Acta Ophthalmol. 2024 Feb 12. doi: 10.1111/aos.16660. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aimed to develop a deep learning (DL) model, named 'DeepAlienorNet', to automatically extract clinical signs of age-related macular degeneration (AMD) from colour fundus photography (CFP).

METHODS AND ANALYSIS: The ALIENOR Study is a cohort of French individuals 77 years of age or older. A multi-label DL model was developed to grade the presence of 7 clinical signs: large soft drusen (>125 μm), intermediate soft (63-125 μm), large area of soft drusen (total area >500 μm), presence of central soft drusen (large or intermediate), hyperpigmentation, hypopigmentation, and advanced AMD (defined as neovascular or atrophic AMD). Prediction performances were evaluated using cross-validation and the expert human interpretation of the clinical signs as the ground truth.

RESULTS: A total of 1178 images were included in the study. Averaging the 7 clinical signs' detection performances, DeepAlienorNet achieved an overall sensitivity, specificity, and AUROC of 0.77, 0.83, and 0.87, respectively. The model demonstrated particularly strong performance in predicting advanced AMD and large areas of soft drusen. It can also generate heatmaps, highlighting the relevant image areas for interpretation.

CONCLUSION: DeepAlienorNet demonstrates promising performance in automatically identifying clinical signs of AMD from CFP, offering several notable advantages. Its high interpretability reduces the black box effect, addressing ethical concerns. Additionally, the model can be easily integrated to automate well-established and validated AMD progression scores, and the user-friendly interface further enhances its usability. The main value of DeepAlienorNet lies in its ability to assist in precise severity scoring for further adapted AMD management, all while preserving interpretability.

PMID:38345159 | DOI:10.1111/aos.16660

J Biomol Struct Dyn. 2024 Feb 12:1-13. doi: 10.1080/07391102.2024.2311343. Online ahead of print.

ABSTRACT

The brain's abnormal and uncontrollable cell partitioning is a severe cancer disease. The tissues around the brain or the skull induce this tumor to develop spontaneously. For the treatment of a brain tumor, surgical techniques are typically preferred. Deep learning models in the biomedical field have recently attracted a lot of attention for detecting and treating diseases. This article proposes a new Ensemble Deep Learning Network (EDLNet) model. This research uses the Modified Faster RCNN approach to classify brain MRI scan images into cancerous and non-cancerous. A deep recurrent convolutional neural network (DRCNN)-based diagnostic method for early-stage brain tumor segmentation is presented. The evaluation outcomes show that the proposed tumor classification and segmentation model's performance accurately segments tissues from MRI images. For the analysis of the proposed model, two different publicly available datasets (D1&D2) are used. For D1 and D2 datasets, a total of 99.76% and 99.87% accuracies are achieved by the proposed model. The performance results of the proposed model are more effective than the state-of-the-art network models as per the experimental results.Communicated by Ramaswamy H. Sarma.

PMID:38345061 | DOI:10.1080/07391102.2024.2311343

Network. 2024 Feb 12:1-22. doi: 10.1080/0954898X.2024.2310687. Online ahead of print.

ABSTRACT

Retinal haemorrhage stands as an early indicator of diabetic retinopathy, necessitating accurate detection for timely diagnosis. Addressing this need, this study proposes an enhanced machine-based diagnostic test for diabetic retinopathy through an updated UNet framework, adept at scrutinizing fundus images for signs of retinal haemorrhages. The customized UNet underwent GPU training using the IDRiD database, validated against the publicly available DIARETDB1 and IDRiD datasets. Emphasizing the complexity of segmentation, the study employed preprocessing techniques, augmenting image quality and data integrity. Subsequently, the trained neural network showcased a remarkable performance boost, accurately identifying haemorrhage regions with 80% sensitivity, 99.6% specificity, and 98.6% accuracy. The experimental findings solidify the network's reliability, showcasing potential to alleviate ophthalmologists' workload significantly. Notably, achieving an Intersection over Union (IoU) of 76.61% and a Dice coefficient of 86.51% underscores the system's competence. The study's outcomes signify substantial enhancements in diagnosing critical diabetic retinal conditions, promising profound improvements in diagnostic accuracy and efficiency, thereby marking a significant advancement in automated retinal haemorrhage detection for diabetic retinopathy.

