Med Phys. 2024 Apr 30. doi: 10.1002/mp.17101. Online ahead of print.

ABSTRACT

BACKGROUND: Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a standardized semi-quantitative method for early ischemic changes in acute ischemic stroke.

PURPOSE: However, ASPECTS is still affected by expert experience and inconsistent results between readers in clinical. This study aims to propose an automatic ASPECTS scoring model based on diffusion-weighted imaging (DWI) mode to help clinicians make accurate treatment plans.

METHODS: Eighty-two patients with stroke were included in the study. First, we designed a new deep learning network for segmenting ASPECTS scoring brain regions. The network is improved based on U-net, which integrates multiple modules. Second, we proposed using hybrid classifiers to classify brain regions. For brain regions with larger areas, we used brain grayscale comparison algorithm to train machine learning classifiers, while using hybrid feature training for brain regions with smaller areas.

RESULTS: The average DICE coefficient of the segmented hindbrain area can reach 0.864. With the proposed hybrid classifier, our method performs significantly on both region-level ASPECTS and dichotomous ASPECTS. The sensitivity and accuracy on the test set are 95.51% and 93.43%, respectively. For dichotomous ASPECTS, the intraclass correlation coefficient (ICC) between our automated ASPECTS score and the expert reading was 0.87.

CONCLUSIONS: This study proposed an automated model for ASPECTS scoring of patients with acute ischemic stroke based on DWI images. Experimental results show that the method of segmentation first and then classification is feasible. Our method has the potential to assist physicians in the Alberta Stroke Program with early CT scoring and clinical stroke diagnosis.

PMID:38687043 | DOI:10.1002/mp.17101

Invest Radiol. 2024 May 1. doi: 10.1097/RLI.0000000000001086. Online ahead of print.

ABSTRACT

OBJECTIVES: Dark-blood late gadolinium enhancement (DB-LGE) cardiac magnetic resonance has been proposed as an alternative to standard white-blood LGE (WB-LGE) imaging protocols to enhance scar-to-blood contrast without compromising scar-to-myocardium contrast. In practice, both DB and WB contrasts may have clinical utility, but acquiring both has the drawback of additional acquisition time. The aim of this study was to develop and evaluate a deep learning method to generate synthetic WB-LGE images from DB-LGE, allowing the assessment of both contrasts without additional scan time.

MATERIALS AND METHODS: DB-LGE and WB-LGE data from 215 patients were used to train 2 types of unpaired image-to-image translation deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation, with 5 different loss function hyperparameter settings each. Initially, the best hyperparameter setting was determined for each model type based on the Fréchet inception distance and the visual assessment of expert readers. Then, the CycleGAN and contrastive unpaired translation models with the optimal hyperparameters were directly compared. Finally, with the best model chosen, the quantification of scar based on the synthetic WB-LGE images was compared with the truly acquired WB-LGE.

RESULTS: The CycleGAN architecture for unpaired image-to-image translation was found to provide the most realistic synthetic WB-LGE images from DB-LGE images. The results showed that it was difficult for visual readers to distinguish if an image was true or synthetic (55% correctly classified). In addition, scar burden quantification with the synthetic data was highly correlated with the analysis of the truly acquired images. Bland-Altman analysis found a mean bias in percentage scar burden between the quantification of the real WB and synthetic white-blood images of 0.44% with limits of agreement from -10.85% to 11.74%. The mean image quality of the real WB images (3.53/5) was scored higher than the synthetic white-blood images (3.03), P = 0.009.

CONCLUSIONS: This study proposed a CycleGAN model to generate synthetic WB-LGE from DB-LGE images to allow assessment of both image contrasts without additional scan time. This work represents a clinically focused assessment of synthetic medical images generated by artificial intelligence, a topic with significant potential for a multitude of applications. However, further evaluation is warranted before clinical adoption.

PMID:38687025 | DOI:10.1097/RLI.0000000000001086

Womens Health (Lond). 2024 Jan-Dec;20:17455057241248121. doi: 10.1177/17455057241248121.

