Talanta. 2024 Mar 7;273:125868. doi: 10.1016/j.talanta.2024.125868. Online ahead of print.

ABSTRACT

Magnetic nanoparticle (MNP)-based immunochromatographic tests (ICTs) display long-term stability and an enhanced capability for multiplex biomarker detection, surpassing conventional gold nanoparticles (AuNPs) and fluorescence-based ICTs. In this study, we innovatively developed zwitterionic silica-coated MNPs (MNP@Si-Zwit/COOH) with outstanding antifouling capabilities and effectively utilised them for the simultaneous identification of the nucleocapsid protein (N protein) of the severe acute respiratory syndrome coronavirus (SARS-CoV-2) and influenza A/B. The carboxyl-functionalised MNPs with 10% zwitterionic ligands (MNP@Si-Zwit 10/COOH) exhibited a wide linear dynamic detection range and the most pronounced signal-to-noise ratio when used as probes in the ICT. The relative limit of detection (LOD) values were achieved in 12 min by using a magnetic assay reader (MAR), with values of 0.0062 ng/mL for SARS-CoV-2 and 0.0051 and 0.0147 ng/mL, respectively, for the N protein of influenza A and influenza B. By integrating computer vision and deep learning to enhance the image processing of immunoassay results for multiplex detection, a classification accuracy in the range of 0.9672-0.9936 was achieved for evaluating the three proteins at concentrations of 0, 0.1, 1, and 10 ng/mL. The proposed MNP-based ICT for the multiplex diagnosis of biomarkers holds substantial promise for applications in both medical institutions and self-administered diagnostic settings.

PMID:38458085 | DOI:10.1016/j.talanta.2024.125868

Comput Methods Programs Biomed. 2024 Feb 29;248:108104. doi: 10.1016/j.cmpb.2024.108104. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Survival analysis plays an essential role in the medical field for optimal treatment decision-making. Recently, survival analysis based on the deep learning (DL) approach has been proposed and is demonstrating promising results. However, developing an ideal prediction model requires integrating large datasets across multiple institutions, which poses challenges concerning medical data privacy.

METHODS: In this paper, we propose FedSurv, an asynchronous federated learning (FL) framework designed to predict survival time using clinical information and positron emission tomography (PET)-based features. This study used two datasets: a public radiogenic dataset of non-small cell lung cancer (NSCLC) from the Cancer Imaging Archive (RNSCLC), and an in-house dataset from the Chonnam National University Hwasun Hospital (CNUHH) in South Korea, consisting of clinical risk factors and F-18 fluorodeoxyglucose (FDG) PET images in NSCLC patients. Initially, each dataset was divided into multiple clients according to histological attributes, and each client was trained using the proposed DL model to predict individual survival time. The FL framework collected weights and parameters from the clients, which were then incorporated into the global model. Finally, the global model aggregated all weights and parameters and redistributed the updated model weights to each client. We evaluated different frameworks including single-client-based approach, centralized learning and FL.

RESULTS: We evaluated our method on two independent datasets. First, on the RNSCLC dataset, the mean absolute error (MAE) was 490.80±22.95 d and the C-Index was 0.69±0.01. Second, on the CNUHH dataset, the MAE was 494.25±40.16 d and the C-Index was 0.71±0.01. The FL approach achieved centralized method performance in PET-based survival time prediction and outperformed single-client-based approaches.

CONCLUSIONS: Our results demonstrated the feasibility and effectiveness of employing FL for individual survival prediction in NSCLC patients, using clinical information and PET-based features.

PMID:38457959 | DOI:10.1016/j.cmpb.2024.108104

Radiat Oncol. 2024 Mar 8;19(1):33. doi: 10.1186/s13014-024-02428-3.

ABSTRACT

BACKGROUND: Radiotherapy (RT) is an important treatment modality for patients with brain malignancies. Traditionally, computed tomography (CT) images are used for RT treatment planning whereas magnetic resonance imaging (MRI) images are used for tumor delineation. Therefore, MRI and CT need to be registered, which is an error prone process. The purpose of this clinical study is to investigate the clinical feasibility of a deep learning-based MRI-only workflow for brain radiotherapy, that eliminates the registration uncertainty through calculation of a synthetic CT (sCT) from MRI data.