PMID:38345038 | DOI:10.1080/0954898X.2024.2310687

Cureus. 2024 Jan 10;16(1):e52035. doi: 10.7759/cureus.52035. eCollection 2024 Jan.

ABSTRACT

The simulation of human intelligence in robots that are designed to think and learn like humans is known as artificial intelligence (AI). AI is creating a world that has never been seen before. By applying AI to do jobs that would otherwise take a long time, humans have the chance to improve our planet. AI has great potential in genetic engineering and gene therapy research. AI is a powerful tool for creating new hypotheses and helping with experimental techniques. From the previous data of a gene model, it can help in the detection of heredity and gene-related disorders. AI developments offer an excellent possibility for rational drug discovery and design, eventually impacting humanity. Drug development and discovery depend greatly on AI and machine learning (ML) technology. Genetics is not an exception to this trend, as ML and AI are expected to have an impact on nearly every aspect of the human experience. AI has significantly aided in the treatment of various biomedical conditions, including genetic disorders. In both basic and applied gene research, deep learning - a highly versatile branch of AI that enables autonomous feature extraction - is increasingly exploited. In this review, we cover a broad spectrum of current uses of AI in genetics. AI has enormous potential in the field of genetics, but its advancement in this area may be hampered in the future by a lack of knowledge about the accompanying difficulties that could mask any possible benefits for patients. This paper examines AI's potential significance in advancing precision genetic disease treatment, provides a peek at its use in genetic clinical care, examines a number of existing AI and ML uses in genetics, provides a clinician primer on critical aspects of these technologies, and makes predictions about AI's potential future applications in genetic illnesses.

PMID:38344556 | PMC:PMC10856672 | DOI:10.7759/cureus.52035

NAR Genom Bioinform. 2024 Feb 10;6(1):lqae013. doi: 10.1093/nargab/lqae013. eCollection 2024 Mar.

ABSTRACT

De novo mutations (DNMs), and among them clustered DNMs within 20 bp of each other (cDNMs) are known to be a potential cause of genetic disorders. However, identifying DNM in whole genome sequencing (WGS) data is a process that often suffers from low specificity. We propose a deep learning framework for DNM and cDNM detection in WGS data based on Google's DeepTrio software for variant calling, which considers regions of 110 bp up- and downstream from possible variants to take information from the surrounding region into account. We trained a model each for the DNM and cDNM detection tasks and tested it on data generated on the HiSeq and NovaSeq platforms. In total, the model was trained on 82 WGS trios generated on the NovaSeq and 16 on the HiSeq. For the DNM detection task, our model achieves a sensitivity of 95.7% and a precision of 89.6%. The extended model adds confidence information for cDNMs, in addition to standard variant classes and DNMs. While this causes a slight drop in DNM sensitivity (91.96%) and precision (90.5%), on HG002 cDNMs can be isolated from other variant classes in all cases (5 out of 5) with a precision of 76.9%. Since the model emits confidence probabilities for each variant class, it is possible to fine-tune cutoff thresholds to allow users to select a desired trade-off between sensitivity and specificity. These results show that DeepTrio can be retrained to identify complex mutational signatures with only little modification effort.

PMID:38344274 | PMC:PMC10858645 | DOI:10.1093/nargab/lqae013

Int J Biomed Imaging. 2024 Feb 3;2024:3022192. doi: 10.1155/2024/3022192. eCollection 2024.

