Heliyon. 2024 Nov 26;10(23):e40689. doi: 10.1016/j.heliyon.2024.e40689. eCollection 2024 Dec 15.

ABSTRACT

[This corrects the article DOI: 10.1016/j.heliyon.2024.e31730.].

PMID:39759858 | PMC:PMC11700673 | DOI:10.1016/j.heliyon.2024.e40689

Front Neuroinform. 2024 Dec 20;18:1459970. doi: 10.3389/fninf.2024.1459970. eCollection 2024.

ABSTRACT

INTRODUCTION: Modeling multi-channel electroencephalographic (EEG) time-series is a challenging tasks, even for the most recent deep learning approaches. Particularly, in this work, we targeted our efforts to the high-fidelity reconstruction of this type of data, as this is of key relevance for several applications such as classification, anomaly detection, automatic labeling, and brain-computer interfaces.

METHODS: We analyzed the most recent works finding that high-fidelity reconstruction is seriously challenged by the complex dynamics of the EEG signals and the large inter-subject variability. So far, previous works provided good results in either high-fidelity reconstruction of single-channel signals, or poor-quality reconstruction of multi-channel datasets. Therefore, in this paper, we present a novel deep learning model, called hvEEGNet, designed as a hierarchical variational autoencoder and trained with a new loss function. We tested it on the benchmark Dataset 2a (including 22-channel EEG data from 9 subjects).

RESULTS: We show that it is able to reconstruct all EEG channels with high-fidelity, fastly (in a few tens of epochs), and with high consistency across different subjects. We also investigated the relationship between reconstruction fidelity and the training duration and, using hvEEGNet as an anomaly detector, we spotted some data in the benchmark dataset that are corrupted and never highlighted before.

DISCUSSION: Thus, hvEEGNet could be very useful in several applications where automatic labeling of large EEG dataset is needed and time-consuming. At the same time, this work opens new fundamental research questions about (1) the effectiveness of deep learning models training (for EEG data) and (2) the need for a systematic characterization of the input EEG data to ensure robust modeling.

PMID:39759760 | PMC:PMC11695360 | DOI:10.3389/fninf.2024.1459970

Int J Clin Health Psychol. 2024 Oct-Dec;24(4):100526. doi: 10.1016/j.ijchp.2024.100526. Epub 2024 Dec 12.

ABSTRACT

OBJECTIVE: College students with subclinical depression often experience sleep disturbances and are at high risk of developing major depressive disorder without early intervention. Clinical guidelines recommend non-pharmacotherapy as the primary option for subclinical depression with comorbid sleep disorders (sDSDs). However, the neuroimaging mechanisms and therapeutic responses associated with these treatments are poorly understood. Additionally, the lack of an early diagnosis and therapeutic effectiveness prediction model hampers the clinical promotion and acceptance of non-pharmacological interventions for subclinical depression.

METHODS: This study involved pre- and post-treatment resting-state functional Magnetic Resonance Imaging (rs-fMRI) and clinical data from a multicenter, single-blind, randomized clinical trial. The trial included 114 first-episode, drug-naïve university students with subclinical depression and comorbid sleep disorders (sDSDs; Mean age=22.8±2.3 years; 73.7% female) and 93 healthy controls (HCs; Mean age=22.2±1.7 years; 63.4% female). We examined altered functional connectivity (FC) and brain network connective mode related to subregions of Default Mode Network (sub-DMN) using seed-to-voxel analysis before and after six weeks of non-pharmacological antidepressant treatment. Additionally, we developed an individualized diagnosing and therapeutic effect predicting model to realize early recognition of subclinical depression and provide objective suggestions to select non-pharmacological therapy by using the newly proposed Hierarchical Functional Brain Network (HFBN) with advanced deep learning algorithms within the transformer framework.

