J Dent. 2024 May 8:105057. doi: 10.1016/j.jdent.2024.105057. Online ahead of print.

ABSTRACT

OBJECTIVES: This study focuses on artificial intelligence (AI)-assisted analysis of alveolar bone for periodontitis in a mouse model with the aim to create an automatic deep-learning segmentation model that enables researchers to easily examine alveolar bone from micro-computed tomography (µCT) data without needing prior machine learning knowledge.

METHODS: Ligature-induced experimental periodontitis was produced by placing a small-diameter silk sling ligature around the left maxillary second molar. At 4, 7, 9, or 14 days, the maxillary bone was harvested and processed with a µCT scanner (µCT-45, Scanco). Using Dragonfly (v2021.3), we developed a 3D deep learning model based on the U-Net AI deep learning engine for segmenting materials in complex images to measure alveolar bone volume (BV) and bone mineral density (BMD) while excluding the teeth from the measurements.

RESULTS: This model generates 3D segmentation output for a selected region of interest with over 98% accuracy on different formats of µCT data. BV on the ligature side gradually decreased from 0.87 mm3 to 0.50 mm3 on day 9 and then increased to 0.63 mm3 on day 14. The ligature side lost 4.6% of BMD on day 4, 9.6% on day 7, 17.7% on day 9, and 21.1% on day 14.

CONCLUSIONS: This study developed an AI model that can be downloaded and easily applied, allowing researchers to assess metrics including BV, BMD, and trabecular bone thickness, while excluding teeth from the measurements of mouse alveolar bone.

CLINICAL SIGNIFICANCE: This work offers an innovative, user-friendly automatic segmentation model that is fast, accurate, and reliable, demonstrating new potential uses of artificial intelligence (AI) in dentistry with great potential in diagnosing, treating, and prognosis of oral diseases.

PMID:38729290 | DOI:10.1016/j.jdent.2024.105057

Int J Surg. 2024 May 9. doi: 10.1097/JS9.0000000000001578. Online ahead of print.

ABSTRACT

INTRODUCTION: The incidence of occult cervical lymph node metastases (OCLNM) is reported to be 20%-30% in early-stage oral cancer and oropharyngeal cancer. There is a lack of an accurate diagnostic method to predict occult lymph node metastasis and to help surgeons make precise treatment decisions.

AIM: To construct and evaluate a preoperative diagnostic method to predict occult lymph node metastasis (OCLNM) in early-stage oral and oropharyngeal squamous cell carcinoma (OC and OP SCC) based on deep learning features (DLFs) and radiomics features.

METHODS: A total of 319 patients diagnosed with early-stage OC or OP SCC were retrospectively enrolled and divided into training, test and external validation sets. Traditional radiomics features and DLFs were extracted from their MRI images. The least absolute shrinkage and selection operator (LASSO) analysis was employed to identify the most valuable features. Prediction models for OCLNM were developed using radiomics features and DLFs. The effectiveness of the models and their clinical applicability were evaluated using the area under the curve (AUC), decision curve analysis (DCA) and survival analysis.

RESULTS: Seventeen prediction models were constructed. The Resnet50 deep learning (DL) model based on the combination of radiomics and DL features achieves the optimal performance, with AUC values of 0.928 (95% CI: 0.881-0.975), 0.878 (95% CI: 0.766-0.990), 0.796 (95% CI: 0.666-0.927) and 0.834 (95% CI: 0.721-0.947) in the training, test, external validation set1 and external validation set2, respectively. Moreover, the Resnet50 model has great prediction value of prognosis in patients with early-stage OC and OP SCC.

CONCLUSION: The proposed MRI-based Resnet50 deep learning model demonstrated high capability in diagnosis of OCLNM and prognosis prediction in the early-stage OC and OP SCC. The Resnet50 model could help refine the clinical diagnosis and treatment of the early-stage OC and OP SCC.

