{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T15:30:36Z","timestamp":1787585436215,"version":"build-2736575974"},"reference-count":33,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["ZCLQN26F0206"],"award-info":[{"award-number":["ZCLQN26F0206"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014768","name":"Public Welfare Project of Jiaxing","doi-asserted-by":"publisher","award":["2023AY11052"],"award-info":[{"award-number":["2023AY11052"]}],"id":[{"id":"10.13039\/501100014768","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Accurate delineation of infarct core and ischemic penumbra in acute ischemic stroke primarily relies on computed tomography perfusion (CTP), where the arterial input function (AIF) is essential for reliable perfusion quantification. However, reliable and fast AIF selection remains challenging in clinical practice due to noise, vascular heterogeneity, and inter-patient variability in bolus dynamics. In this study, we propose TriAIF-RWKV, a three-stage framework for robust and automated AIF extraction. Specifically, ACSANet is first employed for spatial vascular localization using axial and channel-aware attention mechanisms, thereby narrowing the candidate arterial region and reducing the AIF search space. Then, a Dilated-RWKV network is introduced to model temporal intensity dynamics from a global sequence perspective, allowing robust identification of AIF-consistent patterns. Finally, a physiology-informed scoring strategy is used to select the optimal AIF by evaluating baseline stability, peak enhancement, and washout characteristics. Extensive experiments on CTP datasets were conducted from multiple perspectives, including AIF waveform fidelity, perfusion parameter estimation, and lesion-level analysis. The results demonstrate that the proposed method achieved high agreement with expert-selected AIFs, with a global waveform PCC of 0.973, peak correlation of 0.942, and TTP correlation of 0.973 with a mean error of 0.923 s. Furthermore, the proposed method provides more consistent downstream perfusion quantification, achieving higher consistency of CTP-derived parameters and improved lesion-to-normal tissue discrimination compared with existing approaches. These results highlight its potential for reliable clinical perfusion assessment.<\/jats:p>","DOI":"10.3390\/e28090944","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:49:34Z","timestamp":1787582974000},"page":"944","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TriAIF-RWKV: A Physiology-Guided Spatiotemporal Framework for Robust Arterial Input Function Selection in CT Perfusion Imaging"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7703-8603","authenticated-orcid":false,"given":"Lei","family":"Lei","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"},{"name":"Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Nanjing University of Science and Technology, Xiaolingwei Road, Nanjing 210094, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9981-3623","authenticated-orcid":false,"given":"Dawei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi\u2019an 710072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4170-3023","authenticated-orcid":false,"given":"Feng","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Nanjing University of Science and Technology, Xiaolingwei Road, Nanjing 210094, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8758-3776","authenticated-orcid":false,"given":"Yixin","family":"He","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"},{"name":"Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-9660","authenticated-orcid":false,"given":"Chaochao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"},{"name":"Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiandong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Jiaxing University, Guangqiong Road, Jiaxing 314000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"ref_1","unstructured":"Chieng, R., and Binnuhaid, A. (2024). Ischaemic Stroke, Radiopaedia.org."},{"key":"ref_2","first-page":"1","article-title":"Systemic Thrombolysis and Endovascular Therapy for Large Vessel Occlusion Acute Ischemic Stroke","volume":"2","author":"Farrell","year":"2022","journal-title":"Can. J. Health Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1056\/NEJMoa1713973","article-title":"Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging","volume":"378","author":"Albers","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bobe, R.C., Coroiu, R.E., Cirstian, A.E., Cristescu, C.I., Pepelea, D.A., and Manea, R.M. (2025). The Role of CT Perfusion in the Evaluation and Management of Acute Ischemic Stroke\u2014A Systematic Review. Life, 15.","DOI":"10.3390\/life15111693"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chung, K.J., De Sarno, D., and Lee, T.Y. (2023). Quantitative functional imaging with CT perfusion: Technical considerations, kinetic modeling, and applications. Front. Phys., 11.","DOI":"10.3389\/fphy.2023.1246973"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102211","DOI":"10.1016\/j.media.2021.102211","article-title":"AIFNet: Automatic Vascular Function Estimation for Perfusion Analysis Using Deep Learning","volume":"74","author":"Rosa","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1002\/mrm.24260","article-title":"Modeling dispersion in arterial spin labeling: Validation using dynamic angiographic measurements","volume":"69","author":"Chappell","year":"2013","journal-title":"Magn. Reson. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8720","DOI":"10.21037\/qims-24-1076","article-title":"Comparison of normalized cerebral blood flow between different post-processing methods of dynamic susceptibility contrast perfusion-weighted imaging and arterial spin labeling in gliomas with different grading","volume":"14","author":"Wang","year":"2024","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.pnmrs.2013.04.002","article-title":"Arterial input function in perfusion MRI: A comprehensive review","volume":"74","author":"Calamante","year":"2013","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yin, J., Yang, J., and Guo, Q. (2014). Evaluating the Feasibility of an Agglomerative Hierarchy Clustering Algorithm for the Automatic Detection of the Arterial Input Function Using DSC-MRI. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0100308"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/s00234-009-0516-9","article-title":"Automated versus manual postprocessing of perfusion-CT data in patients with acute cerebral ischemia: Influence on interobserver variability","volume":"51","author":"Soares","year":"2009","journal-title":"Neuroradiology"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1002\/mrm.20759","article-title":"Automatic selection of arterial input function using cluster analysis","volume":"55","author":"Mouridsen","year":"2006","journal-title":"Magn. Reson. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e148","DOI":"10.1016\/j.cmpb.2011.02.012","article-title":"Automatic selection of arterial input function on dynamic contrast-enhanced MR images","volume":"104","author":"Peruzzo","year":"2011","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_14","first-page":"266","article-title":"Automated Determination of Arterial Input Function for DCE-MRI of the Prostate","volume":"7963","author":"Zhu","year":"2011","journal-title":"Hologr. Opt. II Princ. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fan, S., Bian, Y., Wang, E., Kang, Y., Wang, D.J.J., Yang, Q., and Ji, X. (2019). An Automatic Estimation of Arterial Input Function Based on Multi-Stream 3D CNN. Front. Neuroinform., 13.","DOI":"10.3389\/fninf.2019.00049"},{"key":"ref_16","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., and Woo, W.C. (2015). Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, MIT Press."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TMI.2018.2863670","article-title":"Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction","volume":"38","author":"Qin","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109133","DOI":"10.1016\/j.compbiomed.2024.109133","article-title":"CRNN-Refined Spatiotemporal Transformer for Dynamic MRI reconstruction","volume":"182","author":"Wang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"10663","DOI":"10.1007\/s00371-025-04061-x","article-title":"Transformer-based arterial spin labeling perfusion MRI denoising","volume":"41","author":"Cheema","year":"2025","journal-title":"Vis. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"110342","DOI":"10.1016\/j.mri.2025.110342","article-title":"Large blood vessel segmentation in quantitative DCE-MRI of brain tumors: A Swin UNETR approach","volume":"118","author":"Kesari","year":"2025","journal-title":"Magn. Reson. Imaging"},{"key":"ref_21","unstructured":"Espinosa, R., Jim\u00e9nez, F., and Palma, J. (2023). Embedded feature selection in LSTM networks with multi-objective evolutionary ensemble learning for time series forecasting. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"660","DOI":"10.3390\/tomography10050051","article-title":"Arterial Input Function (AIF) correction using AIF plus tissue inputs with a Bi-LSTM Network","volume":"10","author":"Huang","year":"2024","journal-title":"Tomography"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s10916-024-02054-2","article-title":"CT perfusion map synthesis from CTP dynamic images using a learned LSTM generative adversarial network for acute ischemic stroke assessment","volume":"48","author":"Soltanpour","year":"2024","journal-title":"J. Med. Syst."},{"key":"ref_24","unstructured":"Amador, K., Wilms, M., Winder, A., Fiehler, J., and Forkert, N. (2021). Stroke Lesion Outcome Prediction Based on 4D CT Perfusion Data Using Temporal Convolutional Networks. Medical Imaging with Deep Learning, PMLR."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102610","DOI":"10.1016\/j.media.2022.102610","article-title":"Predicting treatment-specific lesion outcomes in acute ischemic stroke from 4D CT perfusion imaging using spatio-temporal convolutional neural networks","volume":"82","author":"Amador","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109134","DOI":"10.1016\/j.compbiomed.2024.109134","article-title":"CT perfusion parameter estimation in stroke using neural network with transformer and physical model priors","volume":"182","author":"Luo","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Peng, B., Alcaide, E., Anthony, Q., Albalak, A., Arcadinho, S., Biderman, S., Cao, H., Cheng, X., Chung, M., and Derczynski, L. (2023). RWKV: Reinventing RNNs for the Transformer Era, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4199","DOI":"10.1002\/mp.14351","article-title":"Automatic arterial input function selection in CT and MR perfusion datasets using deep convolutional neural networks","volume":"47","author":"Winder","year":"2020","journal-title":"Med. Phys."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2732","DOI":"10.1002\/mrm.70020","article-title":"Automatic detection of arterial input function for brain DCE-MRI in multi-site cohorts","volume":"94","author":"Saca","year":"2025","journal-title":"Magn. Reson. Med."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., and Chen, L.C. (2020). Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"130711","DOI":"10.1016\/j.neucom.2025.130711","article-title":"A survey of RWKV","volume":"649","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3168416","DOI":"10.1155\/2019\/3168416","article-title":"A Comparative Study of Two-Compartment Exchange Models for Dynamic Contrast-Enhanced MRI in Characterizing Uterine Cervical Carcinoma","volume":"2019","author":"Wang","year":"2019","journal-title":"Contrast Media Mol. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhao, K., Huang, H., Gao, E., Qi, J., Chen, T., Zhao, G., Zhao, G., Zhang, Y., Wang, P., and Bai, J. (2024). Distributed parameter model of dynamic contrast-enhanced MRI in the identification of IDH mutation, 1p19q codeletion, and tumor cell proliferation in glioma patients. Front. Oncol., 14.","DOI":"10.3389\/fonc.2024.1333798"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/944\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:53:15Z","timestamp":1787583195000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/9\/944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":33,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["e28090944"],"URL":"https:\/\/doi.org\/10.3390\/e28090944","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]}}}