{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:09:33Z","timestamp":1788944973004,"version":"build-2803163510"},"reference-count":26,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Tomography"],"abstract":"<jats:p>Background\/Objectives: Radiologists usually read a chest radiograph by comparing it with an earlier one, yet most deep learning models are trained and tested on single images. This study measures how much a longitudinal pair of radiographs improves finding-specific change detection on MIMIC-CXR and tests whether the gain can be explained by encoder pretraining. Methods: One frontal pair per patient was built from the earliest and latest studies within 180 days (14,043 pairs), and paired CheXpert labels defined four transition classes: absent-to-absent, onset, resolved, and persistent. A Siamese DenseNet-121 with two symmetric, weight-sharing branches fused the two images through concatenation and feature difference, and it was compared with a matched baseline that received only the final image. Evaluation used patient-grouped five-fold cross-validation over five seeds and three leakage-free encoder regimes. Results: On two matched binary tasks that hold the final image fixed\u2014resolved versus absent (1\u21920 vs. 0\u21920) and onset versus persistent (0\u21921 vs. 1\u21921)\u2014the single-image baseline performed at chance (AUROC 0.45 to 0.60), while the paired model scored well above it (paired difference +0.18 to +0.37 for resolution and +0.12 to +0.34 for onset; all significant by patient-level bootstrap after multiple-comparison correction), reaching a resolved-versus-absent AUROC of up to 0.87 (support devices). The benefit was stable across seeds, encoder regimes, projection changes, and follow-up intervals, and the CheXpert-derived transitions agreed with radiologist annotations (Cohen\u2019s \u03ba up to 0.97). Conclusions: A prior radiograph adds value whenever the final image alone underdetermines the transition, and they support pair-based designs for longitudinal change analysis.<\/jats:p>","DOI":"10.3390\/tomography12090129","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:05:43Z","timestamp":1788941143000},"page":"129","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Symmetric Siamese Networks for Longitudinal Chest Radiograph Change Detection: A Leakage-Controlled Study on MIMIC-CXR"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1768-7104","authenticated-orcid":false,"given":"\u015eahin","family":"I\u015f\u0131k","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Engineering and Architecture Faculty, Eski\u015fehir Osmangazi University, 26040 Eski\u015fehir, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6105-158X","authenticated-orcid":false,"given":"Hakan Alp","family":"Eren","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Engineering and Architecture Faculty, Eski\u015fehir Osmangazi University, 26040 Eski\u015fehir, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"European Society of Radiology (ESR) (2011). Good Practice for Radiological Reporting. Guidelines from the European Society of Radiology (ESR). Insights Imaging, 2, 93\u201396.","DOI":"10.1007\/s13244-011-0066-7"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s12194-016-0361-6","article-title":"Dynamic Chest Radiography: Flat-Panel Detector (FPD) Based Functional X-ray Imaging","volume":"9","author":"Tanaka","year":"2016","journal-title":"Radiol. Phys. Technol."},{"key":"ref_3","first-page":"590","article-title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","volume":"33","author":"Irvin","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a De-Identified Publicly Available Database of Chest Radiographs with Free-Text Reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"ref_5","unstructured":"Johnson, A., Lungren, M., Peng, Y., Lu, Z., Mark, R., Berkowitz, S., and Horng, S. (2024). MIMIC-CXR-JPG, Chest Radiographs with Structured Labels, PhysioNet. Version 2.1.0."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1038\/s44360-026-00096-z","article-title":"PhysioNet as a Global Platform for Biomedical Research","volume":"1","author":"Pollard","year":"2026","journal-title":"Nat. Health"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Irvin, J., Ball, R.L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., and Langlotz, C.P. (2018). Deep Learning for Chest Radiograph Diagnosis: A Retrospective Comparison of the CheXNeXt Algorithm to Practicing Radiologists. PLoS Med., 15.","DOI":"10.1371\/journal.pmed.1002686"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1148\/radiol.2019191293","article-title":"Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiologist-Adjudicated Reference Standards and Population-Adjusted Evaluation","volume":"294","author":"Majkowska","year":"2020","journal-title":"Radiology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-020-0255-1","article-title":"Siamese Neural Networks for Continuous Disease Severity Evaluation and Change Detection in Medical Imaging","volume":"3","author":"Li","year":"2020","journal-title":"npj Digit. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1007\/978-3-030-32226-7_83","article-title":"Longitudinal Change Detection on Chest X-rays Using Geometric Correlation Maps","volume":"Volume 11769","author":"Oh","year":"2019","journal-title":"Medical Image Computing and Computer Assisted Intervention, MICCAI 2019"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Karwande, G., Mbakwe, A.B., Wu, J.T., Celi, L.A., Moradi, M., and Lourentzou, I. (2022). CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships Between Chest X-rays. Medical Image Computing and Computer Assisted Intervention, MICCAI 2022, Springer.","DOI":"10.1007\/978-3-031-16431-6_55"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Bannur, S., Hyland, S., Liu, Q., P\u00e9rez-Garc\u00eda, F., Ilse, M., Castro, D.C., Boecking, B., Sharma, H., Bouzid, K., and Thieme, A. (2023, January 17\u201324). Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, S., Nooralahzadeh, F., Rohanian, M., Fujimoto, K., Nishio, M., Sakamoto, R., Rinaldi, F., and Krauthammer, M. (2023, January 13). Boosting Radiology Report Generation by Infusing Comparison Prior. Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.bionlp-1.4"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., and Shah, R. (1993). Signature Verification Using a \u201cSiamese\u201d Time Delay Neural Network. Advances in Neural Information Processing Systems, Morgan Kaufmann.","DOI":"10.1142\/9789812797926_0003"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41597-022-01618-6","article-title":"Inflation of Test Accuracy Due to Data Leakage in Deep Learning-Based Classification of OCT Images","volume":"9","author":"Tampu","year":"2022","journal-title":"Sci. Data"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_18","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems, Curran Associates."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.neucom.2020.03.127","article-title":"Interpreting Chest X-rays via CNNs That Exploit Hierarchical Disease Dependencies and Uncertainty Labels","volume":"437","author":"Pham","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/978-3-031-43904-9_66","article-title":"Hierarchical Vision Transformers for Disease Progression Detection in Chest X-Ray Images","volume":"Volume 14224","author":"Mbakwe","year":"2023","journal-title":"Medical Image Computing and Computer Assisted Intervention, MICCAI 2023"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e230277","DOI":"10.1148\/ryai.230277","article-title":"Anatomy-Specific Progression Classification in Chest Radiographs via Weakly Supervised Learning","volume":"6","author":"Yu","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"ref_23","unstructured":"Yang, Z., and Shen, L. (March, January 28). TempA-VLP: Temporal-Aware Vision-Language Pretraining for Longitudinal Exploration in Chest X-ray Image. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA."},{"key":"ref_24","unstructured":"Ko, H., Jeon, K., Choi, D., and Park, C.M. (2026). Temporal Inversion for Learning Interval Change in Chest X-Rays. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cho, S.S., Han, Y., and Do, J. (2026). MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays. Findings of the Association for Computational Linguistics: ACL 2026, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2026.findings-acl.1512"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4106218","DOI":"10.1109\/TGRS.2026.3685508","article-title":"DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery","volume":"64","author":"Sultan","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/129\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:52:14Z","timestamp":1788943934000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":26,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["tomography12090129"],"URL":"https:\/\/doi.org\/10.3390\/tomography12090129","relation":{},"ISSN":["2379-139X"],"issn-type":[{"value":"2379-139X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}