METHODS: A total of 54 patients with an indication for radiation treatment of the brain and stereotactic mask immobilization will be recruited. All study patients will receive standard therapy and imaging including both CT and MRI. All patients will receive dedicated RT-MRI scans in treatment position. An sCT will be reconstructed from an acquired MRI DIXON-sequence using a commercially available deep learning solution on which subsequent radiotherapy planning will be performed. Through multiple quality assurance (QA) measures and reviews during the course of the study, the feasibility of an MRI-only workflow and comparative parameters between sCT and standard CT workflow will be investigated holistically. These QA measures include feasibility and quality of image guidance (IGRT) at the linear accelerator using sCT derived digitally reconstructed radiographs in addition to potential dosimetric deviations between the CT and sCT plan. The aim of this clinical study is to establish a brain MRI-only workflow as well as to identify risks and QA mechanisms to ensure a safe integration of deep learning-based sCT into radiotherapy planning and delivery.

DISCUSSION: Compared to CT, MRI offers a superior soft tissue contrast without additional radiation dose to the patients. However, up to now, even though the dosimetrical equivalence of CT and sCT has been shown in several retrospective studies, MRI-only workflows have still not been widely adopted. The present study aims to determine feasibility and safety of deep learning-based MRI-only radiotherapy in a holistic manner incorporating the whole radiotherapy workflow.

TRIAL REGISTRATION: NCT06106997.

PMID:38459584 | DOI:10.1186/s13014-024-02428-3

J Imaging Inform Med. 2024 Mar 8. doi: 10.1007/s10278-024-01057-2. Online ahead of print.

ABSTRACT

Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI's principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called "Multi-coil Feature Fusion Variation Network" (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622 dB and 0.0021 dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network's architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.

PMID:38459398 | DOI:10.1007/s10278-024-01057-2

Nat Methods. 2024 Mar 8. doi: 10.1038/s41592-024-02210-z. Online ahead of print.

ABSTRACT

Cryo-electron tomography (cryo-ET) enables observation of macromolecular complexes in their native, spatially contextualized cellular environment. Cryo-ET processing software to visualize such complexes at nanometer resolution via iterative alignment and averaging are well developed but rely upon assumptions of structural homogeneity among the complexes of interest. Recently developed tools allow for some assessment of structural diversity but have limited capacity to represent highly heterogeneous structures, including those undergoing continuous conformational changes. Here we extend the highly expressive cryoDRGN (Deep Reconstructing Generative Networks) deep learning architecture, originally created for single-particle cryo-electron microscopy analysis, to cryo-ET. Our new tool, tomoDRGN, learns a continuous low-dimensional representation of structural heterogeneity in cryo-ET datasets while also learning to reconstruct heterogeneous structural ensembles supported by the underlying data. Using simulated and experimental data, we describe and benchmark architectural choices within tomoDRGN that are uniquely necessitated and enabled by cryo-ET. We additionally illustrate tomoDRGN's efficacy in analyzing diverse datasets, using it to reveal high-level organization of human immunodeficiency virus (HIV) capsid complexes assembled in virus-like particles and to resolve extensive structural heterogeneity among ribosomes imaged in situ.

PMID:38459385 | DOI:10.1038/s41592-024-02210-z

Sci Rep. 2024 Mar 8;14(1):5745. doi: 10.1038/s41598-024-56211-1.

ABSTRACT

Semantic segmentation of remote sensing images (RSI) is an important research direction in remote sensing technology. This paper proposes a multi-feature fusion and channel attention network, MFCA-Net, aiming to improve the segmentation accuracy of remote sensing images and the recognition performance of small target objects. The architecture is built on an encoding-decoding structure. The encoding structure includes the improved MobileNet V2 (IMV2) and multi-feature dense fusion (MFDF). In IMV2, the attention mechanism is introduced twice to enhance the feature extraction capability, and the design of MFDF can obtain more dense feature sampling points and larger receptive fields. In the decoding section, three branches of shallow features of the backbone network are fused with deep features, and upsampling is performed to achieve the pixel-level classification. Comparative experimental results of the six most advanced methods effectively prove that the segmentation accuracy of the proposed network has been significantly improved. Furthermore, the recognition degree of small target objects is higher. For example, the proposed MFCA-Net achieves about 3.65-23.55% MIoU improvement on the dataset Vaihingen.