ABSTRACT

Endometriosis, a chronic condition characterized by the growth of endometrial-like tissue outside of the uterus, poses substantial challenges in terms of diagnosis and treatment. Artificial intelligence (AI) has emerged as a promising tool in the field of medicine, offering opportunities to address the complexities of endometriosis. This review explores the current landscape of endometriosis diagnosis and treatment, highlighting the potential of AI to alleviate some of the associated burdens and underscoring common pitfalls and challenges when employing AI algorithms in this context. Women's health research in endometriosis has suffered from underfunding, leading to limitations in diagnosis, classification, and treatment approaches. The heterogeneity of symptoms in patients with endometriosis has further complicated efforts to address this condition. New, powerful methods of analysis have the potential to uncover previously unidentified patterns in data relating to endometriosis. AI, a collection of algorithms replicating human decision-making in data analysis, has been increasingly adopted in medical research, including endometriosis studies. While AI offers the ability to identify novel patterns in data and analyze large datasets, its effectiveness hinges on data quality and quantity and the expertise of those implementing the algorithms. Current applications of AI in endometriosis range from diagnostic tools for ultrasound imaging to predicting treatment success. These applications show promise in reducing diagnostic delays, healthcare costs, and providing patients with more treatment options, improving their quality of life. AI holds significant potential in advancing the diagnosis and treatment of endometriosis, but it must be applied carefully and transparently to avoid pitfalls and ensure reproducibility. This review calls for increased scrutiny and accountability in AI research. Addressing these challenges can lead to more effective AI-driven solutions for endometriosis and other complex medical conditions.

PMID:38686828 | DOI:10.1177/17455057241248121

Otolaryngol Head Neck Surg. 2024 Apr 30. doi: 10.1002/ohn.789. Online ahead of print.

ABSTRACT

OBJECTIVE: Obtaining automated, objective 3-dimensional (3D) models of the Eustachian tube (ET) and the internal carotid artery (ICA) from computed tomography (CT) scans could provide useful navigational and diagnostic information for ET pathologies and interventions. We aim to develop a deep learning (DL) pipeline to automatically segment the ET and ICA and use these segmentations to compute distances between these structures.

STUDY DESIGN: Retrospective cohort.

SETTING: Tertiary referral center.

METHODS: From a database of 30 CT scans, 60 ET and ICA pairs were manually segmented and used to train an nnU-Net model, a DL segmentation framework. These segmentations were also used to develop a quantitative tool to capture the magnitude and location of the minimum distance point (MDP) between ET and ICA. Performance metrics for the nnU-Net automated segmentations were calculated via the average Hausdorff distance (AHD) and dice similarity coefficient (DSC).

RESULTS: The AHD for the ET and ICA were 0.922 and 0.246 mm, respectively. Similarly, the DSC values for the ET and ICA were 0.578 and 0.884. The mean MDP from ET to ICA in the cartilaginous region was 2.6 mm (0.7-5.3 mm) and was located on average 1.9 mm caudal from the bony cartilaginous junction.

CONCLUSION: This study describes the first end-to-end DL pipeline for automated ET and ICA segmentation and analyzes distances between these structures. In addition to helping to ensure the safe selection of patients for ET dilation, this method can facilitate large-scale studies exploring the relationship between ET pathologies and the 3D shape of the ET.

PMID:38686594 | DOI:10.1002/ohn.789

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):413-420. doi: 10.7507/1001-5515.202309079.

ABSTRACT

Pneumoconiosis ranks first among the newly-emerged occupational diseases reported annually in China, and imaging diagnosis is still one of the main clinical diagnostic methods. However, manual reading of films requires high level of doctors, and it is difficult to discriminate the staged diagnosis of pneumoconiosis imaging, and due to the influence of uneven distribution of medical resources and other factors, it is easy to lead to misdiagnosis and omission of diagnosis in primary healthcare institutions. Computer-aided diagnosis system can realize rapid screening of pneumoconiosis in order to assist clinicians in identification and diagnosis, and improve diagnostic efficacy. As an important branch of deep learning, convolutional neural network (CNN) is good at dealing with various visual tasks such as image segmentation, image classification, target detection and so on because of its characteristics of local association and weight sharing, and has been widely used in the field of computer-aided diagnosis of pneumoconiosis in recent years. This paper was categorized into three parts according to the main applications of CNNs (VGG, U-Net, ResNet, DenseNet, CheXNet, Inception-V3, and ShuffleNet) in the imaging diagnosis of pneumoconiosis, including CNNs in pneumoconiosis screening diagnosis, CNNs in staging diagnosis of pneumoconiosis, and CNNs in segmentation of pneumoconiosis foci to conduct a literature review. It aims to summarize the methods, advantages and disadvantages, and optimization ideas of CNN applied to the images of pneumoconiosis, and to provide a reference for the research direction of further development of computer-aided diagnosis of pneumoconiosis.

