Sci Rep. 2024 May 15;14(1):11085. doi: 10.1038/s41598-024-60781-5.

ABSTRACT

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

PMID:38750084 | DOI:10.1038/s41598-024-60781-5

Acad Radiol. 2024 May 14:S1076-6332(24)00237-X. doi: 10.1016/j.acra.2024.04.028. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: The proliferative nature of hepatocellular carcinoma (HCC) is closely related to early recurrence following radical resection. This study develops and validates a deep learning (DL) prediction model to distinguish between proliferative and non-proliferative HCCs using dynamic contrast-enhanced MRI (DCE-MRI), aiming to refine preoperative assessments and optimize treatment strategies by assessing early recurrence risk.

MATERIALS AND METHODS: In this retrospective study, 355 HCC patients from two Chinese medical centers (April 2018-February 2023) who underwent radical resection were included. Patient data were collected from medical records, imaging databases, and pathology reports. The cohort was divided into a training set (n = 251), an internal test set (n = 62), and external test sets (n = 42). A DL model was developed using DCE-MRI images of primary tumors. Clinical and radiological models were generated from their respective features, and fusion strategies were employed for combined model development. The discriminative abilities of the clinical, radiological, DL, and combined models were extensively analyzed. The performances of these models were evaluated against pathological diagnoses, with independent and fusion DL-based models validated for clinical utility in predicting early recurrence.

RESULTS: The DL model, using DCE-MRI, outperformed clinical and radiological feature-based models in predicting proliferative HCC. The area under the curve (AUC) for the DL model was 0.98, 0.89, and 0.83 in the training, internal validation, and external validation sets, respectively. The AUCs for the combined DL and clinical feature models were 0.99, 0.86, and 0.83 in these sets, while the AUCs for the combined DL, clinical, and radiological model were 0.99, 0.87, and 0.8, respectively. Among models predicting early recurrence, the DL plus clinical features model showed superior performance.

CONCLUSION: The DL-based DCE-MRI model demonstrated robust performance in predicting proliferative HCC and stratifying patient risk for early postoperative recurrence. As a non-invasive tool, it shows promise in enhancing decision-making for individualized HCC management strategies.

PMID:38749868 | DOI:10.1016/j.acra.2024.04.028

Clin Radiol. 2024 Apr 20:S0009-9260(24)00199-5. doi: 10.1016/j.crad.2024.04.008. Online ahead of print.

ABSTRACT

PURPOSE: To compare the image quality and pulmonary nodule detectability between deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V) in ultra-low-dose CT (ULD-CT).

METHODS: 142 participants required lung examination who underwent simultaneously ULD-CT (UL-A, 0.57 ± 0.04 mSv or UL-B, 0.33 ± 0.03 mSv), and standard CT (SDCT, 4.32 ± 0.33 mSv) plain scans were included in this prospective study. SDCT was the reference standard using ASIR-V at 50% strength (50%ASIR-V). ULD-CT was reconstructed with 50%ASIR-V, DLIR at medium and high strength (DLIR-M, DLIR-H). The noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective scores were measured. The presence and accuracy of nodules were analyzed using a combination of a deep learning-based nodule evaluation system and a radiologist.

RESULTS: A total of 710 nodules were detected by SDCT, including 358 nodules in UL-A and 352 nodules in UL-B. DLIR-H exhibited superior noise, SNR, and CNR performance, and achieved comparable or even higher subjective scores compared to 50%ASIR-V in ULD-CT. Nodules sensitivity detection of 50%ASIR-V, DLIR-M, and DLIR-H in ULD-CT were identical (96.90%). In multivariate analysis, body mass index (BMI), nodule diameter, and type were independent predictors for the sensitivity of nodule detection (p<.001). DLIR-H provided a lower absolute percent error (APE) in volume (3.10% ± 95.11% vs 8.29% ± 99.14%) compared to 50%ASIR-V of ULD-CT (P<.001).

CONCLUSIONS: ULD-CT scanning has a high sensitivity for detecting pulmonary nodules. Compared with ASIR-V, DLIR can significantly reduce image noise, and improve image quality, and accuracy of the nodule measurement in ULD-CT.

PMID:38749827 | DOI:10.1016/j.crad.2024.04.008

Phys Med Biol. 2024 May 15. doi: 10.1088/1361-6560/ad4c52. Online ahead of print.