PMID:38729119 | DOI:10.1097/JS9.0000000000001578

Cell. 2024 May 9;187(10):2502-2520.e17. doi: 10.1016/j.cell.2024.03.035.

ABSTRACT

Human tissue, which is inherently three-dimensional (3D), is traditionally examined through standard-of-care histopathology as limited two-dimensional (2D) cross-sections that can insufficiently represent the tissue due to sampling bias. To holistically characterize histomorphology, 3D imaging modalities have been developed, but clinical translation is hampered by complex manual evaluation and lack of computational platforms to distill clinical insights from large, high-resolution datasets. We present TriPath, a deep-learning platform for processing tissue volumes and efficiently predicting clinical outcomes based on 3D morphological features. Recurrence risk-stratification models were trained on prostate cancer specimens imaged with open-top light-sheet microscopy or microcomputed tomography. By comprehensively capturing 3D morphologies, 3D volume-based prognostication achieves superior performance to traditional 2D slice-based approaches, including clinical/histopathological baselines from six certified genitourinary pathologists. Incorporating greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, further emphasizing the value of capturing larger extents of heterogeneous morphology.

PMID:38729110 | DOI:10.1016/j.cell.2024.03.035

Respir Res. 2024 May 10;25(1):203. doi: 10.1186/s12931-024-02840-z.

ABSTRACT

BACKGROUND: Although electronic nose (eNose) has been intensively investigated for diagnosing lung cancer, cross-site validation remains a major obstacle to be overcome and no studies have yet been performed.

METHODS: Patients with lung cancer, as well as healthy control and diseased control groups, were prospectively recruited from two referral centers between 2019 and 2022. Deep learning models for detecting lung cancer with eNose breathprint were developed using training cohort from one site and then tested on cohort from the other site. Semi-Supervised Domain-Generalized (Semi-DG) Augmentation (SDA) and Noise-Shift Augmentation (NSA) methods with or without fine-tuning was applied to improve performance.

RESULTS: In this study, 231 participants were enrolled, comprising a training/validation cohort of 168 individuals (90 with lung cancer, 16 healthy controls, and 62 diseased controls) and a test cohort of 63 individuals (28 with lung cancer, 10 healthy controls, and 25 diseased controls). The model has satisfactory results in the validation cohort from the same hospital while directly applying the trained model to the test cohort yielded suboptimal results (AUC, 0.61, 95% CI: 0.47─0.76). The performance improved after applying data augmentation methods in the training cohort (SDA, AUC: 0.89 [0.81─0.97]; NSA, AUC:0.90 [0.89─1.00]). Additionally, after applying fine-tuning methods, the performance further improved (SDA plus fine-tuning, AUC:0.95 [0.89─1.00]; NSA plus fine-tuning, AUC:0.95 [0.90─1.00]).

CONCLUSION: Our study revealed that deep learning models developed for eNose breathprint can achieve cross-site validation with data augmentation and fine-tuning. Accordingly, eNose breathprints emerge as a convenient, non-invasive, and potentially generalizable solution for lung cancer detection.

CLINICAL TRIAL REGISTRATION: This study is not a clinical trial and was therefore not registered.

PMID:38730430 | DOI:10.1186/s12931-024-02840-z

Nat Commun. 2024 May 10;15(1):3956. doi: 10.1038/s41467-024-48322-0.

ABSTRACT

Immunopeptidomics is crucial for immunotherapy and vaccine development. Because the generation of immunopeptides from their parent proteins does not adhere to clear-cut rules, rather than being able to use known digestion patterns, every possible protein subsequence within human leukocyte antigen (HLA) class-specific length restrictions needs to be considered during sequence database searching. This leads to an inflation of the search space and results in lower spectrum annotation rates. Peptide-spectrum match (PSM) rescoring is a powerful enhancement of standard searching that boosts the spectrum annotation performance. We analyze 302,105 unique synthesized non-tryptic peptides from the ProteomeTools project on a timsTOF-Pro to generate a ground-truth dataset containing 93,227 MS/MS spectra of 74,847 unique peptides, that is used to fine-tune the deep learning-based fragment ion intensity prediction model Prosit. We demonstrate up to 3-fold improvement in the identification of immunopeptides, as well as increased detection of immunopeptides from low input samples.

