Med Biol Eng Comput. 2024 Feb 6. doi: 10.1007/s11517-024-03022-1. Online ahead of print.

ABSTRACT

This paper presents a novel multi-scale attention residual network (MAResNet) for diagnosing patients with pulmonary tuberculosis (PTB) by computed tomography (CT) images. First, a three-dimensional (3D) network structure is applied in MAResNet based on the continuity and correlation of nodal features on different slices of CT images. Secondly, MAResNet incorporates the residual module and Convolutional Block Attention Module (CBAM) to reuse the shallow features of CT images and focus on key features to enhance the feature distinguishability of images. In addition, multi-scale inputs can increase the global receptive field of the network, extract the location information of PTB, and capture the local details of nodules. The expression ability of both high-level and low-level semantic information in the network can also be enhanced. The proposed MAResNet shows excellent results, with overall 94% accuracy in PTB classification. MAResNet based on 3D CT images can assist doctors make more accurate diagnosis of PTB and alleviate the burden of manual screening. In the experiment, a called Grad-CAM was employed to enhance the class activation mapping (CAM) technique for analyzing the model's output, which can identify lesions in important parts of the lungs and make transparent decisions.

PMID:38319503 | DOI:10.1007/s11517-024-03022-1

NEJM Evid. 2022 Jun;1(6):EVIDe2200098. doi: 10.1056/EVIDe2200098. Epub 2022 Apr 13.

ABSTRACT

Artificial intelligence (AI) has become a part of many image-based specialties, such as radiology and pathology, as well as medical specialties in which "oscopy" is the key to current practice. In gastroenterology, for example, AI is being explored as an aid to endoscopists to visually distinguish precancerous lesions in upper and lower endoscopy. Although there have been a variety of approaches to the employment of AI for this purpose, deep-learning algorithms, which combine the extraction and classification of image features using deep neural networks,1 have the capability of self-learning.

PMID:38319281 | DOI:10.1056/EVIDe2200098

Cancer Biol Med. 2024 Feb 5;20(12):j.issn.2095-3941.2023.0436. doi: 10.20892/j.issn.2095-3941.2023.0436.

NO ABSTRACT

PMID:38318925 | DOI:10.20892/j.issn.2095-3941.2023.0436

Curr Top Med Chem. 2024 Feb 2. doi: 10.2174/0115680266282179240124072121. Online ahead of print.

ABSTRACT

BACKGROUND: SARS-CoV-2, the unique coronavirus that causes COVID-19, has wreaked damage around the globe, with victims displaying a wide range of difficulties that have encouraged medical professionals to look for innovative technical solutions and therapeutic approaches. Artificial intelligence-based methods have contributed a significant part in tackling complicated issues, and some institutions have been quick to embrace and tailor these solutions in response to the COVID-19 pandemic's obstacles. Here, in this review article, we have covered a few DL techniques for COVID-19 detection and diagnosis, as well as ML techniques for COVID-19 identification, severity classification, vaccine and drug development, mortality rate prediction, contact tracing, risk assessment, and public distancing. This review illustrates the overall impact of AI/ML tools on tackling and managing the outbreak.

PURPOSE: The focus of this research was to undertake a thorough evaluation of the literature on the part of Artificial Intelligence (AI) as a complete and efficient solution in the battle against the COVID-19 epidemic in the domains of detection and diagnostics of disease, mortality prediction and vaccine as well as drug development.

METHODS: A comprehensive exploration of PubMed, Web of Science, and Science Direct was conducted using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) regulations to find all possibly suitable papers conducted and made publicly available between December 1, 2019, and August 2023. COVID-19, along with AI-specific words, was used to create the query syntax.

RESULTS: During the period covered by the search strategy, 961 articles were published and released online. Out of these, a total of 135 papers were chosen for additional investigation. Mortality rate prediction, early detection and diagnosis, vaccine as well as drug development, and lastly, incorporation of AI for supervising and controlling the COVID-19 pandemic were the four main topics focused entirely on AI applications used to tackle the COVID-19 crisis. Out of 135, 60 research papers focused on the detection and diagnosis of the COVID-19 pandemic. Next, 19 of the 135 studies applied a machine-learning approach for mortality rate prediction. Another 22 research publications emphasized the vaccine as well as drug development. Finally, the remaining studies were concentrated on controlling the COVID-19 pandemic by applying AI AI-based approach to it.

