J Imaging Inform Med. 2024 Aug 20. doi: 10.1007/s10278-024-01151-5. Online ahead of print.

ABSTRACT

In this study, we present a method based on Monte Carlo Dropout (MCD) as Bayesian neural network (BNN) approximation for confidence-aware severity classification of lung diseases in COVID-19 patients using chest X-rays (CXRs). Trained and tested on 1208 CXRs from Hospital 1 in the USA, the model categorizes severity into four levels (i.e., normal, mild, moderate, and severe) based on lung consolidation and opacity. Severity labels, determined by the median consensus of five radiologists, serve as the reference standard. The model's performance is internally validated against evaluations from an additional radiologist and two residents that were excluded from the median. The performance of the model is further evaluated on additional internal and external datasets comprising 2200 CXRs from the same hospital and 1300 CXRs from Hospital 2 in South Korea. The model achieves an average area under the curve (AUC) of 0.94 ± 0.01 across all classes in the primary dataset, surpassing human readers in each severity class and achieves a higher Kendall correlation coefficient (KCC) of 0.80 ± 0.03. The performance of the model is consistent across varied datasets, highlighting its generalization. A key aspect of the model is its predictive uncertainty (PU), which is inversely related to the level of agreement among radiologists, particularly in mild and moderate cases. The study concludes that the model outperforms human readers in severity assessment and maintains consistent accuracy across diverse datasets. Its ability to provide confidence measures in predictions is pivotal for potential clinical use, underscoring the BNN's role in enhancing diagnostic precision in lung disease analysis through CXR.

PMID:39164451 | DOI:10.1007/s10278-024-01151-5

Sci Rep. 2024 Aug 20;14(1):19278. doi: 10.1038/s41598-024-70234-8.

ABSTRACT

To investigate quantitative associations between AI-assessed disease activity and optical coherence tomography angiography (OCTA)-derived parameters in patients with neovascular age-related macular degeneration (nAMD) undergoing anti-VEGF therapy. OCTA and SD-OCT images obtained from multicenter, randomized study data were evaluated. A deep learning algorithm (RetInSight) was used to detect and quantify macular fluid on SD-OCT. Mixed effects models were applied to evaluate correlations between fluid volumes, macular neovascularization (MNV)-type and OCTA-derived MNV parameters; lesion size (LS) and vessel area (NVA). 230 patients were included. A significant positive correlation was observed between SRF and NVA (estimate = 199.8 nl/mm2, p = 0.023), while a non-significant but negative correlation was found between SRF and LS (estimate = - 71.3 nl/mm2, p = 0.126). The presence of Type I and Type II MNV was associated with significantly less intraretinal fluid (IRF) compared to Type III MNV (estimate type I:- 52.1 nl, p = 0.019; estimate type II:- 51.7 nl, p = 0.021). A significant correlation was observed between pigment epithelial detachment (PED) and the interaction between NVA and LS (estimate:28.97 nl/mm2; p = 0.012). Residual IRF at week 12 significantly correlated to baseline NVA (estimate:38.1 nl/mm2; p = 0.015) and LS (estimate:- 22.6 nl/mm2; p = 0.012). Fluid in different compartments demonstrated disparate associations with MNV OCTA features. While IRF at baseline was most pronounced in type III MNV, residual IRF was driven by neovascular MNV characteristics. Greater NVA in proportion to LS was associated with higher amounts of SRF and PED. The correlation between these parameters may represent MNV maturation and can be used as a biomarker for resolution of disease activity. AI-based OCT analysis allows for a deeper understanding of neovascular disease in AMD and the potential to adjust therapeutic strategies to optimize outcomes through precision medicine.

PMID:39164449 | DOI:10.1038/s41598-024-70234-8

Network. 2024 Aug 20:1-30. doi: 10.1080/0954898X.2024.2391395. Online ahead of print.