PMID:38730277 | DOI:10.1038/s41467-024-48322-0

Sci Rep. 2024 May 10;14(1):10753. doi: 10.1038/s41598-024-60245-w.

ABSTRACT

This paper proposes an approach to enhance the differentiation task between benign and malignant Breast Tumors (BT) using histopathology images from the BreakHis dataset. The main stages involve preprocessing, which encompasses image resizing, data partitioning (training and testing sets), followed by data augmentation techniques. Both feature extraction and classification tasks are employed by a Custom CNN. The experimental results show that the proposed approach using the Custom CNN model exhibits better performance with an accuracy of 84% than applying the same approach using other pretrained models, including MobileNetV3, EfficientNetB0, Vgg16, and ResNet50V2, that present relatively lower accuracies, ranging from 74 to 82%; these four models are used as both feature extractors and classifiers. To increase the accuracy and other performance metrics, Grey Wolf Optimization (GWO), and Modified Gorilla Troops Optimization (MGTO) metaheuristic optimizers are applied to each model separately for hyperparameter tuning. In this case, the experimental results show that the Custom CNN model, refined with MGTO optimization, reaches an exceptional accuracy of 93.13% in just 10 iterations, outperforming the other state-of-the-art methods, and the other four used pretrained models based on the BreakHis dataset.

PMID:38730248 | DOI:10.1038/s41598-024-60245-w

Nat Commun. 2024 May 10;15(1):3974. doi: 10.1038/s41467-024-48072-z.

ABSTRACT

Antibodies are engineerable quantities in medicine. Learning antibody molecular recognition would enable the in silico design of high affinity binders against nearly any proteinaceous surface. Yet, publicly available experiment antibody sequence-binding datasets may not contain the mutagenic, antigenic, or antibody sequence diversity necessary for deep learning approaches to capture molecular recognition. In part, this is because limited experimental platforms exist for assessing quantitative and simultaneous sequence-function relationships for multiple antibodies. Here we present MAGMA-seq, an integrated technology that combines multiple antigens and multiple antibodies and determines quantitative biophysical parameters using deep sequencing. We demonstrate MAGMA-seq on two pooled libraries comprising mutants of nine different human antibodies spanning light chain gene usage, CDR H3 length, and antigenic targets. We demonstrate the comprehensive mapping of potential antibody development pathways, sequence-binding relationships for multiple antibodies simultaneously, and identification of paratope sequence determinants for binding recognition for broadly neutralizing antibodies (bnAbs). MAGMA-seq enables rapid and scalable antibody engineering of multiple lead candidates because it can measure binding for mutants of many given parental antibodies in a single experiment.

PMID:38730230 | DOI:10.1038/s41467-024-48072-z

Sci Rep. 2024 May 10;14(1):10724. doi: 10.1038/s41598-024-60982-y.

ABSTRACT

The challenge of developing an Android malware detection framework that can identify malware in real-world apps is difficult for academicians and researchers. The vulnerability lies in the permission model of Android. Therefore, it has attracted the attention of various researchers to develop an Android malware detection model using permission or a set of permissions. Academicians and researchers have used all extracted features in previous studies, resulting in overburdening while creating malware detection models. But, the effectiveness of the machine learning model depends on the relevant features, which help in reducing the value of misclassification errors and have excellent discriminative power. A feature selection framework is proposed in this research paper that helps in selecting the relevant features. In the first stage of the proposed framework, t-test, and univariate logistic regression are implemented on our collected feature data set to classify their capacity for detecting malware. Multivariate linear regression stepwise forward selection and correlation analysis are implemented in the second stage to evaluate the correctness of the features selected in the first stage. Furthermore, the resulting features are used as input in the development of malware detection models using three ensemble methods and a neural network with six different machine-learning algorithms. The developed models' performance is compared using two performance parameters: F-measure and Accuracy. The experiment is performed by using half a million different Android apps. The empirical findings reveal that malware detection model developed using features selected by implementing proposed feature selection framework achieved higher detection rate as compared to the model developed using all extracted features data set. Further, when compared to previously developed frameworks or methodologies, the experimental results indicates that model developed in this study achieved an accuracy of 98.8%.

