Turning brain MRI into diagnostic PET: 15O-water PET CBF synthesis from multi-contrast MRI via attention-based encoder–decoder networks
Open accessAbstract
Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of a wide range of neurological diseases. Positron emission tomography (PET) with radiolabeled water (15 O-water) is the gold-standard for the measurement of CBF in humans, however, it is not widely available due to its prohibitive costs and the use of short-lived radiopharmaceutical tracers that require onsite cyclotron production. Magnetic resonance imaging (MRI), in contrast, is more accessible and does not involve ionizing radiation. This study presents a convolutional encoder-decoder network with attention mechanisms to predict the gold-standard 15 O-water PET CBF from multi-contrast MRI scans, thus eliminating the need for radioactive tracers. The model was trained and validated using 5-fold cross-validation in a group of 126 subjects consisting of healthy controls and cerebrovascular disease patients, all of whom underwent simultaneous 15 O-water PET/MRI. The results demonstrate that the model can successfully synthesize high-quality PET CBF measurements (with an average SSIM of 0.924 and PSNR of 38.8 dB) and is more accurate compared to concurrent and previous PET synthesis methods. We also demonstrate the clinical significance of the proposed algorithm by evaluating the agreement for identifying the vascular territories with impaired CBF. Such methods may enable more widespread and accurate CBF evaluation in larger cohorts who cannot undergo PET imaging due to radiation concerns, lack of access, or logistic challenges.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Encoder-decoder networks synthesize cerebral blood flow measurements from structural MRI alone, delivering PET-comparable data without radioactive tracers.
“encoder–decoder networks now synthesize cerebral blood flow measurements from structural MRI alone, delivering PET-comparable data without radioactive tracers”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Hussein et al., 2024
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Advances in functional and structural MR image analysis and implementation as FSL
Smith, S. M., Jenkinson, M., Woolrich, M. W., Beckmann, C. F., Behrens, T. E. J., Johansen-Berg, H., Bannister, P. R., De Luca, M., Drobnjak, I., Flitney, D. E., et al. (2004) · NeuroImage · doi:10.1016/j.neuroimage.2004.07.051 · Cited by 13,630 · see citing works
Attention U-Net: Learning Where to Look for the Pancreas
Oktay, O., Schlemper, J., Folgoc, L. L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., et al. (2018) · arXiv · doi:10.48550/arxiv.1804.03999 · Cited by 5,458 · see citing works
Self-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353 · see citing works
Barber, P. A., Demchuk, A. M., Zhang, J., & Buchan, A. M. (2000) · The Lancet · doi:10.1016/s0140-6736(00)02237-6 · Cited by 2,673 · see citing works
Loss Functions for Image Restoration With Neural Networks
Zhao, H., Gallo, O., Frosio, I., & Kautz, J. (2016) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2016.2644865 · Cited by 2,659 · see citing works
Universal Definition of Myocardial Infarction: Clinical Insights
Paiva, L., Providencia, R. A., Barra, S., Dinis, P., Faustino, C., & Gonçalves, L. M. M. (2015) · Cardiology · doi:10.1159/000371739 · Cited by 2,513 · see citing works
Mazziotta, J. C., Toga, A. W., Evans, A. C., Fox, P. T., Lancaster, J. L., Zilles, K., Woods, R. P., Paus, T., Simpson, G. V., Pike, G. B., et al. (2001) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2001.0915 · Cited by 2,334 · see citing works