PMID:38686425 | DOI:10.7507/1001-5515.202309079

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):262-271. doi: 10.7507/1001-5515.202306008.

ABSTRACT

Accurate reconstruction of tissue elasticity modulus distribution has always been an important challenge in ultrasound elastography. Considering that existing deep learning-based supervised reconstruction methods only use simulated displacement data with random noise in training, which cannot fully provide the complexity and diversity brought by in-vivo ultrasound data, this study introduces the use of displacement data obtained by tracking in-vivo ultrasound radio frequency signals (i.e., real displacement data) during training, employing a semi-supervised approach to enhance the prediction accuracy of the model. Experimental results indicate that in phantom experiments, the semi-supervised model augmented with real displacement data provides more accurate predictions, with mean absolute errors and mean relative errors both around 3%, while the corresponding data for the fully supervised model are around 5%. When processing real displacement data, the area of prediction error of semi-supervised model was less than that of fully supervised model. The findings of this study confirm the effectiveness and practicality of the proposed approach, providing new insights for the application of deep learning methods in the reconstruction of elastic distribution from in-vivo ultrasound data.

PMID:38686406 | DOI:10.7507/1001-5515.202306008

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):253-261. doi: 10.7507/1001-5515.202307030.

ABSTRACT

The deep learning-based automatic detection of epilepsy electroencephalogram (EEG), which can avoid the artificial influence, has attracted much attention, and its effectiveness mainly depends on the deep neural network model. In this paper, an attention-based multi-scale residual network (AMSRN) was proposed in consideration of the multiscale, spatio-temporal characteristics of epilepsy EEG and the information flow among channels, and it was combined with multiscale principal component analysis (MSPCA) to realize the automatic epilepsy detection. Firstly, MSPCA was used for noise reduction and feature enhancement of original epilepsy EEG. Then, we designed the structure and parameters of AMSRN. Among them, the attention module (AM), multiscale convolutional module (MCM), spatio-temporal feature extraction module (STFEM) and classification module (CM) were applied successively to signal reexpression with attention weighted mechanism as well as extraction, fusion and classification for multiscale and spatio-temporal features. Based on the Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT) public dataset, the AMSRN model achieved good results in sensitivity (98.56%), F1 score (98.35%), accuracy (98.41%) and precision (98.43%). The results show that AMSRN can make good use of brain network information flow caused by seizures to enhance the difference among channels, and effectively capture the multiscale and spatio-temporal features of EEG to improve the performance of epilepsy detection.

PMID:38686405 | DOI:10.7507/1001-5515.202307030

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):246-252. doi: 10.7507/1001-5515.202304030.

ABSTRACT

Due to the high dimensionality and complexity of the data, the analysis of spatial transcriptome data has been a challenging problem. Meanwhile, cluster analysis is the core issue of the analysis of spatial transcriptome data. In this article, a deep learning approach is proposed based on graph attention networks for clustering analysis of spatial transcriptome data. Our method first enhances the spatial transcriptome data, then uses graph attention networks to extract features from nodes, and finally uses the Leiden algorithm for clustering analysis. Compared with the traditional non-spatial and spatial clustering methods, our method has better performance in data analysis through the clustering evaluation index. The experimental results show that the proposed method can effectively cluster spatial transcriptome data and identify different spatial domains, which provides a new tool for studying spatial transcriptome data.

PMID:38686404 | DOI:10.7507/1001-5515.202304030

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):220-227. doi: 10.7507/1001-5515.202302024.

