Neuroinformatics. 2024 Oct 18. doi: 10.1007/s12021-024-09685-3. Online ahead of print.

ABSTRACT

Attention Deficit Hyperactivity Disorder (ADHD) is a widespread neurobehavioral disorder affecting children and adolescents, requiring early detection for effective treatment. EEG connectivity measures can reveal the interdependencies between EEG recordings, highlighting brain network patterns and functional behavior that improve diagnostic accuracy. This study introduces a novel ADHD diagnostic method by combining linear and nonlinear brain connectivity maps with an attention-based convolutional neural network (Att-CNN). Pearson Correlation Coefficient (PCC) and Phase-Locking Value (PLV) are used to create fused connectivity maps (FCMs) from various EEG frequency subbands, which are then inputted into the Att-CNN. The attention module is strategically placed after the latest convolutional layer in the CNN. The performance of different optimizers (Adam and SGD) and learning rates are assessed. The suggested model obtained 98.88%, 98.41%, 98.19%, and 98.30% for accuracy, precision, recall, and F1 Score, respectively, using the SGD optimizer in the FCM of the theta band with a learning rate of 1e-1. With the use of FCM, Att-CNN, and advanced optimizers, the proposed technique has the potential to produce trustworthy instruments for the early diagnosis of ADHD, greatly enhancing both patient outcomes and diagnostic accuracy.

PMID:39422820 | DOI:10.1007/s12021-024-09685-3

J Cancer Res Clin Oncol. 2024 Oct 18;150(10):467. doi: 10.1007/s00432-024-05992-z.

ABSTRACT

BACKGROUND: The advancements in artificial intelligence (AI) technology for image recognition were propelling molecular pathology research into a new era.

OBJECTIVE: To summarize the hot spots and research trends in the field of molecular pathology image recognition.

METHODS: Relevant articles from January 1st, 2010, to August 25th, 2023, were retrieved from the Web of Science Core Collection. Subsequently, CiteSpace was employed for bibliometric and visual analysis, generating diverse network diagrams illustrating keywords, highly cited references, hot topics, and research trends.

RESULTS: A total of 110 relevant articles were extracted from a pool of 10,205 articles. The overall publication count exhibited a rising trend each year. The leading contributors in terms of institutions, countries, and authors were Maastricht University (11 articles), the United States (38 articles), and Kather Jacob Nicholas (9 articles), respectively. Half of the top ten research institutions, based on publication volume, were affiliated with Germany. The most frequently cited article was authored by Nicolas Coudray et al. accumulating 703 citations. The keyword "Deep learning" had the highest frequency in 2019. Notably, the highlighted keywords from 2022 to 2023 included "microsatellite instability", and there were 21 articles focusing on utilizing algorithms to recognize microsatellite instability (MSI) in colorectal cancer (CRC) pathological images.

CONCLUSION: The use of DL is expected to provide a new strategy to effectively solve the current problem of time-consuming and expensive molecular pathology detection. Therefore, further research is needed to address issues, such as data quality and standardization, model interpretability, and resource and infrastructure requirements.

PMID:39422817 | DOI:10.1007/s00432-024-05992-z

Sci China Life Sci. 2024 Oct 12. doi: 10.1007/s11427-023-2618-y. Online ahead of print.

ABSTRACT

The concept of synthetic lethality (SL) has been successfully used for targeted therapies. To further explore SL for cancer therapy, identifying more SL interactions with therapeutic potential are essential. Recently, graph neural network-based deep learning methods have been proposed for SL prediction, which reduce the SL search space of wet-lab based methods. However, these methods ignore that most SL interactions depend strongly on genetic context, which limits the application of the predicted results. In this study, we proposed a graph recurrent network-based model for specific context-dependent SL prediction (SLGRN). In particular, we introduced a Graph Recurrent Network-based encoder to acquire a context-specific, low-dimensional feature representation for each node, facilitating the prediction of novel SL. SLGRN leveraged gate recurrent unit (GRU) and it incorporated a context-dependent-level state to effectively integrate information from all nodes. As a result, SLGRN outperforms the state-of-the-arts models for SL prediction. We subsequently validate novel SL interactions under different contexts based on combination therapy or patient survival analysis. Through in vitro experiments and retrospective clinical analysis, we emphasize the potential clinical significance of this context-specific SL prediction model.