ABSTRACT

The quality of optical coherence tomography (OCT) en face images is crucial for clinical visualization of early disease. As a three dimensional and coherent imaging, defocus and speckle noise are inevitable, which seriously affect evaluation of microstructure of bio-samples in OCT images. The deep learning has demonstrated great potential in OCT refocusing and denoising, but it is limited by the difficulty of sufficient paired training data. We proposed an unsupervised deep learning-based pipeline to enhance the quality of OCT en face images in this paper. The unregistered defocused conventional OCT images and focused speckle-free OCT images were collected by a home-made speckle modulating OCT system to construct the dataset. The image enhancement model was trained with the cycle training strategy. Finally, the speckle noise and defocus were both effectively improved. The experimental results on complex bio-samples indicated that the proposed method is effective and generalized in enhancing the quality of OCT en face images. The proposed unsupervised deep learning method helps to reduce the complexity of data construction, which is conducive to practical applications in OCT bio-sample imaging.&#xD.

PMID:38749469 | DOI:10.1088/1361-6560/ad4c52

Phys Med Biol. 2024 May 15. doi: 10.1088/1361-6560/ad4c4f. Online ahead of print.

ABSTRACT

Objective&#xD;Fast and accurate deformable image registration (DIR) that include DIR uncertainty estimation are essential for safe and reliable clinical deployment. While recent deep learning models have shown promise in predicting DIR with its uncertainty, challenges persist in proper uncertainty evaluation and hyperparameter optimization for these methods. This work aims to develop and evaluate a model that can perform fast DIR and predict its uncertainty in seconds.&#xD;Approach&#xD;In this study, we introduce a novel probabilistic multi-resolution image registration model utilizing convolutional neural networks (CNNs) to estimate a multivariate normal distributed dense displacement field (DDF) in a multimodal image registration problem. To assess the quality of the DDF distribution predicted by the model, we propose a new metric based on the Kullback-Leibler divergence. The performance of our approach was evaluated against three other DIR algorithms (VoxelMorph, Monte Carlo Drop-Out, and Monte Carlo B-splines) capable of predicting uncertainty. The evaluation of the models included not only the quality of the deformation but also the reliability of the estimated uncertainty. Our application investigated registration of a treatment planning computed tomography (CT) to follow-up cone beam CT for daily adaptive radiotherapy.&#xD;Main results&#xD;The hyperparameter tuning of the models showed that there is a trade-off between the reliability of the estimated uncertainty and the accuracy of the deformation. In the optimal trade-off our model excelled in contour propagation and uncertainty estimation (p < 0.01) compared to existing uncertainty estimation models. We obtained an average dice similarity coefficient of 0.89 and a KL-divergence of 0.15.&#xD;Significance&#xD;By addressing challenges in DIR uncertainty estimation and evaluation, our work showed that both the DIR and its uncertainty can be reliably predicted paving the way for safe deployment in clinical environment.&#xD.

PMID:38749468 | DOI:10.1088/1361-6560/ad4c4f

Phys Med Biol. 2024 May 15. doi: 10.1088/1361-6560/ad4c50. Online ahead of print.

ABSTRACT

This study aims to leverage a deep learning approach, specifically a deformable convolutional layer, for staging cervical cancer using multi-sequence MRI images. This is in response to the challenges doctors face in simultaneously identifying multiple sequences, a task that computer-aided diagnosis systems can potentially improve due to their vast information storage capabilities.&#xD;&#xD;Approach: To address the challenge of limited sample sizes, we introduce a sequence enhancement strategy to diversify samples and mitigate overfitting. We propose a novel deformable ConvLSTM module that integrates a deformable mechanism with ConvLSTM, enabling the model to adapt to data with varying structures. Furthermore, we introduce the deformable multi-sequence guidance model (DMGM) as an auxiliary diagnostic tool for cervical cancer staging.&#xD;&#xD;Main Results: Through extensive testing, including comparative and ablation studies, we validate the effectiveness of the deformable ConvLSTM module and the DMGM. Our findings highlight the model's ability to adapt to the deformation mechanism and address the challenges in cervical cancer tumor staging, thereby overcoming the overfitting issue and ensuring the synchronization of asynchronous scan sequences. The research also utilized the multi-modal data from BraTS 2019 as an external test dataset to validate the effectiveness of the proposed methodology presented in this study.&#xD;&#xD;Significance: The DMGM represents the first deep learning model to analyze multiple MRI sequences for cervical cancer, demonstrating strong generalization capabilities and effective staging in small dataset scenarios. This has significant implications for both deep learning applications and medical diagnostics. The source code will be made available subsequently.