ABSTRACT

In computer-aided medical diagnosis, obtaining labeled medical image data is expensive, while there is a high demand for model interpretability. However, most deep learning models currently require a large amount of data and lack interpretability. To address these challenges, this paper proposes a novel data augmentation method for medical image segmentation. The uniqueness and advantages of this method lie in the utilization of gradient-weighted class activation mapping to extract data efficient features, which are then fused with the original image. Subsequently, a new channel weight feature extractor is constructed to learn the weights between different channels. This approach achieves non-destructive data augmentation effects, enhancing the model's performance, data efficiency, and interpretability. Applying the method of this paper to the Hyper-Kvasir dataset, the intersection over union (IoU) and Dice of the U-net were improved, respectively; and on the ISIC-Archive dataset, the IoU and Dice of the DeepLabV3+ were also improved respectively. Furthermore, even when the training data is reduced to 70 %, the proposed method can still achieve performance that is 95 % of that achieved with the entire dataset, indicating its good data efficiency. Moreover, the data-efficient features used in the method have interpretable information built-in, which enhances the interpretability of the model. The method has excellent universality, is plug-and-play, applicable to various segmentation methods, and does not require modification of the network structure, thus it is easy to integrate into existing medical image segmentation method, enhancing the convenience of future research and applications.

PMID:38686401 | DOI:10.7507/1001-5515.202302024

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Apr 25;41(2):213-219. doi: 10.7507/1001-5515.202309014.

ABSTRACT

Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.

PMID:38686400 | DOI:10.7507/1001-5515.202309014

Front Neurosci. 2024 Apr 15;18:1333712. doi: 10.3389/fnins.2024.1333712. eCollection 2024.

ABSTRACT

Structural and functional MRI (magnetic resonance imaging) based diagnostic classification using machine learning has long held promise, but there are many roadblocks to achieving their potential. While traditional machine learning models suffered from their inability to capture the complex non-linear mapping, deep learning models tend to overfit the model. This is because there is data scarcity and imbalanced classes in neuroimaging; it is expensive to acquire data from human subjects and even more so in clinical populations. Due to their ability to augment data by learning underlying distributions, generative adversarial networks (GAN) provide a potential solution to this problem. Here, we provide a methodological primer on GANs and review the applications of GANs to classification of mental health disorders from neuroimaging data such as functional MRI and showcase the progress made thus far. We also highlight gaps in methodology as well as interpretability that are yet to be addressed. This provides directions about how the field can move forward. We suggest that since there are a range of methodological choices available to users, it is critical for users to interact with method developers so that the latter can tailor their development according to the users' needs. The field can be enriched by such synthesis between method developers and users in neuroimaging.

PMID:38686334 | PMC:PMC11057233 | DOI:10.3389/fnins.2024.1333712

PeerJ Comput Sci. 2024 Feb 23;10:e1769. doi: 10.7717/peerj-cs.1769. eCollection 2024.

ABSTRACT

Object detection methods based on deep learning have been used in a variety of sectors including banking, healthcare, e-governance, and academia. In recent years, there has been a lot of attention paid to research endeavors made towards text detection and recognition from different scenesor images of unstructured document processing. The article's novelty lies in the detailed discussion and implementation of the various transfer learning-based different backbone architectures for printed text recognition. In this research article, the authors compared the ResNet50, ResNet50V2, ResNet152V2, Inception, Xception, and VGG19 backbone architectures with preprocessing techniques as data resizing, normalization, and noise removal on a standard OCR Kaggle dataset. Further, the top three backbone architectures selected based on the accuracy achieved and then hyper parameter tunning has been performed to achieve more accurate results. Xception performed well compared with the ResNet, Inception, VGG19, MobileNet architectures by achieving high evaluation scores with accuracy (98.90%) and min loss (0.19). As per existing research in this domain, until now, transfer learning-based backbone architectures that have been used on printed or handwritten data recognition are not well represented in literature. We split the total dataset into 80 percent for training and 20 percent for testing purpose and then into different backbone architecture models with the same number of epochs, and found that the Xception architecture achieved higher accuracy than the others. In addition, the ResNet50V2 model gave us higher accuracy (96.92%) than the ResNet152V2 model (96.34%).

PMID:38686011 | PMC:PMC11057569 | DOI:10.7717/peerj-cs.1769

PeerJ Comput Sci. 2024 Apr 23;10:e2005. doi: 10.7717/peerj-cs.2005. eCollection 2024.