ABSTRACT

In cloud computing (CC), task scheduling allocates the task to best suitable resource for execution. This article proposes a model for task scheduling utilizing the multi-objective optimization and deep learning (DL) model. Initially, the multi-objective task scheduling is carried out by the incoming user utilizing the proposed hybrid fractional flamingo beetle optimization (FFBO) which is formed by integrating dung beetle optimization (DBO), flamingo search algorithm (FSA) and fractional calculus (FC). Here, the fitness function depends on reliability, cost, predicted energy, and makespan, the predicted energy is forecasted by a deep residual network (DRN). Thereafter, task scheduling is accomplished based on DL using the proposed deep feedforward neural network fused long short-term memory (DFNN-LSTM), which is the combination of DFNN and LSTM. Moreover, when scheduling the workflow, the task parameters and the virtual machine's (VM) live parameters are taken into consideration. Task parameters are earliest finish time (EFT), earliest start time (EST), task length, task priority, and actual task running time, whereas VM parameters include memory utilization, bandwidth utilization, capacity, and central processing unit (CPU). The proposed model DFNN-LSTM+FFBO has achieved superior makespan, energy, and resource utilization of 0.188, 0.950J, and 0.238, respectively.

PMID:39163538 | DOI:10.1080/0954898X.2024.2391395

Environ Sci Technol. 2024 Aug 20. doi: 10.1021/acs.est.4c02498. Online ahead of print.

ABSTRACT

Wildfires generate abundant smoke primarily composed of fine-mode aerosols. However, accurately measuring the fine-mode aerosol optical depth (fAOD) is highly uncertain in most existing satellite-based aerosol products. Deep learning offers promise for inferring fAOD, but little has been done using multiangle satellite data. We developed an innovative angle-dependent deep-learning model (ADLM) that accounts for angular diversity in dual-angle observations. The model captures aerosol properties observed from dual angles in the contiguous United States and explores the potential of Greenhouse gases Observing Satellite-2's (GOSAT-2) measurements to retrieve fAOD at a 460 m spatial resolution. The ADLM demonstrates a strong performance through rigorous validation against ground-based data, revealing small biases. By comparison, the official fAOD product from the Moderate Resolution Imaging Spectroradiometer (MODIS), the Visible Infrared Imaging Radiometer Suite (VIIRS), and the Multiangle Imaging Spectroradiometer (MISR) during wildfire events is underestimated by more than 40% over western USA. This leads to significant differences in estimates of aerosol radiative forcing (ARF) from wildfires. The ADLM shows more than 20% stronger ARF than the MODIS, VIIRS, and MISR estimates, highlighting a greater impact of wildfire fAOD on Earth's energy balance.

PMID:39163486 | DOI:10.1021/acs.est.4c02498

Proc Natl Acad Sci U S A. 2024 Aug 27;121(35):e2410662121. doi: 10.1073/pnas.2410662121. Epub 2024 Aug 20.

ABSTRACT

Proteins perform their biological functions through motion. Although high throughput prediction of the three-dimensional static structures of proteins has proved feasible using deep-learning-based methods, predicting the conformational motions remains a challenge. Purely data-driven machine learning methods encounter difficulty for addressing such motions because available laboratory data on conformational motions are still limited. In this work, we develop a method for generating protein allosteric motions by integrating physical energy landscape information into deep-learning-based methods. We show that local energetic frustration, which represents a quantification of the local features of the energy landscape governing protein allosteric dynamics, can be utilized to empower AlphaFold2 (AF2) to predict protein conformational motions. Starting from ground state static structures, this integrative method generates alternative structures as well as pathways of protein conformational motions, using a progressive enhancement of the energetic frustration features in the input multiple sequence alignment sequences. For a model protein adenylate kinase, we show that the generated conformational motions are consistent with available experimental and molecular dynamics simulation data. Applying the method to another two proteins KaiB and ribose-binding protein, which involve large-amplitude conformational changes, can also successfully generate the alternative conformations. We also show how to extract overall features of the AF2 energy landscape topography, which has been considered by many to be black box. Incorporating physical knowledge into deep-learning-based structure prediction algorithms provides a useful strategy to address the challenges of dynamic structure prediction of allosteric proteins.

PMID:39163334 | DOI:10.1073/pnas.2410662121

Aesthet Surg J. 2024 Aug 20:sjae182. doi: 10.1093/asj/sjae182. Online ahead of print.

ABSTRACT

BACKGROUND: Aesthetic standards vary and are subjective for each person, and artificial intelligence is booming in this era.

OBJECTIVES: the authors aim to provide a relatively objective assessment of the aesthetic outcomes, enhancing the decision-making process and understanding of the surgical results.