RESULTS: Neuroimaging responses to non-pharmacologic treatments are characterized by alterations in functional connectivity (FC) and shifts in brain network connectivity patterns, particularly within the sub-DMN. At baseline, significantly increased FC was observed between the sub-DMN and both Executive Control Network (ECN) and Dorsal Attention Network (DAN). Following six weeks of non-pharmacologic intervention, connectivity patterns primarily shifted within the sub-DMN and ECN, with a predominant decrease in FCs. The HFBN model demonstrated superior performance over traditional deep learning models, accurately predicting therapeutic outcomes and diagnosing subclinical depression, achieving cumulative scores of 80.47% for sleep quality prediction and 84.67% for depression prediction, along with an overall diagnostic accuracy of 82.34%.

CONCLUSIONS: Two-scale neuroimaging signatures related to the sub-DMN underlying the antidepressant mechanisms of non-pharmacological treatments for subclinical depression. The HFBN model exhibited supreme capability in early diagnosing and predicting non-pharmacological treatment outcomes for subclinical depression, thereby promoting objective clinical psychological treatment decision-making.

PMID:39759571 | PMC:PMC11699106 | DOI:10.1016/j.ijchp.2024.100526

Phys Imaging Radiat Oncol. 2024 Nov 22;32:100677. doi: 10.1016/j.phro.2024.100677. eCollection 2024 Oct.

ABSTRACT

BACKGROUND AND PURPOSE: With the increasing amount of in-house created deep learning models in radiotherapy, it is important to know how to minimise the risks associated with the local clinical implementation prior to clinical use. The goal of this study is to give an example of how to identify the risks and find mitigation strategies to reduce these risks in an implemented workflow containing a deep learning based planning tool for breast Volumetric Modulated Arc Therapy.

MATERIALS AND METHODS: The deep learning model ran on a private Google Cloud environment for adequate computational capacity and was integrated into a workflow that could be initiated within the clinical Treatment Planning System (TPS). A proactive Failure Mode and Effect Analysis (FMEA) was conducted by a multidisciplinary team, including physicians, physicists, dosimetrists, technologists, quality managers, and the research and development team. Failure modes categorised as 'Not acceptable' and 'Tolerable' on the risk matrix were further examined to find mitigation strategies.

RESULTS: In total, 39 failure modes were defined for the total workflow, divided over four steps. Of these, 33 were deemed 'Acceptable', five 'Tolerable', and one 'Not acceptable'. Mitigation strategies, such as a case-specific Quality Assurance report, additional scripted checks and properties, a pop-up window, and time stamp analysis, reduced the failure modes to two 'Tolerable' and none in the 'Not acceptable' region.

CONCLUSIONS: The pro-active risk analysis revealed possible risks in the implemented workflow and led to the implementation of mitigation strategies that decreased the risk scores for safer clinical use.

PMID:39759485 | PMC:PMC11697787 | DOI:10.1016/j.phro.2024.100677

Front Artif Intell. 2024 Dec 20;7:1452563. doi: 10.3389/frai.2024.1452563. eCollection 2024.

ABSTRACT

BACKGROUND: Detecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H&E) stained lung squamous cell carcinoma is of great significance.

METHODS: We constructed a dataset comprising H&E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS).

RESULTS: The results showed that the dice similarity coefficient (DSC) and intersection overunion (IoU) of deep learning for PD-L1 expression segmentation of H&E-stained digital slides of lung squamous cell carcinoma were 80 and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90-0.93), which was better than the consistency between the results of five pathologists and the gold standard.

CONCLUSION: The deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H&E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments. And the link to the code is https://github.com/Baron-Huang/PD-L1-prediction-via-HE-image.

PMID:39759385 | PMC:PMC11695341 | DOI:10.3389/frai.2024.1452563

Front Artif Intell. 2024 Dec 20;7:1509179. doi: 10.3389/frai.2024.1509179. eCollection 2024.