PMID:38459115 | DOI:10.1038/s41598-024-56211-1

Sci Rep. 2024 Mar 8;14(1):5695. doi: 10.1038/s41598-024-56079-1.

ABSTRACT

The successful integration of neural networks in a clinical setting is still uncommon despite major successes achieved by artificial intelligence in other domains. This is mainly due to the black box characteristic of most optimized models and the undetermined generalization ability of the trained architectures. The current work tackles both issues in the radiology domain by focusing on developing an effective and interpretable cardiomegaly detection architecture based on segmentation models. The architecture consists of two distinct neural networks performing the segmentation of both cardiac and thoracic areas of a radiograph. The respective segmentation outputs are subsequently used to estimate the cardiothoracic ratio, and the corresponding radiograph is classified as a case of cardiomegaly based on a given threshold. Due to the scarcity of pixel-level labeled chest radiographs, both segmentation models are optimized in a semi-supervised manner. This results in a significant reduction in the costs of manual annotation. The resulting segmentation outputs significantly improve the interpretability of the architecture's final classification results. The generalization ability of the architecture is assessed in a cross-domain setting. The assessment shows the effectiveness of the semi-supervised optimization of the segmentation models and the robustness of the ensuing classification architecture.

PMID:38459104 | DOI:10.1038/s41598-024-56079-1

Sci Rep. 2024 Mar 8;14(1):5740. doi: 10.1038/s41598-024-56405-7.

ABSTRACT

Multi-parametric MRI (mpMRI) is widely used for prostate cancer (PCa) diagnosis. Deep learning models show good performance in detecting PCa on mpMRI, but domain-specific PCa-related anatomical information is sometimes overlooked and not fully explored even by state-of-the-art deep learning models, causing potential suboptimal performances in PCa detection. Symmetric-related anatomical information is commonly used when distinguishing PCa lesions from other visually similar but benign prostate tissue. In addition, different combinations of mpMRI findings are used for evaluating the aggressiveness of PCa for abnormal findings allocated in different prostate zones. In this study, we investigate these domain-specific anatomical properties in PCa diagnosis and how we can adopt them into the deep learning framework to improve the model's detection performance. We propose an anatomical-aware PCa detection Network (AtPCa-Net) for PCa detection on mpMRI. Experiments show that the AtPCa-Net can better utilize the anatomical-related information, and the proposed anatomical-aware designs help improve the overall model performance on both PCa detection and patient-level classification.

PMID:38459100 | DOI:10.1038/s41598-024-56405-7

Sci Rep. 2024 Mar 8;14(1):5753. doi: 10.1038/s41598-024-56323-8.

ABSTRACT

Parasitic organisms pose a major global health threat, mainly in regions that lack advanced medical facilities. Early and accurate detection of parasitic organisms is vital to saving lives. Deep learning models have uplifted the medical sector by providing promising results in diagnosing, detecting, and classifying diseases. This paper explores the role of deep learning techniques in detecting and classifying various parasitic organisms. The research works on a dataset consisting of 34,298 samples of parasites such as Toxoplasma Gondii, Trypanosome, Plasmodium, Leishmania, Babesia, and Trichomonad along with host cells like red blood cells and white blood cells. These images are initially converted from RGB to grayscale followed by the computation of morphological features such as perimeter, height, area, and width. Later, Otsu thresholding and watershed techniques are applied to differentiate foreground from background and create markers on the images for the identification of regions of interest. Deep transfer learning models such as VGG19, InceptionV3, ResNet50V2, ResNet152V2, EfficientNetB3, EfficientNetB0, MobileNetV2, Xception, DenseNet169, and a hybrid model, InceptionResNetV2, are employed. The parameters of these models are fine-tuned using three optimizers: SGD, RMSprop, and Adam. Experimental results reveal that when RMSprop is applied, VGG19, InceptionV3, and EfficientNetB0 achieve the highest accuracy of 99.1% with a loss of 0.09. Similarly, using the SGD optimizer, InceptionV3 performs exceptionally well, achieving the highest accuracy of 99.91% with a loss of 0.98. Finally, applying the Adam optimizer, InceptionResNetV2 excels, achieving the highest accuracy of 99.96% with a loss of 0.13, outperforming other optimizers. The findings of this research signify that using deep learning models coupled with image processing methods generates a highly accurate and efficient way to detect and classify parasitic organisms.