METHODS: 150 patients who had undergone lower blepharoplasty-related surgeries were included in our study. FaceAge software was created by our research team, which included four publicly age estimation convolution neural network (CNN) models, Amazon AWS Rekognition (Seattle, WA), Microsoft Azure Face (Redmond, WA), Face++ Detect (Beijing, China), and Inferdo face detection (New York, NY). We then first used this application for age accuracy between the real age and the age estimated by the four CNNs. Second, we used this application to estimate all the preoperative and postoperative images' age of 150 patients and evaluate the effort of lower blepharoplasty.

RESULTS: In terms of accuracy in age prediction, all CNN models exhibited a certain degree of accuracy. For all 150 patients undergoing lower blepharoplasty-related surgeries, the surgeries' effect showed about 2 years of rejuvenation with a statistically significant difference; for the sex difference, men had more age reduction than women also with a statistically significant difference; quadrilateral blepharoplasty showed the most significant effect on anti-aging effect.

CONCLUSIONS: By using the deep learning models, lower blepharoplasty-related surgeries actually had an effect on age reduction. The potential of deep learning models will provide quantitative evidence for the rejuvenation effects of blepharoplasty or other cosmetic surgeries.

PMID:39163263 | DOI:10.1093/asj/sjae182

IEEE J Biomed Health Inform. 2024 Aug 20;PP. doi: 10.1109/JBHI.2024.3445952. Online ahead of print.

ABSTRACT

Breast cancer significantly impacts women's health, with ultrasound being crucial for lesion assessment. To enhance diagnostic accuracy, computer-aided detection (CAD) systems have attracted considerable interest. This study introduces a prospective deep learning architecture called "Multi-modal Multi-task Network" (3MT-Net). 3MT-Net utilizes a combination of clinical data, B-mode, and color Doppler ultrasound. We have designed the AM-CapsNet network, specifically tailored to extract crucial tumor features from ultrasound. To combine clinical data in 3MT-Net, we have employed a cascaded cross-attention to fuse information from three distinct sources. To ensure the preservation of pertinent information during the fusion of high-dimensional and low-dimensional data, we adopt the idea of ensemble learning and design an optimization algorithm to assign weights to different modalities. Eventually, 3MT-Net performs binary classification of benign and malignant lesions as well as pathological subtype classification. In addition, we retrospectively collected data from nine medical centers. To ensure the broad applicability of the 3MT-Net, we created two separate testsets and conducted extensive experiments. Furthermore, a comparative analysis was conducted between 3MT-Net and the industrial-grade CAD product S-detect. The AUC of 3MT-Net surpasses S-Detect by 1.4% to 3.8%.

PMID:39163184 | DOI:10.1109/JBHI.2024.3445952

IEEE J Biomed Health Inform. 2024 Aug 20;PP. doi: 10.1109/JBHI.2024.3446040. Online ahead of print.

ABSTRACT

In radiology, particularly in lung cancer diagnosis, diagnostic errors and cognitive biases pose substantial challenges. These issues, including perceptual errors, interpretive mistakes, and cognitive biases such as anchoring and premature closure, are often unnoticed by experienced radiologists. To address these challenges, we propose the Multi-Eyes principle approach, which utilises multiple deep learning models to reduce bias and potentially improve diagnostic accuracy. Inspired by the Four-Eyes principle in business and cybersecurity, this methodology employs various 3D and 2D (for validation) deep learning architectures and three uncertainty quantification techniques: Monte Carlo Dropout, Deep Ensemble, and Ensemble Monte Carlo Dropout. Each model functions as an independent reviewer, similar to blind reviews. With entropy selected as the uncertainty measurement, it is averaged, followed by ensemble averaging of predictions. The effectiveness of this approach was demonstrated using the LIDC-IDRI dataset for lung cancer classification. Statistical analysis of the uncertainty's distribution reveals that with more models, uncertainty in incorrect predictions becomes more peaked and left skewed, indicating consensus on uncertainty levels. This results in accuracy and F1 score improvements, even with the best performing model, addressing overconfidence in single-model systems. These findings highlight the potential of the Multi-Eyes principle to significantly improve diagnostic performance in computer-aided diagnostic systems. Future research may explore different uncertainty quantification methods and feedback mechanisms for further advancement.

PMID:39163183 | DOI:10.1109/JBHI.2024.3446040

J Med Internet Res. 2024 Aug 20;26:e48320. doi: 10.2196/48320.