ABSTRACT

Social media platforms, including X, Facebook, and Instagram, host millions of daily users, giving rise to bots automated programs disseminating misinformation and ideologies with tangible real-world consequences. While bot detection in platform X has been the area of many deep learning models with adequate results, most approaches neglect the graph structure of social media relationships and often rely on hand-engineered architectures. Our work introduces the implementation of a Neural Architecture Search (NAS) technique, namely Deep and Flexible Graph Neural Architecture Search (DFG-NAS), tailored to Relational Graph Convolutional Neural Networks (RGCNs) in the task of bot detection in platform X. Our model constructs a graph that incorporates both the user relationships and their metadata. Then, DFG-NAS is adapted to automatically search for the optimal configuration of Propagation and Transformation functions in the RGCNs. Our experiments are conducted on the TwiBot-20 dataset, constructing a graph with 229,580 nodes and 227,979 edges. We study the five architectures with the highest performance during the search and achieve an accuracy of 85.7%, surpassing state-of-the-art models. Our approach not only addresses the bot detection challenge but also advocates for the broader implementation of NAS models in neural network design automation.

PMID:39759384 | PMC:PMC11695282 | DOI:10.3389/frai.2024.1509179

Brief Bioinform. 2024 Nov 22;26(1):bbae672. doi: 10.1093/bib/bbae672.

ABSTRACT

Identifying phage-host interactions (PHIs) is a crucial step in developing phage therapy, which is the promising solution to addressing the issue of antibiotic resistance in superbugs. However, the lifestyle of phages, which strongly depends on their host for life activities, limits their cultivability, making the study of predicting PHIs time-consuming and labor-intensive for traditional wet lab experiments. Although many deep learning (DL) approaches have been applied to PHIs prediction, most DL methods are predominantly based on sequence information, failing to comprehensively model the intricate relationships within PHIs. Moreover, most existing approaches are limited for sub-optimal performance, due to the potential risk of overfitting induced by the highly data sparsity in the task of PHIs prediction. In this study, we propose a novel approach called MI-RGC, which introduces mutual information for feature augmentation and employs regional graph convolution to learn meaningful representations. Specifically, MI-RGC treats the presence status of phages in environmental samples as random variables, and derives the mutual information between these random variables as the dependency relationships among phages. Consequently, a mutual information-based heterogeneous network is construted as feature augmentation for sequence information of phages, which is utilized for building a sequence information-based heterogeneous network. By considering the different contributions of neighboring nodes at varying distances, a regional graph convolutional model is designed, in which the neighboring nodes are segmented into different regions and a regional-level attention mechanism is employed to derive node embeddings. Finally, the embeddings learned from these two networks are aggregated through an attention mechanism, on which the prediction of PHIs is condcuted accordingly. Experimental results on three benchmark datasets demonstrate that MI-RGC derives superior performance over other methods on the task of PHIs prediction.

PMID:39756070 | DOI:10.1093/bib/bbae672

Adv Sci (Weinh). 2025 Jan 4:e2410722. doi: 10.1002/advs.202410722. Online ahead of print.

ABSTRACT

Powder X-ray diffraction (PXRD) is a prevalent technique in materials characterization. While the analysis of PXRD often requires extensive human manual intervention, and most automated method only achieved at coarse-grained level. The more difficult and important task of fine-grained crystal structure prediction from PXRD remains unaddressed. This study introduces XtalNet, the first equivariant deep generative model for end-to-end crystal structure prediction from PXRD. Unlike previous crystal structure prediction methods that rely solely on composition, XtalNet leverages PXRD as an additional condition, eliminating ambiguity and enabling the generation of complex organic structures with up to 400 atoms in the unit cell. XtalNet comprises two modules: a Contrastive PXRD-Crystal Pretraining (CPCP) module that aligns PXRD space with crystal structure space, and a Conditional Crystal Structure Generation (CCSG) module that generates candidate crystal structures conditioned on PXRD patterns. Evaluation on two MOF datasets (hMOF-100 and hMOF-400) demonstrates XtalNet's effectiveness. XtalNet achieves a top-10 Match Rate of 90.2% and 79% for hMOF-100 and hMOF-400 in conditional crystal structure prediction task, respectively. XtalNet enables the direct prediction of crystal structures from experimental measurements, eliminating the need for manual intervention and external databases. This opens up new possibilities for automated crystal structure determination and the accelerated discovery of novel materials.