Alsop, D. C., Detre, J. A., Golay, X., Günther, M., Hendrikse, J., Hernández-García, L., Lu, H., MacIntosh, B. J., Parkes, L. M., Smits, M., et al. (2014) · Magnetic Resonance in Medicine · doi:10.1002/mrm.25197 · Cited by 2,218 · see citing works
Self-citationDetre, J. A., LEIGH, J. S. J., Williams, D. S., & Koretsky, A. P. (1992) · Magnetic Resonance in Medicine · doi:10.1002/mrm.1910230106 · Cited by 1,606 · see citing works
Incorporating Nesterov Momentum into Adam
Dozat, T. (2016) · Cited by 1,293 · see citing works
A general kinetic model for quantitative perfusion imaging with arterial spin labeling
Buxton, R. B., Frank, L. R., Wong, E. C., Siewert, B., Warach, S. J., & Edelman, R. R. (1998) · Magnetic Resonance in Medicine · doi:10.1002/mrm.1910400308 · Cited by 1,265 · see citing works
Iturria-Medina, Y., Sotero, R. C., Toussaint, P. J., Mateos-Pérez, J. M., Evans, A. C., Initiative, T. A. D. N., Weiner, M. W., Aisen, P., Petersen, R., Jack, C. R., et al. (2016) · Nature Communications · doi:10.1038/ncomms11934 · Cited by 1,202 · see citing works
Yusuf, S., Reddy, S., Ôunpuu, S., & Anand, S. (2001) · Circulation · doi:10.1161/hc4701.099488 · Cited by 1,141 · see citing works
Estimating Regression Models with Multiplicative Heteroscedasticity
Harvey, A. C. (1976) · Econometrica · doi:10.2307/1913974 · Cited by 966 · see citing works
MedGAN: Medical image translation using GANs
Armanious, K., Jiang, C., Fischer, M., Küstner, T., Hepp, T., Nikolaou, K., Gatidis, S., & Yang, B. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.101684 · Cited by 739 · see citing works
Villringer, A., Rosen, B. R., Belliveau, J. W., Ackerman, J. L., Lauffer, R. B., Buxton, R. B., Chao, Y. S., Wedeenand, V. J., & Brady, T. J. (1988) · Magnetic Resonance in Medicine · doi:10.1002/mrm.1910060205 · Cited by 706 · see citing works
Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements
Tustison, N. J., Cook, P. A., Klein, A., Song, G., Das, S. R., Duda, J. T., Kandel, B. M., van Strien, N., Stone, J. R., Gee, J. C., et al. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.05.044 · Cited by 670 · see citing works
Deep MR to CT Synthesis Using Unpaired Data
Wolterink, J. M., Dinkla, A. M., Savenije, M. H. F., Seevinck, P. R., van den Berg, C. A. T., & Išgum, I. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68127-6_2 · Cited by 652 · see citing works
Epidemiology and the Global Burden of Stroke
Mukherjee, D. R., & Patil, C. G. (2011) · World Neurosurgery · doi:10.1016/j.wneu.2011.07.023 · Cited by 648 · see citing works
Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks
Dar, S. U. H., Yurt, M., Karacan, L., Erdem, A., Erdem, E., & Çukur, T. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2901750 · Cited by 614 · see citing works
Deep Learning Based Imaging Data Completion for Improved Brain Disease Diagnosis
Li, R., Zhang, W., Suk, H., Wang, L., Jiang, L., Shen, D. G., & Ji, S. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10443-0_39 · Cited by 480 · see citing works
3D conditional generative adversarial networks for high-quality PET image estimation at low dose
Wang, Y., Yu, B., Wang, L., Zu, C., Lalush, D. S., Lin, W., Wu, X., Zhou, J., Shen, D. G., & Zhou, L. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2018.03.045 · Cited by 452 · see citing works
Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI
Gong, E., Pauly, J. M., Wintermark, M., & Zaharchuk, G. (2018) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.25970 · Cited by 351 · see citing works
Self-citationA neuroradiologist’s guide to arterial spin labeling MRI in clinical practice
Grade, M. M., Hernandez-Tamames, J. A., Pizzini, F. B., Achten, E., Golay, X., & Smits, M. (2015) · Neuroradiology · doi:10.1007/s00234-015-1571-z · Cited by 300 · see citing works
