Resolution-Enhancement for an Integral Imaging Microscopy Using Deep Learning by Ki-Chul Kwon, Ki Hoon Kwon, Munkh-Uchral Erdenebat, Yan-Ling Piao, Young-Tae Lim, Min Young Kim, Nam Kim

“…Since a pretrained model is applied, the proposed system processes the images directly without data training. The experimental results indicate that the proposed system produces resolution-enhanced directional-view images, and quantitative evaluation methods for reconstructed images such as the peak signal-to-noise ratio and the power spectral density confirm that the proposed system provides improvements in image quality.…”
Get full text

Intracranial volume segmentation for neurodegenerative populations using multicentre FLAIR MRI by Justin DiGregorio, Giordano Arezza, Adam Gibicar, Alan R. Moody, Pascal N. Tyrrell, April Khademi

“…In this work, we develop and evaluate 2 traditional and 8 deep learning algorithms for ICV segmentation in FLAIR MRI. …”
Get full text

Deep learning object detection-based early detection of lung cancer by Kuo-Yang Huang, Kuo-Yang Huang, Kuo-Yang Huang, Che-Liang Chung, Che-Liang Chung, Che-Liang Chung, Jia-Lang Xu

“…The Lung-PET-CT-Dx public dataset was used for the model training and evaluation. The performance of the You Only Look Once (YOLO) series of models in the lung CT image object detection task is compared in terms of algorithms, and different versions of YOLOv5, YOLOv8, YOLOv9, YOLOv10, and YOLOv11 are examined for lung cancer detection and classification. …”
Get full text

Predictive factors of cardiovascular changes depending on the type and intensity of physical activity in professional athletes by N. P Garganeeva, I. F. Taminova, V. V. Kalyuzhin, E. V Kalyuzhina, I. N. Smirnova

“…Predictive models of logistic regression using ROC analysis showed high sensitivity and specificity, a high percentage of correct predictions using data from echocardiography — 86,8%, CE — 80,9%, ECG and other indicators — 83,1%. A stepwise algorithm was used to select prognostic factors determining early cardiovascular changes in young athletes, depending on the stage of sports training, the intensity and type of dynamic and/or static exercise: left ventricular posterior wall thickness (p=0,008), left ventricular mass (p=0,001), stroke volume (p=0,002), end-systolic volume (p=0,001), PWC170 (p=0,025), MOC (p=0,003), recovery time of heart rate (HR) (p=0,029) and blood pressure (p=0,032) after submaximal exercise on a cycle ergometer, body mass index (p=0,029), heart rate (p=0,034), office systolic blood pressure (p=0,009), intraventricular (bundle) block (p=0,046), left ventricular repolarization abnormalities (p=0,010), mild cardiac connective tissue anomalies (p=0,035).Conclusion. …”
Get full text

Prediction of Flexural Ultimate Capacity for Reinforced UHPC Beams Using Ensemble Learning and SHAP Method by Zhe Zhang, Xuemei Zhou, Ping Zhu, Zhaochao Li, Yichuan Wang

“…Subsequently, a highly efficient evaluation of ML models is taken by analyzing the sensitivity of ML models to varying data subsets. …”
Get full text

Comparison of Faster R-CNN and YOLOv5 for Overlapping Objects Recognition by Muhamad Munawar Yusro, Rozniza Ali, Muhammad Suzuri Hitam

“…A kitchen utensil benchmark image database and overlapping kitchen utensils from internet were used as base benchmark objects. The evaluation and training/validation sets are set at 20% and 80% respectively. …”
Get full text

FedHSP: A Robust Federated Learning Framework Coherently Addressing Heterogeneity, Security, and Performance Challenges by Divya G. Nair, C. V. Aswartha Narayana, K. Jaideep Reddy, Jyothisha J. Nair

“…Federated Learning (FL) is a machine learning training method that leverages local model gradients instead of accessing private data from individual clients, ensuring privacy. …”
Get full text

A Reconfigurable 1x2 Photonic Digital Switch Controlled by an Externally Induced Metasurface by Alessandro Fantoni, Paolo Di Giamberardino

“…This dataset has been used for training and testing of a machine learning algorithm for the classification of the MMI configuration in terms of binary digital output for a 1x2 switch. …”
Get full text

Enhancing precision in multiple sclerosis lesion segmentation: A U-net based machine learning approach with data augmentation by Oezdemir Cetin, Berkay Canel, Gamze Dogali, Unal Sakoglu

“…The dataset for this study was created from MRI data of 20 subjects. The algorithm's effectiveness was evaluated using the DSC score, a statistical tool that measures the similarity between two samples. …”
Get full text

Better Cone-Beam CT Artifact Correction via Spatial and Channel Reconstruction Convolution Based on Unsupervised Adversarial Diffusion Models by Guoya Dong, Yutong He, Xuan Liu, Jingjing Dai, Yaoqin Xie, Xiaokun Liang