ABSTRACT

Skin cancer is a significant health concern worldwide, and early and accurate diagnosis plays a crucial role in improving patient outcomes. In recent years, deep learning models have shown remarkable success in various computer vision tasks, including image classification. In this research study, we introduce an approach for skin cancer classification using vision transformer, a state-of-the-art deep learning architecture that has demonstrated exceptional performance in diverse image analysis tasks. The study utilizes the HAM10000 dataset; a publicly available dataset comprising 10,015 skin lesion images classified into two categories: benign (6705 images) and malignant (3310 images). This dataset consists of high-resolution images captured using dermatoscopes and carefully annotated by expert dermatologists. Preprocessing techniques, such as normalization and augmentation, are applied to enhance the robustness and generalization of the model. The vision transformer architecture is adapted to the skin cancer classification task. The model leverages the self-attention mechanism to capture intricate spatial dependencies and long-range dependencies within the images, enabling it to effectively learn relevant features for accurate classification. Segment Anything Model (SAM) is employed to segment the cancerous areas from the images; achieving an IOU of 96.01% and Dice coefficient of 98.14% and then various pretrained models are used for classification using vision transformer architecture. Extensive experiments and evaluations are conducted to assess the performance of our approach. The results demonstrate the superiority of the vision transformer model over traditional deep learning architectures in skin cancer classification in general with some exceptions. Upon experimenting on six different models, ViT-Google, ViT-MAE, ViT-ResNet50, ViT-VAN, ViT-BEiT, and ViT-DiT, we found out that the ML approach achieves 96.15% accuracy using Google's ViT patch-32 model with a low false negative ratio on the test dataset, showcasing its potential as an effective tool for aiding dermatologists in the diagnosis of skin cancer.

PMID:38344227 | PMC:PMC10858797 | DOI:10.1155/2024/3022192

Front Plant Sci. 2024 Jan 26;15:1369791. doi: 10.3389/fpls.2024.1369791. eCollection 2024.

NO ABSTRACT

PMID:38344185 | PMC:PMC10853811 | DOI:10.3389/fpls.2024.1369791

Imaging Neurosci (Camb). 2023;1. doi: 10.1162/imag_a_00023. Epub 2023 Oct 17.

ABSTRACT

Diffusion MRI (dMRI) is a widely used method to investigate the microstructure of the brain. Quality control (QC) of dMRI data is an important processing step that is performed prior to analysis using models such as diffusion tensor imaging (DTI) or neurite orientation dispersion and density imaging (NODDI). When processing dMRI data from infants and young children, where intra-scan motion is common, the identification and removal of motion artifacts is of the utmost importance. Manual QC of dMRI data is (1) time-consuming due to the large number of diffusion directions, (2) expensive, and (3) prone to subjective errors and observer variability. Prior techniques for automated dMRI QC have mostly been limited to adults or school-age children. Here, we propose a deep learning-based motion artifact detection tool for dMRI data acquired from infants and toddlers. The proposed framework uses a simple three-dimensional convolutional neural network (3DCNN) trained and tested on an early pediatric dataset of 2,276 dMRI volumes from 121 exams acquired at 1 month and 24 months of age. An average classification accuracy of 95% was achieved following four-fold cross-validation. A second dataset with different acquisition parameters and ages ranging from 2-36 months (consisting of 2,349 dMRI volumes from 26 exams) was used to test network generalizability, achieving 98% classification accuracy. Finally, to demonstrate the importance of motion artifact volume removal in a dMRI processing pipeline, the dMRI data were fit to the DTI and NODDI models and the parameter maps were compared with and without motion artifact removal.

PMID:38344118 | PMC:PMC10854394 | DOI:10.1162/imag_a_00023

Food Res Int. 2024 Mar;179:113967. doi: 10.1016/j.foodres.2024.113967. Epub 2024 Jan 3.