2018 26th European Signal Processing Conference (EUSIPCO)
(2018) · doi:10.23919/eusipco43300.2018 · Cited by 250 · see citing works
Ultra–Low-Dose18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs
Chen, K. T., Gong, E., Macruz, F., Xu, J., Boumis, A., Khalighi, M. M., Poston, K. L., Sha, S. J., Greicius, M. D., Mormino, E. C., et al. (2018) · Radiology · doi:10.1148/radiol.2018180940 · Cited by 248 · see citing works
Self-citationBen-Cohen, A., Klang, E., Raskin, S. P., Soffer, S., Ben-Haim, S., Konen, E., Amitai, M. M., & Greenspan, H. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2018.11.013 · Cited by 231 · see citing works
Deep CT to MR Synthesis Using Paired and Unpaired Data
Jin, C., Kim, H., Liu, M., Jung, W., Joo, S., Park, E., Ahn, Y., Han, I. H., Lee, J., & Cui, X. (2019) · Sensors · doi:10.3390/s19102361 · Cited by 226 · see citing works
Pan, Y., Liu, M., Lian, C., Zhou, T., Xia, Y., & Shen, D. G. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00931-1_52 · Cited by 205 · see citing works
Unsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN
Yang, H., Sun, J., Carass, A., Zhao, C., Lee, J., Prince, J. L., & Xu, Z. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3015379 · Cited by 204 · see citing works
Gao, X., Shi, F., Shen, D. G., & Liu, M. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3097721 · Cited by 188 · see citing works
Dai, W., Robson, P. M., Shankaranarayanan, A., & Alsop, D. C. (2011) · Magnetic Resonance in Medicine · doi:10.1002/mrm.23103 · Cited by 184 · see citing works
Iida, A., Okazawa, H., Hayashida, K., Tsuyuguchi, N., Ishii, K., Kuwabara, Y., Senda, M., Ito, H., Kanno, I., Kato, C., et al. (2004) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-003-1430-8 · Cited by 180 · see citing works
Early stopping and non-parametric regression: An optimal data-dependent stopping rulePreprint
Raskutti, G., Wainwright, M. J., & Yu, B. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.3574 · Cited by 174 · see citing works
Chen, K. T., Gong, E., Macruz, F., Xu, J., Boumis, A., Khalighi, M. M., Poston, K. L., Sha, S. J., Greicius, M. D., Mormino, E. C., et al. (2020) · Radiology · doi:10.1148/radiol.2020202527 · Cited by 152 · see citing works
Self-citationMRI Cross-Modality Image-to-Image Translation
Yang, Q., Li, N., Zhao, Z., Fan, X., Chang, E., & Xu, Y. L. (2020) · Scientific Reports · doi:10.1038/s41598-020-60520-6 · Cited by 150 · see citing works
Unsupervised Medical Image Translation Using Cycle-MedGAN
Armanious, K., Jiang, C., Abdulatif, S., Küstner, T., Gatidis, S., & Yang, B. (2019) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8902799 · Cited by 132 · see citing works
Preetha, C. J., Meredig, H., Brugnara, G., Mahmutoglu, M. A., Foltyn‐Dumitru, M., Isensee, F., Kessler, T., Pflüger, I., Schell, M., Neuberger, U., et al. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00205-3 · Cited by 129 · see citing works
Zhang, J., He, X., Qing, L., Gao, F., & Wang, B. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106676 · Cited by 117 · see citing works
One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation
Liu, J., Pasumarthi, S., Duffy, B. A., Gong, E., Datta, K., & Zaharchuk, G. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3261707 · Cited by 113 · see citing works
Self-citationLan, H., Initiative, T. A. D. N., Toga, A. W., & Sepehrband, F. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28819 · Cited by 99 · see citing works
Kearney, V. P., Ziemer, B. P., Perry, A., Wang, T., Chan, J. W. S., Ma, L., Morin, O., Yom, S. S., & Solberg, T. D. (2020) · Radiology Artificial Intelligence · doi:10.1148/ryai.2020190027 · Cited by 85 · see citing works
