectly target the CCCs for disease treatments.

Short-axis PET image quality improvement based on a uEXPLORER total-body PET system through deep learning

PURPOSE

The axial field of view (AFOV) of a positron emission tomography (PET) scanner greatly affects the quality of PET images. Although a total-body PET scanner (uEXPLORER) with a large AFOV is more sensitive, it is more expensive and difficult to widely use. Therefore, we attempt to utilize high-quality images generated by uEXPLORER to optimize the quality of images from short-axis PET scanners through deep learning technology while controlling costs.

METHODS

The experiments were conducted using PET images of three anatomical locations (brain, lung, and abdomen) from 335 patients. To simulate PET images from different axes, two protocols were used to obtain PET image pairs (each patient was scanned once). For low-quality PET (LQ-PET) images with a 320-mm AFOV, we applied a 300-mm FOV for brain reconstruction and a 500-mm FOV for lung and abdomen reconstruction. For high-quality PET (HQ-PET) images, we applied a 1940-mm AFOV during the reconstruction process. A 3D Unet was utilized to learn the mapping relationship between LQ-PET and HQ-PET images. In addition, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed to evaluate the model performance. Furthermore, two nuclear medicine doctors evaluated the image quality based on clinical readings.

RESULTS

The generated PET images of the brain, lung, and abdomen were quantitatively and qualitatively compatible with the HQ-PET images. In particular, our method achieved PSNR values of 35.41 ± 5.45 dB (p < 0.05), 33.77 ± 6.18 dB (p < 0.05), and 38.58 ± 7.28 dB (p < 0.05) for the three beds. The overall mean SSIM was greater than 0.94 for all patients who underwent testing. Moreover, the total subjective quality levels of the generated PET images for three beds were 3.74 ± 0.74, 3.69 ± 0.81, and 3.42 ± 0.99 (the highest possible score was 5, and the minimum score was 1) from two experienced nuclear medicine experts. Additionally, we evaluated the distribution of quantitative standard uptake values (SUV) in the region of interest (ROI). Both the SUV distribution and the peaks of the profile show that our results are consistent with the HQ-PET images, proving the superiority of our approach.

CONCLUSION

The findings demonstrate the potential of the proposed technique for improving the image quality of a PET scanner with a 320 mm or even shorter AFOV. Furthermore, this study explored the potential of utilizing uEXPLORER to achieve improved short-axis PET image quality at a limited economic cost, and computer-aided diagnosis systems that are related can help patients and radiologists.

Universal generative modeling in dual domains for dynamic MRI

Dynamic magnetic resonance image reconstruction from incomplete k-space data has generated great research interest due to its ability to reduce scan time. Nevertheless, the reconstruction problem remains a thorny issue due to its ill posed nature. Recently, diffusion models, especially score-based generative models, have demonstrated great potential in terms of algorithmic robustness and flexibility of utilization. Moreover, a unified framework through the variance exploding stochastic differential equation is proposed to enable new sampling methods and further extend the capabilities of score-based generative models. Therefore, by taking advantage of the unified framework, we propose a k-space and image dual-domain collaborative universal generative model (DD-UGM), which combines the score-based prior with a low-rank regularization penalty to reconstruct highly under-sampled measurements. More precisely, we extract prior components from both image and k-space domains via a universal generative model and adaptively handle these prior components for faster processing while maintaining good generation quality. Experimental comparisons demonstrate the noise reduction and detail preservation abilities of the proposed method. Moreover, DD-UGM can reconstruct data of different frames by only training a single frame image, which reflects the flexibility of the proposed model.

Equilibrated Zeroth-Order Unrolled Deep Network for Parallel MR Imaging

In recent times, model-driven deep learning has evolved an iterative algorithm into a cascade network by replacing the regularizer's first-order information, such as the (sub)gradient or proximal operator, with a network module. This approach offers greater explainability and predictability compared to typical data-driven networks. However, in theory, there is no assurance that a functional regularizer exists whose first-order information matches the substituted network module. This implies that the unrolled network output may not align with the regularization models. Furthermore, there are few established theories that guarantee global convergence and robustness (regularity) of unrolled networks under practical assumptions. To address this gap, we propose a safeguarded methodology for network unrolling. Specifically, for parallel MR imaging, we unroll a zeroth-order algorithm, where the network module serves as a regularizer itself, allowing the network output to be covered by a regularization model. Additionally, inspired by deep equilibrium models, we conduct the unrolled network before backpropagation to converge to a fixed point and then demonstrate that it can tightly approximate the actual MR image. We also prove that the proposed network is robust against noisy interferences if the measurement data contain noise. Finally, numerical experiments indicate that the proposed network consistently outperforms state-of-the-art MRI reconstruction methods, including traditional regularization and unrolled deep learning techniques.