PMID:38749463 | DOI:10.1088/1361-6560/ad4c50

Rofo. 2024 May 15. doi: 10.1055/a-2290-4781. Online ahead of print.

ABSTRACT

To evaluate the effect of a vendor-agnostic deep learning denoising (DLD) algorithm on diagnostic image quality of non-contrast cranial computed tomography (ncCT) across five CT scanners.This retrospective single-center study included ncCT data of 150 consecutive patients (30 for each of the five scanners) who had undergone routine imaging after minor head trauma. The images were reconstructed using filtered back projection (FBP) and a vendor-agnostic DLD method. Using a 4-point Likert scale, three readers performed a subjective evaluation assessing the following quality criteria: overall diagnostic image quality, image noise, gray matter-white matter differentiation (GM-WM), artifacts, sharpness, and diagnostic confidence. Objective analysis included evaluation of noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and an artifact index for the posterior fossa.In subjective image quality assessment, DLD showed constantly superior results compared to FBP in all categories and for all scanners (p<0.05) across all readers. The objective image quality analysis showed significant improvement in noise, SNR, and CNR as well as for the artifact index using DLD for all scanners (p<0.001).The vendor-agnostic deep learning denoising algorithm provided significantly superior results in the subjective as well as in the objective analysis of ncCT images of patients with minor head trauma concerning all parameters compared to the FBP reconstruction. This effect has been observed in all five included scanners. · Significant improvement of image quality for 5 scanners due to the vendor-agnostic DLD. · Subjects were patients with routine imaging after minor head trauma. · Reduction of artifacts in the posterior fossa due to the DLD. · Access to improved image quality even for older scanners from different vendors. · Kapper C, Müller L, Kronfeld A et al. Value of vendor-agnostic deep learning image denoising in brain computed tomography: A multi-scanner study. Fortschr Röntgenstr 2024; DOI 10.1055/a-2290-4781.

PMID:38749431 | DOI:10.1055/a-2290-4781

Comput Biol Med. 2024 May 9;176:108572. doi: 10.1016/j.compbiomed.2024.108572. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Melanoma, a malignant form of skin cancer, is a critical health concern worldwide. Early and accurate detection plays a pivotal role in improving patient's conditions. Current diagnosis of skin cancer largely relies on visual inspections such as dermoscopy examinations, clinical screening and histopathological examinations. However, these approaches are characterized by low efficiency, high costs, and a lack of guaranteed accuracy. Consequently, deep learning based techniques have emerged in the field of melanoma detection, successfully aiding in improving the accuracy of diagnosis. However, the high similarity between benign and malignant melanomas, combined with the class imbalance issue in skin lesion datasets, present a significant challenge in further improving the diagnosis accuracy. We propose a two-stage framework for melanoma detection to address these issues.

METHODS: In the first stage, we use Style Generative Adversarial Networks with Adaptive discriminator augmentation synthesis to generate realistic and diverse melanoma images, which are then combined with the original dataset to create an augmented dataset. In the second stage, we utilize a vision Transformer of BatchFormer to extract features and detect melanoma or non-melanoma skin lesions on the augmented dataset obtained in the previous step, specifically, we employed a dual-branch training strategy in this process.

RESULTS: Our experimental results on the ISIC2020 dataset demonstrate the effectiveness of the proposed approach, showing a significant improvement in melanoma detection. The method achieved an accuracy of 98.43%, an AUC value of 98.63%, and an F1 value of 99.01%, surpassing some existing methods.

CONCLUSION: The method is feasible, efficient, and achieves early melanoma screening. It significantly enhances detection accuracy and can assist physicians in diagnosis to a great extent.

PMID:38749327 | DOI:10.1016/j.compbiomed.2024.108572

Comput Biol Med. 2024 May 8;176:108570. doi: 10.1016/j.compbiomed.2024.108570. Online ahead of print.