ABSTRACT

Training with soft labels instead of hard labels can effectively improve the robustness and generalization of deep learning models. Label smoothing often provides uniformly distributed soft labels during the training process, whereas it does not take the semantic difference of labels into account. This article introduces discrimination-aware label smoothing, an adaptive label smoothing approach that learns appropriate distributions of labels for iterative optimization objectives. In this approach, positive and negative samples are employed to provide experience from both sides, and the performances of regularization and model calibration are improved through an iterative learning method. Experiments on five text classification datasets demonstrate the effectiveness of the proposed method.

PMID:38686010 | PMC:PMC11057568 | DOI:10.7717/peerj-cs.2005

Phys Med Biol. 2024 Apr 29. doi: 10.1088/1361-6560/ad450b. Online ahead of print.

ABSTRACT

Automated biopsy needle segmentation in 3D ultrasound images can be used for biopsy navigation, but it is quite challenging due to the low ultrasound image resolution and interference similar to the needle appearance. For 3D medical image segmentation, such deep learning (DL) networks as convolutional neural network (CNN) and transformer have been investigated. However, these segmentation methods require numerous labeled data for training, have difficulty in meeting the real-time segmentation requirement and involve high memory consumption.
Approach. In this paper, we have proposed the temporal information-based semi-supervised training framework for fast and accurate needle segmentation. Firstly, a novel circle transformer module based on the static and dynamic features has been designed after the encoders for extracting and fusing the temporal information. Then, the consistency constraints of the outputs before and after combining temporal information are proposed to provide the semi-supervision for the unlabeled volume. Finally, the model is trained using the loss function which combines the cross-entropy and Dice similarity coefficient (DSC) based segmentation loss with mean square error based consistency loss. The trained model with the single ultrasound volume input is applied to realize the needle segmentation in ultrasound volume.
Main results. Experimental results on three needle ultrasound datasets acquired during the beagle biopsy show that our approach is superior to the most competitive mainstream temporal segmentation model and semi-supervised method by providing higher DSC (77.1% vs 76.5%), smaller needle tip position (1.28mm vs 1.87mm) and length (1.78mm vs 2.19mm) errors on the kidney dataset as well as DSC (78.5% vs 76.9%), needle tip position (0.86mm vs 1.12mm) and length (1.01mm vs 1.26mm) errors on the prostate dataset.
Significance. The proposed method can significantly enhance needle segmentation accuracy by training with sequential images at no additional cost. This enhancement may further improve the effectiveness of biopsy navigation systems.&#xD.

PMID:38684166 | DOI:10.1088/1361-6560/ad450b

J Neural Eng. 2024 Apr 29. doi: 10.1088/1741-2552/ad44d7. Online ahead of print.

ABSTRACT

OBJECTIVE: The patterns of brain activity associated with different brain processes can be used to identify different brain states and make behavioral predictions. However, the relevant features are not readily apparent and accessible. Our aim is to design a system for learning informative latent representations from multichannel recordings of ongoing EEG activity.

APPROACH: We propose a novel differentiable decoding pipeline consisting of learnable filters and a pre-determined feature extraction module. Specifically, we introduce filters parameterized by generalized Gaussian functions that offer a smooth derivative for stable end-to-end model training and allow for learning interpretable features. For the feature module, we use signal magnitude and functional connectivity estimates.

MAIN RESULTS: We demonstrate the utility of our model on a new EEG dataset of unprecedented size (i.e., 761 subjects), where we identify consistent trends of music perception and related individual differences. Furthermore, we train and apply our model in two additional datasets, specifically for emotion recognition on SEED and workload classification on STEW. The discovered features align well with previous neuroscience studies and offer new insights, such as marked differences in the functional connectivity profile between left and right temporal areas during music listening. This agrees with the specialisation of the temporal lobes regarding music perception proposed in the literature.

SIGNIFICANCE: The proposed method offers strong interpretability of learned features while reaching similar levels of accuracy achieved by black box deep learning models. This improved trustworthiness may promote the use of deep learning models in real world applications. The model code is available at https://github.com/SMLudwig/EEGminer/.