CONCLUSION: We compiled papers from the available COVID-19 literature that used AI-based methodologies to impart insights into various COVID-19 topics in this comprehensive study. Our results suggest crucial characteristics, data types, and COVID-19 tools that can aid in medical and translational research facilitation.

PMID:38318824 | DOI:10.2174/0115680266282179240124072121

Int J Neural Syst. 2024 Feb 6:2450009. doi: 10.1142/S0129065724500096. Online ahead of print.

ABSTRACT

Large-scale benchmark datasets are crucial in advancing research within the computer science communities. They enable the development of more sophisticated AI models and serve as "golden" benchmarks for evaluating their performance. Thus, ensuring the quality of these datasets is of utmost importance for academic research and the progress of AI systems. For the emerging vision-language tasks, some datasets have been created and frequently used, such as Flickr30k, COCO, and NoCaps, which typically contain a large number of images paired with their ground-truth textual descriptions. In this paper, an automatic method is proposed to assess the quality of large-scale benchmark datasets designed for vision-language tasks. In particular, a new cross-modal matching model is developed, which is capable of automatically scoring the textual descriptions of visual images. Subsequently, this model is employed to evaluate the quality of vision-language datasets by automatically assigning a score to each 'ground-truth' description for every image picture. With a good agreement between manual and automated scoring results on the datasets, our findings reveal significant disparities in the quality of the ground-truth descriptions included in the benchmark datasets. Even more surprising, it is evident that a small portion of the descriptions are unsuitable for serving as reliable ground-truth references. These discoveries emphasize the need for careful utilization of these publicly accessible benchmark databases.

PMID:38318751 | DOI:10.1142/S0129065724500096

Front Plant Sci. 2024 Jan 22;15:1278161. doi: 10.3389/fpls.2024.1278161. eCollection 2024.

ABSTRACT

Detecting and localizing standing dead trees (SDTs) is crucial for effective forest management and conservation. Due to challenges posed by mountainous terrain and road conditions, conducting a swift and comprehensive survey of SDTs through traditional manual inventory methods is considerably difficult. In recent years, advancements in deep learning and remote sensing technology have facilitated real-time and efficient detection of dead trees. Nevertheless, challenges persist in identifying individual dead trees in airborne remote sensing images, attributed to factors such as small target size, mutual occlusion and complex backgrounds. These aspects collectively contribute to the increased difficulty of detecting dead trees at a single-tree scale. To address this issue, the paper introduces an improved You Only Look Once version 7 (YOLOv7) model that incorporates the Simple Parameter-Free Attention Module (SimAM), an unparameterized attention mechanism. This improvement aims to enhance the network's feature extraction capabilities and increase the model's sensitivity to small target dead trees. To validate the superiority of SimAM_YOLOv7, we compared it with four widely adopted attention mechanisms. Additionally, a method to enhance model robustness is presented, involving the replacement of the Complete Intersection over Union (CIoU) loss in the original YOLOv7 model with the Wise-IoU (WIoU) loss function. Following these, we evaluated detection accuracy using a self-developed dataset of SDTs in forests. The results indicate that the improved YOLOv7 model can effectively identify dead trees in airborne remote sensing images, achieving precision, recall and mAP@0.5 values of 94.31%, 93.13% and 98.03%, respectively. These values are 3.67%, 2.28% and 1.56% higher than those of the original YOLOv7 model. This improvement model provides a convenient solution for forest management.

PMID:38318496 | PMC:PMC10839092 | DOI:10.3389/fpls.2024.1278161

Ophthalmic Med Image Anal (2023). 2023 Oct;14096:42-51. doi: 10.1007/978-3-031-44013-7_5. Epub 2023 Sep 16.