PMID:39422810 | DOI:10.1007/s11427-023-2618-y

Mol Divers. 2024 Oct 18. doi: 10.1007/s11030-024-11006-4. Online ahead of print.

ABSTRACT

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying highly potent umami tastants from large molecular databases. We curated the most extensive classification dataset containing 439 umami and 428 non-umami molecules and trained a transformer-based architecture to differentiate between the two classes, achieving 93% accuracy. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. The classification and potency prediction models were combined with similarity analysis and toxicity screening to build an end-to-end virtual framework for the rational discovery of novel tastants. We applied this framework to the FooDB database containing around 70,000 molecules as an illustrative use case for screening potent umami compounds. The screened molecules were validated using molecular docking with the umami taste receptor. This study demonstrates the potential of data-driven methods in discovering new tastants from structural and chemical features of molecules and proposes an efficient implementation for industrial applications.

PMID:39422798 | DOI:10.1007/s11030-024-11006-4

Eur Radiol. 2024 Oct 18. doi: 10.1007/s00330-024-11105-8. Online ahead of print.

ABSTRACT

OBJECTIVES: Despite showing encouraging outcomes, the precision of deep learning (DL) models using different convolutional neural networks (CNNs) for diagnosis remains under investigation. This systematic review aims to summarise the status of DL MRI models developed for assisting the diagnosis of a variety of knee abnormalities.

MATERIALS AND METHODS: Five databases were systematically searched, employing predefined terms such as 'Knee AND 3D AND MRI AND DL'. Selected inclusion criteria were used to screen publications by title, abstract, and full text. The synthesis of results was performed by two independent reviewers.

RESULTS: Fifty-four articles were included. The studies focused on anterior cruciate ligament injuries (n = 19, 36%), osteoarthritis (n = 9, 17%), meniscal injuries (n = 13, 24%), abnormal knee appearance (n = 11, 20%), and other (n = 2, 4%). The DL models in this review primarily used the following CNNs: ResNet (n = 11, 21%), VGG (n = 6, 11%), DenseNet (n = 4, 8%), and DarkNet (n = 3, 6%). DL models showed high-performance metrics compared to ground truth. DL models for the detection of a specific injury outperformed those by up to 4.5% for general abnormality detection.

CONCLUSION: Despite the varied study designs used among the reviewed articles, DL models showed promising outcomes in the assisted detection of selected knee pathologies by MRI. This review underscores the importance of validating these models with larger MRI datasets to close the existing gap between current DL model performance and clinical requirements.

KEY POINTS: Question What is the status of DL model availability for knee pathology detection in MRI and their clinical potential? Findings Pathology-specific DL models reported higher accuracy compared to DL models for the detection of general abnormalities of the knee. DL model performance was mainly influenced by the quantity and diversity of data available for model training. Clinical relevance These findings should encourage future developments to improve patient care, support personalised diagnosis and treatment, optimise costs, and advance artificial intelligence-based medical imaging practices.

PMID:39422725 | DOI:10.1007/s00330-024-11105-8

Adv Sci (Weinh). 2024 Oct 18:e2406183. doi: 10.1002/advs.202406183. Online ahead of print.