ABSTRACT

The two major challenges to deep-learning-based medical image segmentation are multi-modality and a lack of expert annotations. Existing semi-supervised segmentation models can mitigate the problem of insufficient annotations by utilizing a small amount of labeled data. However, most of these models are limited to single-modal data and cannot exploit the complementary information from multi-modal medical images. A few semi-supervised multi-modal models have been proposed recently, but they have rigid structures and require additional training steps for each modality. In this work, we propose a novel flexible method, semi-supervised multi-modal medical image segmentation with unified translation (SMSUT), and a unique semi-supervised procedure that can leverage multi-modal information to improve the semi-supervised segmentation performance. Our architecture capitalizes on unified translation to extract complementary information from multi-modal data which compels the network to focus on the disparities and salient features among each modality. Furthermore, we impose constraints on the model at both pixel and feature levels, to cope with the lack of annotation information and the diverse representations within semi-supervised multi-modal data. We introduce a novel training procedure tailored for semi-supervised multi-modal medical image analysis, by integrating the concept of conditional translation. Our method has a remarkable ability for seamless adaptation to varying numbers of distinct modalities in the training data. Experiments show that our model exceeds the semi-supervised segmentation counterparts in the public datasets which proves our network's high-performance capabilities and the transferability of our proposed method. The code of our method will be openly available at https://github.com/Sue1347/SMSUT-MedicalImgSegmentation.

PMID:38749326 | DOI:10.1016/j.compbiomed.2024.108570

Comput Biol Med. 2024 Apr 29;176:108545. doi: 10.1016/j.compbiomed.2024.108545. Online ahead of print.

ABSTRACT

Reliable classification of sleep stages is crucial in sleep medicine and neuroscience research for providing valuable insights, diagnoses, and understanding of brain states. The current gold standard method for sleep stage classification is polysomnography (PSG). Unfortunately, PSG is an expensive and cumbersome process involving numerous electrodes, often conducted in an unfamiliar clinic and annotated by a professional. Although commercial devices like smartwatches track sleep, their performance is well below PSG. To address these disadvantages, we present a feed-forward neural network that achieves gold-standard levels of agreement using only a single lead of electrocardiography (ECG) data. Specifically, the median five-stage Cohen's kappa is 0.725 on a large, diverse dataset of 5 to 90-year-old subjects. Comparisons with a comprehensive meta-analysis of between-human inter-rater agreement confirm the non-inferior performance of our model. Finally, we developed a novel loss function to align the training objective with Cohen's kappa. Our method offers an inexpensive, automated, and convenient alternative for sleep stage classification-further enhanced by a real-time scoring option. Cardiosomnography, or a sleep study conducted with ECG only, could take expert-level sleep studies outside the confines of clinics and laboratories and into realistic settings. This advancement democratizes access to high-quality sleep studies, considerably enhancing the field of sleep medicine and neuroscience. It makes less-expensive, higher-quality studies accessible to a broader community, enabling improved sleep research and more personalized, accessible sleep-related healthcare interventions.

PMID:38749325 | DOI:10.1016/j.compbiomed.2024.108545

Comput Biol Med. 2024 May 1;176:108530. doi: 10.1016/j.compbiomed.2024.108530. Online ahead of print.

ABSTRACT

As an autoimmune-mediated inflammatory demyelinating disease of the central nervous system, multiple sclerosis (MS) is often confused with cerebral small vessel disease (cSVD), which is a regional pathological change in brain tissue with unknown pathogenesis. This is due to their similar clinical presentations and imaging manifestations. That misdiagnosis can significantly increase the occurrence of adverse events. Delayed or incorrect treatment is one of the most important causes of MS progression. Therefore, the development of a practical diagnostic imaging aid could significantly reduce the risk of misdiagnosis and improve patient prognosis. We propose an interpretable deep learning (DL) model that differentiates MS and cSVD using T2-weighted fluid-attenuated inversion recovery (FLAIR) images. Transfer learning (TL) was utilized to extract features from the ImageNet dataset. This pioneering model marks the first of its kind in neuroimaging, showing great potential in enhancing differential diagnostic capabilities within the field of neurological disorders. Our model extracts the texture features of the images and achieves more robust feature learning through two attention modules. The attention maps provided by the attention modules provide model interpretation to validate model learning and reveal more information to physicians. Finally, the proposed model is trained end-to-end using focal loss to reduce the influence of class imbalance. The model was validated using clinically diagnosed MS (n=112) and cSVD (n=321) patients from the Beijing Tiantan Hospital. The performance of the proposed model was better than that of two commonly used DL approaches, with a mean balanced accuracy of 86.06 % and a mean area under the receiver operating characteristic curve of 98.78 %. Moreover, the generated attention heat maps showed that the proposed model could focus on the lesion signatures in the image. The proposed model provides a practical diagnostic imaging aid for the use of routinely available imaging techniques such as magnetic resonance imaging to classify MS and cSVD by linking DL to human brain disease. We anticipate a substantial improvement in accurately distinguishing between various neurological conditions through this novel model.