ABSTRACT

BACKGROUND: Electronic health records (EHRs) contain patients' health information over time, including possible early indicators of disease. However, the increasing amount of data hinders clinicians from using them. There is accumulating evidence suggesting that machine learning (ML) and deep learning (DL) can assist clinicians in analyzing these large-scale EHRs, as algorithms thrive on high volumes of data. Although ML has become well developed, studies mainly focus on engineering but lack medical outcomes.

OBJECTIVE: This study aims for a scoping review of the evidence on how the use of ML on longitudinal EHRs can support the early detection and prevention of disease. The medical insights and clinical benefits that have been generated were investigated by reviewing applications in a variety of diseases.

METHODS: This study was conducted according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A literature search was performed in 2022 in collaboration with a medical information specialist in the following databases: PubMed, Embase, Web of Science Core Collection (Clarivate Analytics), and IEEE Xplore Digital Library and computer science bibliography. Studies were eligible when longitudinal EHRs were used that aimed for the early detection of disease via ML in a prevention context. Studies with a technical focus or using imaging or hospital admission data were beyond the scope of this review. Study screening and selection and data extraction were performed independently by 2 researchers.

RESULTS: In total, 20 studies were included, mainly published between 2018 and 2022. They showed that a variety of diseases could be detected or predicted, particularly diabetes; kidney diseases; diseases of the circulatory system; and mental, behavioral, and neurodevelopmental disorders. Demographics, symptoms, procedures, laboratory test results, diagnoses, medications, and BMI were frequently used EHR data in basic recurrent neural network or long short-term memory techniques. By developing and comparing ML and DL models, medical insights such as a high diagnostic performance, an earlier detection, the most important predictors, and additional health indicators were obtained. A clinical benefit that has been evaluated positively was preliminary screening. If these models are applied in practice, patients might also benefit from personalized health care and prevention, with practical benefits such as workload reduction and policy insights.

CONCLUSIONS: Longitudinal EHRs proved to be helpful for support in health care. Current ML models on EHRs can support the detection of diseases in terms of accuracy and offer preliminary screening benefits. Regarding the prevention of diseases, ML and specifically DL models can accurately predict or detect diseases earlier than current clinical diagnoses. Adding personally responsible factors allows targeted prevention interventions. While ML models based on textual EHRs are still in the developmental stage, they have high potential to support clinicians and the health care system and improve patient outcomes.

PMID:39163096 | DOI:10.2196/48320

Invest Ophthalmol Vis Sci. 2024 Aug 1;65(10):25. doi: 10.1167/iovs.65.10.25.

ABSTRACT

PURPOSE: In AMD, rod-mediated dark adaptation (RMDA) at 5° eccentricity is slower in eyes with subretinal drusenoid deposits (SDDs) than in eyes without. Here we quantified SDD burden using supervised deep learning for comparison to vision and photoreceptor topography.

METHODS: In persons ≥60 years from the Alabama Study on Early Age-Related Macular Degeneration 2, normal, early AMD, and intermediate AMD eyes were classified by the AREDS nine-step system. A convolutional neural network was trained on 55°-wide near-infrared reflectance images for SDD segmentation. Trained graders annotated ground truth (SDD yes/no). Predicted and true datasets agreed (Dice coefficient, 0.92). Inference was manually proofread using optical coherence tomography. The mean SDD area (mm2) was compared among diagnostic groups (linear regression) and to vision (age-adjusted Spearman correlations). Fundus autofluorescence images were used to mask large vessels in SDD maps.

RESULTS: In 428 eyes of 428 persons (normal, 218; early AMD, 120; intermediate AMD, 90), the mean SDD area differed by AMD severity (P < 0.0001): 0.16 ± 0.87 (normal), 2.48 ± 11.23 (early AMD), 11.97 ± 13.33 (intermediate AMD). Greater SDD area was associated with worse RMDA (r = 0.27; P < 0.0001), mesopic (r = -0.13; P = 0.02) and scotopic sensitivity (r = -0.17; P < 0.001). SDD topography peaked at 5° superior, extended beyond the Early Treatment of Diabetic Retinopathy Study grid and optic nerve, then decreased.

CONCLUSIONS: SDD area is associated with degraded rod-mediated vision. RMDA 5° (superior retina) probes where SDD is maximal, closer to the foveal center than the rod peak at 3 to 6 mm (10.4°-20.8°) superior and the further eccentric peak of rod:cone ratio. Topographic data imply that factors in addition to rod density influence SDD formation.

