Open Access

ARTICLE

Optimized Deep Learning Framework for Robust Detection of GAN-Induced Hallucinations in Medical Imaging

Jarrar Amjad¹, Muhammad Zaheer Sajid², Mudassir Khalil³, Ayman Youssef⁴, Muhammad Fareed Hamid⁵, Imran Qureshi^6,*, Haya Aldossary⁷, Qaisar Abbas⁶

1 Department of Computer Science, Kansas State University, Manhattan, KS, USA
2 Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA
3 Computer Engineering Department, Bahauddin Zakariya University, Multan, Pakistan
4 Department of Computers and Systems, Electronics Research Institute, Cairo, Egypt
5 Department of Electrical Engineering, Military College of Signals (MCS), National University of Science and Technology, Islamabad, Pakistan
6 College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia
7 Computer Science Department, College of Science and Humanities, Imam Abdulrahman Bin Faisal University, Jubail, Saudi Arabia

* Corresponding Author: Imran Qureshi. Email:

(This article belongs to the Special Issue: Intelligent Medical Decision Support Systems: Methods and Applications)

Computer Modeling in Engineering & Sciences 2026, 146(2), 42 https://doi.org/10.32604/cmes.2026.073473

Received 18 September 2025; Accepted 16 January 2026; Issue published 26 February 2026

Abstract

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.

---

Keywords

---