PMID:39755935 | DOI:10.1002/advs.202410722

Adv Sci (Weinh). 2025 Jan 4:e2407812. doi: 10.1002/advs.202407812. Online ahead of print.

ABSTRACT

β-secretase (BACE1) is instrumental in amyloid-β (Aβ) production, with overexpression noted in Alzheimer's disease (AD) neuropathology. The interaction of Aβ with the receptor for advanced glycation endproducts (RAGE) facilitates cerebral uptake of Aβ and exacerbates its neurotoxicity and neuroinflammation, further augmenting BACE1 expression. Given the limitations of previous BACE1 inhibition efforts, the study explores reducing BACE1 expression to mitigate AD pathology. The research reveals that the anticancer agent 6-thioguanosine (6-TG) markedly diminishes BACE1 expression without eliciting cytotoxicity while enhancing microglial phagocytic activity, and ameliorate cognitive impairments with reducing Aβ accumulation in AD mice. Leveraging advanced deep learning-based tool for target identification, and corroborating with surface plasmon resonance assays, it is elucidated that 6-TG directly interacts with RAGE, modulating BACE1 expression through the JAK2-STAT1 pathway and elevating soluble RAGE (sRAGE) levels in the brain. The findings illuminate the therapeutic potential of 6-TG in ameliorating AD manifestations and advocate for small molecule strategies to increase brain sRAGE levels, offering a strategic alternative to the challenges posed by the complexity of AD.

PMID:39755927 | DOI:10.1002/advs.202407812

Int J Med Inform. 2024 Dec 26;195:105754. doi: 10.1016/j.ijmedinf.2024.105754. Online ahead of print.

ABSTRACT

BACKGROUND: Ischemic stroke affects 15 million people worldwide, causing five million deaths annually. Despite declining mortality rates, stroke incidence and readmission risks remain high, highlighting the need for preventing readmission to improve the quality of life of survivors. This study developed a machine-learning model to predict 90-day stroke readmission using electronic medical records converted to the common data model (CDM) from the Regional Accountable Care Hospital in Gangwon state in South Korea.

METHODS: We retrospectively analyzed data from 1,136 patients with ischemic stroke admitted between August 2003 and August 2021 after excluding cases with missing blood test values. Demographics, blood test results, treatments, and comorbidities were used as key features. Six machine learning models and three deep learning models were used to predict 90-day readmission using the synthetic minority over-sampling technique to address class imbalance. Models were evaluated using threefold cross-validation, and SHapley Additive exPlanations (SHAP) values were calculated to interpret feature importance.

RESULTS: Among 1,136 patients, 196 (17.2 %) were readmitted within 90 days. Male patients were significantly more likely to experience readmission (p = 0.02). LightGBM achieved an area under the curve of 0.94, demonstrating that analyzing stroke and stroke-related conditions provides greater predictive accuracy than predicting stroke alone or all-cause readmissions. SHAP analysis highlighted renal and metabolic variables, including creatinine, blood urea nitrogen, calcium, sodium, and potassium, as key predictors of readmission.

CONCLUSION: Machine-learning models using electronic health record-based CDM data demonstrated strong predictive performance for 90-day stroke readmission. These results support personalized post-discharge management and lay the groundwork for future multicenter studies.

PMID:39755003 | DOI:10.1016/j.ijmedinf.2024.105754

Radiography (Lond). 2025 Jan 3;31(1):372-378. doi: 10.1016/j.radi.2024.12.018. Online ahead of print.

ABSTRACT

BACKGROUND: Facial recognition technology in medical imaging, particularly with head scans, poses privacy risks due to identifiable facial features. This study evaluates the use of facial recognition software in identifying facial features from head CT scans and explores a defacing pipeline using TotalSegmentator to reduce re-identification risks while preserving data integrity for research.