PMID:39163034 | DOI:10.1167/iovs.65.10.25

Mol Divers. 2024 Aug 20. doi: 10.1007/s11030-024-10960-3. Online ahead of print.

ABSTRACT

Generative machine learning models offer a novel strategy for chemogenomics and de novo drug design, allowing researchers to streamline their exploration of the chemical space and concentrate on specific regions of interest. In cases with limited inhibitor data available for the target of interest, de novo drug design plays a crucial role. In this study, we utilized a package called 'mollib,' trained on ChEMBL data containing approximately 365,000 bioactive molecules. By leveraging transfer learning techniques with this package, we generated a series of compounds, starting from five initial compounds, which are potential Plasmodium falciparum (Pf) Lactate dehydrogenase inhibitors. The resulting compounds exhibit structural diversity and hold promise as potential novel Pf Lactate dehydrogenase inhibitors.

PMID:39162960 | DOI:10.1007/s11030-024-10960-3

Radiology. 2024 Aug;312(2):e233197. doi: 10.1148/radiol.233197.

ABSTRACT

Background Deep learning (DL) could improve the labor-intensive, challenging processes of diagnosing cerebral aneurysms but requires large multicenter data sets. Purpose To construct a DL model using a multicenter data set for accurate cerebral aneurysm segmentation and detection on CT angiography (CTA) images and to compare its performance with radiology reports. Materials and Methods Consecutive head or head and neck CTA images of suspected unruptured cerebral aneurysms were gathered retrospectively from eight hospitals between February 2018 and October 2021 for model development. An external test set with reference standard digital subtraction angiography (DSA) scans was obtained retrospectively from one of the eight hospitals between February 2022 and February 2023. Radiologists (reference standard) assessed aneurysm segmentation, while model performance was evaluated using the Dice similarity coefficient (DSC). The model's aneurysm detection performance was assessed by sensitivity and comparing areas under the receiver operating characteristic curves (AUCs) between the model and radiology reports in the DSA data set with use of the DeLong test. Results Images from 6060 patients (mean age, 56 years ± 12 [SD]; 3375 [55.7%] female) were included for model development (training: 4342; validation: 1086; and internal test set: 632). Another 118 patients (mean age, 59 years ± 14; 79 [66.9%] female) were included in an external test set to evaluate performance based on DSA. The model achieved a DSC of 0.87 for aneurysm segmentation performance in the internal test set. Using DSA, the model achieved 85.7% (108 of 126 aneurysms [95% CI: 78.1, 90.1]) sensitivity in detecting aneurysms on per-vessel analysis, with no evidence of a difference versus radiology reports (AUC, 0.93 [95% CI: 0.90, 0.95] vs 0.91 [95% CI: 0.87, 0.94]; P = .67). Model processing time from reconstruction to detection was 1.76 minutes ± 0.32 per scan. Conclusion The proposed DL model could accurately segment and detect cerebral aneurysms at CTA with no evidence of a significant difference in diagnostic performance compared with radiology reports. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Payabvash in this issue.

PMID:39162636 | DOI:10.1148/radiol.233197

Radiology. 2024 Aug;312(2):e241367. doi: 10.1148/radiol.241367.

NO ABSTRACT

PMID:39162629 | DOI:10.1148/radiol.241367

Brief Bioinform. 2024 Jul 25;25(5):bbae409. doi: 10.1093/bib/bbae409.

ABSTRACT

Turnover numbers (kcat), which indicate an enzyme's catalytic efficiency, have a wide range of applications in fields including protein engineering and synthetic biology. Experimentally measuring the enzymes' kcat is always time-consuming. Recently, the prediction of kcat using deep learning models has mitigated this problem. However, the accuracy and robustness in kcat prediction still needs to be improved significantly, particularly when dealing with enzymes with low sequence similarity compared to those within the training dataset. Herein, we present DeepEnzyme, a cutting-edge deep learning model that combines the most recent Transformer and Graph Convolutional Network (GCN) to capture the information of both the sequence and 3D-structure of a protein. To improve the prediction accuracy, DeepEnzyme was trained by leveraging the integrated features from both sequences and 3D-structures. Consequently, DeepEnzyme exhibits remarkable robustness when processing enzymes with low sequence similarity compared to those in the training dataset by utilizing additional features from high-quality protein 3D-structures. DeepEnzyme also makes it possible to evaluate how point mutations affect the catalytic activity of the enzyme, which helps identify residue sites that are crucial for the catalytic function. In summary, DeepEnzyme represents a pioneering effort in predicting enzymes' kcat values with improved accuracy and robustness compared to previous algorithms. This advancement will significantly contribute to our comprehension of enzyme function and its evolutionary patterns across species.