Synthesizing MR Image Contrast Enhancement Using 3D High-Resolution ConvNets
Chen, C., Raymond, C., Speier, W. F., Jin, X., Cloughesy, T. F., Enzmann, D. R., Ellingson, B. M., & Arnold, C. W. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3192309 · Cited by 75 · see citing works
Zhou, Y., Huang, S., & Bergsneider, M. (2001) · IEEE Transactions on Nuclear Science · doi:10.1109/23.910842 · Cited by 75 · see citing works
Brain MR to PET Synthesis via Bidirectional Generative Adversarial Network
Hu, S., Shen, Y., Wang, S., & Lei, B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59713-9_67 · Cited by 74 · see citing works
Image-derived input function estimation on a TOF-enabled PET/MR for cerebral blood flow mapping
Khalighi, M. M., Deller, T. W., Fan, A. P., Gulaka, P., Shen, B., Singh, P., Park, J. H., Chin, F. T., & Zaharchuk, G. (2017) · Journal of Cerebral Blood Flow & Metabolism · doi:10.1177/0271678x17691784 · Cited by 64 · see citing works
Self-citationLeijenaar, J. F., van Maurik, I. S., Kuijer, J. P. A., van der Flier, W. M., Scheltens, P., Barkhof, F., & Prins, N. D. (2017) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1016/j.dadm.2017.10.001 · Cited by 59 · see citing works
Wei, W., Poirion, É., Bodini, B., Durrleman, S., Ayache, N., Stankoff, B., & Colliot, O. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101546 · Cited by 50 · see citing works
Zhao, M. Y., Fan, A. P., Chen, D. Y. T., Sokolska, M., Guo, J., Ishii, Y., Shin, D. D., Khalighi, M. M., Holley, D., Halbert, K., et al. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.117955 · Cited by 49 · see citing works
Self-citationPreetha, C. J., Meredig, H., Brugnara, G., Mahmutoglu, M. A., Foltyn‐Dumitru, M., al, E., & Weller, M. (2021) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-209425 · Cited by 45 · see citing works
Guo, J., Gong, E., Fan, A. P., Goubran, M., Khalighi, M. M., & Zaharchuk, G. (2019) · Journal of Cerebral Blood Flow & Metabolism · doi:10.1177/0271678x19888123 · Cited by 37 · see citing works
Self-citationXie, H., Lei, Y., Wang, T., Roper, J. R., Axente, M., Bradley, J. D., Liu, T., & Yang, X. (2022) · Medical Physics · doi:10.1002/mp.15578 · Cited by 37 · see citing works
Chen, D. Y. T., Ishii, Y., Fan, A. P., Guo, J., Zhao, M. Y., Steinberg, G. K., & Zaharchuk, G. (2020) · Radiology · doi:10.1148/radiol.2020192793 · Cited by 29 · see citing works
Self-citationShin, H.-C., Ihsani, A., Mandava, S., Sreenivas, S. T., Forster, C. J., Cha, J., & Initiative, A. D. N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04393 · Cited by 26 · see citing works
FDG-PET to T1 Weighted MRI Translation with 3D Elicit Generative Adversarial Network (E-GAN)
Bazangani, F., Richard, F. J. P., Ghattas, B., & Guedj, É. (2022) · Sensors · doi:10.3390/s22124640 · Cited by 24 · see citing works
Yaakub, S. N., McGinnity, C. J., Clough, J. R., Kerfoot, E., Girard, N. J., Guedj, É., & Hammers, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32778-1_5 · Cited by 19 · see citing works
Yousefi, S., Sokooti, H., Teeuwisse, W. M., Heijtel, D., Nederveen, A. J., Staring, M., & van Osch, M. J. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.05116 · Cited by 2 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
1 of the 62 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Khojaste-Sarakhsi, M., Haghighi, S. S., Ghomi, S. M. T. F., & Marchiori, E. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105017 · Cited by 12 · see citing works
“Considering a single MRI modality is also opposed to [18,50,53] where four, two, and eight different contrast MRI modalities are used simultaneously for PET generation, respectively.”