PMID:38749324 | DOI:10.1016/j.compbiomed.2024.108530

Comput Biol Med. 2024 May 11;176:108555. doi: 10.1016/j.compbiomed.2024.108555. Online ahead of print.

ABSTRACT

Cardiovascular diagnostics relies heavily on the ECG (ECG), which reveals significant information about heart rhythm and function. Despite their significance, traditional ECG measures employing electrodes have limitations. As a result of extended electrode attachments, patients may experience skin irritation or pain, and motion artifacts may interfere with signal accuracy. Additionally, ECG monitoring usually requires highly trained professionals and specialized equipment, which increases the treatment's complexity and cost. In critical care scenarios, such as continuous monitoring of hospitalized patients, wearable sensors for collecting ECG data may be difficult to use. Although there are issues with ECG, it remains a valuable tool for diagnosing and monitoring cardiac disorders due to its non-invasive nature and the detailed information it provides about the heart. The goal of this study is to present an innovative method for generating continuous ECG waveforms from non-contact radar data by using Deep Learning. The method can eliminate the need for invasive or wearable biosensors and expensive equipment to collect ECGs. In this paper, we propose the MultiResLinkNet, a one-dimensional convolutional neural network (1D CNN) model for generating ECG signals from radar waveforms. With the help of a publicly accessible radar benchmark dataset, an end-to-end DL architecture is trained and assessed. There are six ports of raw radar data in this dataset, along with ground truth physiological signals collected from 30 participants in five distinct scenarios: Resting, Valsalva, Apnea, Tilt-up, and Tilt-down. By using strong temporal and spectral measurements, we assessed our proposed framework's ability to convert ECG data from Radar signals in three distinct scenarios, namely Resting, Valsalva, and Apnea (RVA). ECG segmentation performed better by MultiResLinkNet than by state-of-the-art networks in both combined and individual cases. As a result of the simulations, the resting, valsalva, and RVA scenarios showed the highest average temporal values, respectively: 66.09523 ± 19.33, 60.13625 ± 21.92, and 61.86265 ± 21.37. In addition, it exhibited the highest spectral correlation values (82.4388 ± 18.42 (Resting), 77.05186 ± 23.26 (Valsalva), 74.65785 ± 23.17 (Apnea), and 79.96201 ± 20.82 (RVA)), along with minimal temporal and spectral errors in almost every case. The qualitative evaluation revealed strong similarities between generated and actual ECG waveforms. As a result of our method of forecasting ECG patterns from remote radar data, we can monitor high-risk patients, especially those undergoing surgery.

PMID:38749323 | DOI:10.1016/j.compbiomed.2024.108555

Comput Biol Med. 2024 May 6;176:108525. doi: 10.1016/j.compbiomed.2024.108525. Online ahead of print.

ABSTRACT

Deep neural networks have become increasingly popular for analyzing ECG data because of their ability to accurately identify cardiac conditions and hidden clinical factors. However, the lack of transparency due to the black box nature of these models is a common concern. To address this issue, explainable AI (XAI) methods can be employed. In this study, we present a comprehensive analysis of post-hoc XAI methods, investigating the glocal (aggregated local attributions over multiple samples) and global (concept based XAI) perspectives. We have established a set of sanity checks to identify saliency as the most sensible attribution method. We provide a dataset-wide analysis across entire patient subgroups, which goes beyond anecdotal evidence, to establish the first quantitative evidence for the alignment of model behavior with cardiologists' decision rules. Furthermore, we demonstrate how these XAI techniques can be utilized for knowledge discovery, such as identifying subtypes of myocardial infarction. We believe that these proposed methods can serve as building blocks for a complementary assessment of the internal validity during a certification process, as well as for knowledge discovery in the field of ECG analysis.

PMID:38749322 | DOI:10.1016/j.compbiomed.2024.108525

Med Phys. 2024 May 15. doi: 10.1002/mp.17128. Online ahead of print.

ABSTRACT

BACKGROUND: Segmentation of the parotid glands and tumors by MR images is essential for treating parotid gland tumors. However, segmentation of the parotid glands is particularly challenging due to their variable shape and low contrast with surrounding structures.