METHODS: 1404 high-quality renderings from the UCLH EIT Stroke dataset, both with and without defacing were analysed. The performance of defacing with the face mask created by TotalSegmentator was compared to a state-of-the-art CT defacing algorithm. Face detection was performed using deep learning models. The cosine similarity between facial embeddings for intra- and inter-patient images was compared. A Support Vector Machine was trained on cosine similarity values to assess defacing performance, determining if two renderings came from the same patient. This analysis was conducted on defaced and non-defaced images using 5-fold cross-validation.

RESULTS: Faces were detected in 76.5 % of non-defaced images. Intra-patient images exhibited a median cosine similarity of 0.65 (IQR: 0.47-0.80), compared to 0.50 (IQR: 0.39-0.62) for inter-patient images. A binary classifier performed moderately on non-defaced images, achieving a ROC-AUC of 0.69 (SD = 0.01) and an accuracy of 0.65 (SD = 0.01) in distinguishing whether a scan belonged to the same or a different individual. Following defacing, performance declined markedly. Defacing with the TotalSegmentator decreased the ROC-AUC to 0.55 (SD = 0.02) and the accuracy to 0.56 (SD = 0.01), whereas the CTA-DEFACE algorithm brought the performance down to a ROC-AUC of 0.60 (SD = 0.02) and an accuracy of 0.59 (SD = 0.01). These results demonstrate the effectiveness of defacing algorithms in mitigating re-identification risks, with the TotalSegmentator providing slightly superior privacy protection.

CONCLUSION: Facial recognition software can identify facial features from partial and complete head CT scan renderings. However, using the TotalSegmentator to deface images reduces re-identification risks to a near-chance level. We offer code to implement this privacy-preserving pipeline.

IMPLICATIONS FOR PRACTICE: Utilizing the TotalSegmentator framework, the proposed pipeline efficiently removes facial features from CT images, making it ideal for multi-site research and data sharing. It is a useful tool for radiographers and radiologists who must comply with medico-legal requirements necessitating the removal of facial features.

PMID:39754865 | DOI:10.1016/j.radi.2024.12.018

Sci Rep. 2025 Jan 4;15(1):818. doi: 10.1038/s41598-024-84421-0.

ABSTRACT

Mobile Ad Hoc Networks (MANETs) are increasingly replacing conventional communication systems due to their decentralized and dynamic nature. However, their wireless architecture makes them highly vulnerable to flooding attacks, which can disrupt communication, deplete energy resources, and degrade network performance. This study presents a novel hybrid deep learning approach integrating Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to effectively detect and mitigate flooding attacks in MANETs. To optimize the model's efficiency, a unique DECEHGS algorithm combining Differential Evolution and Evolutionary Population Dynamics techniques is employed, enhancing both convergence and performance. The proposed model demonstrates significant improvements over existing methods, achieving an accuracy of 95%, a 12% increase in packet delivery ratio, and a 20% reduction in routing overhead compared to traditional techniques. These advancements underline the model's superiority in detecting malicious nodes, conserving energy, and ensuring reliable network performance. The comprehensive evaluation using MATLAB R2023a validates the proposed approach as an effective and energy-efficient solution for enhancing MANET security.

PMID:39755804 | DOI:10.1038/s41598-024-84421-0

NPJ Digit Med. 2025 Jan 4;8(1):7. doi: 10.1038/s41746-024-01364-6.

ABSTRACT

Adaptive deep brain stimulation (DBS) provides individualized therapy for people with Parkinson's disease (PWP) by adjusting the stimulation in real-time using neural signals that reflect their motor state. Current algorithms, however, utilize condensed and manually selected neural features which may result in a less robust and biased therapy. In this study, we propose Neural-to-Gait Neural network (N2GNet), a novel deep learning-based regression model capable of tracking real-time gait performance from subthalamic nucleus local field potentials (STN LFPs). The LFP data were acquired when eighteen PWP performed stepping in place, and the ground reaction forces were measured to track their weight shifts representing gait performance. By exhibiting a stronger correlation with weight shifts compared to the higher-correlation beta power from the two leads and outperforming other evaluated model designs, N2GNet effectively leverages a comprehensive frequency band, not limited to the beta range, to track gait performance solely from STN LFPs.