ABSTRACT

The spectral properties are the most prevalent continuous representation for characterizing transport phenomena and excitation responses, yet their accurate predictions remain a challenge due to the inability to perceive series correlations by existing machine learning (ML) models. Herein, a ML model named cluster-based series graph networks (CSGN) is developed based on the dynamical theory of crystal lattices to predict phonon density of states (PDOS) spectrum for crystal materials. The multiple atomic cluster representation is constructed to capture the diverse vibration modes, while the mixture Gaussian process and dynamic time warping mechanism are compiled to project from clusters to PDOS spectrum. Accurate predictions of complicated spectra with multiple or overlapping peaks are achieved. The high performance of CSGN model can be attributed to the pertinent feature extraction and the appropriate similarity evaluation, which enable the natural perception of structure-property relation and intrinsic series correlations as confirmed in the predictive results. The transferable and interpretable CSGN model advances ML predictions of spectral properties and reveals the potential of designing ML methods based on physical mechanisms.

PMID:39422637 | DOI:10.1002/advs.202406183

J Dent Res. 2024 Oct 18:220345241272052. doi: 10.1177/00220345241272052. Online ahead of print.

ABSTRACT

The development of artificial intelligence (AI) in dentistry requires large and well-annotated datasets. However, the availability of public dental imaging datasets remains unclear. This study aimed to provide a comprehensive overview of all publicly available dental imaging datasets to address this gap and support AI development. This observational study searched all publicly available dataset resources (academic databases, preprints, and AI challenges), focusing on datasets/articles from 2020 to 2023, with PubMed searches extending back to 2011. We comprehensively searched for dental AI datasets containing images (intraoral photos, scans, radiographs, etc.) using relevant keywords. We included datasets of >50 images obtained from publicly available sources. We extracted dataset characteristics, patient demographics, country of origin, dataset size, ethical clearance, image details, FAIRness metrics, and metadata completeness. We screened 131,028 records and extracted 16 unique dental imaging datasets. The datasets were obtained from Kaggle (18.8%), GitHub, Google, Mendeley, PubMed, Zenodo (each 12.5%), Grand-Challenge, OSF, and arXiv (each 6.25%). The primary focus was tooth segmentation (62.5%) and labeling (56.2%). Panoramic radiography was the most common imaging modality (58.8%). Of the 13 countries, China contributed the most images (2,413). Of the datasets, 75% contained annotations, whereas the methods used to establish labels were often unclear and inconsistent. Only 31.2% of the datasets reported ethical approval, and 56.25% did not specify a license. Most data were obtained from dental clinics (50%). Intraoral radiographs had the highest findability score in the FAIR assessment, whereas cone-beam computed tomography datasets scored the lowest in all categories. These findings revealed a scarcity of publicly available imaging dental data and inconsistent metadata reporting. To promote the development of robust, equitable, and generalizable AI tools for dental diagnostics, treatment, and research, efforts are needed to address data scarcity, increase diversity, mandate metadata completeness, and ensure FAIRness in AI dental imaging research.

PMID:39422586 | DOI:10.1177/00220345241272052

Mol Inform. 2024 Oct 18:e202400169. doi: 10.1002/minf.202400169. Online ahead of print.

ABSTRACT

In silico methods for prediction of chemical toxicity can decrease the cost and increase the efficiency in the early stage of drug discovery. However, due to low accessibility of sufficient and reliable toxicity data, constructing robust and accurate prediction models is challenging. Contrastive learning, a type of self-supervised learning, leverages large unlabeled data to obtain more expressive molecular representations, which can boost the prediction performance on downstream tasks. While molecular graph contrastive learning has gathered growing attentions, current models neglect the quality of negative data set. Here, we proposed a self-supervised pretraining deep learning framework named GCLmf. We first utilized molecular fragments that meet specific conditions as hard negative samples to boost the quality of the negative set and thus increase the difficulty of the proxy tasks during pre-training to learn informative representations. GCLmf has shown excellent predictive power on various molecular property benchmarks and demonstrates high performance in 33 toxicity tasks in comparison with multiple baselines. In addition, we further investigated the necessity of introducing hard negatives in model building and the impact of the proportion of hard negatives on the model.