ABSTRACT

Optical coherence tomography (OCT) is a valuable imaging technique in ophthalmology, providing high-resolution, cross-sectional images of the retina for early detection and monitoring of various retinal and neurological diseases. However, discrepancies in retinal layer thickness measurements among different OCT devices pose challenges for data comparison and interpretation, particularly in longitudinal analyses. This work introduces the idea of a recurrent self fusion (RSF) algorithm to address this issue. Our RSF algorithm, built upon the self fusion methodology, iteratively denoises retinal OCT images. A deep learning-based retinal OCT segmentation algorithm is employed for downstream analyses. A large dataset of paired OCT scans acquired on both a Spectralis and Cirrus OCT device are used for validation. The results demonstrate that the RSF algorithm effectively reduces speckle contrast and enhances the consistency of retinal OCT segmentation.

PMID:38318463 | PMC:PMC10840975 | DOI:10.1007/978-3-031-44013-7_5

iScience. 2024 Jan 12;27(2):108881. doi: 10.1016/j.isci.2024.108881. eCollection 2024 Feb 16.

ABSTRACT

Automated tools to detect large vessel occlusion (LVO) in acute ischemic stroke patients using brain computed tomography angiography (CTA) have been shown to reduce the time for treatment, leading to better clinical outcomes. There is a lot of information in a single CTA and deep learning models do not have an obvious way of being conditioned on areas most relevant for LVO detection, i.e., the vasculature structure. In this work, we compare and contrast strategies to make convolutional neural networks focus on the vasculature without discarding context information of the brain parenchyma and propose an attention-inspired strategy to encourage this. We use brain CTAs from which we obtain 3D vasculature images. Then, we compare ways of combining the vasculature and the CTA images using a general-purpose network trained to detect LVO. The results show that the proposed strategies allow to improve LVO detection and could potentially help to learn other cerebrovascular-related tasks.

PMID:38318348 | PMC:PMC10838777 | DOI:10.1016/j.isci.2024.108881

Heliyon. 2024 Jan 20;10(3):e25030. doi: 10.1016/j.heliyon.2024.e25030. eCollection 2024 Feb 15.

ABSTRACT

OBJECTIVE: This study trains a U-shaped fully convolutional neural network (U-Net) model based on peripheral contour measures to achieve rapid, accurate, automated identification and segmentation of periprostatic adipose tissue (PPAT).

METHODS: Currently, no studies are using deep learning methods to discriminate and segment periprostatic adipose tissue. This paper proposes a novel and modified, U-shaped convolutional neural network contour control points on a small number of datasets of MRI T2W images of PPAT combined with its gradient images as a feature learning method to reduce feature ambiguity caused by the differences in PPAT contours of different patients. This paper adopts a supervised learning method on the labeled dataset, combining the probability and spatial distribution of control points, and proposes a weighted loss function to optimize the neural network's convergence speed and detection performance. Based on high-precision detection of control points, this paper uses a convex curve fitting to obtain the final PPAT contour. The imaging segmentation results were compared with those of a fully convolutional network (FCN), U-Net, and semantic segmentation convolutional network (SegNet) on three evaluation metrics: Dice similarity coefficient (DSC), Hausdorff distance (HD), and intersection over union ratio (IoU).

RESULTS: Cropped images with a 270 × 270-pixel matrix had DSC, HD, and IoU values of 70.1%, 27 mm, and 56.1%, respectively; downscaled images with a 256 × 256-pixel matrix had 68.7%, 26.7 mm, and 54.1%. A U-Net network based on peripheral contour characteristics predicted the complete periprostatic adipose tissue contours on T2W images at different levels. FCN, U-Net, and SegNet could not completely predict them.

CONCLUSION: This U-Net convolutional neural network based on peripheral contour features can identify and segment periprostatic adipose tissue quite well. Cropped images with a 270 × 270-pixel matrix are more appropriate for use with the U-Net convolutional neural network based on contour features; reducing the resolution of the original image will lower the accuracy of the U-Net convolutional neural network. FCN and SegNet are not appropriate for identifying PPAT on T2 sequence MR images. Our method can automatically segment PPAT rapidly and accurately, laying a foundation for PPAT image analysis.

