{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T15:31:25Z","timestamp":1788017485595,"version":"build-2784847793"},"reference-count":51,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T00:00:00Z","timestamp":1704153600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fundamental Research Funds for Central Universities","award":["328202204"],"award-info":[{"award-number":["328202204"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Using generative adversarial network (GAN) Goodfellow et al. (2014) for data enhancement of medical images is significantly helpful for many computer-aided diagnosis (CAD) tasks. A new GAN-based automated tampering attack, like CT-GAN Mirsky et al. (2019), has emerged. It can inject or remove lung cancer lesions to CT scans. Because the tampering region may even account for less than 1% of the original image, even state-of-the-art methods are challenging to detect the traces of such tampering. This paper proposes a two-stage cascade framework to detect GAN-based medical image small region forgery like CT-GAN. In the local detection stage, we train the detector network with small sub-images so that interference information in authentic regions will not affect the detector. We use depthwise separable convolution and residual networks to prevent the detector from over-fitting and enhance the ability to find forged regions through the attention mechanism. The detection results of all sub-images in the same image will be combined into a heatmap. In the global classification stage, using gray-level co-occurrence matrix (GLCM) can better extract features of the heatmap. Because the shape and size of the tampered region are uncertain, we use hyperplanes in an infinite-dimensional space for classification. Our method can classify whether a CT image has been tampered and locate the tampered position. Sufficient experiments show that our method can achieve excellent performance than the state-of-the-art detection methods.<\/jats:p>","DOI":"10.1371\/journal.pone.0290303","type":"journal-article","created":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:40:48Z","timestamp":1704206448000},"page":"e0290303","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":20,"title":["GAN-based medical image small region forgery detection via a two-stage cascade framework"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8765-053X","authenticated-orcid":true,"given":"Jianyi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanxi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,1,2]]},"reference":[{"key":"pone.0290303.ref001","unstructured":"I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., \u201cGenerative adversarial nets,\u201d 2014."},{"key":"pone.0290303.ref002","doi-asserted-by":"crossref","unstructured":"L. Chai, D. Bau, S.-N. Lim, and P. Isola, \u201cWhat makes fake images detectable? understanding properties that generalize,\u201d in European Conference on Computer Vision. Springer, 2020, pp. 103\u2013120.","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"pone.0290303.ref003","doi-asserted-by":"crossref","unstructured":"A. Rossler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nie\u00dfner, \u201cFaceforensics++: Learning to detect manipulated facial images,\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"pone.0290303.ref004","doi-asserted-by":"crossref","unstructured":"F. Marra, D. Gragnaniello, D. Cozzolino, and L. Verdoliva, \u201cDetection of gan-generated fake images over social networks,\u201d in 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2018, pp. 384\u2013389.","DOI":"10.1109\/MIPR.2018.00084"},{"key":"pone.0290303.ref005","doi-asserted-by":"crossref","unstructured":"S. McCloskey and M. Albright, \u201cDetecting gan-generated imagery using saturation cues,\u201d in 2019 IEEE International Conference on Image Processing (ICIP), 2019, pp. 4584\u20134588.","DOI":"10.1109\/ICIP.2019.8803661"},{"key":"pone.0290303.ref006","doi-asserted-by":"crossref","first-page":"129 494","DOI":"10.1109\/ACCESS.2019.2939812","article-title":"No one can escape: A general approach to detect tampered and generated image","volume":"vol. 7","author":"K. Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0290303.ref007","doi-asserted-by":"crossref","unstructured":"N. Yu, L. S. Davis, and M. Fritz, \u201cAttributing fake images to gans: Learning and analyzing gan fingerprints,\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2019, pp. 7556\u20137566.","DOI":"10.1109\/ICCV.2019.00765"},{"issue":"no. 5","key":"pone.0290303.ref008","first-page":"532","article-title":"Detecting gan generated fake images using co-occurrence matrices","volume":"vol. 2019","author":"L. Nataraj","year":"2019","journal-title":"Electronic Imaging"},{"key":"pone.0290303.ref009","unstructured":"J. Frank, T. Eisenhofer, L. Sch\u00f6nherr, A. Fischer, D. Kolossa, and T. Holz, \u201cLeveraging frequency analysis for deep fake image recognition,\u201d in International Conference on Machine Learning. PMLR, 2020, pp. 3247\u20133258."},{"key":"pone.0290303.ref010","doi-asserted-by":"crossref","unstructured":"R. Durall, M. Keuper, and J. Keuper, \u201cWatch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 7890\u20137899.","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"pone.0290303.ref011","doi-asserted-by":"crossref","unstructured":"F. Marra, C. Saltori, G. Boato, and L. Verdoliva, \u201cIncremental learning for the detection and classification of gan-generated images,\u201d in 2019 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 2019, pp. 1\u20136.","DOI":"10.1109\/WIFS47025.2019.9035099"},{"key":"pone.0290303.ref012","unstructured":"D. Cozzolino, J. Thies, A. R\u00f6ssler, C. Riess, M. Nie\u00dfner, and L. Verdoliva, \u201cForensictransfer: Weakly-supervised domain adaptation for forgery detection,\u201d arXiv preprint arXiv:1812.02510, 2018."},{"key":"pone.0290303.ref013","unstructured":"Y. Mirsky, T. Mahler, I. Shelef, and Y. Elovici, \u201cCt-gan: Malicious tampering of 3d medical imagery using deep learning,\u201d in 28th USENIX Security Symposium (USENIX Security 19), 2019, pp. 461\u2013478."},{"key":"pone.0290303.ref014","unstructured":"M. Arjovsky, S. Chintala, and L. Bottou, \u201cWasserstein generative adversarial networks,\u201d in International conference on machine learning. PMLR, 2017, pp. 214\u2013223."},{"key":"pone.0290303.ref015","unstructured":"T. Karras, T. Aila, S. Laine, and J. Lehtinen, \u201cProgressive growing of gans for improved quality, stability, and variation,\u201d 2017."},{"key":"pone.0290303.ref016","doi-asserted-by":"crossref","unstructured":"T. Karras, S. Laine, and T. Aila, \u201cA style-based generator architecture for generative adversarial networks,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"pone.0290303.ref017","doi-asserted-by":"crossref","unstructured":"P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, \u201cImage-to-image translation with conditional adversarial networks,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"pone.0290303.ref018","doi-asserted-by":"crossref","unstructured":"J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros, \u201cUnpaired image-to-image translation using cycle-consistent adversarial networks,\u201d in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"pone.0290303.ref019","doi-asserted-by":"crossref","unstructured":"D. Jin, Z. Xu, Y. Tang, A. P. Harrison, and D. J. Mollura, \u201cCt-realistic lung nodule simulation from 3d conditional generative adversarial networks for robust lung segmentation,\u201d in International Conference on Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, Springer, 2018, pp. 732\u2013740.","DOI":"10.1007\/978-3-030-00934-2_81"},{"key":"pone.0290303.ref020","doi-asserted-by":"crossref","unstructured":"D. Mahapatra, B. Bozorgtabar, J.-P. Thiran, and M. Reyes, \u201cEfficient active learning for image classification and segmentation using a sample selection and conditional generative adversarial network,\u201d in Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, 2018, pp. 580\u2013588.","DOI":"10.1007\/978-3-030-00934-2_65"},{"key":"pone.0290303.ref021","doi-asserted-by":"crossref","unstructured":"A. Madani, M. Moradi, A. Karargyris, and T. Syeda-Mahmood, \u201cSemi-supervised learning with generative adversarial networks for chest x-ray classification with ability of data domain adaptation,\u201d in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 1038\u20131042.","DOI":"10.1109\/ISBI.2018.8363749"},{"key":"pone.0290303.ref022","doi-asserted-by":"crossref","unstructured":"M. J. M. Chuquicusma, S. Hussein, J. Burt, and U. Bagci, \u201cHow to fool radiologists with generative adversarial networks? a visual turing test for lung cancer diagnosis,\u201d in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 240\u2013244.","DOI":"10.1109\/ISBI.2018.8363564"},{"key":"pone.0290303.ref023","doi-asserted-by":"crossref","unstructured":"F. Tom and D. Sheet, \u201cSimulating patho-realistic ultrasound images using deep generative networks with adversarial