PMID:38459096 | DOI:10.1038/s41598-024-56323-8

Nat Commun. 2024 Mar 8;15(1):2148. doi: 10.1038/s41467-024-46361-1.

ABSTRACT

Gene expression is inherently dynamic, due to complex regulation and stochastic biochemical events. However, the effects of these dynamics on cell phenotypes can be difficult to determine. Researchers have historically been limited to passive observations of natural dynamics, which can preclude studies of elusive and noisy cellular events where large amounts of data are required to reveal statistically significant effects. Here, using recent advances in the fields of machine learning and control theory, we train a deep neural network to accurately predict the response of an optogenetic system in Escherichia coli cells. We then use the network in a deep model predictive control framework to impose arbitrary and cell-specific gene expression dynamics on thousands of single cells in real time, applying the framework to generate complex time-varying patterns. We also showcase the framework's ability to link expression patterns to dynamic functional outcomes by controlling expression of the tetA antibiotic resistance gene. This study highlights how deep learning-enabled feedback control can be used to tailor distributions of gene expression dynamics with high accuracy and throughput without expert knowledge of the biological system.

PMID:38459057 | DOI:10.1038/s41467-024-46361-1

J Chem Inf Model. 2024 Mar 8. doi: 10.1021/acs.jcim.3c01151. Online ahead of print.

ABSTRACT

Predicting the protein-nucleic acid (PNA) binding affinity solely from their sequences is of paramount importance for the experimental design and analysis of PNA interactions (PNAIs). A large number of currently developed models for binding affinity prediction are limited to specific PNAIs while also relying on the sequence and structural information of the PNA complexes for both training and testing, and also as inputs. As the PNA complex structures available are scarce, this significantly limits the diversity and generalizability due to the small training data set. Additionally, a majority of the tools predict a single parameter, such as binding affinity or free energy changes upon mutations, rendering a model less versatile for usage. Hence, we propose DeePNAP, a machine learning-based model built from a vast and heterogeneous data set with 14,401 entries (from both eukaryotes and prokaryotes) from the ProNAB database, consisting of wild-type and mutant PNA complex binding parameters. Our model precisely predicts the binding affinity and free energy changes due to the mutation(s) of PNAIs exclusively from their sequences. While other similar tools extract features from both sequence and structure information, DeePNAP employs sequence-based features to yield high correlation coefficients between the predicted and experimental values with low root mean squared errors for PNA complexes in predicting KD and ΔΔG, implying the generalizability of DeePNAP. Additionally, we have also developed a web interface hosting DeePNAP that can serve as a powerful tool to rapidly predict binding affinities for a myriad of PNAIs with high precision toward developing a deeper understanding of their implications in various biological systems. Web interface: http://14.139.174.41:8080/.

PMID:38458968 | DOI:10.1021/acs.jcim.3c01151

Acad Radiol. 2024 Mar 7:S1076-6332(24)00086-2. doi: 10.1016/j.acra.2024.02.016. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: To develop a Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) for generating super-resolution computed tomography (SRCT) images from normal-resolution CT (NRCT) images and evaluate the performance of DGCN in multi-center datasets.

MATERIALS AND METHODS: This retrospective study included 278 patients with chest CT from two hospitals between January 2020 and June 2023, and each patient had all three NRCT (512×512 matrix CT images with a resolution of 0.70 mm, 0.70 mm,1.0 mm), high-resolution CT (HRCT, 1024×1024 matrix CT images with a resolution of 0.35 mm, 0.35 mm,1.0 mm), and ultra-high-resolution CT (UHRCT, 1024×1024 matrix CT images with a resolution of 0.17 mm, 0.17 mm, 0.5 mm) examinations. Initially, a deep chest CT super-resolution residual network (DCRN) was built to generate HRCT from NRCT. Subsequently, we employed the DCRN as a pre-trained model for the training of DGCN to further enhance resolution along all three axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective evaluation scores, and objective evaluation parameters related to pulmonary nodule segmentation in the testing set were recorded and analyzed.