PMID:39421969 | DOI:10.1002/minf.202400169

Biomed Opt Express. 2024 Sep 6;15(10):5723-5738. doi: 10.1364/BOE.529662. eCollection 2024 Oct 1.

ABSTRACT

Optical coherence tomography (OCT) can be an important tool for non-invasive dermatological evaluation, providing useful data on epidermal integrity for diagnosing skin diseases. Despite its benefits, OCT's utility is limited by the challenges of accurate, fast epidermal segmentation due to the skin morphological diversity. To address this, we introduce a lightweight segmentation network (LS-Net), a novel deep learning model that combines the robust local feature extraction abilities of Convolution Neural Network and the long-term information processing capabilities of Vision Transformer. LS-Net has a depth-wise convolutional transformer for enhanced spatial contextualization and a squeeze-and-excitation block for feature recalibration, ensuring precise segmentation while maintaining computational efficiency. Our network outperforms existing methods, demonstrating high segmentation accuracy (mean Dice: 0.9624 and mean IoU: 0.9468) with significantly reduced computational demands (floating point operations: 1.131 G). We further validate LS-Net on our acquired dataset, showing its effectiveness in various skin sites (e.g., face, palm) under realistic clinical conditions. This model promises to enhance the diagnostic capabilities of OCT, making it a valuable tool for dermatological practice.

PMID:39421780 | PMC:PMC11482159 | DOI:10.1364/BOE.529662

Biomed Opt Express. 2024 Sep 23;15(10):5980-5998. doi: 10.1364/BOE.527972. eCollection 2024 Oct 1.

ABSTRACT

Dysregulation of lung tissue collagen level plays a vital role in understanding how lung diseases progress. However, traditional scoring methods rely on manual histopathological examination introducing subjectivity and inconsistency into the assessment process. These methods are further hampered by inter-observer variability, lack of quantification, and their time-consuming nature. To mitigate these drawbacks, we propose a machine learning-driven framework for automated scoring of lung collagen content. Our study begins with the collection of a lung slide image dataset from adult female mice using second harmonic generation (SHG) microscopy. In our proposed approach, first, we manually extracted features based on the 46 statistical parameters of fibrillar collagen. Subsequently, we pre-processed the images and utilized a pre-trained VGG16 model to uncover hidden features from pre-processed images. We then combined both image and statistical features to train various machine learning and deep neural network models for classification tasks. We employed advanced unsupervised techniques like K-means, principal component analysis (PCA), t-distributed stochastic neighbour embedding (t-SNE), and uniform manifold approximation and projection (UMAP) to conduct thorough image analysis for lung collagen content. Also, the evaluation of the trained models using the collagen data includes both binary and multi-label classification to predict lung cancer in a urethane-induced mouse model. Experimental validation of our proposed approach demonstrates promising results. We obtained an average accuracy of 83% and an area under the receiver operating characteristic curve (ROC AUC) values of 0.96 through the use of a support vector machine (SVM) model for binary categorization tasks. For multi-label classification tasks, to quantify the structural alteration of collagen, we attained an average accuracy of 73% and ROC AUC values of 1.0, 0.38, 0.95, and 0.86 for control, baseline, treatment_1, and treatment_2 groups, respectively. Our findings provide significant potential for enhancing diagnostic accuracy, understanding disease mechanisms, and improving clinical practice using machine learning and deep learning models.

PMID:39421774 | PMC:PMC11482176 | DOI:10.1364/BOE.527972

Biomed Opt Express. 2024 Sep 3;15(10):5592-5608. doi: 10.1364/BOE.525928. eCollection 2024 Oct 1.

