Triple-attentions based salient object detector for strip steel surface defects

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 20, 2025

Accurate detection of surface defects on strip steel is essential for ensuring product quality. Existing deep learning based detectors typically strive to iteratively refine and integrate the coarse outputs backbone network, enhancing models' ability express defect characteristics. Attention mechanisms including spatial attention, channel attention self-attention are among most prevalent techniques feature extraction fusion. This paper introduces an innovative triple-attention mechanism (TA), characterized by interrelated complementary interactions, that concurrently refines integrates maps from three distinct perspectives, thereby features' capacity representation. The idea following observation: given a three-dimensional map, we can examine map different yet two-dimensional planar perspectives: channel-width, channel-height, width-height perspectives. Based TA, novel detector, called TADet, proposed, which encoder-decoder network: decoder uses proposed TA refines/fuses multiscale rough features generated encoder (backbone network) perspectives (branches) then purified branches. Extensive experimental results show TADet superior state-of-the-art methods in terms mean absolute error, S-measure, E-measure F-measure, confirming effectiveness robustness TADet. Our code available at https://github.com/hpguo1982/TADet .

Language: Английский

---

Synthetic electroretinogram signal generation using a conditional generative adversarial network

Documenta Ophthalmologica, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Abstract Purpose The electroretinogram (ERG) records the functional response of retina. In some neurological conditions, ERG waveform may be altered and could support biomarker discovery. heterogeneous or rare populations, where either large data sets availability a challenge, synthetic signals with Artificial Intelligence (AI) help to mitigate against these factors classification models. Methods This approach was tested using publicly available dataset real ERGs, n = 560 (ASD) 498 (Control) recorded at 9 different flash strengths from 18 ASD (mean age 12.2 ± 2.7 years) 31 Controls 11.8 3.3 that were augmented waveforms, generated through Conditional Generative Adversarial Network. Two deep learning models used classify groups only combined ERGs. One Time Series Transformer (with waveforms in their original form) second Visual model utilizing images wavelets derived Continuous Wavelet Transform Model performance classifying evaluated Balanced Accuracy (BA) as main outcome measure. Results BA improved 0.756 0.879 when ERGs included across all recordings for training Transformer. also achieved best 0.89 single strength 0.95 log cd s m −2 . Conclusions supports application AI improve group recordings.

Language: Английский

---

Exploring autism via the retina: Comparative insights in children with autism spectrum disorder and typical development

Autism Research, Journal Year: 2024, Volume and Issue: 17(8), P. 1520 - 1533

Published: July 29, 2024

Abstract Autism spectrum disorder (ASD) is a widely recognized neurodevelopmental disorder, yet the identification of reliable imaging biomarkers for its early diagnosis remains challenge. Considering specific manifestations ASD in eyes and interconnectivity between brain eyes, this study investigates through lens retinal analysis. We specifically examined differences macular region retina using optical coherence tomography (OCT)/optical angiography (OCTA) images children diagnosed with those typical development (TD). Our findings present potential novel characteristics ASD: thickness ellipsoid zone (EZ) cone photoreceptors was significantly increased ASD; large‐caliber arteriovenous inner reduced these changes EZ were more significant left eye than right eye. These observations photoreceptor alterations, vascular function changes, lateralization phenomena warrant further investigation, we hope that work can advance interdisciplinary understanding ASD.

Language: Английский

---

Artificial intelligence for detection of retinal toxicity in chloroquine and hydroxychloroquine therapy using multifocal electroretinogram waveforms

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 22, 2024

Abstract Chloroquine and hydroxychloroquine, while effective in rheumatology, pose risks of retinal toxicity, necessitating regular screening to prevent visual disability. The gold standard for includes imaging automated perimetry, with multifocal electroretinography (mfERG) being a recognized but less accessible method. This study explores the efficacy Artificial Intelligence (AI) algorithms detecting damage patients undergoing (hydroxy-)chloroquine therapy. We analyze mfERG data, comparing performance AI models that utilize raw time-series signals against using conventional waveform parameters. Our classification aimed identify maculopathy, regression were developed predict perimetric sensitivity. findings reveal more adept at predicting non-disease-related variation, AI-based models, particularly those utilizing full traces, demonstrated superior predictive power disease-related changes compared linear models. indicates significant potential improve diagnostic capabilities, although unbalanced nature dataset may limit some applications.

Language: Английский

---

Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning

Bioengineering, Journal Year: 2024, Volume and Issue: 12(1), P. 15 - 15

Published: Dec. 28, 2024

Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity (ADHD). In series ERGs collected in ASD (n = 77), ADHD 43), + 21), control 137) groups, this analysis explores the use machine learning feature selection techniques to improve classification these clinically defined groups. Standard time domain signal features were evaluated different models. For classification, balanced accuracy (BA) 0.87 was achieved for male participants. ADHD, BA 0.84 female When three-group model (ASD, control) lower, at 0.70, fell further 0.53 when all groups included control). The findings support role ERG establishing broad two-group but model's performance depends upon sex is limited multiple classes are modeling.

Language: Английский

---