GANSim is a generative adversarial networks(GANs)-based geomodelling framework with direct conditioning capabilities.To extend GANSim for geomodelling of multi-scenario and non-stationary reservoirs,and to address its...GANSim is a generative adversarial networks(GANs)-based geomodelling framework with direct conditioning capabilities.To extend GANSim for geomodelling of multi-scenario and non-stationary reservoirs,and to address its tendency to overlook single-pixel well facies conditioning data that can cause local facies disconnections around wells,an enhanced GANSim framework is proposed.The effectiveness of the enhanced GANSim is validated using a 3D multi-scenario,non-stationary turbidite fan reservoir.For reservoirs that may involve multiple geological scenarios,two GANSim geomodelling workflows are proposed:(1)training a comprehensive GANSim model that covers all possible geological scenarios;and(2)first performing geological scenario falsification and then training GANSim models only for the unfalsified scenarios.On this basis,a local discriminator architecture is designed to improve facies continuity around wells.The modelling results show that both workflows can generate non-stationary facies models that conform to expected geological patterns and honor conditioning data,and the facies discontinuity issue around wells is effectively resolved.Compared with multipoint geostatistical methods(SNESIM),GANSim exhibits superior capability in reproducing geological patterns and modelling efficiency.Although GANSim requires a long training time,once training is completed,it can be applied to geomodelling reservoirs of arbitrary scale with similar geological structures,achieving modelling speeds approximately 1000 times faster than SNESIM.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
文摘GANSim is a generative adversarial networks(GANs)-based geomodelling framework with direct conditioning capabilities.To extend GANSim for geomodelling of multi-scenario and non-stationary reservoirs,and to address its tendency to overlook single-pixel well facies conditioning data that can cause local facies disconnections around wells,an enhanced GANSim framework is proposed.The effectiveness of the enhanced GANSim is validated using a 3D multi-scenario,non-stationary turbidite fan reservoir.For reservoirs that may involve multiple geological scenarios,two GANSim geomodelling workflows are proposed:(1)training a comprehensive GANSim model that covers all possible geological scenarios;and(2)first performing geological scenario falsification and then training GANSim models only for the unfalsified scenarios.On this basis,a local discriminator architecture is designed to improve facies continuity around wells.The modelling results show that both workflows can generate non-stationary facies models that conform to expected geological patterns and honor conditioning data,and the facies discontinuity issue around wells is effectively resolved.Compared with multipoint geostatistical methods(SNESIM),GANSim exhibits superior capability in reproducing geological patterns and modelling efficiency.Although GANSim requires a long training time,once training is completed,it can be applied to geomodelling reservoirs of arbitrary scale with similar geological structures,achieving modelling speeds approximately 1000 times faster than SNESIM.
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.