RESULTS: DCRN obtained a PSNR of 52.16, SSIM of 0.9941, FID of 137.713, and an average diameter difference of 0.0981 mm. DGCN obtained a PSNR of 46.50, SSIM of 0.9990, FID of 166.421, and an average diameter difference of 0.0981 mm on 39 testing cases. There were no significant differences between the SRCT and UHRCT images in subjective evaluation.

CONCLUSION: Our model exhibited a significant enhancement in generating HRCT and SRCT images and outperformed established methods regarding image quality and clinical segmentation accuracy across both internal and external testing datasets.

PMID:38458886 | DOI:10.1016/j.acra.2024.02.016

Biomed Phys Eng Express. 2024 Mar 8. doi: 10.1088/2057-1976/ad31fa. Online ahead of print.

ABSTRACT

Contrast-enhanced computed tomography (CE-CT) images are vital
for clinical diagnosis of focal liver lesions (FLLs). However, the use of CE-CT
images imposes a significant burden on patients due to the injection of contrast
agents and extended shooting. Deep learning-based image synthesis models offer
a promising solution that synthesizes CE-CT images from non-contrasted CT
(NC-CT) images. Unlike natural images, medical image synthesis requires a
specific focus on certain organs or localized regions to ensure accurate diagnosis.
Determining how to effectively emphasize target organs poses a challenging issue
in medical image synthesis. To solve this challenge, we present a novel CECT image synthesis model called, Organ-Aware Generative Adversarial Network
(OA-GAN). The OA-GAN comprises an organ-aware (OA) network and a dual
decoder-based generator. First, the OA network learns the most discriminative
spatial features about the target organ (i.e., liver) by utilizing the ground truth
organ mask as localization cues. Subsequently, NC-CT image and captured
feature are fed into the dual decoder-based generator, which employs a local and
global decoder network to simultaneously synthesize the organ and entire CECT
image. Moreover, the semantic information extracted from the local decoder is
transferred to the global decoder to facilitate better reconstruction of the organ
in entire CE-CT image. The qualitative and quantitative evaluation on a CE-CT
dataset demonstrates that the OA-GAN outperforms state-of-the-art approaches
for synthesizing two types of CE-CT images such as arterial phase and portal
venous phase. Additionally, subjective evaluations by expert radiologists and a
deep learning-based FLLs classification also affirm that CE-CT images synthesized
from the OA-GAN exhibit a remarkable resemblance to real CE-CT images.

PMID:38457851 | DOI:10.1088/2057-1976/ad31fa

Phys Med Biol. 2024 Mar 8. doi: 10.1088/1361-6560/ad31c7. Online ahead of print.

ABSTRACT

X-ray computed tomography employing sparse projection views has emerged as a contemporary technique to mitigate radiation dose. However, due to the inadequate number of projection views, an analytic reconstruction method utilizing filtered backprojection results in severe streaking artifacts. Recently, deep learning strategies employing image-domain networks have demonstrated remarkable performance in eliminating the streaking artifact caused by analytic reconstruction methods with sparse projection views. Nevertheless, it is difficult to clarify the theoretical justification for applying deep learning to sparse view CT reconstruction, and it has been understood as restoration by removing image artifacts, not reconstruction. 

Approach: By leveraging the theory of deep convolutional framelets and the hierarchical decomposition of measurement, this research reveals the constraints of conventional image- and projection-domain deep learning methodologies, subsequently, the research proposes a novel dual-domain deep learning framework utilizing hierarchical decomposed measurements. Specifically, the research elucidates how the performance of the projection-domain network can be enhanced through a low- rank property of deep convolutional framelets and a bowtie support of hierarchical decomposed measurement in the Fourier domain. 

Main Results: This study demonstrated performance improvement of the proposed framework based on the low-rank property, resulting in superior reconstruction performance compared to conventional analytic and deep learning methods. 

Significance: By providing a theoretically justified deep learning approach for sparse-view CT reconstruction, this study not only offers a superior alternative to existing methods but also opens new avenues for research in medical imaging. It highlights the potential of dual-domain deep learning frameworks to achieve high-quality reconstructions with lower radiation doses, thereby advancing the field towards safer and more efficient diagnostic techniques. The code is available at https://github.com/hanyoseob/HDD-DL-for-SVCT.