PURPOSE: The lack of large and well-annotated datasets limits the development of deep learning in medical images. As an unsupervised learning method, contrastive learning has seen rapid development in recent years. It can better use unlabeled images and is hopeful to improve parotid gland segmentation.

METHODS: We propose Swin MoCo, a momentum contrastive learning network with Swin Transformer as its backbone. The ImageNet supervised model is used as the initial weights of Swin MoCo, thus improving the training effects on small medical image datasets.

RESULTS: Swin MoCo trained with transfer learning improves parotid gland segmentation to 89.78% DSC, 85.18% mIoU, 3.60 HD, and 90.08% mAcc. On the Synapse multi-organ computed tomography (CT) dataset, using Swin MoCo as the pre-trained model of Swin-Unet yields 79.66% DSC and 12.73 HD, which outperforms the best result of Swin-Unet on the Synapse dataset.

CONCLUSIONS: The above improvements require only 4 h of training on a single NVIDIA Tesla V100, which is computationally cheap. Swin MoCo provides new approaches to improve the performance of tasks on small datasets. The code is publicly available at https://github.com/Zian-Xu/Swin-MoCo.

PMID:38749016 | DOI:10.1002/mp.17128

ACS Appl Mater Interfaces. 2024 May 15. doi: 10.1021/acsami.4c02428. Online ahead of print.

ABSTRACT

Bubble dynamics significantly impact mass transfer and energy conversion in electrochemical gas evolution reactions. Micro-/nanostructured surfaces with extreme wettability have been employed as gas-evolving electrodes to promote bubble departure and decrease the bubble-induced overpotential. However, effects of the electrodes' wickability on the electrochemical reaction performances remain elusive. In this work, hydrogen evolution reaction (HER) performances are experimentally investigated using micropillar array electrodes with varying interpillar spacings, and effects of the electrodes' wettability, wickability as well as bubble adhesion are discussed. A deep learning-based object detection model was used to obtain bubble counts and bubble departure size distributions. We show that microstructures on the electrode have little effect on the total bubble counts and bubble size distribution characteristics at low current densities. At high current densities, however, micropillar array electrodes have much higher total bubble counts and smaller bubble departure sizes compared with the flat electrode. We also demonstrate that surface wettability is a critical factor influencing HER performances under low current densities, where bubbles exist in an isolated regime. Under high current densities, where bubbles are in an interacting regime, the wickability of the micropillar array electrodes emerges as a determining factor. This work elucidates the roles of surface wettability and wickability on enhancing electrochemical performances, providing guidelines for the optimal design of micro-/nanostructured electrodes in various gas evolution reactions.

PMID:38749009 | DOI:10.1021/acsami.4c02428

STAR Protoc. 2024 May 14;5(2):103067. doi: 10.1016/j.xpro.2024.103067. Online ahead of print.

ABSTRACT

Single-cell RNA sequencing (scRNA-seq) provides high resolution of cell-to-cell variation in gene expression and offers insights into cell heterogeneity, differentiating dynamics, and disease mechanisms. However, technical challenges such as low capture rates and dropout events can introduce noise in data analysis. Here, we present a deep learning framework, called the dynamic batching adversarial autoencoder (DB-AAE), for denoising scRNA-seq datasets. First, we describe steps to set up the computing environment, training, and tuning. Then, we depict the visualization of the denoising results. For complete details on the use and execution of this protocol, please refer to Ko et al.1.

PMID:38748883 | DOI:10.1016/j.xpro.2024.103067

STAR Protoc. 2024 May 14;5(2):103066. doi: 10.1016/j.xpro.2024.103066. Online ahead of print.

ABSTRACT

The advent of single-cell multi-omics sequencing technology makes it possible for researchers to leverage multiple modalities for individual cells. Here, we present a protocol to perform integrative analysis of high-dimensional single-cell multimodal data using an interpretable deep learning technique called moETM. We describe steps for data preprocessing, multi-omics integration, inclusion of prior pathway knowledge, and cross-omics imputation. As a demonstration, we used the single-cell multi-omics data collected from bone marrow mononuclear cells (GSE194122) as in our original study. For complete details on the use and execution of this protocol, please refer to Zhou et al.1.

PMID:38748882 | DOI:10.1016/j.xpro.2024.103066

J Med Chem. 2024 May 15. doi: 10.1021/acs.jmedchem.4c00692. Online ahead of print.