PMID:38684154 | DOI:10.1088/1741-2552/ad44d7

Biomed Phys Eng Express. 2024 Apr 29. doi: 10.1088/2057-1976/ad449a. Online ahead of print.

ABSTRACT

Objectives
Current lung cancer screening protocols primarily evaluate pulmonary nodules, yet often neglect the malignancy risk associated with small nodules (≤10 mm). This study endeavors to optimize the management of pulmonary nodules in this population by devising and externally validating a Multimodal Integrated Feature Neural Network (MIFNN). We hypothesize that the fusion of deep learning algorithms with morphological nodule features will significantly enhance diagnostic accuracy.
Materials and Methods
Data were retrospectively collected from the Lung Nodule Analysis 2016 (LUNA16) dataset and four local centers in Beijing, China. The study includes patients with small pulmonary nodules (≤10 mm). We developed a neural network, termed MIFNN, that synergistically combines computed tomography (CT) images and morphological characteristics of pulmonary nodules. The network is designed to acquire clinically relevant deep learning features, thereby elevating the diagnostic accuracy of existing models. Importantly, the network's simple architecture and use of standard screening variables enable seamless integration into standard lung cancer screening protocols.
Results
In summary, the study analyzed a total of 382 small pulmonary nodules (85 malignant) from the LUNA16 dataset and 101 small pulmonary nodules (33 malignant) obtained from four specialized centers in Beijing, China, for model training and external validation. Both internal and external validation metrics indicate that the MIFNN significantly surpasses extant state-of-the-art models, achieving an internal area under the curve (AUC) of 0.890 (95% CI: 0.848-0.932) and an external AUC of 0.843 (95% CI: 0.784-0.891).
Conclusion
The MIFNN model significantly enhances the diagnostic accuracy of small pulmonary nodules, outperforming existing benchmarks by Zhang et al. with a 6.34% improvement for nodules less than 10 mm. Leveraging advanced integration techniques for imaging and clinical data, MIFNN increases the efficiency of lung cancer screenings and optimizes nodule management, potentially reducing false positives and unnecessary biopsies.

PMID:38684143 | DOI:10.1088/2057-1976/ad449a

BMC Med Imaging. 2024 Apr 29;24(1):100. doi: 10.1186/s12880-024-01283-8.

ABSTRACT

PURPOSE: To detect the Marchiafava Bignami Disease (MBD) using a distinct deep learning technique.

BACKGROUND: Advanced deep learning methods are becoming more crucial in contemporary medical diagnostics, particularly for detecting intricate and uncommon neurological illnesses such as MBD. This rare neurodegenerative disorder, sometimes associated with persistent alcoholism, is characterized by the loss of myelin or tissue death in the corpus callosum. It poses significant diagnostic difficulties owing to its infrequency and the subtle signs it exhibits in its first stages, both clinically and on radiological scans.

METHODS: The novel method of Variational Autoencoders (VAEs) in conjunction with attention mechanisms is used to identify MBD peculiar diseases accurately. VAEs are well-known for their proficiency in unsupervised learning and anomaly detection. They excel at analyzing extensive brain imaging datasets to uncover subtle patterns and abnormalities that traditional diagnostic approaches may overlook, especially those related to specific diseases. The use of attention mechanisms enhances this technique, enabling the model to concentrate on the most crucial elements of the imaging data, similar to the discerning observation of a skilled radiologist. Thus, we utilized the VAE with attention mechanisms in this study to detect MBD. Such a combination enables the prompt identification of MBD and assists in formulating more customized and efficient treatment strategies.

RESULTS: A significant breakthrough in this field is the creation of a VAE equipped with attention mechanisms, which has shown outstanding performance by achieving accuracy rates of over 90% in accurately differentiating MBD from other neurodegenerative disorders.

CONCLUSION: This model, which underwent training using a diverse range of MRI images, has shown a notable level of sensitivity and specificity, significantly minimizing the frequency of false positive results and strengthening the confidence and dependability of these sophisticated automated diagnostic tools.

PMID:38684964 | DOI:10.1186/s12880-024-01283-8

Sci Rep. 2024 Apr 29;14(1):9791. doi: 10.1038/s41598-024-60675-6.