PMID:38457843 | DOI:10.1088/1361-6560/ad31c7

Neural Comput. 2024 Feb 28:1-26. doi: 10.1162/neco_a_01650. Online ahead of print.

ABSTRACT

Combining information-theoretic learning with deep learning has gained significant attention in recent years, as it offers a promising approach to tackle the challenges posed by big data. However, the theoretical understanding of convolutional structures, which are vital to many structured deep learning models, remains incomplete. To partially bridge this gap, this letter aims to develop generalization analysis for deep convolutional neural network (CNN) algorithms using learning theory. Specifically, we focus on investigating robust regression using correntropy-induced loss functions derived from information-theoretic learning. Our analysis demonstrates an explicit convergence rate for deep CNN-based robust regression algorithms when the target function resides in the Korobov space. This study sheds light on the theoretical underpinnings of CNNs and provides a framework for understanding their performance and limitations.

PMID:38457767 | DOI:10.1162/neco_a_01650

Neural Comput. 2024 Feb 28:1-59. doi: 10.1162/neco_a_01642. Online ahead of print.

ABSTRACT

The free energy principle and its corollary, the active inference framework, serve as theoretical foundations in the domain of neuroscience, explaining the genesis of intelligent behavior. This principle states that the processes of perception, learning, and decision making-within an agent-are all driven by the objective of "minimizing free energy," evincing the following behaviors: learning and employing a generative model of the environment to interpret observations, thereby achieving perception, and selecting actions to maintain a stable preferred state and minimize the uncertainty about the environment, thereby achieving decision making. This fundamental principle can be used to explain how the brain processes perceptual information, learns about the environment, and selects actions. Two pivotal tenets are that the agent employs a generative model for perception and planning and that interaction with the world (and other agents) enhances the performance of the generative model and augments perception. With the evolution of control theory and deep learning tools, agents based on the FEP have been instantiated in various ways across different domains, guiding the design of a multitude of generative models and decision-making algorithms. This letter first introduces the basic concepts of the FEP, followed by its historical development and connections with other theories of intelligence, and then delves into the specific application of the FEP to perception and decision making, encompassing both low-dimensional simple situations and high-dimensional complex situations. It compares the FEP with model-based reinforcement learning to show that the FEP provides a better objective function. We illustrate this using numerical studies of Dreamer3 by adding expected information gain into the standard objective function. In a complementary fashion, existing reinforcement learning, and deep learning algorithms can also help implement the FEP-based agents. Finally, we discuss the various capabilities that agents need to possess in complex environments and state that the FEP can aid agents in acquiring these capabilities.

PMID:38457757 | DOI:10.1162/neco_a_01642

Neural Comput. 2024 Feb 28:1-15. doi: 10.1162/neco_a_01653. Online ahead of print.

ABSTRACT

Recent advancements in deep learning have achieved significant progress by increasing the number of parameters in a given model. However, this comes at the cost of computing resources, prompting researchers to explore model compression techniques that reduce the number of parameters while maintaining or even improving performance. Convolutional neural networks (CNN) have been recognized as more efficient and effective than fully connected (FC) networks. We propose a column row convolutional neural network (CRCNN) in this letter that applies 1D convolution to image data, significantly reducing the number of learning parameters and operational steps. The CRCNN uses column and row local receptive fields to perform data abstraction, concatenating each direction's feature before connecting it to an FC layer. Experimental results demonstrate that the CRCNN maintains comparable accuracy while reducing the number of parameters and compared to prior work. Moreover, the CRCNN is employed for one-class anomaly detection, demonstrating its feasibility for various applications.

PMID:38457753 | DOI:10.1162/neco_a_01653

Biochemistry. 2024 Mar 8. doi: 10.1021/acs.biochem.3c00596. Online ahead of print.