PMID:38730228 | DOI:10.1038/s41598-024-60982-y

Nat Comput Sci. 2024 May 10. doi: 10.1038/s43588-024-00625-4. Online ahead of print.

ABSTRACT

Single-cell epigenomic data has been growing continuously at an unprecedented pace, but their characteristics such as high dimensionality and sparsity pose substantial challenges to downstream analysis. Although deep learning models-especially variational autoencoders-have been widely used to capture low-dimensional feature embeddings, the prevalent Gaussian assumption somewhat disagrees with real data, and these models tend to struggle to incorporate reference information from abundant cell atlases. Here we propose CASTLE, a deep generative model based on the vector-quantized variational autoencoder framework to extract discrete latent embeddings that interpretably characterize single-cell chromatin accessibility sequencing data. We validate the performance and robustness of CASTLE for accurate cell-type identification and reasonable visualization compared with state-of-the-art methods. We demonstrate the advantages of CASTLE for effective incorporation of existing massive reference datasets in a weakly supervised or supervised manner. We further demonstrate CASTLE's capacity for intuitively distilling cell-type-specific feature spectra that unveil cell heterogeneity and biological implications quantitatively.

PMID:38730185 | DOI:10.1038/s43588-024-00625-4

Sci Rep. 2024 May 10;14(1):10705. doi: 10.1038/s41598-024-61598-y.

ABSTRACT

This paper aims to propose a prediction method based on Deep Learning (DL) and Internet of Things (IoT) technology, focusing on the ecological security and tourist satisfaction of Ice-and-Snow Tourism (IST) to solve practical problems in this field. Accurate predictions of ecological security and tourist satisfaction in IST have been achieved by collecting and analyzing environment and tourist behavior data and combining with DL models, such as convolutional and recurrent neural networks. The experimental results show that the proposed method has significant advantages in performance indicators, such as accuracy, F1 score, Mean Squared Error (MSE), and correlation coefficient. Compared to other similar methods, the method proposed improves accuracy by 3.2%, F1 score by 0.03, MSE by 0.006, and correlation coefficient by 0.06. These results emphasize the important role of combining DL with IoT technology in predicting ecological security and tourist satisfaction in IST.

PMID:38730047 | DOI:10.1038/s41598-024-61598-y

J Hum Genet. 2024 May 10. doi: 10.1038/s10038-024-01256-3. Online ahead of print.

ABSTRACT

Cell-type-specific regulatory elements, cataloged through extensive experiments and bioinformatics in large-scale consortiums, have enabled enrichment analyses of genetic associations that primarily utilize positional information of the regulatory elements. These analyses have identified cell types and pathways genetically associated with human complex traits. However, our understanding of detailed allelic effects on these elements' activities and on-off states remains incomplete, hampering the interpretation of human genetic study results. This review introduces machine learning methods to learn sequence-dependent transcriptional regulation mechanisms from DNA sequences for predicting such allelic effects (not associations). We provide a concise history of machine-learning-based approaches, the requirements, and the key computational processes, focusing on primers in machine learning. Convolution and self-attention, pivotal in modern deep-learning models, are explained through geometrical interpretations using dot products. This facilitates understanding of the concept and why these have been used for machine learning for DNA sequences. These will inspire further research in this genetics and genomics field.