ABSTRACT

In addressing the generalization issue faced by data-driven methods in food origin traceability, especially when encountering diverse input variable sets, such as elemental contents (C, N, S), stable isotopes (C, N, S, H and O) and 43 elements measured under varying laboratory conditions. We introduce an innovative, versatile deep learning-based framework incorporating explainable analysis, adept at determining feature importance through learned neuron weights. Our proposed framework, validated using three rice sample batches from four Asian countries, totaling 354 instances, exhibited exceptional identification accuracy of up to 97%, surpassing traditional reference methods like decision tree and support vector machine. The adaptable methodological system accommodates various combinations of traceability indicators, facilitating seamless replication and extensive applicability. This groundbreaking solution effectively tackles generalization challenges arising from disparate variable sets across distinct data batches, paving the way for enhanced food origin traceability in real-world applications.

PMID:38342523 | DOI:10.1016/j.foodres.2024.113967

Neural Netw. 2024 Feb 3;173:106159. doi: 10.1016/j.neunet.2024.106159. Online ahead of print.

ABSTRACT

In recent years, human physical activity recognition has increasingly attracted attention from different research fields such as healthcare, computer-human interaction, lifestyle monitoring, and athletics. Deep learning models have been extensively employed in developing physical activity recognition systems. To improve these models, their hyperparameters need to be initialized with optimal values. However, tuning these hyperparameters manually is time-consuming and may lead to inaccurate results. Moreover, the application of these models to different data resources and the integration of their results into the overall data processing pipeline are challenging issues in physical activity recognition systems. In this paper, we propose a novel ensemble method for physical activity recognition based on a deep transformer-based time-series classification model that uses heart rate, speed, and distance time-series data to recognize physical activities. In particular, we develop a modified arithmetic optimization algorithm to automatically adjust the optimal values of the classification models' hyperparameters. Moreover, a reinforcement learning-based ensemble approach is proposed to optimally integrate the results of the classification models obtained using heart rate, speed, and distance time-series data and, subsequently, recognize the physical activities. Experiments performed on a real-world dataset demonstrated that the proposed method achieves promising efficiency in comparison to other state-of-the-art models. More specifically, the proposed method increases the performance compared to the second-best performer by around 3.44 %, 9.45 %, 5.43 %, 2.54 %, and 7.53 % based on accuracy, precision, recall, specificity, and F1-score evaluation metrics, respectively.

PMID:38342080 | DOI:10.1016/j.neunet.2024.106159

Magn Reson Med. 2024 Feb 11. doi: 10.1002/mrm.30045. Online ahead of print.

ABSTRACT

PURPOSE: This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust.

METHODS: Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitative T 1 $$ {\mathrm{T}}_1 $$ mapping as an example, the proposed method was applied to the brain, knee and phantom data.

RESULTS: The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping.

CONCLUSION: This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

PMID:38342980 | DOI:10.1002/mrm.30045

Sci Rep. 2024 Feb 12;14(1):3463. doi: 10.1038/s41598-024-53733-6.

ABSTRACT

Alzheimer's disease (AD) is a debilitating neurodegenerative disorder that requires accurate diagnosis for effective management and treatment. In this article, we propose an architecture for a convolutional neural network (CNN) that utilizes magnetic resonance imaging (MRI) data from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset to categorize AD. The network employs two separate CNN models, each with distinct filter sizes and pooling layers, which are concatenated in a classification layer. The multi-class problem is addressed across three, four, and five categories. The proposed CNN architecture achieves exceptional accuracies of 99.43%, 99.57%, and 99.13%, respectively. These high accuracies demonstrate the efficacy of the network in capturing and discerning relevant features from MRI images, enabling precise classification of AD subtypes and stages. The network architecture leverages the hierarchical nature of convolutional layers, pooling layers, and fully connected layers to extract both local and global patterns from the data, facilitating accurate discrimination between different AD categories. Accurate classification of AD carries significant clinical implications, including early detection, personalized treatment planning, disease monitoring, and prognostic assessment. The reported accuracy underscores the potential of the proposed CNN architecture to assist medical professionals and researchers in making precise and informed judgments regarding AD patients.

PMID:38342924 | DOI:10.1038/s41598-024-53733-6

Cereb Cortex. 2024 Jan 31;34(2):bhae030. doi: 10.1093/cercor/bhae030.