ABSTRACT

In air traffic control (ATC), Key Information Recognition (KIR) of ATC instructions plays a pivotal role in automation. The field's specialized nature has led to a scarcity of related research and a gap with the industry's cutting-edge developments. Addressing this, an innovative end-to-end deep learning framework, Small Sample Learning for Key Information Recognition (SLKIR), is introduced for enhancing KIR in ATC instructions. SLKIR incorporates a novel Multi-Head Local Lexical Association Attention (MHLA) mechanism, specifically designed to enhance accuracy in identifying boundary words of key information by capturing their latent representations. Furthermore, the framework includes a task focused on prompt, aiming to bolster the semantic comprehension of ATC instructions within the core network. To overcome the challenges posed by category imbalance in boundary word and prompt discrimination tasks, tailored loss function optimization strategies are implemented, effectively expediting the learning process and boosting recognition accuracy. The framework's efficacy and adaptability are demonstrated through experiments on two distinct ATC instruction datasets. Notably, SLKIR outperforms the leading baseline model, W2NER, achieving a 3.65% increase in F1 score on the commercial flight dataset and a 12.8% increase on the training flight dataset. This study is the first of its kind to apply small-sample learning in KIR for ATC and the source code of SLKIR will be available at: https://github.com/PANPANKK/ATC_KIR .

PMID:38684909 | DOI:10.1038/s41598-024-60675-6

Sci Rep. 2024 Apr 29;14(1):9784. doi: 10.1038/s41598-024-60668-5.

ABSTRACT

Accurate multi-organ segmentation in 3D CT images is imperative for enhancing computer-aided diagnosis and radiotherapy planning. However, current deep learning-based methods for 3D multi-organ segmentation face challenges such as the need for labor-intensive manual pixel-level annotations and high hardware resource demands, especially regarding GPU resources. To address these issues, we propose a 3D proxy-bridged region-growing framework specifically designed for the segmentation of the liver and spleen. Specifically, a key slice is selected from each 3D volume according to the corresponding intensity histogram. Subsequently, a deep learning model is employed to pinpoint the semantic central patch on this key slice, to calculate the growing seed. To counteract the impact of noise, segmentation of the liver and spleen is conducted on superpixel images created through proxy-bridging strategy. The segmentation process is then extended to adjacent slices by applying the same methodology iteratively, culminating in the comprehensive segmentation results. Experimental results demonstrate that the proposed framework accomplishes segmentation of the liver and spleen with an average Dice Similarity Coefficient of approximately 0.93 and a Jaccard Similarity Coefficient of around 0.88. These outcomes substantiate the framework's capability to achieve performance on par with that of deep learning methods, albeit requiring less guidance information and lower GPU resources.

PMID:38684904 | DOI:10.1038/s41598-024-60668-5

Sci Rep. 2024 Apr 29;14(1):9796. doi: 10.1038/s41598-024-60249-6.

ABSTRACT

Preclinical management of patients with acute chest pain and their identification as candidates for urgent coronary revascularization without the use of high sensitivity troponin essays remains a critical challenge in emergency medicine. We enrolled 2760 patients (average age 70 years, 58.6% male) with chest pain and suspected ACS, who were admitted to the Emergency Department of the University Hospital Tübingen, Germany, between August 2016 and October 2020. Using 26 features, eight Machine learning models (non-deep learning models) were trained with data from the preclinical rescue protocol and compared to the "TropOut" score (a modified version of the "preHEART" score which consists of history, ECG, age and cardiac risk but without troponin analysis) to predict major adverse cardiac event (MACE) and acute coronary artery occlusion (ACAO). In our study population MACE occurred in 823 (29.8%) patients and ACAO occurred in 480 patients (17.4%). Interestingly, we found that all machine learning models outperformed the "TropOut" score. The VC and the LR models showed the highest area under the receiver operating characteristic (AUROC) for predicting MACE (AUROC = 0.78) and the VC showed the highest AUROC for predicting ACAO (AUROC = 0.81). A SHapley Additive exPlanations (SHAP) analyses based on the XGB model showed that presence of ST-elevations in the electrocardiogram (ECG) were the most important features to predict both endpoints.

PMID:38684774 | DOI:10.1038/s41598-024-60249-6