PMID:38730006 | DOI:10.1038/s10038-024-01256-3

J Appl Clin Med Phys. 2024 May 10:e14378. doi: 10.1002/acm2.14378. Online ahead of print.

ABSTRACT

BACKGROUND: The diagnosis of lumbar spinal stenosis (LSS) can be challenging because radicular pain is not often present in the culprit-level localization. Accurate segmentation and quantitative analysis of the lumbar dura on radiographic images are key to the accurate differential diagnosis of LSS. The aim of this study is to develop an automatic dura-contouring tool for radiographic quantification on computed tomography myelogram (CTM) for patients with LSS.

METHODS: A total of 518 CTM cases with or without lumbar stenosis were included in this study. A deep learning (DL) segmentation algorithm 3-dimensional (3D) U-Net was deployed. A total of 210 labeled cases were used to develop the dura-contouring tool, with the ratio of the training, independent testing, and external validation datasets being 150:30:30. The Dice score (DCS) was the primary measure to evaluate the segmentation performance of the 3D U-Net, which was subsequently developed as the dura-contouring tool to segment another unlabeled 308 CTM cases with LSS. Automatic masks of 446 slices on the stenotic levels were then meticulously reviewed and revised by human experts, and the cross-sectional area (CSA) of the dura was compared.

RESULTS: The mean DCS of the 3D U-Net were 0.905 ± 0.080, 0.933 ± 0.018, and 0.928 ± 0.034 in the five-fold cross-validation, the independent testing, and the external validation datasets, respectively. The segmentation performance of the dura-contouring tool was also comparable to that of the second observer (the human expert). With the dura-contouring tool, only 59.0% (263/446) of the automatic masks of the stenotic slices needed to be revised. In the revised cases, there were no significant differences in the dura CSA between automatic masks and corresponding revised masks (p = 0.652). Additionally, a strong correlation of dura CSA was found between the automatic masks and corresponding revised masks (r = 0.805).

CONCLUSIONS: A dura-contouring tool was developed that could automatically segment the dural sac on CTM, and it demonstrated high accuracy and generalization ability. Additionally, the dura-contouring tool has the potential to be applied in patients with LSS because it facilitates the quantification of the dural CSA on stenotic slices.

PMID:38729652 | DOI:10.1002/acm2.14378

J Dent. 2024 May 8:105056. doi: 10.1016/j.jdent.2024.105056. Online ahead of print.

ABSTRACT

OBJECTIVES: The transition from manual to automatic cephalometric landmark identification has not yet reached a consensus for clinical application in orthodontic diagnosis. The present umbrella review aimed to assess artificial intelligence (AI) performance in automatic 2D and 3D cephalometric landmark identification.

DATA: A combination of free text words and MeSH keywords pooled by boolean operators: Automa* AND cephalo* AND ("artificial intelligence" OR "machine learning" OR "deep learning" OR "learning").

SOURCES: A search strategy without a timeframe setting was conducted on PubMed, Scopus, Web of Science, Cochrane Library and LILACS.

STUDY SELECTION: The study protocol followed the PRISMA guidelines and the PICO question was formulated according to the aim of the article. The database search led to the selection of 15 articles that were assessed for eligibility in full-text. Finally, 11 systematic reviews met the inclusion criteria and were analyzed according to the risk of bias in systematic reviews (ROBIS) tool.

CONCLUSIONS: AI was not able to identify the various cephalometric landmarks with the same accuracy. Since most of the included studies' conclusions were based on a wrong 2 mm cut-off difference between the AI automatic landmark location and that allocated by human operators, future research should focus on refining the most powerful architectures to improve the clinical relevance of AI-driven automatic cephalometric analysis.