Predicting Antiseizure Medication Treatment in Children with Rare Tuberous Sclerosis Complex-Related Epilepsy Using Deep Learning

BACKGROUND AND PURPOSE

Tuberous sclerosis complex disease is a rare, multisystem genetic disease, but appropriate drug treatment allows many pediatric patients to have positive outcomes. The purpose of this study was to predict the effectiveness of antiseizure medication treatment in children with tuberous sclerosis complex-related epilepsy.

MATERIALS AND METHODS

We conducted a retrospective study involving 300 children with tuberous sclerosis complex-related epilepsy. The study included the analysis of clinical data and T2WI and FLAIR images. The clinical data consisted of sex, age of onset, age at imaging, infantile spasms, and antiseizure medication numbers. To forecast antiseizure medication treatment, we developed a multitechnique deep learning method called WAE-Net. This method used multicontrast MR imaging and clinical data. The T2WI and FLAIR images were combined as FLAIR3 to enhance the contrast between tuberous sclerosis complex lesions and normal brain tissues. We trained a clinical data-based model using a fully connected network with the above-mentioned variables. After that, a weighted-average ensemble network built from the ResNet3D architecture was created as the final model.

RESULTS

The experiments had shown that age of onset, age at imaging, infantile spasms, and antiseizure medication numbers were significantly different between the 2 drug-treatment outcomes (P < .05). The hybrid technique of FLAIR3 could accurately localize tuberous sclerosis complex lesions, and the proposed method achieved the best performance (area under the curve = 0.908 and accuracy of 0.847) in the testing cohort among the compared methods.

CONCLUSIONS

The proposed method could predict antiseizure medication treatment of children with rare tuberous sclerosis complex-related epilepsy and could be a strong baseline for future studies.

Imaging-proteomic analysis for prediction of neoadjuvant chemotherapy responses in patients with breast cancer

BACKGROUND

Optimizing patient selection for neoadjuvant chemotherapy in patients with breast cancer remains an unmet clinical need. Quantitative features from medical imaging were reported to be predictive of treatment responses. However, the biologic meaning of these latent features is poorly understood, preventing the clinical use of such noninvasive imaging markers. The study aimed to develop a deep learning signature (DLS) from pretreatment magnetic resonance imaging (MRI) for predicting responses to neoadjuvant chemotherapy in patients with breast cancer and to further investigate the biologic meaning of the DLS by identifying its underlying pathways using paired MRI and proteomic sequencing data.

METHODS

MRI-based DLS was constructed (radiogenomic training dataset, n = 105) and validated (radiogenomic validation dataset, n = 26) for the prediction of pathologic complete response (pCR) to neoadjuvant chemotherapy. Proteomic sequencing revealed biological functions facilitating pCR (n = 139). Their associations with DLS were uncovered by radiogenomic analysis.

RESULTS

The DLS achieved a prediction accuracy of 0.923 with an AUC of 0.958, higher than the performance of the model trained by transfer learning. Cellular membrane formation, endocytosis, insulin-like growth factor binding, protein localization to membranes, and cytoskeleton-dependent trafficking were differentially regulated in patients showing pCR. Oncogenic signaling pathways, features correlated with human phenotypes, and features correlated with general biological processes were significantly correlated with DLS in both training and validation dataset (p.adj < 0.05).

CONCLUSIONS

Our study offers a biologically interpretable DLS for the prediction of pCR to neoadjuvant chemotherapy in patients with breast cancer, which may guide personalized medication.

Robust RGB-T Tracking via Graph Attention-Based Bilinear Pooling

RGB-T tracker possesses strong capability of fusing two different yet complementary target observations, thus providing a promising solution to fulfill all-weather tracking in intelligent transportation systems. Existing convolutional neural network (CNN)-based RGB-T tracking methods often consider the multisource-oriented deep feature fusion from global viewpoint, but fail to yield satisfactory performance when the target pair only contains partially useful information. To solve this problem, we propose a four-stream oriented Siamese network (FS-Siamese) for RGB-T tracking. The key innovation of our network structure lies in that we formulate multidomain multilayer feature map fusion as a multiple graph learning problem, based on which we develop a graph attention-based bilinear pooling module to explore the partial feature interaction between the RGB and the thermal targets. This can effectively avoid uninformed image blocks disturbing feature embedding fusion. To enhance the efficiency of the proposed Siamese network structure, we propose to adopt meta-learning to incorporate category information in the updating of bilinear pooling results, which can online enforce the exemplar and current target appearance obtaining similar sematic representation. Extensive experiments on grayscale-thermal object tracking (GTOT) and RGBT234 datasets demonstrate that the proposed method outperforms the state-of-the-art methods for the task of RGB-T tracking.