ABSTRACT

Optimization of aptamers in length and chemistry is crucial for industrial applications. Here, we developed aptamers against the SARS-CoV-2 spike protein and achieved optimization with a deep-learning-based algorithm, RaptGen. We conducted a primer-less SELEX against the receptor binding domain (RBD) of the spike with an RNA/DNA hybrid library, and the resulting sequences were subjected to RaptGen analysis. Based on the sequence profiling by RaptGen, a short truncation aptamer of 26 nucleotides was obtained and further optimized by a chemical modification of relevant nucleotides. The resulting aptamer is bound to RBD not only of SARS-CoV-2 wildtype but also of its variants, SARS-CoV-1, and Middle East respiratory syndrome coronavirus (MERS-CoV). We concluded that the RaptGen-assisted discovery is efficient for developing optimized aptamers.

PMID:38457656 | DOI:10.1021/acs.biochem.3c00596

Medicine (Baltimore). 2024 Mar 8;103(10):e37528. doi: 10.1097/MD.0000000000037528.

ABSTRACT

BACKGROUND: Adolescents with hemiplegic cerebral palsy undergo conventional physical therapy (CPT) to improve static and dynamic balance, activities of daily living and cardiopulmonary function. To overcome this problem, we developed an innovative deep learning-based rehabilitation application (DRA) to provide a motivational and chaffed platform for such individuals. DRA evaluates the patients' functional abilities and diagnosis an appropriate therapeutic intervention like CPT.

METHODS: We compared the effects of DRA and CPT on 6-minute walking test (6 MWT), Borg rating of perceived exertion scale, Berg balance scale, functional ambulation category, and modified Barthel index in adolescents with hemiplegic cerebral palsy. A convenience sample of 30 adolescents with hemiplegic cerebral palsy was randomized into either the DRA or CPT group. DRA and CPT were administered to the participants, with each session lasting 30 minutes and apportioned thrice a week for a total of 4 weeks.

RESULTS: Analysis of variance was performed and the level of significance was set at P < .05. The analysis indicated that DRA showed therapeutic effects on 6 MWT, Berg balance scale, and modified Barthel index compared to CPT.

CONCLUSION: Our results provide evidence that DRA can improve cardiopulmonary function, balance, and activities of daily living more effectively than CPT in adolescents with hemiplegic cerebral palsy.

PMID:38457533 | DOI:10.1097/MD.0000000000037528

PLoS One. 2024 Mar 8;19(3):e0299448. doi: 10.1371/journal.pone.0299448. eCollection 2024.

ABSTRACT

BACKGROUND: Total marrow irradiation (TMI) and total marrow and lymphoid irradiation (TMLI) have the advantages. However, delineating target lesions according to TMI and TMLI plans is labor-intensive and time-consuming. In addition, although the delineation of target lesions between TMI and TMLI differs, the clinical distinction is not clear, and the lymph node (LN) area coverage during TMI remains uncertain. Accordingly, this study calculates the LN area coverage according to the TMI plan. Further, a deep learning-based model for delineating LN areas is trained and evaluated.

METHODS: Whole-body regional LN areas were manually contoured in patients treated according to a TMI plan. The dose coverage of the delineated LN areas in the TMI plan was estimated. To train the deep learning model for automatic segmentation, additional whole-body computed tomography data were obtained from other patients. The patients and data were divided into training/validation and test groups and models were developed using the "nnU-NET" framework. The trained models were evaluated using Dice similarity coefficient (DSC), precision, recall, and Hausdorff distance 95 (HD95). The time required to contour and trim predicted results manually using the deep learning model was measured and compared.

RESULTS: The dose coverage for LN areas by TMI plan had V100% (the percentage of volume receiving 100% of the prescribed dose), V95%, and V90% median values of 46.0%, 62.1%, and 73.5%, respectively. The lowest V100% values were identified in the inguinal (14.7%), external iliac (21.8%), and para-aortic (42.8%) LNs. The median values of DSC, precision, recall, and HD95 of the trained model were 0.79, 0.83, 0.76, and 2.63, respectively. The time for manual contouring and simply modified predicted contouring were statistically significantly different.

CONCLUSIONS: The dose coverage in the inguinal, external iliac, and para-aortic LN areas was suboptimal when treatment is administered according to the TMI plan. This research demonstrates that the automatic delineation of LN areas using deep learning can facilitate the implementation of TMLI.

PMID:38457432 | DOI:10.1371/journal.pone.0299448