PMID:38318024 | PMC:PMC10839980 | DOI:10.1016/j.heliyon.2024.e25030

Heliyon. 2024 Jan 24;10(3):e25120. doi: 10.1016/j.heliyon.2024.e25120. eCollection 2024 Feb 15.

ABSTRACT

An aircraft is a highly intricate system that features numerous subsystems, assemblies, and individual components for which regular maintenance is inevitable. The operational efficiency of an aircraft can be maximised, and its maintenance needs can be reduced using an effective yet automatic AI-based health monitoring systems which are more efficient as compared to designing and constructing expensive and harder to operate engine testbeds. It has been observed that aircraft engine anomalies such as undergoing flameouts can occur due to the rapid change in the temperature of the engine. Engine oil temperature and cylinder head temperature, two measures connected to this issue, might be affected differently depending on flight modes and operational conditions which in turn hamper AI-based algorithms to yield accurate prediction on engine failures. In general, previous studies lack comprehensive analysis on anomaly prediction in piston engine aircraft using modern machine learning solutions. Furthermore, abrupt variation in aircraft sensors' data and noise result in either overfitting or unfavourable performance by such techniques. This work aims at studying conventional machine learning and deep learning models to foretell the possibility of engine flameout using engine oil and cylinder head temperatures of a widely used Textron Lycoming IO-540 six-cylinder piston engine. This is achieved through pre-processing the data extracted from the aircraft's real-time flight data recorder followed by prediction using specially designed multi-modal regularised Long Short-Term Memory network to enhance generalisation and avoid overfitting on highly variable data. The proposed architecture yields improved results with root mean square error of 0.55 and 3.20 on cylinder head and engine oil temperatures respectively averaged over three case studies of five different flights. These scores are significantly better i.e., up to 84% as compared to other popular machine learning predictive approaches including Random Forest, Decision Tree Regression, Artificial Neural Networks and vanilla Long Short-Term Memory networks. Through performance evaluation, it can be established that the proposed system is capable of predicting engine flameout 2 minutes ahead and is suitable for integration with the software system of aircraft's engine control unit.

PMID:38317899 | PMC:PMC10840123 | DOI:10.1016/j.heliyon.2024.e25120

Heliyon. 2024 Jan 14;10(3):e24221. doi: 10.1016/j.heliyon.2024.e24221. eCollection 2024 Feb 15.

ABSTRACT

BACKGROUND: In the past, dentistry heavily relied on manual image analysis and diagnostic procedures, which could be time-consuming and prone to human error. The advent of artificial intelligence (AI) has brought transformative potential to the field, promising enhanced accuracy and efficiency in various dental imaging tasks. This systematic review and meta-analysis aimed to comprehensively evaluate the applications of AI in dental imaging modalities, focusing on in-vitro studies.

METHODS: A systematic literature search was conducted, in accordance with the PRISMA guidelines. The following databases were systematically searched: PubMed/MEDLINE, Embase, Web of Science, Scopus, IEEE Xplore, Cochrane Library, CINAHL (Cumulative Index to Nursing and Allied Health Literature), and Google Scholar. The meta-analysis employed fixed-effects models to assess AI accuracy, calculating odds ratios (OR) for true positive rate (TPR), true negative rate (TNR), positive predictive value (PPV), and negative predictive value (NPV) with 95 % confidence intervals (CI). Heterogeneity and overall effect tests were applied to ensure the reliability of the findings.

RESULTS: 9 studies were selected that encompassed various objectives, such as tooth segmentation and classification, caries detection, maxillofacial bone segmentation, and 3D surface model creation. AI techniques included convolutional neural networks (CNNs), deep learning algorithms, and AI-driven tools. Imaging parameters assessed in these studies were specific to the respective dental tasks. The analysis of combined ORs indicated higher odds of accurate dental image assessments, highlighting the potential for AI to improve TPR, TNR, PPV, and NPV. The studies collectively revealed a statistically significant overall effect in favor of AI in dental imaging applications.