ABSTRACT

Skin microvasculature is essential for cardiovascular health and thermoregulation in humans, yet its imaging and analysis pose significant challenges. Established methods, such as speckle decorrelation applied to optical coherence tomography (OCT) B-scans for OCT-angiography (OCTA), often require a high number of B-scans, leading to long acquisition times that are prone to motion artifacts. In our study, we propose a novel approach integrating a deep learning algorithm within our OCTA processing. By integrating a convolutional neural network with a squeeze-and-excitation block, we address these challenges in microvascular imaging. Our method enhances accuracy and reduces measurement time by efficiently utilizing local information. The Squeeze-and-Excitation block further improves stability and accuracy by dynamically recalibrating features, highlighting the advantages of deep learning in this domain.

PMID:39421773 | PMC:PMC11482165 | DOI:10.1364/BOE.525928

F1000Res. 2024 Oct 7;13:524. doi: 10.12688/f1000research.148008.2. eCollection 2024.

ABSTRACT

BACKGROUND: To gauge the impact of an interventional workshop conducted to measure the observation skills of 34 postgraduates during induction into an ophthalmology fellowship.

METHODS: A seven-hour workshop was conducted with the ophthalmology trainees. Trainees from the 2022 batch of ophthalmology fellowships (21 females and 13 males) were included in the study. The pre-workshop assessment comprised two non-clinical images to spot the difference and five clinical images from various subspecialties of ophthalmology. This was followed by workshop and Post workshop assessment. The pre- and post-observation grades of participants were then compared by masked ophthalmologists. The Wilcoxon signed-rank test was used to compare scores at two time points, with a p-value < 0.05 for statistical significance.

RESULTS: Statistical analysis revealed that the observation skill score was significantly higher after the workshop intervention (M d = 4.00, n = 34) compared to the pre-workshop score (M d = 1.85, n = 34), p-value = 0.000.

CONCLUSIONS: Workshops on specific/selected foundational skills, such as observation skills and communication skills, must be integrated into the curricula of basic medical degree and specialty medicine to equip medical professionals with attentive observation and deep learning.

PMID:39421757 | PMC:PMC11484534 | DOI:10.12688/f1000research.148008.2

Cancer Inform. 2024 Oct 16;23:11769351241289719. doi: 10.1177/11769351241289719. eCollection 2024.

ABSTRACT

OBJECTIVES: Patients with intermediate or advanced hepatocellular carcinoma (HCC) require repeated disease monitoring, prognosis assessment and treatment planning. In 2018, a novel machine learning methodology "survival path" (SP) was developed to facilitate dynamic prognosis prediction and treatment planning. One year after, a deep learning approach called Dynamic Deephit was developed. The performance of the two state-of-art models in dynamic prognostication have not been compared.

METHODS: We trained and tested the SP and Dynamic DeepHit models in a large cohort of 2511 HCC patients using time-series data. The time-series data were converted into data of time slices, with an interval of three months. The time-dependent c-index for OS at given prediction time (t = 1, 6, 12, 18 months) and evaluation time (∆t = 3, 6, 9, 12, 18, 24, 36, 48 months) were compared.

RESULTS: The comparison between SP model and Dynamic DeepHit-HCC model showed the latter had significant better performance at the time of initial admission. The time-dependent c-index of Dynamic DeepHit-HCC model gradually decreased with the extension of time (from 0.756 to 0.639 in the training set; from 0.787 to 0.661 in internal testing set; from 0.725 to 0.668 in multicenter testing set); while the time-dependent c-index of SP model displayed an increased trend (from 0.665 to 0.748 in the training set; from 0.608 to 0.743 in internal testing set; from 0.643 to 0.720 in multicenter testing set). When the prediction time comes to 6 months or later since initial treatment, the survival path model outperformed the dynamic DeepHit model at late evaluation times (∆t > 12 months).

CONCLUSIONS: This research highlighted the unique strengths of both models. The SP model had advantage in long term prediction while the Dynamic DeepHit-HCC model had advantages in prediction at near time points. Fine selection of models is needed in dealing with different scenarios.

PMID:39421722 | PMC:PMC11483769 | DOI:10.1177/11769351241289719

Front Microbiol. 2024 Oct 3;15:1483052. doi: 10.3389/fmicb.2024.1483052. eCollection 2024.