CLINICAL SIGNIFICANCE: Despite a progressively improved performance, AI has exceeded the recommended magnitude of error for most cephalometric landmarks. Moreover, AI automatic landmarking on 3D CBCT appeared to be less accurate compared to that on 2D X-rays. To date, AI-driven cephalometric landmarking still requires the final supervision of an experienced orthodontist.

PMID:38729291 | DOI:10.1016/j.jdent.2024.105056

Waste Manag. 2024 May 9;183:74-86. doi: 10.1016/j.wasman.2024.04.040. Online ahead of print.

ABSTRACT

The increasing volume of garment waste underscores the need for advanced sorting and recycling strategies. As a critical procedure in the secondary usage of waste clothes, qualitative classification of garments categorizes post-consumer clothes based on types and styles. However, this process currently relies on manual labor, which is inefficient, labor-intensive, and poses risks to workers. Despite efforts to implement automatic clothes classification systems, challenges persist due to visual complexities such as similar colors, deformations, and occlusions. In response to these challenges, this study introduces an enhanced intelligent machine vision system with attention mechanisms designed to automate the laborious and skill-demanding task of garment classification. Initially, a waste garment dataset comprising approximately 27,000 garments was curated using a self-developed automatic classification platform. Subsequently, the proposed attention method parameters were selected, and a series of benchmarks were conducted against state-of-the-art methods. Finally, the proposed system underwent a two-week online deployment to evaluate its running stability and sensitivity to similar colors, deformation, and occlusion in industrial production settings. The benchmarks indicate that the proposed method significantly improves classification accuracy across various models. The visualization interpretation of Grad-CAM reveals that the proposed method effectively handles complex environments by directing its focus toward garment-related pixels. Notably, the proposed system elevates classification accuracy from 68.28 % to human-level performance (>90 %) while ensuring greater running stability. This advancement holds promise for automating the classification process and potentially alleviating workers from labor-intensive and hazardous tasks associated with clothes recycling.

PMID:38728770 | DOI:10.1016/j.wasman.2024.04.040

J Med Internet Res. 2024 May 10;26:e49848. doi: 10.2196/49848.

ABSTRACT

BACKGROUND: Acute myocardial infarction (AMI) is one of the most severe cardiovascular diseases and is associated with a high risk of in-hospital mortality. However, the current deep learning models for in-hospital mortality prediction lack interpretability.

OBJECTIVE: This study aims to establish an explainable deep learning model to provide individualized in-hospital mortality prediction and risk factor assessment for patients with AMI.

METHODS: In this retrospective multicenter study, we used data for consecutive patients hospitalized with AMI from the Chongqing University Central Hospital between July 2016 and December 2022 and the Electronic Intensive Care Unit Collaborative Research Database. These patients were randomly divided into training (7668/10,955, 70%) and internal test (3287/10,955, 30%) data sets. In addition, data of patients with AMI from the Medical Information Mart for Intensive Care database were used for external validation. Deep learning models were used to predict in-hospital mortality in patients with AMI, and they were compared with linear and tree-based models. The Shapley Additive Explanations method was used to explain the model with the highest area under the receiver operating characteristic curve in both the internal test and external validation data sets to quantify and visualize the features that drive predictions.

RESULTS: A total of 10,955 patients with AMI who were admitted to Chongqing University Central Hospital or included in the Electronic Intensive Care Unit Collaborative Research Database were randomly divided into a training data set of 7668 (70%) patients and an internal test data set of 3287 (30%) patients. A total of 9355 patients from the Medical Information Mart for Intensive Care database were included for independent external validation. In-hospital mortality occurred in 8.74% (670/7668), 8.73% (287/3287), and 9.12% (853/9355) of the patients in the training, internal test, and external validation cohorts, respectively. The Self-Attention and Intersample Attention Transformer model performed best in both the internal test data set and the external validation data set among the 9 prediction models, with the highest area under the receiver operating characteristic curve of 0.86 (95% CI 0.84-0.88) and 0.85 (95% CI 0.84-0.87), respectively. Older age, high heart rate, and low body temperature were the 3 most important predictors of increased mortality, according to the explanations of the Self-Attention and Intersample Attention Transformer model.