CONCLUSION: In summary, this systematic review and meta-analysis underscore the transformative impact of AI on dental imaging. AI has the potential to revolutionize the field by enhancing accuracy, efficiency, and time savings in various dental tasks. While further research in clinical settings is needed to validate these findings and address study limitations, the future implications of integrating AI into dental practice hold great promise for advancing patient care and the field of dentistry.

PMID:38317889 | PMC:PMC10838702 | DOI:10.1016/j.heliyon.2024.e24221

Ophthalmol Sci. 2023 Dec 6;4(3):100445. doi: 10.1016/j.xops.2023.100445. eCollection 2024 May-Jun.

ABSTRACT

PURPOSE: Advances in artificial intelligence have enabled the development of predictive models for glaucoma. However, most work is single-center and uncertainty exists regarding the generalizability of such models. The purpose of this study was to build and evaluate machine learning (ML) approaches to predict glaucoma progression requiring surgery using data from a large multicenter consortium of electronic health records (EHR).

DESIGN: Cohort study.

PARTICIPANTS: Thirty-six thousand five hundred forty-eight patients with glaucoma, as identified by International Classification of Diseases (ICD) codes from 6 academic eye centers participating in the Sight OUtcomes Research Collaborative (SOURCE).

METHODS: We developed ML models to predict whether patients with glaucoma would progress to glaucoma surgery in the coming year (identified by Current Procedural Terminology codes) using the following modeling approaches: (1) penalized logistic regression (lasso, ridge, and elastic net); (2) tree-based models (random forest, gradient boosted machines, and XGBoost), and (3) deep learning models. Model input features included demographics, diagnosis codes, medications, and clinical information (intraocular pressure, visual acuity, refractive status, and central corneal thickness) available from structured EHR data. One site was reserved as an "external site" test set (N = 1550); of the patients from the remaining sites, 10% each were randomly selected to be in development and test sets, with the remaining 27 999 reserved for model training.

MAIN OUTCOME MEASURES: Evaluation metrics included area under the receiver operating characteristic curve (AUROC) on the test set and the external site.

RESULTS: Six thousand nineteen (16.5%) of 36 548 patients underwent glaucoma surgery. Overall, the AUROC ranged from 0.735 to 0.771 on the random test set and from 0.706 to 0.754 on the external test site, with the XGBoost and random forest model performing best, respectively. There was greatest performance decrease from the random test set to the external test site for the penalized regression models.

CONCLUSIONS: Machine learning models developed using structured EHR data can reasonably predict whether glaucoma patients will need surgery, with reasonable generalizability to an external site. Additional research is needed to investigate the impact of protected class characteristics such as race or gender on model performance and fairness.

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

PMID:38317869 | PMC:PMC10838906 | DOI:10.1016/j.xops.2023.100445

Front Cardiovasc Med. 2024 Jan 22;11:1323461. doi: 10.3389/fcvm.2024.1323461. eCollection 2024.

ABSTRACT

BACKGROUND: Segmentation of cardiac structures is an important step in evaluation of the heart on imaging. There has been growing interest in how artificial intelligence (AI) methods-particularly deep learning (DL)-can be used to automate this process. Existing AI approaches to cardiac segmentation have mostly focused on cardiac MRI. This systematic review aimed to appraise the performance and quality of supervised DL tools for the segmentation of cardiac structures on CT.

METHODS: Embase and Medline databases were searched to identify related studies from January 1, 2013 to December 4, 2023. Original research studies published in peer-reviewed journals after January 1, 2013 were eligible for inclusion if they presented supervised DL-based tools for the segmentation of cardiac structures and non-coronary great vessels on CT. The data extracted from eligible studies included information about cardiac structure(s) being segmented, study location, DL architectures and reported performance metrics such as the Dice similarity coefficient (DSC). The quality of the included studies was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM).