“…We propose a new unsupervised CBCT image artifact correction algorithm, named Spatial Convolution Diffusion (ScDiff), based on a conditional diffusion model, which combines the unsupervised learning ability of generative adaptive networks (GAN) with the stable training characteristics of diffusion models. …”
Get full text

Probabilistic phase labeling and lattice refinement for autonomous materials research by Ming-Chiang Chang, Sebastian Ament, Maximilian Amsler, Duncan R. Sutherland, Lan Zhou, John M. Gregoire, Carla P. Gomes, R. Bruce van Dover, Michael O. Thompson

“…To address these issues, we developed CrystalShift for rapid and efficient probabilistic XRD phase labeling employing symmetry-constrained optimization, best-first tree search, and Bayesian model comparison. The algorithm estimates probabilities for phase combinations without requiring additional phase space information or training. …”
Get full text

CLUMM: Contrastive Learning for Unobtrusive Motion Monitoring by Pius Gyamenah, Hari Iyer, Heejin Jeong, Shenghan Guo

“…A custom dataset of human subjects simulating various tasks in a workplace setting is used for training and evaluation. By fine-tuning the learned model for a downstream motion classification task, we achieve up to 90% accuracy, demonstrating the effectiveness of our proposed solution in real-time human motion monitoring.…”
Get full text

TECHNOLOGIES FOR DEVELOPING DECISION SUPPORT SYSTEMS FOR THE DIAGNOSIS OF BLOOD DISORDERS USING CONVOLUTIONAL NEURAL NETWORKS by U. V. Maslikova, A. A. Supilnikov

“…We selected the most promising machine learning algorithms optimal for the processing of medical images, investigated the technologies of analyzing medical texts, studied the aspects of using the Watson neural network for analyzing the semantics of medical images, as well as the aspect of using the unified medical language UMLS for the needs of syndromic diagnostics for the evaluation of medical texts from medical histories in natural language. …”
Get full text

Machine learning with sparse nutrition data to improve cardiovascular mortality risk prediction in the USA using nationally randomly sampled data by Joseph Rigdon, Sanjay Basu

“…Objectives We aimed to test whether or not adding (1) nutrition predictor variables and/or (2) using machine learning models improves cardiovascular death prediction versus standard Cox models without nutrition predictor variables.Design Retrospective study.Setting Six waves of Survey (NHANES) data collected from 1999 to 2011 linked to the National Death Index (NDI).Participants 29 390 participants were included in the training set for model derivation and 12 600 were included in the test set for model evaluation. …”
Get full text

Predicting cancer risk using machine learning on lifestyle and genetic data by Mohamed Abdelmoaty Ahmed, Ahmed AbdelMoety, Asmaa Mohamed Ahmed Soliman

“…A full end-to-end ML pipeline was implemented, encompassing data exploration, preprocessing, feature scaling, model training, and evaluation using stratified cross-validation and a separate test set. …”
Get full text

Improving myocardial infarction diagnosis with Siamese network-based ECG analysis. by Vaibhav Gadag, Simrat Singh, Anshul Harish Khatri, Shruti Mishra, Sandeep Kumar Satapathy, Sung-Bae Cho, Abishi Chowdhury, Amrit Pal, Sachi Nandan Mohanty

“…<h4>Methods</h4>The dataset is then imported, pre-processed, and split into a 70:20:10 ratio of training, validation, and testing. It is then trained using the Siamese Network Model.…”
Get full text

Neuroscience-informed nomogram model for early prediction of cognitive impairment in Parkinson's disease by Sudharshan Putha, Swaroop Reddy Gayam, Bhavani Prasad Kasaraneni, Krishna Kanth Kondapaka, Sateesh Kumar Nallamala, Praveen Thuniki

“…The least absolute shrinkage and selection operator (LASSO) algorithm was applied to identify highly correlated clinical variables influencing cognitive function. …”
Get full text

Addressing human–elephant conflicts in Taita Taveta County, Kenya: Integrating species distribution modeling into targeted conservation strategies by Tino Johansson, Martha Munyao, Petri K.E. Pellikka, Sakari Äärilä, Patrick Omondi, Mika Siljander

Get full text

Improved estimation of two-phase capillary pressure with nuclear magnetic resonance measurements via machine learning by Oriyomi Raheem, Misael M. Morales, Wen Pan, Carlos Torres-Verdín

“…The new model integrates cumulative NMR data and densely resampled core measurements as training data, with prediction errors quantified throughout the process. …”
Get full text

Machine learning, clinical-radiomics approach with HIM for hemorrhagic transformation prediction after thrombectomy and treatment by Sheng Hu, Junyu Liu, Jiayi Hong, Yuting Chen, Ziwen Wang, Jibo Hu, Shiying Gai, Xiaochao Yu, Jingjing Fu

“…The datasets were randomly divided into training and test cohorts at a ratio of 8:2. An optimal machine learning (ML) algorithm was used for model development. …”
Get full text