PMID:39755754 | DOI:10.1038/s41746-024-01364-6

Sci Rep. 2025 Jan 4;15(1):845. doi: 10.1038/s41598-024-81248-7.

ABSTRACT

This study presents a novel approach to identifying meters and their pointers in modern industrial scenarios using deep learning. We developed a neural network model that can detect gauges and one or more of their pointers on low-quality images. We use an encoder network, jump connections, and a modified Convolutional Block Attention Module (CBAM) to detect gauge panels and pointer keypoints in images. We also combine the output of the decoder network and the output of the improved CBAM as inputs to the Object Heatmap-Scalarmap Module to find pointer tip heat map peaks and predict pointer pointing. The method proposed in this paper is compared with several deep learning networks. The experimental results show that the model in this paper has the highest recognition correctness, with an average precision of 0.95 and 0.763 for Object Keypoint Similarity and Vector Direction Similarity, and an average recall of 0.951 and 0.856 in the test set, respectively, and achieves the best results in terms of efficiency and accuracy achieve the best trade-off, and performs well in recognizing multiple pointer targets. This demonstrates its robustness in real scenarios and provides a new idea for recognizing pointers in low-quality images more efficiently and accurately in complex industrial scenarios.

PMID:39755689 | DOI:10.1038/s41598-024-81248-7

Cancer Lett. 2025 Jan 2:217438. doi: 10.1016/j.canlet.2025.217438. Online ahead of print.

ABSTRACT

Preoperative detection of muscle-invasive bladder cancer (MIBC) remains a great challenge in practice. We aimed to develop and validate a deep Vesical Imaging Network (ViNet) model for the detection of MIBC using high-resolution T2-weighted MR imaging (hrT2WI) in a multicenter cohort. ViNet was designed using a modified 3D ResNet, in which, the encoder layers were pretrained using a self-supervised foundation model on over 40,000 cross-modal imaging datasets for transfer learning, and the classification modules were weakly supervised by an experiential knowledge-domain mask indicated by a nnUNet segmentation model. Optimal ViNet model was trained in derivation data (cohort 1, n = 312) and validated in multicenter data (cohort 2, n = 79; cohort 3, n = 44; cohort 4, n = 56) across a multi-ablation-test for model selection. In internal validation, ViNet using hrT2WI outperformed all ablation-test models (odds ratio [OR], 7.41 versus 1.85 - 2.70; all P < 0.05). In external validation, the performance of ViNet using hrT2WI versus ablation-test models was heterogeneous (OR, 1.31 - 3.89 versus 0.89 - 9.75; P = 0.03 - 0.15). In addition, clinical benefit of ViNet was evaluated between six readers using the Vesical Imaging-Reporting and Data System (VI-RADS) versus ViNet-adjusted VI-RADS. As a result, ViNet-adjusted VI-RADS upgraded 62.9% (17/27) of MIBC missed in VI-RADS score 2, while downgraded 84.1% (69/84), 62.5% (35/56) and 67.9% (19/28) of non-muscle-invasive bladder cancer (NMIBC) overestimated in VI-RADS score 3-5. We concluded that ViNet presents a promising alternative for diagnosing MIBC using hrT2WI instead of conventional multiparametric MRI.

PMID:39755362 | DOI:10.1016/j.canlet.2025.217438

Methods. 2025 Jan 2:S1046-2023(24)00283-4. doi: 10.1016/j.ymeth.2024.11.016. Online ahead of print.