ABSTRACT

INTRODUCTION: Fast, accurate, and automatic analysis of histopathological images using digital image processing and deep learning technology is a necessary task. Conventional histopathological image analysis algorithms require the manual design of features, while deep learning methods can achieve fast prediction and accurate analysis, but rely on the drive of a large amount of labeled data.

METHODS: In this work, we introduce WSSS-CRAM a weakly-supervised semantic segmentation that can obtain detailed pixel-level labels from image-level annotated data. Specifically, we use a discriminative activation strategy to generate category-specific image activation maps via class labels. The category-specific activation maps are then post-processed using conditional random fields to obtain reliable regions that are directly used as ground-truth labels for the segmentation branch. Critically, the two steps of the pseudo-label acquisition and training segmentation model are integrated into an end-to-end model for joint training in this method.

RESULTS: Through quantitative evaluation and visualization results, we demonstrate that the framework can predict pixel-level labels from image-level labels, and also perform well when testing images without image-level annotations.

DISCUSSION: Future, we consider extending the algorithm to different pathological datasets and types of tissue images to validate its generalization capability.

PMID:39421560 | PMC:PMC11484024 | DOI:10.3389/fmicb.2024.1483052

Front Surg. 2024 Oct 3;11:1441346. doi: 10.3389/fsurg.2024.1441346. eCollection 2024.

ABSTRACT

BACKGROUND: Surgical approaches that access the posterior temporal bone require careful drilling motions to achieve adequate exposure while avoiding injury to critical structures.

OBJECTIVE: We assessed a deep learning hand motion detector to potentially refine hand motion and precision during power drill use in a cadaveric mastoidectomy procedure.

METHODS: A deep-learning hand motion detector tracked the movement of a surgeon's hands during three cadaveric mastoidectomy procedures. The model provided horizontal and vertical coordinates of 21 landmarks on both hands, which were used to create vertical and horizontal plane tracking plots. Preliminary surgical performance metrics were calculated from the motion detections.

RESULTS: 1,948,837 landmark detections were collected, with an overall 85.9% performance. There was similar detection of the dominant hand (48.2%) compared to the non-dominant hand (51.7%). A loss of tracking occurred due to the increased brightness caused by the microscope light at the center of the field and by movements of the hand outside the field of view of the camera. The mean (SD) time spent (seconds) during instrument changes was 21.5 (12.4) and 4.4 (5.7) during adjustments of the microscope.

CONCLUSION: A deep-learning hand motion detector can measure surgical motion without physical sensors attached to the hands during mastoidectomy simulations on cadavers. While preliminary metrics were developed to assess hand motion during mastoidectomy, further studies are needed to expand and validate these metrics for potential use in guiding and evaluating surgical training.

PMID:39421406 | PMC:PMC11484057 | DOI:10.3389/fsurg.2024.1441346

Ophthalmol Sci. 2024 Aug 30;5(1):100613. doi: 10.1016/j.xops.2024.100613. eCollection 2025 Jan-Feb.

ABSTRACT

PURPOSE: To develop and validate a deep learning algorithm capable of differentiating small choroidal melanomas from nevi.

DESIGN: Retrospective multicenter cohort study.

PARTICIPANTS: A total of 802 images from 688 patients diagnosed with choroidal nevi or melanoma.

METHODS: Wide field and standard field fundus photographs were collected from patients diagnosed with choroidal nevi or melanoma by ocular oncologists during clinical examinations. A lesion was classified as a nevus if it was followed for at least 5 years without being rediagnosed as melanoma. A neural network optimized for image classification was trained and validated on cohorts of 495 and 168 images and subsequently tested on independent sets of 86 and 53 images.

MAIN OUTCOME MEASURES: Area under the curve (AUC) in receiver operating characteristic analysis for differentiating small choroidal melanomas from nevi.