CONCLUSIONS: The explainable deep learning model that we developed could provide estimates of mortality and visual contribution of the features to the prediction for a patient with AMI. The explanations suggested that older age, unstable vital signs, and metabolic disorders may increase the risk of mortality in patients with AMI.

PMID:38728685 | DOI:10.2196/49848

Sci Adv. 2024 May 10;10(19):eadj6990. doi: 10.1126/sciadv.adj6990. Epub 2024 May 10.

ABSTRACT

Mosquito-borne diseases like malaria are rising globally, and improved mosquito vector surveillance is needed. Survival of Anopheles mosquitoes is key for epidemiological monitoring of malaria transmission and evaluation of vector control strategies targeting mosquito longevity, as the risk of pathogen transmission increases with mosquito age. However, the available tools to estimate field mosquito age are often approximate and time-consuming. Here, we show a rapid method that combines matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry with deep learning for mosquito age prediction. Using 2763 mass spectra from the head, legs, and thorax of 251 field-collected Anopheles arabiensis mosquitoes, we developed deep learning models that achieved a best mean absolute error of 1.74 days. We also demonstrate consistent performance at two ecological sites in Senegal, supported by age-related protein changes. Our approach is promising for malaria control and the field of vector biology, benefiting other disease vectors like Aedes mosquitoes.

PMID:38728404 | DOI:10.1126/sciadv.adj6990

PLoS One. 2024 May 10;19(5):e0299603. doi: 10.1371/journal.pone.0299603. eCollection 2024.

ABSTRACT

Accurate forecasting of PM2.5 concentrations serves as a critical tool for mitigating air pollution. This study introduces a novel hybrid prediction model, termed MIC-CEEMDAN-CNN-BiGRU, for short-term forecasting of PM2.5 concentrations using a 24-hour historical data window. Utilizing the Maximal Information Coefficient (MIC) for feature selection, the model integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Convolutional Neural Network (CNN), and Bidirectional Recurrent Gated Neural Network (BiGRU) to optimize predictive accuracy. We used 2016 PM2.5 monitoring data from Beijing, China as the empirical basis of this study and compared the model with several deep learning frameworks. RNN, LSTM, GRU, and other hybrid models based on GRU, respectively. The experimental results show that the prediction results of the hybrid model proposed in this question are more accurate than those of other models, and the R2 of the hybrid model proposed in this paper improves the R2 by nearly 5 percentage points compared with that of the single model; reduces the MAE by nearly 5 percentage points; and reduces the RMSE by nearly 11 percentage points. The results show that the hybrid prediction model proposed in this study is more accurate than other models in predicting PM2.5.

PMID:38728371 | DOI:10.1371/journal.pone.0299603

PLoS One. 2024 May 10;19(5):e0299696. doi: 10.1371/journal.pone.0299696. eCollection 2024.

ABSTRACT

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) caused the COVID-19 disease, which represents a new life-threatening disaster. Regarding viral infection, many therapeutics have been investigated to alleviate the epidemiology such as vaccines and receptor decoys. However, the continuous mutating coronavirus, especially the variants of Delta and Omicron, are tended to invalidate the therapeutic biological product. Thus, it is necessary to develop molecular entities as broad-spectrum antiviral drugs. Coronavirus replication is controlled by the viral 3-chymotrypsin-like cysteine protease (3CLpro) enzyme, which is required for the virus's life cycle. In the cases of severe acute respiratory syndrome coronavirus (SARS-CoV) and middle east respiratory syndrome coronavirus (MERS-CoV), 3CLpro has been shown to be a promising therapeutic development target. Here we proposed an attention-based deep learning framework for molecular graphs and sequences, training from the BindingDB 3CLpro dataset (114,555 compounds). After construction of such model, we conducted large-scale screening the in vivo/vitro dataset (276,003 compounds) from Zinc Database and visualize the candidate compounds with attention score. geometric-based affinity prediction was employed for validation. Finally, we established a 3CLpro-specific deep learning framework, namely GraphDPI-3CL (AUROC: 0.958) achieved superior performance beyond the existing state of the art model and discovered 10 molecules with a high binding affinity of 3CLpro and superior binding mode.