PMID:39162313 | DOI:10.1093/bib/bbae409

Nucleic Acids Res. 2024 Aug 20:gkae715. doi: 10.1093/nar/gkae715. Online ahead of print.

ABSTRACT

Nucleic acid electron density interpretation after phasing by molecular replacement or other methods remains a difficult problem for computer programs to deal with. Programs tend to rely on time-consuming and computationally exhaustive searches to recognise characteristic features. We present NucleoFind, a deep-learning-based approach to interpreting and segmenting electron density. Using an electron density map from X-ray crystallography obtained after molecular replacement, the positions of the phosphate group, sugar ring and nitrogenous base group can be predicted with high accuracy. On average, 78% of phosphate atoms, 85% of sugar atoms and 83% of base atoms are positioned in predicted density after giving NucleoFind maps produced following successful molecular replacement. NucleoFind can use the wealth of context these predicted maps provide to build more accurate and complete nucleic acid models automatically.

PMID:39162213 | DOI:10.1093/nar/gkae715

PeerJ. 2024 Aug 16;12:e17509. doi: 10.7717/peerj.17509. eCollection 2024.

ABSTRACT

BACKGROUND: Hip fractures are a common and debilitating condition, particularly among older adults. Loss of muscle mass and strength is a common consequence of hip fractures, which further contribute to functional decline and increased disability. Assessing changes in individual thigh muscles volume in follow-up patients can provide valuable insights into the quantitative recovery process and guide rehabilitation interventions. However, accurately measuring anatomical individual thigh muscle volume can be challenging due to various, labor intensive and time-consuming.

MATERIALS AND METHODS: This study aimed to evaluate differences in thigh muscle volume in followed-up hip fracture patients computed tomography (CT) scans using an AI based automatic muscle segmentation model. The study included a total of 18 patients at Gyeongsang National University, who had undergone surgical treatment for a hip fracture. We utilized the automatic segmentation algorithm which we have already developed using UNETR (U-net Transformer) architecture, performance dice score = 0.84, relative absolute volume difference 0.019 ± 0.017%.

RESULTS: The results revealed intertrochanteric fractures result in more significant muscle volume loss (females: -97.4 cm3, males: -178.2 cm3) compared to femoral neck fractures (females: -83 cm3, males: -147.2 cm3). Additionally, the study uncovered substantial disparities in the susceptibility to volume loss among specific thigh muscles, including the Vastus lateralis, Adductor longus and brevis, and Gluteus maximus, particularly in cases of intertrochanteric fractures.

CONCLUSIONS: The use of an automatic muscle segmentation model based on deep learning algorithms enables efficient and accurate analysis of thigh muscle volume differences in followed up hip fracture patients. Our findings emphasize the significant muscle loss tied to sarcopenia, a critical condition among the elderly. Intertrochanteric fractures resulted in greater muscle volume deformities, especially in key muscle groups, across both genders. Notably, while most muscles exhibited volume reduction following hip fractures, the sartorius, vastus and gluteus groups demonstrated more significant disparities in individuals who sustained intertrochanteric fractures. This non-invasive approach provides valuable insights into the extent of muscle atrophy following hip fracture and can inform targeted rehabilitation interventions.

PMID:39161969 | PMC:PMC11332390 | DOI:10.7717/peerj.17509

Empir Softw Eng. 2024;29(6):139. doi: 10.1007/s10664-024-10533-w. Epub 2024 Aug 17.

ABSTRACT

Software systems log massive amounts of data, recording important runtime information. Such logs are used, for example, for log-based anomaly detection, which aims to automatically detect abnormal behaviors of the system under analysis by processing the information recorded in its logs. Many log-based anomaly detection techniques based on deep learning models include a pre-processing step called log parsing. However, understanding the impact of log parsing on the accuracy of anomaly detection techniques has received surprisingly little attention so far. Investigating what are the key properties log parsing techniques should ideally have to help anomaly detection is therefore warranted. In this paper, we report on a comprehensive empirical study on the impact of log parsing on anomaly detection accuracy, using 13 log parsing techniques, seven anomly detection techniques (five based on deep learning and two based on traditional machine learning) on three publicly available log datasets. Our empirical results show that, despite what is widely assumed, there is no strong correlation between log parsing accuracy and anomaly detection accuracy, regardless of the metric used for measuring log parsing accuracy. Moreover, we experimentally confirm existing theoretical results showing that it is a property that we refer to as distinguishability in log parsing results-as opposed to their accuracy-that plays an essential role in achieving accurate anomaly detection.