Construction of Graphene@Ag-MLF composite structure SERS platform and its differentiating performance for different foodborne bacterial spores

A new surface-enhanced Raman spectroscopy (SERS) biosensor of Graphene@Ag-MLF composite structure has been fabricated by loading AgNPs on graphene films. The response of the biosensor is  based on plasmonic sensing. The results showed that the enhancement factor of three different spores reached 107 based on the Graphene@Ag-MLF substrate. In addition, the SERS performance was stable, with good reproducibility (RSD<3%). Multivariate statistical analysis and chemometrics were used to distinguish different spores. The accumulated variance contribution rate was up to 96.35% for the top three PCs, while HCA results revealed that the spectra were differentiated completely. Based on optimal principal components, chemometrics of KNN and LS-SVM were applied to construct a model for rapid qualitative identification of different spores, of which the prediction set and training set of LS-SVM achieved 100%. Finally, based on the Graphene@Ag-MLF substrate, the LOD of three different spores was lower than 102 CFU/mL. Hence, this novel Graphene@Ag-MLF SERS substrate sensor was rapid, sensitive, and stable in detecting spores, providing strong technical support for the application of SERS technology in food safety.

Dynamic landscapes and the influence of human activities in the Yellow River Delta wetland region

The Yellow River Delta (YRD) wetland is one of the largest and youngest wetland ecosystems in the world. It plays an important role in regulating climate and maintaining ecological balance in the region. This study analyzes the spatiotemporal changes in land use, wetland migration, and landscape pattern from 2013 to 2022 using Landsat-8 and Sentinel-1 data in YRD. Then wetland landscape changes and the impact of human activities are determined by analyzing correlation between landscape and socio-economic indicators including nighttime light centroid, total light intensity, cultivated land area and centroid, building area and centroid, economic and population. The results show that the total wetland area increased 1426 km2 during this decade. However, the wetland landscape pattern tended to be fragmented from 2013 to 2022, with wetlands of different types interlacing and connectivity decreasing, and distribution becoming more concentrated. Different types of human activities had influences on different aspects of wetland landscape, with the expansion of cultivated land mainly compressing the core area of wetlands from the edge, the expansion of buildings mainly disrupting wetland connectivity, and socio-economic indicators such as total light intensity and the centroid mainly causing wetland fragmentation. The results show the changes of the YRD wetland and provide an explanation of how human activities effect the change of its landscape, which provides available data to achieve sustainable development goals 6.6 and may give an access to measure the change of wetland using human-activity data, which could help to adject behaviors to protect wetlands.

Melatonin Promotes Iron Reactivation and Reutilization in Peach Plants under Iron Deficiency

The yellowing of leaves due to iron deficiency is a prevalent issue in peach production. Although the capacity of exogenous melatonin (MT) to promote iron uptake in peach plants has been demonstrated, its underlying mechanism remains ambiguous. This investigation was carried out to further study the effects of exogenous MT on the iron absorption and transport mechanisms of peach (Prunus persica) plants under iron-deficient conditions through transcriptome sequencing. Under both iron-deficient and iron-supplied conditions, MT increased the content of photosynthetic pigments in peach leaves and decreased the concentrations of pectin, hemicellulose, cell wall iron, pectin iron, and hemicellulose iron in peach plants to a certain extent. These effects stemmed from the inhibitory effect of MT on the polygalacturonase (PG), cellulase (Cx), phenylalanine ammonia-lyase (PAL), and cinnamoyl-coenzyme A reductase (CCR) activities, as well as the promotional effect of MT on the cinnamic acid-4-hydroxylase (C4H) activity, facilitating the reactivation of cell wall component iron. Additionally, MT increased the ferric-chelate reductase (FCR) activity and the contents of total and active iron in various organs of peach plants under iron-deficient and iron-supplied conditions. Transcriptome analysis revealed that the differentially expressed genes (DEGs) linked to iron metabolism in MT-treated peach plants were primarily enriched in the aminoacyl-tRNA biosynthesis pathway under iron-deficient conditions. Furthermore, MT influenced the expression levels of these DEGs, regulating cell wall metabolism, lignin metabolism, and iron translocation within peach plants. Overall, the application of exogenous MT promotes the reactivation and reutilization of iron in peach plants.

Correction of a homoplasmic mitochondrial tRNA mutation in patient-derived iPSCs via a mitochondrial base editor

Pathogenic mutations in mitochondrial DNA cause severe and often lethal multi-system symptoms in primary mitochondrial defects. However, effective therapies for these defects are still lacking. Strategies such as employing mitochondrially targeted restriction enzymes or programmable nucleases to shift the ratio of heteroplasmic mutations and allotopic expression of mitochondrial protein-coding genes have limitations in treating mitochondrial homoplasmic mutations, especially in non-coding genes. Here, we conduct a proof of concept study applying a screened DdCBE pair to correct the homoplasmic m.A4300G mutation in induced pluripotent stem cells derived from a patient with hypertrophic cardiomyopathy. We achieve efficient G4300A correction with limited off-target editing, and successfully restore mitochondrial function in corrected induced pluripotent stem cell clones. Our study demonstrates the feasibility of using DdCBE to treat primary mitochondrial defects caused by homoplasmic pathogenic mitochondrial DNA mutations.