PMID:38728335 | DOI:10.1371/journal.pone.0299696

PLoS One. 2024 May 10;19(5):e0302067. doi: 10.1371/journal.pone.0302067. eCollection 2024.

ABSTRACT

Many lumbar spine diseases are caused by defects or degeneration of lumbar intervertebral discs (IVD) and are usually diagnosed through inspection of the patient's lumbar spine MRI. Efficient and accurate assessments of the lumbar spine are essential but a challenge due to the size of the clinical radiologist workforce not keeping pace with the demand for radiology services. In this paper, we present a methodology to automatically annotate lumbar spine IVDs with their height and degenerative state which is quantified using the Pfirrmann grading system. The method starts with semantic segmentation of a mid-sagittal MRI image into six distinct non-overlapping regions, including the IVD and vertebrae regions. Each IVD region is then located and assigned with its label. Using geometry, a line segment bisecting the IVD is determined and its Euclidean distance is used as the IVD height. We then extract an image feature, called self-similar color correlogram, from the nucleus of the IVD region as a representation of the region's spatial pixel intensity distribution. We then use the IVD height data and machine learning classification process to predict the Pfirrmann grade of the IVD. We considered five different deep learning networks and six different machine learning algorithms in our experiment and found the ResNet-50 model and Ensemble of Decision Trees classifier to be the combination that gives the best results. When tested using a dataset containing 515 MRI studies, we achieved a mean accuracy of 88.1%.

PMID:38728318 | DOI:10.1371/journal.pone.0302067

J Xray Sci Technol. 2024 May 9. doi: 10.3233/XST-240016. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate volumetric segmentation of primary central nervous system lymphoma (PCNSL) is essential for assessing and monitoring the tumor before radiotherapy and the treatment planning. The tedious manual segmentation leads to interindividual and intraindividual differences, while existing automatic segmentation methods cause under-segmentation of PCNSL due to the complex and multifaceted nature of the tumor.

OBJECTIVE: To address the challenges of small size, diffused distribution, poor inter-layer continuity on the same axis, and tendency for over-segmentation in brain MRI PCNSL segmentation, we propose an improved attention module based on nnUNet for automated segmentation.

METHODS: We collected 114 T1 MRI images of patients in the Huashan Hospital, Shanghai. Then randomly split the total of 114 cases into 5 distinct training and test sets for a 5-fold cross-validation. To efficiently and accurately delineate the PCNSL, we proposed an improved attention module based on nnU-Net with 3D convolutions, batch normalization, and residual attention (res-attention) to learn the tumor region information. Additionally, multi-scale dilated convolution kernels with different dilation rates were integrated to broaden the receptive field. We further used attentional feature fusion with 3D convolutions (AFF3D) to fuse the feature maps generated by multi-scale dilated convolution kernels to reduce under-segmentation.

RESULTS: Compared to existing methods, our attention module improves the ability to distinguish diffuse and edge enhanced types of tumors; and the broadened receptive field captures tumor features of various scales and shapes more effectively, achieving a 0.9349 Dice Similarity Coefficient (DSC).

CONCLUSIONS: Quantitative results demonstrate the effectiveness of the proposed method in segmenting the PCNSL. To our knowledge, this is the first study to introduce attention modules into deep learning for segmenting PCNSL based on brain magnetic resonance imaging (MRI), promoting the localization of PCNSL before radiotherapy.

PMID:38728198 | DOI:10.3233/XST-240016