RESULTS: The algorithm achieved an AUC of 0.88 in both test cohorts, outperforming ophthalmologists using the Mushroom shape, Orange pigment, Large size, Enlargement, and Subretinal fluid (AUC 0.77) and To Find Small Ocular Melanoma Using Helpful Hints Daily (AUC 0.67) risk factors (DeLong's test, P < 0.001). The algorithm performed equally well for wide field and standard field photos (AUC 0.89 for both when analyzed separately). Using an optimal operating point of 0.63 (on a scale from 0.00 to 1.00) determined from the training and validation datasets, the algorithm achieved 100% sensitivity and 74% specificity in the first test cohort (F-score 0.72), and 80% sensitivity and 81% specificity in the second (F-score 0.71), which consisted of images from external clinics nationwide. It outperformed 12 ophthalmologists in sensitivity (Mann-Whitney U, P = 0.006) but not specificity (P = 0.54). The algorithm showed higher sensitivity than both resident and consultant ophthalmologists (Dunn's test, P = 0.04 and P = 0.006, respectively) but not ocular oncologists (P > 0.99, all P values Bonferroni corrected).

CONCLUSIONS: This study develops and validates a deep learning algorithm for differentiating small choroidal melanomas from nevi, matching or surpassing the discriminatory performance of experienced human ophthalmologists. Further research will aim to validate its utility in clinical settings.

FINANCIAL DISCLOSURES: Financial DisclosuresProprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PMID:39421390 | PMC:PMC11483474 | DOI:10.1016/j.xops.2024.100613

Heliyon. 2024 Sep 30;10(19):e38515. doi: 10.1016/j.heliyon.2024.e38515. eCollection 2024 Oct 15.

ABSTRACT

Feature extraction plays a critical role in text classification, as it converts textual data into numerical representations suitable for machine learning models. A key challenge lies in effectively capturing both semantic and contextual information from text at various levels of granularity while avoiding overfitting. Prior methods have often demonstrated suboptimal performance, largely due to the limitations of the feature extraction techniques employed. To address these challenges, this study introduces Multi-TextCNN, an advanced feature extractor designed to capture essential textual information across multiple levels of granularity. Multi-TextCNN is integrated into a proposed classification model named MuTCELM, which aims to enhance text classification performance. The proposed MuTCELM leverages five distinct sub-classifiers, each designed to capture different linguistic features from the text data. These sub-classifiers are integrated into an ensemble framework, enhancing the overall model performance by combining their complementary strengths. Empirical results indicate that MuTCELM achieves average improvements across all datasets in accuracy, precision, recall, and F1-macro scores by 0.2584, 0.2546, 0.2668, and 0.2612, respectively, demonstrating significant performance gains over baseline models. These findings underscore the effectiveness of Multi-TextCNN in improving model performance relative to other ensemble methods. Further analysis reveals that the non-overlapping confidence intervals between MuTCELM and baseline models indicate statistically significant differences, suggesting that the observed performance improvements of MuTCELM are not attributable to random chance but are indeed statistically meaningful. This evidence indicates the robustness and superiority of MuTCELM across various languages and text classification tasks.

PMID:39421375 | PMC:PMC11483334 | DOI:10.1016/j.heliyon.2024.e38515

BMC Cardiovasc Disord. 2024 Oct 17;24(1):571. doi: 10.1186/s12872-024-04250-x.

ABSTRACT

BACKGROUND: Late gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMR) is a valuable cardiovascular imaging technique. Segmentation of cardiac chambers from LGE-CMR is a fundamental step in electrophysiological modeling and cardiovascular disease diagnosis. Deep learning methods have demonstrated extremely promising performance. However, excellent performance often depended on a large amount of finely annotated data. The purpose of this manuscript was to develop a semi-supervised segmentation method to use unlabeled data to improve model performance.

