Single-crystal GaN epilayers were irradiated with heavy inert gas ions(2.3-MeV Ne^(8+),5.3-MeV Kr^(19+))to fluences ranging from 1.0×1.0^(11) to 1.0×1.0^(15)ions∕cm^(2).The strain-related damage accumulatio...Single-crystal GaN epilayers were irradiated with heavy inert gas ions(2.3-MeV Ne^(8+),5.3-MeV Kr^(19+))to fluences ranging from 1.0×1.0^(11) to 1.0×1.0^(15)ions∕cm^(2).The strain-related damage accumulation versus ion fluences was studied using highresolution X-ray diffraction(HRXRD)and ultraviolet–visible(UV–Vis)spectroscopy.The results showed that the damage accumulation was mainly dominated by nuclear energy loss.When the ion fluence was less than∼0.055 displacement per atom(dpa),the lattice expansions and lattice strains markedly increased linearly with increasing ion fluences,accompanied by a slow enhancement in the dislocation densities,distortion parameters,and Urbach energy for both ion irradiations.Above this fluence(∼0.055 dpa),the lattice strains presented a slight increase,whereas a remarkable increase was observed in the dislocation densities,distortion parameters,and Urbach energy with the ion fluences after both ion irradiations.∼0.055 dpa is the threshold ion fluence for defect evolution and lattice damage related to strain.The mechanisms underlying the damage accumulation are discussed in detail.展开更多
Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows rais...Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.展开更多
基金supported by the Program for National Natural Science Foundation of China(No.11675231)the Sichuan Science and Technology Program(Nos.2022YFG0263 and 2024NSFSC1097)the Scientific Research Starting Foundation for talents(Nos.21zx7109 and 22zx7175,24ycx1005).
文摘Single-crystal GaN epilayers were irradiated with heavy inert gas ions(2.3-MeV Ne^(8+),5.3-MeV Kr^(19+))to fluences ranging from 1.0×1.0^(11) to 1.0×1.0^(15)ions∕cm^(2).The strain-related damage accumulation versus ion fluences was studied using highresolution X-ray diffraction(HRXRD)and ultraviolet–visible(UV–Vis)spectroscopy.The results showed that the damage accumulation was mainly dominated by nuclear energy loss.When the ion fluence was less than∼0.055 displacement per atom(dpa),the lattice expansions and lattice strains markedly increased linearly with increasing ion fluences,accompanied by a slow enhancement in the dislocation densities,distortion parameters,and Urbach energy for both ion irradiations.Above this fluence(∼0.055 dpa),the lattice strains presented a slight increase,whereas a remarkable increase was observed in the dislocation densities,distortion parameters,and Urbach energy with the ion fluences after both ion irradiations.∼0.055 dpa is the threshold ion fluence for defect evolution and lattice damage related to strain.The mechanisms underlying the damage accumulation are discussed in detail.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.