ABSTRACT

Spatial transcriptomics has significantly advanced the measurement of spatial gene expression in the field of biology. However, the high cost of ST limits its application in large-scale studies. Using deep learning to predict spatial gene expression from H&E-stained histology images offers a more cost-effective alternative, but existing methods fail to fully leverage the multimodal information provided by Spatial transcriptomics and pathology images. In response, this paper proposes STMCL, a novel multimodal contrastive learning framework. STMCL integrates multimodal information, including histology images, gene expression features of spots, and their locations, to accurately infer spatial gene expression profiles. We tested four different types of multi-slice spatial transcriptomics datasets generated by the 10X Genomics platform. The results indicate that STMCL has advantages over baseline methods in predicting spatial gene expression profiles. Furthermore, STMCL is capable of capturing cancer-specific highly expressed genes and preserving gene expression patterns while maintaining the original spatial structure of gene expression. Our code is available at https://github.com/wenwenmin/STMCL.

PMID:39755346 | DOI:10.1016/j.ymeth.2024.11.016

J Neurosci Methods. 2025 Jan 2:110359. doi: 10.1016/j.jneumeth.2024.110359. Online ahead of print.

ABSTRACT

BACKGROUND: The hippocampus plays a crucial role in memory and is one of the first structures affected by Alzheimer's disease. Postmortem MRI offers a way to quantify the alterations by measuring the atrophy of the inner structures of the hippocampus. Unfortunately, the manual segmentation of hippocampal subregions required to carry out these measures is very time-consuming.

NEW METHOD: In this study, we explore the use of fully automated methods relying on state-of-the-art Deep Learning approaches to produce these annotations. More specifically, we propose a new segmentation framework made of a set of encoder-decoder blocks embedding self-attention mechanisms and atrous spatial pyramidal pooling to produce better maps of the hippocampus and identify four hippocampal regions: the dentate gyrus, the hippocampal head, the hippocampal body, and the hippocampal tail.

RESULTS: Trained using slices extracted from 15 postmortem T1-weighted, T2-weighted, and susceptibility-weighted MRI scans, our new approach produces hippocampus parcellations that are better aligned with the manually delineated parcellations provided by neuroradiologists.

COMPARISON WITH EXISTING METHODS: Four standard deep learning segmentation architectures: UNet, Double UNet, Attention UNet, and Multi-resolution UNet have been utilized for the qualitative and quantitative comparison of the proposed hippocampal region segmentation model.

CONCLUSIONS: Postmortem MRI serves as a highly valuable neuroimaging technique for examining the effects of neurodegenerative diseases on the intricate structures within the hippocampus. This study opens the way to large sample-size postmortem studies of the hippocampal substructures.

PMID:39755177 | DOI:10.1016/j.jneumeth.2024.110359

Ageing Res Rev. 2025 Jan 2:102651. doi: 10.1016/j.arr.2024.102651. Online ahead of print.

ABSTRACT

Parkinson's disease (PD) is one of the most incapacitating neurodegenerative diseases (NDDs). PD is the second most common NDD worldwide which affects approximately 1 to 2 percent of people over 65 years. It is an attractive pursuit for artificial intelligence (AI) to contribute to and evolve PD treatments through drug repositioning by repurposing existing drugs, shelved drugs, or even candidates that do not meet the criteria for clinical trials. A search was conducted in three databases Web of Science, Scopus, and PubMed. We reviewed the data related to the last years (1975-present) to identify those drugs currently being proposed for repositioning in PD. Moreover, we reviewed the present status of the computational approach, including AI/Machine Learning (AI/ML)-powered pharmaceutical discovery efforts and their implementation in PD treatment. It was found that the number of drug repositioning studies for PD has increased recently. Repositioning of drugs in PD is taking off, and scientific communities are increasingly interested in communicating its results and finding effective treatment alternatives for PD. A better chance of success in PD drug discovery has been made possible due to AI/ML algorithm advancements. In addition to the experimentation stage of drug discovery, it is also important to leverage AI in the planning stage of clinical trials to make them more effective. New AI-based models or solutions that increase the success rate of drug development are greatly needed.

PMID:39755176 | DOI:10.1016/j.arr.2024.102651

Med Phys. 2025 Jan 4. doi: 10.1002/mp.17609. Online ahead of print.