RESULTS: 18 studies published after 2020 were included. The DSC scores median achieved for the most commonly segmented structures were left atrium (0.88, IQR 0.83-0.91), left ventricle (0.91, IQR 0.89-0.94), left ventricle myocardium (0.83, IQR 0.82-0.92), right atrium (0.88, IQR 0.83-0.90), right ventricle (0.91, IQR 0.85-0.92), and pulmonary artery (0.92, IQR 0.87-0.93). Compliance of studies with CLAIM was variable. In particular, only 58% of studies showed compliance with dataset description criteria and most of the studies did not test or validate their models on external data (81%).

CONCLUSION: Supervised DL has been applied to the segmentation of various cardiac structures on CT. Most showed similar performance as measured by DSC values. Existing studies have been limited by the size and nature of the training datasets, inconsistent descriptions of ground truth annotations and lack of testing in external data or clinical settings.

SYSTEMATIC REVIEW REGISTRATION: [www.crd.york.ac.uk/prospero/], PROSPERO [CRD42023431113].

PMID:38317865 | PMC:PMC10839106 | DOI:10.3389/fcvm.2024.1323461

Data Brief. 2024 Jan 15;53:110065. doi: 10.1016/j.dib.2024.110065. eCollection 2024 Apr.

ABSTRACT

When training Artificial Intelligence and Deep Learning models, especially by using Supervised Learning techniques, a labeled dataset is required to have an input with data and its corresponding labeled output data. In the case of images, for classification, segmentation, or other processing tasks, a pair of images is required in the same sense, one image as an input (the noisy image) and the desired (the denoised image) one as an output. For SAR despeckling applications, the common approach is to have a set of optical images that then are corrupted with synthetic noise, since there is no ground truth available. The corrupted image is considered the input and the optical one is the noiseless one (ground truth). In this paper, we provide a dataset based on actual SAR images. The ground truth was obtained from SAR images of Sentinel 1 of the same region in different instants of time and then they were processed and merged into one single image that serves as the output of the dataset. Every SAR image (noisy and ground truth) was split into 1600 images of 512 × 512 pixels, so a total of 3200 images were obtained. The dataset was also split into 3000 for training and 200 for validation, all of them available in four labeled folders.

PMID:38317735 | PMC:PMC10838683 | DOI:10.1016/j.dib.2024.110065

Sci Rep. 2024 Feb 5;14(1):2991. doi: 10.1038/s41598-024-53460-y.

ABSTRACT

Multivariate time series forecasting is a critical problem in many real-world scenarios. Recent advances in deep learning have significantly enhanced the ability to tackle such problems. However, a primary challenge in time series forecasting comes from the imbalanced time series data that include extreme events. Despite being a small fraction of the data instances, extreme events can have a negative impact on forecasting as they deviate from the majority. However, many recent time series forecasting methods neglect this issue, leading to suboptimal performance. To address these challenges, we introduce a novel model, the Extreme Event Adaptive Gated Recurrent Unit (eGRU), tailored explicitly for forecasting tasks. The eGRU is designed to effectively learn both normal and extreme event patterns within time series data. Furthermore, we introduce a time series data segmentation technique that divides the input sequence into segments, each comprising multiple time steps. This segmentation empowers the eGRU to capture data patterns at different time step resolutions while simultaneously reducing the overall input length. We conducted comprehensive experiments on four real-world benchmark datasets to evaluate the eGRU's performance. Our results showcase its superiority over vanilla RNNs, LSTMs, GRUs, and other state-of-the-art RNN variants in multivariate time series forecasting. Additionally, we conducted ablation studies to demonstrate the consistently superior performance of eGRU in generating accurate forecasts while incorporating a diverse range of labeling results.

PMID:38316972 | DOI:10.1038/s41598-024-53460-y

Pediatr Res. 2024 Feb 5. doi: 10.1038/s41390-024-03064-z. Online ahead of print.

ABSTRACT

BACKGROUND: The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses.

METHODS: An observational study was conducted in 23 babies randomly selected from 170 neonates who were ventilated with SIPPV-VG, SIMV-VG or PSV-VG mode for at least 12 h. 500 breaths were randomly selected and manually annotated from each recording to train convolutional neural network (CNN) models for PVI classification.