learning,\u201d in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018, pp. 1174\u20131177.","DOI":"10.1109\/ISBI.2018.8363780"},{"key":"pone.0290303.ref024","doi-asserted-by":"crossref","unstructured":"B. Cao, H. Zhang, N. Wang, X. Gao, and D. Shen, \u201cAuto-gan: self-supervised collaborative learning for medical image synthesis,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 07, 2020, pp. 10 486\u201310 493.","DOI":"10.1609\/aaai.v34i07.6619"},{"issue":"no. 6","key":"pone.0290303.ref025","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/TMI.2018.2827462","article-title":"Low-dose ct image denoising using a generative adversarial network with wasserstein distance and perceptual loss","volume":"vol. 37","author":"Q. Yang","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0290303.ref026","doi-asserted-by":"crossref","first-page":"41 839","DOI":"10.1109\/ACCESS.2018.2858196","article-title":"Structurally-sensitive multi-scale deep neural network for low-dose ct denoising","volume":"vol. 6","author":"C. You","year":"2018","journal-title":"IEEE Access"},{"issue":"no. 6","key":"pone.0290303.ref027","doi-asserted-by":"crossref","first-page":"1522","DOI":"10.1109\/TMI.2018.2832217","article-title":"3-d convolutional encoder-decoder network for low-dose ct via transfer learning from a 2-d trained network","volume":"vol. 37","author":"H. Shan","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0290303.ref028","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.media.2019.05.001","article-title":"Denoising of 3d magnetic resonance images using a residual encoder\u2013decoder wasserstein generative adversarial network","volume":"vol. 55","author":"M. Ran","year":"2019","journal-title":"Medical Image Analysis"},{"key":"pone.0290303.ref029","doi-asserted-by":"crossref","unstructured":"Y. Pan, M. Liu, C. Lian, T. Zhou, Y. Xia, and D. Shen, \u201cSynthesizing missing pet from mri with cycle-consistent generative adversarial networks for alzheimer\u2019s disease diagnosis,\u201d in Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, 2018, pp. 455\u2013463.","DOI":"10.1007\/978-3-030-00931-1_52"},{"key":"pone.0290303.ref030","doi-asserted-by":"crossref","unstructured":"Y. Zhang, S. Miao, T. Mansi, and R. Liao, \u201cTask driven generative modeling for unsupervised domain adaptation: Application to x-ray image segmentation,\u201d in Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, A. F. Frangi, J. A. Schnabel, C. Davatzikos, C. Alberola-L\u00f3pez, and G. Fichtinger, Eds. Springer International Publishing, 2018, pp. 599\u2013607.","DOI":"10.1007\/978-3-030-00934-2_67"},{"key":"pone.0290303.ref031","doi-asserted-by":"crossref","unstructured":"J. Jiang, Y.-C. Hu, N. Tyagi, P. Zhang, A. Rimner, G. S. Mageras, et al., \u201cTumor-aware, adversarial domain adaptation from ct to mri for lung cancer segmentation,\u201d in Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, 2018, pp. 777\u2013785.","DOI":"10.1007\/978-3-030-00934-2_86"},{"key":"pone.0290303.ref032","doi-asserted-by":"crossref","unstructured":"Z. Zhang, L. Yang, and Y. Zheng, \u201cTranslating and segmenting multimodal medical volumes with cycle-and shape-consistency generative adversarial network,\u201d in Proceedings of the IEEE conference on computer vision and pattern Recognition, 2018, pp. 9242\u20139251.","DOI":"10.1109\/CVPR.2018.00963"},{"key":"pone.0290303.ref033","doi-asserted-by":"crossref","unstructured":"R. Oulbacha and S. Kadoury, \u201cMri to ct synthesis of the lumbar spine from a pseudo-3d cycle gan,\u201d in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020, pp. 1784\u20131787.","DOI":"10.1109\/ISBI45749.2020.9098421"},{"key":"pone.0290303.ref034","doi-asserted-by":"crossref","unstructured":"X. Ying, H. Guo, K. Ma, J. Wu, Z. Weng, and Y. Zheng, \u201cX2ct-gan: reconstructing ct from biplanar x-rays with generative adversarial networks,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10 619\u201310 628.","DOI":"10.1109\/CVPR.2019.01087"},{"issue":"no. 12","key":"pone.0290303.ref035","doi-asserted-by":"crossref","first-page":"3955","DOI":"10.1109\/TMI.2021.3101937","article-title":"Structure and illumination constrained gan for medical image enhancement","volume":"vol. 40","author":"Y. Ma","year":"2021","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0290303.ref036","doi-asserted-by":"crossref","unstructured":"J. Zhu, G. Yang, and P. Lio, \u201cHow can we make gan perform better in single medical image super-resolution? a lesion focused multi-scale approach,\u201d in 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE, 2019, pp. 1669\u20131673.","DOI":"10.1109\/ISBI.2019.8759517"},{"issue":"no. 1","key":"pone.0290303.