{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:48:50Z","timestamp":1773802130912,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"15","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Low-count positron emission tomography (PET) reconstruction is a challenging inverse problem due to severe degradations arising from Poisson noise, photon scarcity, and attenuation correction errors. Existing deep learning methods\ntypically address these in the spatial domain with an undifferentiated optimization objective, making it difficult to disentangle overlapping artifacts and limiting correction effectiveness. In this work, we perform a Fourier-domain analysis and reveal that these degradations are spectrally separable: Poisson noise and photon scarcity cause high-frequency\nphase perturbations, while attenuation errors suppress low-frequency amplitude components. Leveraging this insight, we\npropose FourierPET, a Fourier-based unrolled reconstruction\nframework grounded in the Alternating Direction Method of\nMultipliers. It consists of three tailored modules: a spectral\nconsistency module that enforces global frequency alignment\nto maintain data fidelity, an amplitude\u2013phase correction module that decouples and compensates for high-frequency phase\ndistortions and low-frequency amplitude suppression, and a\ndual adjustment module that accelerates convergence during\niterative reconstruction. Extensive experiments demonstrate\nthat FourierPET achieves state-of-the-art performance with\nsignificantly fewer parameters, while offering enhanced interpretability through frequency-aware correction.<\/jats:p>","DOI":"10.1609\/aaai.v40i15.38299","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:19:43Z","timestamp":1773793183000},"page":"12997-13005","source":"Crossref","is-referenced-by-count":0,"title":["FourierPET: Deep Fourier-based Unrolled Network for Low-count PET Reconstruction"],"prefix":"10.1609","volume":"40","author":[{"given":"Zheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanli","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38299\/42261","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38299\/42261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:19:43Z","timestamp":1773793183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i15.38299","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}