RESULTS: The average asynchrony index (AI) over all recordings was 52.5%. The most frequently occurring PVIs included expiratory work (median: 28.4%, interquartile range: 23.2-40.2%), late cycling (7.6%, 2.8-10.2%), failed triggering (4.6%, 1.2-6.2%) and late triggering (4.4%, 2.8-7.4%). Approximately 25% of breaths with a PVI had two or more PVIs occurring simultaneously. Binary CNN classifiers were developed for PVIs affecting ≥1% of all breaths (n = 7) and they achieved F1 scores of >0.9 on the test set except for early triggering where it was 0.809.

CONCLUSIONS: PVIs occur frequently in neonates undergoing conventional mechanical ventilation with a significant proportion of breaths containing multiple PVIs. We have developed computational models for seven different PVIs to facilitate automated detection and further evaluation of their clinical significance in neonates.

IMPACT: The study of patient-ventilator interactions (PVI) in mechanically ventilated neonates is limited by the lack of unified PVI definitions and tools to perform large scale analyses. By adapting a recent taxonomy of PVI definitions in adults, we have manually annotated neonatal ventilator waveforms to determine prevalence and co-occurrence of neonatal PVIs. We have also developed binary deep learning classifiers for common PVIs to facilitate their automatic detection and quantification.

PMID:38316942 | DOI:10.1038/s41390-024-03064-z

Sci Rep. 2024 Feb 5;14(1):2911. doi: 10.1038/s41598-024-53278-8.

ABSTRACT

This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI were obtained with six and three directions of the motion probing gradient (MPG), respectively. The identical imaging plane was paired for the image-to-image translation model that synthesized one direction of the MPG from DWI. This process was repeated six times in the respective MPG directions. Regions of interest (ROIs) in the lentiform nucleus, thalamus, posterior limb of the internal capsule, posterior thalamic radiation, and splenium of the corpus callosum were created and applied to maps derived from the original and synthetic DTI. The mean values and signal-to-noise ratio (SNR) of the original and synthetic maps for each ROI were compared. The Bland-Altman plot between the original and synthetic data was evaluated. Although the test dataset showed a larger standard deviation of all values and lower SNR in the synthetic data than in the original data, the Bland-Altman plots showed each plot localizing in a similar distribution. Synthetic DTI could be generated from conventional DWI with an image-to-image translation model.

PMID:38316892 | DOI:10.1038/s41598-024-53278-8

Sci Rep. 2024 Feb 6;14(1):2999. doi: 10.1038/s41598-024-53323-6.

ABSTRACT

Endocrine-disrupting chemicals (EDCs) pose a significant threat to human well-being and the ecosystem. However, in managing the many thousands of uncharacterized chemical entities, the high-throughput screening of EDCs using relevant biological endpoints remains challenging. Three-dimensional (3D) culture technology enables the development of more physiologically relevant systems in more realistic biochemical microenvironments. The high-content and quantitative imaging techniques enable quantifying endpoints associated with cell morphology, cell-cell interaction, and microtissue organization. In the present study, 3D microtissues formed by MCF-7 breast cancer cells were exposed to the model EDCs estradiol (E2) and propyl pyrazole triol (PPT). A 3D imaging and image analysis pipeline was established to extract quantitative image features from estrogen-exposed microtissues. Moreover, a machine-learning classification model was built using estrogenic-associated differential imaging features. Based on 140 common differential image features found between the E2 and PPT group, the classification model predicted E2 and PPT exposure with AUC-ROC at 0.9528 and 0.9513, respectively. Deep learning-assisted analysis software was developed to characterize microtissue gland lumen formation. The fully automated tool can accurately characterize the number of identified lumens and the total luminal volume of each microtissue. Overall, the current study established an integrated approach by combining non-supervised image feature profiling and supervised luminal volume characterization, which reflected the complexity of functional ER signaling and highlighted a promising conceptual framework for estrogenic EDC risk assessment.

PMID:38316851 | DOI:10.1038/s41598-024-53323-6

Br J Ophthalmol. 2024 Feb 5:bjo-2023-323400. doi: 10.1136/bjo-2023-323400. Online ahead of print.