ABSTRACT

As a biomarker of human brain health during development, brain age is estimated based on subtle differences in brain structure from those under typical developmental. Magnetic resonance imaging (MRI) is a routine diagnostic method in neuroimaging. Brain age prediction based on MRI has been widely studied. However, few studies based on Chinese population have been reported. This study aimed to construct a brain age predictive model for the Chinese population across its lifespan. We developed a partition prediction method based on transfer learning and atlas attention enhancement. The participants were separated into four age groups, and a deep learning model was trained for each group to identify the brain regions most critical for brain age prediction. The Atlas attention-enhancement method was also used to help the models focus only on critical brain regions. The proposed method was validated using 354 participants from domestic datasets. For prediction performance in the testing sets, the mean absolute error was 2.218 ± 1.801 years, and the Pearson correlation coefficient (r) was 0.969, exceeding previous results for wide-range brain age prediction. In conclusion, the proposed method could provide brain age estimation to assist in assessing the status of brain health.

PMID:38342684 | DOI:10.1093/cercor/bhae030

J Dent. 2024 Feb 9:104886. doi: 10.1016/j.jdent.2024.104886. Online ahead of print.

ABSTRACT

OBJECTIVE: Secondary caries lesions adjacent to restorations, a leading cause of restoration failure, require accurate diagnostic methods to ensure an optimal treatment outcome. Traditional diagnostic strategies rely on visual inspection complemented by radiographs. Recent advancements in artificial intelligence (AI), particularly deep learning, provide potential improvements in caries detection. This study aimed to develop a convolutional neural network (CNN)-based algorithm for detecting primary caries and secondary caries around restorations using bitewings.

METHODS: Clinical data from 7 general dental practices in the Netherlands, comprising 425 bitewings of 383 patients, were utilized. The study used the Mask-RCNN architecture, for instance, segmentation, supported by the Swin Transformer backbone. After data augmentation, model training was performed through a ten-fold cross-validation. The diagnostic accuracy of the algorithm was evaluated by calculating the area under the Free-Response Receiver Operating Characteristics curve, sensitivity, precision, and F1 scores.

RESULTS: The model achieved areas under FROC curves of 0.806 and 0.804, and F1-scores of 0.689 and 0.719 for primary and secondary caries detection, respectively.

CONCLUSION: An accurate CNN-based automated system was developed to detect primary and secondary caries lesions on bitewings, highlighting a significant advancement in automated caries diagnostics.

CLINICAL SIGNIFICANCE: An accurate algorithm that integrates the detection of both primary and secondary caries will permit the development of automated systems to aid clinicians in their daily clinical practice.

PMID:38342368 | DOI:10.1016/j.jdent.2024.104886

Curr Probl Cardiol. 2024 Feb 9:102454. doi: 10.1016/j.cpcardiol.2024.102454. Online ahead of print.

ABSTRACT

The rapid evolution of neural networks and deep learning has revolutionized various fields, with clinical cardiology being no exception. As traditional methods in cardiology encounter limitations, the integration of advanced computational techniques offers unprecedented opportunities in diagnostics and patient care. This review explores the transformative role of neural networks and deep learning in clinical cardiology, particularly focusing on their applications in electrocardiogram (ECG) analysis, imaging technologies, and cardiac prediction models. Deep Neural Networks (DNNs) have significantly surpassed traditional approaches in accuracy and efficiency in automatic ECG diagnosis. Convolutional Neural Networks (CNNs) are successfully applied in PET/CT and PET/MR imaging, enhancing diagnostic capabilities. Furthermore, deep learning algorithms have shown potential in improving cardiac prediction models, although challenges in interpretability and clinical integration remain. The review also addresses the 'black box' nature of neural networks and the ethical considerations surrounding their use in clinical settings. Overall, this review underscores the significant impact of neural networks and deep learning in cardiology, providing insights into current applications and future directions in the field.

PMID:38342351 | DOI:10.1016/j.cpcardiol.2024.102454

Caries Res. 2024 Feb 9. doi: 10.1159/000536277. Online ahead of print.