ABSTRACT

Precisely predicting molecular properties is crucial in drug discovery, but the scarcity of labeled data poses a challenge for applying deep learning methods. While large-scale self-supervised pretraining has proven an effective solution, it often neglects domain-specific knowledge. To tackle this issue, we introduce Task-Oriented Multilevel Learning based on BERT (TOML-BERT), a dual-level pretraining framework that considers both structural patterns and domain knowledge of molecules. TOML-BERT achieved state-of-the-art prediction performance on 10 pharmaceutical datasets. It has the capability to mine contextual information within molecular structures and extract domain knowledge from massive pseudo-labeled data. The dual-level pretraining accomplished significant positive transfer, with its two components making complementary contributions. Interpretive analysis elucidated that the effectiveness of the dual-level pretraining lies in the prior learning of a task-related molecular representation. Overall, TOML-BERT demonstrates the potential of combining multiple pretraining tasks to extract task-oriented knowledge, advancing molecular property prediction in drug discovery.

PMID:38748846 | DOI:10.1021/acs.jmedchem.4c00692

IUBMB Life. 2024 May 15. doi: 10.1002/iub.2819. Online ahead of print.

ABSTRACT

This research delves into the exploration of the potential of tocopherol-based nanoemulsion as a therapeutic agent for cardiovascular diseases (CVD) through an in-depth molecular docking analysis. The study focuses on elucidating the molecular interactions between tocopherol and seven key proteins (1O8a, 4YAY, 4DLI, 1HW9, 2YCW, 1BO9 and 1CX2) that play pivotal roles in CVD development. Through rigorous in silico docking investigations, assessment was conducted on the binding affinities, inhibitory potentials and interaction patterns of tocopherol with these target proteins. The findings revealed significant interactions, particularly with 4YAY, displaying a robust binding energy of -6.39 kcal/mol and a promising Ki value of 20.84 μM. Notable interactions were also observed with 1HW9, 4DLI, 2YCW and 1CX2, further indicating tocopherol's potential therapeutic relevance. In contrast, no interaction was observed with 1BO9. Furthermore, an examination of the common residues of 4YAY bound to tocopherol was carried out, highlighting key intermolecular hydrophobic bonds that contribute to the interaction's stability. Tocopherol complies with pharmacokinetics (Lipinski's and Veber's) rules for oral bioavailability and proves safety non-toxic and non-carcinogenic. Thus, deep learning-based protein language models ESM1-b and ProtT5 were leveraged for input encodings to predict interaction sites between the 4YAY protein and tocopherol. Hence, highly accurate predictions of these critical protein-ligand interactions were achieved. This study not only advances the understanding of these interactions but also highlights deep learning's immense potential in molecular biology and drug discovery. It underscores tocopherol's promise as a cardiovascular disease management candidate, shedding light on its molecular interactions and compatibility with biomolecule-like characteristics.

PMID:38748776 | DOI:10.1002/iub.2819

PLoS One. 2024 May 15;19(5):e0303688. doi: 10.1371/journal.pone.0303688. eCollection 2024.

ABSTRACT

Deep learning models struggle to effectively capture data features and make accurate predictions because of the strong non-linear characteristics of arbitrage data. Therefore, to fully exploit the model performance, researchers have focused on network structure and hyperparameter selection using various swarm intelligence algorithms for optimization. Sparrow Search Algorithm (SSA), a classic heuristic method that simulates the sparrows' foraging and anti-predatory behavior, has demonstrated excellent performance in various optimization problems. Hence, in this study, the Multi-Strategy Modified Sparrow Search Algorithm (MSMSSA) is applied to the Long Short-Term Memory (LSTM) network to construct an arbitrage spread prediction model (MSMSSA-LSTM). In the modified algorithm, the good point set theory, the proportion-adaptive strategy, and the improved location update method are introduced to further enhance the spatial exploration capability of the sparrow. The proposed model was evaluated using the real spread data of rebar and hot coil futures in the Chinese futures market. The obtained results showed that the mean absolute percentage error, root mean square error, and mean absolute error of the proposed model had decreased by a maximum of 58.5%, 65.2%, and 67.6% compared to several classical models. The model has high accuracy in predicting arbitrage spreads, which can provide some reference for investors.

PMID:38748753 | DOI:10.1371/journal.pone.0303688