Dang, M., Liu, B., Chen, Y., & Zhang, Z. (2026) · Psychoradiology · doi:10.1093/psyrad/kkag007 · Cited by 7 · see citing works
Vaccaro, M., Rosa, E., Placidi, E., Guarnera, A., Secinaro, A., Gandolfo, C., Garganese, M. C., & Napolitano, A. (2026) · European Radiology Experimental · doi:10.1186/s41747-025-00651-5 · Cited by 4 · see citing works
“The values of rRMSE range between 0.04 (Zhang et al, Hussein et al [15, 19]) and 0.27 [4].”
InfluentialA Latent Multi-Scale Residual Transformer Approach for Cross-Modal Medical Image Synthesis
Zhu, X., & Li, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3555879 · Cited by 2 · see citing works
“Such tasks typically include multi-contrast MRI synthesis [11], [12], [13], MRI-CT synthesis [14], [15], and MRI-PET synthesis [16], among other application scenarios.”
Whole-body CT-to-PET synthesis using a customized transformer-enhanced GAN
Xu, B., Nie, Z., He, J., Li, A., & Wu, T. (2025) · Physics in Medicine and Biology · doi:10.1088/1361-6560/add8dd · Cited by 2 · see citing works
“Hussein et al (2024) proposed a 3D convolutional encoder-decoder network combined with an attention mechanism and a custom-designed loss function to synthesize Oxygen-15 labeled water (15O-water) PET from multi-contrast MRI.”
Unisyn: A Generative Foundation Model for Universal Medical Image Synthesis Across MRI, CT and PET
Wang, Y., Xiong, H., Sun, K., Liu, J., Lin, X., Chen, Z., He, Y., Wang, Q., & Shen, D. G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04947-6_64 · Cited by 2 · see citing works
Guo, J., Sharma, A. K., Zaharchuk, G., Rahimzadeh, H., & Ilyas, N. (2025) · Magnetic Resonance in Medicine · doi:10.1002/mrm.70013 · Cited by 1 · see citing works
Self-citationVadali, C., Lucas, A., Arnold, T. C., Dolui, S., Das, S. R., Wolk, D. A., Davis, K. A., Stein, J. M., & Detre, J. A. (2025) · medRxiv · doi:10.1101/2025.07.08.25331145
“Hussein et al. utilized convolutional encoder-decoder networks to synthesize 15 O-water PET from multi-contrast MRI 18 , Chen et al. leveraged diffusion models for synthesis of FDG-PET from T1-weighted (T1w) MRI 19 , and Ouyang et al. applied convolutional neural networks to generate FDG-PET-like…”
- Authors
- Hussein, R., Shin, D., Zhao, M. Y., Guo, J., Davidzon, G., Steinberg, G., Moseley, M., & Zaharchuk, G.
- Affiliations
- Stanford Medicine (US)
- University of California, Riverside (US)
- Stanford University (US)
- Corresponding author
- Hussein, Ramy
- ORCID
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2024-04
- Volume
- 93
- Pages
- 103072
- ISSN
- 1361-8415 (ISSN-L)
- PMC
- PMC10922206
- OpenAlex
- W4390399664
- Cited by
- 9
- References
- 62
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 2
- FWCI
- 1.42
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- www.elsevier.com/open-access/userlicense/1.0/ (am, 277 d)
- doi.org/10.15223/policy-017 (stm-asf)
- doi.org/10.15223/policy-037 (stm-asf)
- doi.org/10.15223/policy-012 (stm-asf)
- doi.org/10.15223/policy-029 (stm-asf)
- doi.org/10.15223/policy-004 (stm-asf)
- Locations
- Medical Image Analysis (acceptedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Europe PMC (PubMed Central) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- American Heart Association (826254)
- NIH
- Alzheimer's Disease Research Center, Emory University
- National Institute on Aging (P30 AG066515)
- GE Healthcare
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced MRI Techniques and Applications
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Medical Imaging Techniques and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- 15O-water PET, cerebral blood flow, multi-contrast MRI, vascular territories
- MeSH terms
- Algorithms, Brain, Cerebrovascular Circulation, Humans, Magnetic Resonance Imaging, Positron-Emission Tomography
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