ABSTRACT

INTRODUCTION: A growing number of studies on diagnostic imaging show superior efficiency and accuracy of computer-aided diagnostic systems compared to certified dentists. This methodological systematic review aims to evaluate the different methodological approaches used by studies focusing on machine learning and deep learning and that have used radiographic databases to classify, detect, and segment dental caries.

METHODS: The protocol was registered in PROSPERO before data collection (CRD42022348097). Literature research was performed in MEDLINE, Embase, IEEE Xplore, and Web of Science until December 2022, without language restrictions. Studies and surveys using a dental radiographic database for the classification, detection, or segmentation of carious lesions were sought. Records deemed eligible were retrieved and further assessed for inclusion by two reviewers who resolved any discrepancies through consensus. A third reviewer was consulted when any disagreements or discrepancies persist between the two reviewers. After data extraction, the same reviewers assessed the methodological quality using the CLAIM and QUADAS-AI checklists.

RESULTS: After screening 325 articles, 35 studies were eligible and included. The bitewing was the most commonly used radiograph (n=17) at the time when detection (n=15) was the most explored computer vision task. The sample sizes used ranged from 95 to 38437, while the augmented training set ranged from 300 to 315786. Convolutional neural network (CNN) was the most commonly used model. The mean completeness of CLAIM items was 49 % (SD ± 34%). The applicability of the CLAIM checklist items revealed several weaknesses in the methodology of the selected studies: most of the studies were monocentric, and only 9% of them used an external test set when evaluating the model's performance. The QUADAS-AI tool revealed that only 43% of the studies included in this systematic review were at low risk of bias concerning the standard reference domain.

CONCLUSION: This review demonstrates that the overall scientific quality of studies conducted to feed AI algorithms is low. Some improvement in the design and validation of studies can be made with the development of a standardized guideline for the reproducibility and generalizability of results and, thus, their clinical applications.

PMID:38342096 | DOI:10.1159/000536277

Comput Med Imaging Graph. 2024 Feb 6;113:102352. doi: 10.1016/j.compmedimag.2024.102352. Online ahead of print.

ABSTRACT

Automated medical image segmentation plays a crucial role in diverse clinical applications. The high annotation costs of fully-supervised medical segmentation methods have spurred a growing interest in semi-supervised methods. Existing semi-supervised medical segmentation methods train the teacher segmentation network using labeled data to establish pseudo labels for unlabeled data. The quality of these pseudo labels is constrained as these methods fail to effectively address the significant bias in the data distribution learned from the limited labeled data. To address these challenges, this paper introduces an innovative Correspondence-based Generative Bayesian Deep Learning (C-GBDL) model. Built upon the teacher-student architecture, we design a multi-scale semantic correspondence method to aid the teacher model in generating high-quality pseudo labels. Specifically, our teacher model, embedded with the multi-scale semantic correspondence, learns a better-generalized data distribution from input volumes by feature matching with the reference volumes. Additionally, a double uncertainty estimation schema is proposed to further rectify the noisy pseudo labels. The double uncertainty estimation takes the predictive entropy as the first uncertainty estimation and takes the structural similarity between the input volume and its corresponding reference volumes as the second uncertainty estimation. Four groups of comparative experiments conducted on two public medical datasets demonstrate the effectiveness and the superior performance of our proposed model. Our code is available on https://github.com/yumjoo/C-GBDL.

PMID:38341947 | DOI:10.1016/j.compmedimag.2024.102352

Comput Med Imaging Graph. 2024 Feb 9;113:102347. doi: 10.1016/j.compmedimag.2024.102347. Online ahead of print.