PMID:39161930 | PMC:PMC11330418 | DOI:10.1007/s10664-024-10533-w

Heliyon. 2024 Jul 24;10(15):e35150. doi: 10.1016/j.heliyon.2024.e35150. eCollection 2024 Aug 15.

ABSTRACT

The advent of online education has become indispensable for nursing students seeking to acquire knowledge. However, the efficacy of online education often falls short of initial expectations. Deep learning (DL) can assist learners tackle complex problems and make innovative decisions. Despite its potential, there has been limited exploration into the underlying mechanisms of DL among nursing students, both domestically and globally. This study examined the potential moderating effect of psychological capital (PC) on the association between academic self-concept (AS-c) and DL among nursing students from China enrolled in online courses. Conducted from October 2022 to January 2023, the survey involved 635 nursing students from four public universities in eastern China, utilizing convenience sampling. Data was collected using the AS-c scale, psychological capital scale, and DL scale in online courses. Correlation analyses, univariate analyses, multiple linear regression analyses, and the PROCESS macro were employed for a comprehensive examination. The results revealed a strong positive relationship between nursing students' DL and both their AS-c (r = 0.766, P < 0.01) and PC (r = 0.714, P < 0.01), respectively. Additionally, the effect of AS-c on DL was stronger among individuals with high PC (β = 0.34, SE = 0.03, P < 0.001) compared to those with low (β = 0.29, SE = 0.02, P < 0.001) or medium (β = 0.24, SE = 0.02, P < 0.001) levels of PC, indicating that PC exerts moderating effects and promotes DL among nursing students enrolled in online courses. Based on these findings, several implications are suggested for the theory and practice of facilitating DL.

PMID:39161810 | PMC:PMC11332870 | DOI:10.1016/j.heliyon.2024.e35150

Phys Imaging Radiat Oncol. 2024 Jul 19;31:100612. doi: 10.1016/j.phro.2024.100612. eCollection 2024 Jul.

ABSTRACT

BACKGROUND AND PURPOSE: Magnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis is essential in MRI-only radiotherapy workflows, particularly through deep learning techniques known for their accuracy. However, current supervised methods are limited to specific center's learnings and depend on registration precision. The aim of this study was to evaluate the accuracy of unsupervised and supervised approaches in the context of prostate MRI-to-CT generation for radiotherapy dose calculation.

METHODS: CT/MRI image pairs from 99 prostate cancer patients across three different centers were used. A comparison between supervised and unsupervised conditional Generative Adversarial Networks (cGAN) was conducted. Unsupervised training incorporates a style transfer method with. Content and Style Representation for Enhanced Perceptual synthesis (CREPs) loss. For dose evaluation, the photon prescription dose was 60 Gy delivered in volumetric modulated arc therapy (VMAT). Imaging endpoint for sCT evaluation was Mean Absolute Error (MAE). Dosimetric endpoints included absolute dose differences and gamma analysis between CT and sCT dose calculations.

RESULTS: The unsupervised paired network exhibited the highest accuracy for the body with a MAE at 33.6 HU, the highest MAE was 45.5 HU obtained with unsupervised unpaired learning. All architectures provided clinically acceptable results for dose calculation with gamma pass rates above 94 % (1 % 1 mm 10 %).

CONCLUSIONS: This study shows that multicenter data can produce accurate sCTs via unsupervised learning, eliminating CT-MRI registration. The sCTs not only matched HU values but also enabled precise dose calculations, suggesting their potential for wider use in MRI-only radiotherapy workflows.

PMID:39161728 | PMC:PMC11332181 | DOI:10.1016/j.phro.2024.100612

Front Cardiovasc Med. 2024 Aug 5;11:1466344. doi: 10.3389/fcvm.2024.1466344. eCollection 2024.

NO ABSTRACT

PMID:39161659 | PMC:PMC11330872 | DOI:10.3389/fcvm.2024.1466344