{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:14:13Z","timestamp":1774642453179,"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>Medical image synthesis is an important topic for both clinical and research applications. Recently, diffusion models have become a leading approach in this area. Despite their strengths, many existing methods struggle with (1) limited generalizability, only working for specific body regions or voxel spacings, (2) slow inference, which is a common issue for diffusion models, and (3) weak alignment with input conditions, which is a critical issue for medical imaging. MAISI, a previously proposed framework, addresses generalizability issues but still suffers from slow inference and limited condition consistency. In this work, we present MAISI-v2, the first accelerated 3D medical image synthesis framework that integrates rectified flow to enable fast and high-quality generation. To further enhance condition fidelity, we introduce a novel region-specific contrastive loss to improve sensitivity to the region of interest. Our experiments show that MAISI-v2 can achieve state-of-the-art image quality with 33\u00d7 acceleration for latent diffusion models. We also conducted a downstream segmentation experiment to show that the synthetic images can be used for data augmentation. We release our code, training details, model weights, and a GUI demo to facilitate reproducibility and promote further development within the community.<\/jats:p>","DOI":"10.1609\/aaai.v40i15.38309","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:20:06Z","timestamp":1773793206000},"page":"13088-13098","source":"Crossref","is-referenced-by-count":1,"title":["MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss"],"prefix":"10.1609","volume":"40","author":[{"given":"Can","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Pengfei","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yufan","family":"He","sequence":"additional","affiliation":[]},{"given":"Yucheng","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Benjamin","family":"Simon","sequence":"additional","affiliation":[]},{"given":"Mason","family":"Belue","sequence":"additional","affiliation":[]},{"given":"Stephanie","family":"Harmon","sequence":"additional","affiliation":[]},{"given":"Baris","family":"Turkbey","sequence":"additional","affiliation":[]},{"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[]}],"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\/38309\/42271","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38309\/42271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:20:06Z","timestamp":1773793206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38309"}},"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.v40i15.38309","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]]}}}