ABSTRACT

BACKGROUND: Respiratory motion during radiotherapy (RT) may reduce the therapeutic effect and increase the dose received by organs at risk. This can be addressed by real-time tracking, where respiration motion prediction is currently required to compensate for system latency in RT systems. Notably, for the prediction of future images in image-guided adaptive RT systems, the use of deep learning has been considered.

PURPOSE: This study proposed a modified generative adversarial network (GAN) for predicting cine-MR images in real time.

METHODS: Sagittal cine magnetic resonance (cine-MR) images of 15 patients with liver cancer who received RT were collected. The image series length of each patient was 300, and each series was divided into training, validation, and test sets. The datasets were further divided using a sliding window size of 10 and a stride of 1. A pix2pix GAN with the generator replaced by convolutional long short-term memory (ConvLSTM) was proposed herein. A five-frame cine-MR image series was inputted into the network, which predicted the next five frames. The proposed network was compared with three advanced networks: ConvLSTM, Eidetic 3D LSTM (E3D-LSTM), and SwinLSTM. Personalized models were trained for each patient. The peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), visual information fidelity (VIF), Pearson correlation coefficient (Pearson corr), and respiratory motion accuracy of the predicted images were used to evaluate the methods.

RESULTS: The proposed network demonstrated optimal performance in the four networks across various indicators. The proposed method provided better SSIM values than ConvLSTM at time steps 1, 2, 3, and 4, and outperformed E3DLSTM at all time steps. In terms of the VIF, the proposed method outperformed E3D-LSTM at all time steps and SwinLSTM at time steps 2, 3, 4, and 5. The proposed method was not significantly different from other methods in terms of Pearson correlation values except that it outperformed E3DLSTM at time step 1. In terms of the Pearson corr, the proposed method consistently achieves better values, especially in the high-frequency components. Low average landmark tracking errors were provided by the proposed method at time steps 4 and 5 (2.42 ± 0.91 and 2.44 ± 0.96 mm, respectively).

CONCLUSIONS: The GAN-ConvLSTM network can generate high-acutance real-time cine-MR images and predict respiratory motion with better accuracy.

PMID:39755123 | DOI:10.1002/mp.17609

Eur J Nucl Med Mol Imaging. 2025 Jan 4. doi: 10.1007/s00259-024-07043-8. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aims to conduct a bibliometric analysis to explore research trends, collaboration patterns, and emerging themes in the PET/MR field based on published literature from 2010 to 2024.

METHODS: A detailed literature search was performed using the Web of Science Core Collection (WoSCC) database with keywords related to PET/MR. A total of 4,349 publications were retrieved and analyzed using various bibliometric tools, including VOSviewer and CiteSpace.

RESULTS: The analysis revealed an initial increase in PET/MR publications, peaking at 495 in 2021, followed by a slight decline. The USA, Germany, and China were the most prolific countries, with the USA demonstrating strong collaborative networks. Key institutions included the Stanford University, Technical University of Munich and University of Duisburg-Essen. Prominent authors were primarily from Germany, with significant contributions from University Hospital Essen. Major journals in the field included the European Journal of Nuclear Medicine, Journal of Nuclear Medicine, and Physics in Medicine and Biology. Emerging research areas focused on oncology, neurological disorders, and cardiovascular diseases, with keywords such as "prostate cancer," "Alzheimer's disease," and "breast cancer" showing high research activity. Recent trends also highlight the growing integration of AI, particularly deep learning, to improve imaging reconstruction and diagnostic accuracy.

CONCLUSION: The findings emphasize the need for continuous investment, strategic planning, and technological innovations to expand PET/MR's clinical applications. Future research should focus on optimizing imaging techniques, fostering international collaborations, and integrating emerging technologies like artificial intelligence to enhance PET/MR's diagnostic and therapeutic potential in precision medicine.

PMID:39754665 | DOI:10.1007/s00259-024-07043-8