ABSTRACT

Characterizing coronary calcified plaque (CCP) provides essential insight into diagnosis and treatment of atherosclerosis. Intravascular optical coherence tomography (OCT) offers significant advantages for detecting CCP and even automated segmentation with recent advances in deep learning techniques. Most of current methods have achieved promising results by adopting existing convolution neural networks (CNNs) in computer vision domain. However, their performance can be detrimentally affected by unseen plaque patterns and artifacts due to inherent limitation of CNNs in contextual reasoning. To overcome this obstacle, we proposed a Transformer-based pyramid network called AFS-TPNet for robust, end-to-end segmentation of CCP from OCT images. Its encoder is built upon CSWin Transformer architecture, allowing for better perceptual understanding of calcified arteries at a higher semantic level. Specifically, an augmented feature split (AFS) module and residual convolutional position encoding (RCPE) mechanism are designed to effectively enhance the capability of Transformer in capturing both fine-grained features and global contexts. Extensive experiments showed that AFS-TPNet trained using Lovasz Loss achieved superior performance in segmentation CCP under various contexts, surpassing prior state-of-the-art CNN and Transformer architectures by more than 6.58% intersection over union (IoU) score. The application of this promising method to extract CCP features is expected to enhance clinical intervention and translational research using OCT.

PMID:38341945 | DOI:10.1016/j.compmedimag.2024.102347

Magn Reson Med. 2024 Feb 11. doi: 10.1002/mrm.30021. Online ahead of print.

ABSTRACT

PURPOSE: We introduced a novel reconstruction network, jointly unrolled cross-domain optimization-based spatio-temporal reconstruction network (JUST-Net), aimed at accelerating 3D multi-echo gradient-echo (mGRE) data acquisition and improving the quality of resulting myelin water imaging (MWI) maps.

METHOD: An unrolled cross-domain spatio-temporal reconstruction network was designed. The main idea is to combine frequency and spatio-temporal image feature representations and to sequentially implement convolution layers in both domains. The k-space subnetwork utilizes shared information from adjacent frames, whereas the image subnetwork applies separate convolutions in both spatial and temporal dimensions. The proposed reconstruction network was evaluated for both retrospectively and prospectively accelerated acquisition. Furthermore, it was assessed in simulation studies and real-world cases with k-space corruptions to evaluate its potential for motion artifact reduction.

RESULTS: The proposed JUST-Net enabled highly reproducible and accelerated 3D mGRE acquisition for whole-brain MWI, reducing the acquisition time from fully sampled 15:23 to 2:22 min within a 3-min reconstruction time. The normalized root mean squared error of the reconstructed mGRE images increased by less than 4.0%, and the correlation coefficients for MWI showed a value of over 0.68 when compared to the fully sampled reference. Additionally, the proposed method demonstrated a mitigating effect on both simulated and clinical motion-corrupted cases.

CONCLUSION: The proposed JUST-Net has demonstrated the capability to achieve high acceleration factors for 3D mGRE-based MWI, which is expected to facilitate widespread clinical applications of MWI.

PMID:38342983 | DOI:10.1002/mrm.30021

Small. 2024 Feb 11:e2311036. doi: 10.1002/smll.202311036. Online ahead of print.

ABSTRACT

Wearable devices play an indispensable role in modern life, and the human body contains multiple wasted energies available for wearable devices. This study proposes a self-sensing and self-powered wearable system (SS-WS) based on scavenging waist motion energy and knee negative energy. The proposed SS-WS consists of a three-degree-of-freedom triboelectric nanogenerator (TDF-TENG) and a negative energy harvester (NEH). The TDF-TENG is driven by waist motion energy and the generated triboelectric signals are processed by deep learning for recognizing the human motion. The triboelectric signals generated by TDF-TENG can accurately recognize the motion state after processing based on Gate Recurrent Unit deep learning model. With double frequency up-conversion, the NEH recovers knee negative energy generation for powering wearable devices. A model wearing the single energy harvester can generate the power of 27.01 mW when the movement speed is 8 km h-1 , and the power density of NEH reaches 0.3 W kg-1 at an external excitation condition of 3 Hz. Experiments and analysis prove that the proposed SS-WS can realize self-sensing and effectively power wearable devices.

PMID:38342584 | DOI:10.1002/smll.202311036