ABSTRACT

BACKGROUND/AIMS: National guidelines of many countries set screening intervals for diabetic retinopathy (DR) based on grading of the last screening retinal images. We explore the potential of deep learning (DL) on images to predict progression to referable DR beyond DR grading, and the potential impact on assigned screening intervals, within the Scottish screening programme.

METHODS: We consider 21 346 and 247 233 people with type 1 diabetes mellitus (T1DM) and type 2 diabetes mellitus (T2DM), respectively, each contributing on average 4.8 and 4.4 screening intervals of which 1339 and 4675 intervals concluded with a referable screening episode. Information extracted from fundus images using DL was used to predict referable status at the end of interval and its predictive value in comparison to screening-assigned DR grade was assessed.

RESULTS: The DL predictor increased the area under the receiver operating characteristic curve in comparison to a predictor using current DR grades from 0.809 to 0.87 for T1DM and from 0.825 to 0.87 for T2DM. Expected sojourn time-the time from becoming referable to being rescreened-was found to be 3.4 (T1DM) and 2.7 (T2DM) weeks less for a DL-derived policy compared with the current recall policy.

CONCLUSIONS: We showed that, compared with using the current retinopathy grade, DL of fundus images significantly improves the prediction of incident referable retinopathy before the next screening episode. This can impact screening recall interval policy positively, for example, by reducing the expected time with referable disease for a fixed workload-which we show as an exemplar. Additionally, it could be used to optimise workload for a fixed sojourn time.

PMID:38316534 | DOI:10.1136/bjo-2023-323400

Environ Res. 2024 Feb 3:118412. doi: 10.1016/j.envres.2024.118412. Online ahead of print.

ABSTRACT

The temperature of surface and epilimnetic waters, closely related to regional air temperatures, responds quickly and directly to climatic changes. As a result, lake surface temperature (LSWT) can be considered an effective indicator of climate change. In this study, we reconstructed and investigated historical and future LSWT across different scenarios for over 80 major lakes in mainland Southeast Asia (SEA), an ecologically diverse region vulnerable to climate impacts. Five different predicting models, incorporating statistical, machine and deep learning approaches, were trained and validated using ERA5 and CHIRPS climatic feature datasets as predictors and 8-day MODIS-derived LSWT from 2000 to 2020 as reference dataset. Best performing model was then applied to predict both historical (1986-2020) and future (2020-2100) LSWT for SEA lakes, utilizing downscaled climatic CORDEX-SEA feature data and multiple Representative Concentration Pathway (RCP). The analysis uncovered historical and future thermal dynamics and long-term trends for both daytime and nighttime LSWT. Among 5 models, XGboost results the most performant (NSE 0.85, RMSE 1.14 °C, MAE 0.69 °C, MBE -0.08 °C) and it has been used for historical reconstruction and future LSWT prediction. The historical analysis revealed a warming trend in SEA lakes, with daytime LSWT increasing at a rate of +0.18 °C/decade and nighttime LSWT at +0.13 °C/decade over the past three decades. These trends appeared of smaller magnitude compared to global estimates of LSWT change rates and less pronounced than concurrent air temperature and LSWT increases in neighbouring regions. Projections under various RCP scenarios indicated continued LSWT warming. Daytime LSWT is projected to increase at varying rates per decade: +0.03 °C under RCP2.6, +0.14 °C under RCP4.5, and +0.29 °C under RCP8.5. Similarly, nighttime LSWT projections under these scenarios are: +0.03 °C, +0.10 °C, and +0.16 °C per decade, respectively. The most optimistic scenario predicted marginal increases of +0.38 °C on average, while the most pessimistic scenario indicated an average LSWT increase of +2.29 °C by end of the century. This study highlights the relevance of LSWT as a climate change indicator in major SEA's freshwater ecosystems. The integration of satellite-derived LSWT, historical and projected climate data into data-driven modelling has enabled new and a more nuanced understanding of LSWT dynamics in relation to climate throughout the entire SEA region.

PMID:38316380 | DOI:10.1016/j.envres.2024.118412