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-00898-z","article-title":"Impact of gan-based lesion-focused medical image super-resolution on the robustness of radiomic features","volume":"vol. 11","author":"E. C. de Farias","year":"2021","journal-title":"Scientific reports"},{"key":"pone.0290303.ref038","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0290303.ref039","doi-asserted-by":"crossref","unstructured":"F. Chollet, \u201cXception: Deep learning with depthwise separable convolutions,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"pone.0290303.ref040","unstructured":"M. Tan and Q. Le, \u201cEfficientnet: Rethinking model scaling for convolutional neural networks,\u201d in Proceedings of the 36th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, vol. 97. PMLR, 09\u201315 Jun 2019, pp. 6105\u20136114."},{"issue":"no. 1","key":"pone.0290303.ref041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3425780","article-title":"The creation and detection of deepfakes: A survey","volume":"vol. 54","author":"Y. Mirsky","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"pone.0290303.ref042","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, \u201cU-net: Convolutional networks for biomedical image segmentation,\u201d in Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"pone.0290303.ref043","doi-asserted-by":"crossref","unstructured":"C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, \u201cRethinking the inception architecture for computer vision,\u201d in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"pone.0290303.ref044","doi-asserted-by":"crossref","unstructured":"A. Howard, M. Sandler, B. Chen, W. Wang, L. Chen, M. Tan, et al., \u201cSearching for mobilenetv3,\u201d in 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"pone.0290303.ref045","doi-asserted-by":"crossref","unstructured":"S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, \u201cCbam: Convolutional block attention module,\u201d ser. Computer Vision\u2014ECCV 2018. Springer International Publishing, Conference Proceedings, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"pone.0290303.ref046","unstructured":"G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter, \u201cSelf-normalizing neural networks,\u201d 2017."},{"key":"pone.0290303.ref047","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.media.2017.06.015","article-title":"Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the luna16 challenge","volume":"vol. 42","author":"A. A. A. Setio","year":"2017","journal-title":"Medical image analysis"},{"key":"pone.0290303.ref048","doi-asserted-by":"crossref","unstructured":"B. Reichman, L. Jing, O. Akin, and Y. Tian, \u201cMedical image tampering detection: A new dataset and baseline,\u201d in International Conference on Pattern Recognition. Springer, 2021, pp. 266\u2013277.","DOI":"10.1007\/978-3-030-68763-2_20"},{"key":"pone.0290303.ref049","doi-asserted-by":"crossref","unstructured":"S.-Y. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, \u201cCnn-generated images are surprisingly easy to spot\u2026 for now,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8695\u20138704.","DOI":"10.1109\/CVPR42600.2020.00872"},{"issue":"no. 2","key":"pone.0290303.ref050","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s10044-017-0678-8","article-title":"State of the art in passive digital image forgery detection: copy-move image forgery","volume":"vol. 21","author":"S. Sadeghi","year":"2018","journal-title":"Pattern Analysis and Applications"},{"issue":"no. 4","key":"pone.0290303.ref051","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1109\/JBHI.2016.2575398","article-title":"Computed tomography image origin identification based on original sensor pattern noise and 3-d image reconstruction algorithm footprints","volume":"vol. 21","author":"Y. Duan","year":"2016","journal-title":"IEEE journal of biomedical and health informatics"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0290303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:41:18Z","timestamp":1704206478000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0290303"}},"subtitle":[],"editor":[{"given":"Ali Mohammad","family":"Alqudah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,1,2]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0290303","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,2]]}}}