METHODS: This manuscript proposed a semi-supervised network that integrates triple-consistency constraints (data-level, task-level, and feature-level) for cardiac chambers segmentation from LGE-CMR. Specifically, we designed a network that integrated segmentation and edge prediction tasks based on the mean teacher architecture. This addressed the problem of ignoring some challenging regions because of excluding low-confidence regions of previous research. We also applied a voxel-level contrastive learning strategy to achieve feature-level consistency, helping the model pay attention to the consistency between features overlooked in previous research.

RESULTS: In terms of the Dice, Jaccard, Average Surface Distance (ASD), and 95% Hausdorff Distance (95HD) metrics, for the atrial segmentation dataset, the proposed method achieved scores of 88.34%, 79.30%, 7.92, and 2.02 when trained with 10% labeled data, and 90.70%, 83.09%, 6.41, and 1.72 when trained with 20% labeled data. For the ventricular segmentation task, the results were 87.22%, 77.95%, 2.27, and 0.61 with 10% labeled data, and 88.99%, 80.45%, 1.87, and 0.51 with 20% labeled data, respectively.

CONCLUSION: Experiments demonstrated that our method outperforms previous semi-supervised methods, showing the potential of the proposed network for semi-supervised segmentation problems.

PMID:39420256 | DOI:10.1186/s12872-024-04250-x

Sci Rep. 2024 Oct 17;14(1):24406. doi: 10.1038/s41598-024-75112-x.

ABSTRACT

A new method was proposed to address fault diagnosis by applying the digital twin (DT) high-fidelity behavior and the deep learning (DL) data mining capabilities. Subsequently, the proposed fault distribution GAN (FDGAN) was built to map virtual and physical entities for the data from the established test platform. Finally, the MobileViG was employed to validate the model and diagnose faults. The accuracy of the proposed method with training samples of 600 and 800 were 88.4% and 99.5%, respectively. These accuracies surpass those of other methods based on CycleGAN (98.86%), CACGAN (94.92%), ACGAN (86.45%), ML1D-GAN (82.33%), and transfer learning (99.38%). Therefore, with the integration of global connectivity, an innovative network structure, and training methods, FDGAN can effectively address challenges such as network degradation, limited feature extraction in small windows, and insufficient model robustness.

PMID:39420213 | DOI:10.1038/s41598-024-75112-x

Commun Med (Lond). 2024 Oct 17;4(1):203. doi: 10.1038/s43856-024-00634-4.

ABSTRACT

BACKGROUND: In the era of personalized cancer treatment, understanding the intrinsic heterogeneity of tumors is crucial. Despite some patients responding favorably to a particular treatment, others may not benefit, leading to the varied efficacy observed in standard therapies. This study focuses on the prediction of tumor response to chemo-immunotherapy, exploring the potential of tumor mechanics and medical imaging as predictive biomarkers. We have extensively studied "desmoplastic" tumors, characterized by a dense and very stiff stroma, which presents a substantial challenge for treatment. The increased stiffness of such tumors can be restored through pharmacological intervention with mechanotherapeutics.

METHODS: We developed a deep learning methodology based on shear wave elastography (SWE) images, which involved a convolutional neural network (CNN) model enhanced with attention modules. The model was developed and evaluated as a predictive biomarker in the setting of detecting responsive, stable, and non-responsive tumors to chemotherapy, immunotherapy, or the combination, following mechanotherapeutics administration. A dataset of 1365 SWE images was obtained from 630 tumors from our previous experiments and used to train and successfully evaluate our methodology. SWE in combination with deep learning models, has demonstrated promising results in disease diagnosis and tumor classification but their potential for predicting tumor response prior to therapy is not yet fully realized.

RESULTS: We present strong evidence that integrating SWE-derived biomarkers with automatic tumor segmentation algorithms enables accurate tumor detection and prediction of therapeutic outcomes.

CONCLUSIONS: This approach can enhance personalized cancer treatment by providing non-invasive, reliable predictions of therapeutic outcomes.

PMID:39420199 | DOI:10.1038/s43856-024-00634-4