CONSeg: Voxelwise Uncertainty Quantification for Glioma Segmentation Using Conformal Prediction
Open accessAbstract
ABSTRACT BACKGROUND AND PURPOSE: Accurate glioma segmentation has the potential to enhance clinical decision-making and treatment planning. Uncertainty quantification methods, including conformal prediction (CP), can enhance segmentation models reliability. CP quantifies uncertainty with statistical confidence guarantees. This study aims to use CP in glioma segmentation. MATERIALS AND METHODS: We used the publicly available UCSF and UPenn glioma datasets, with the UCSF dataset (495 cases) split into training (70%), validation (10%), calibration (10%), and test (10%) sets, and the UPenn dataset (147 cases) divided into external calibration (30%) and external test (70%) sets. A UNet model was trained, and its optimal threshold was set to 0.5 using prediction normalization. To apply CP, the conformal threshold was selected based on the internal/external calibration nonconformity score, and CP was subsequently applied to the internal/external test sets, with coverage -the proportion of true labels within prediction sets-reported for all. We defined the uncertainty ratio (UR) and assessed its correlation with the Dice score coefficient (DSC) and 95th percentile Hausdorff distance (HD95). Additionally, we categorized cases into certain and uncertain groups based on UR and compared their DSC and HD95. We also evaluate the correlation between UR and the evaluation metrics (DSC and HD95) of the BraTS fusion model segmentation (BFMS), and compare evaluation metrics in the certain and uncertain subgroups. RESULTS: The base model achieved a DSC of 0.86 and 0.83, and an HD95 of 7.35 and 11.71 on the internal and external test sets, respectively. The CP coverage was 0.9982 for the internal test set and 0.9977 for the external test set. Statistical analysis showed significant correlations between UR and evaluation metrics for test sets (p values <0.001). Additionally, certain cases had significantly better evaluation metrics (higher DSC and lower HD95) than uncertain cases in test sets and the BFMS (p values <0.001). CONCLUSIONS: CP effectively quantifies uncertainty in glioma segmentation. Using CONSeg improves the reliability of segmentation models and enhances human-computer interaction. Additionally, CONSeg can identify uncertain cases and suggest them for manual segmentation. ABBREVIATIONS: CP = conformal prediction; UR = uncertainty ratio; DSC = Dice score coefficient; BFMS = BraTS fusion model segmentation; DL = deep learning; UQ = uncertainty quantification; BCE = binary cross-entropy; BMOT = base model optimal threshold; NCST = nonconformity score threshold; CONSeg = conformal segmentation; BMPN = base model prediction normalization.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Ostrom, Q. T., Gittleman, H. R., Liao, P., Vecchione-Koval, T., Wolinsky, Y., Kruchko, C., & Barnholtz‐Sloan, J. S. (2017) · Neuro-Oncology · doi:10.1093/neuonc/nox158 · Cited by 1,804 · see citing works
MONAI: An open-source framework for deep learning in healthcarePreprint
Cardoso, M. J., Li, W., Brown, R., Ma, N., Kerfoot, E., Wang, Y., Murrey, B., Myronenko, A., Zhao, C. H., Yang, D., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.02701 · Cited by 485 · see citing works
Kwon, Y., Won, J.-H., Kim, B. J., & Paik, M. C. (2020) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2019.106816 · Cited by 424 · see citing works
A gentle introduction to conformal prediction and distribution-free uncertainty quantification
Angelopoulos, A. N., & Bates, S. (2021) · arXiv · doi:10.48550/arxiv.2107.07511 · Cited by 240 · see citing works
Bakas, S., Sako, C., Akbari, H., Bilello, M., Sotiras, A., Shukla, G., Rudie, J. D., Santamaría, N. A. F., Kazerooni, A. F., Pati, S., et al. (2022) · Scientific Data · doi:10.1038/s41597-022-01560-7 · Cited by 199 · see citing works
HappyMap : A Generalized Multicalibration Method
Poujade, K., Travé-Massuyès, L., Pirard, J., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itcs.2023.41 · Cited by 190 · see citing works
The University of California San Francisco Preoperative Diffuse Glioma MRI Dataset
Calabrese, E., Villanueva-Meyer, J. E., Rudie, J. D., Rauschecker, A. M., Baid, U., Bakas, S., Cha, S., Mongan, J., & Hess, C. P. (2022) · Radiology Artificial Intelligence · doi:10.1148/ryai.220058 · Cited by 188 · see citing works
Quantifying Uncertainty in Deep Learning of Radiologic Images
Faghani, S., Moassefi, M., Rouzrokh, P., Khosravi, B., Baffour, F. I., Ringler, M. D., & Erickson, B. J. (2023) · Radiology · doi:10.1148/radiol.222217 · Cited by 117 · see citing works
Self-citationHuang, L., Ruan, S., Xing, Y.-C., & Feng, M.-L. (2024) · Medical Image Anal. · doi:10.1016/j.media.2024.103223 · Cited by 90 · see citing works
Poursaeed, R., Mohammadzadeh, M., & Safaei, A. A. (2024) · BMC Cancer · doi:10.1186/s12885-024-13320-4 · Cited by 76 · see citing works
Quantifying the unknown impact of segmentation uncertainty on image-based simulations
Krygier, M., LaBonte, T., Martinez, C., Norris, C., Sharma, K., Collins, L. N., Mukherjee, P. P., & Roberts, S. A. (2021) · Nature Communications · doi:10.1038/s41467-021-25493-8 · Cited by 67 · see citing works
Improved Glioma Grading Using Deep Convolutional Neural Networks
Gutta, S., Acharya, J., Shiroishi, M. S., Hwang, D., & Nayak, K. S. (2020) · American Journal of Neuroradiology · doi:10.3174/ajnr.a6882 · Cited by 66 · see citing works
Li, H., Yang, N., Ser, J. D., & Yang, G. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08016-4 · Cited by 65 · see citing works
Uncertainty quantification and attention-aware fusion guided multi-modal MR brain tumor segmentation
Zhou, T., & Zhu, S. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107142 · Cited by 33 · see citing works
Uncover This Tech Term: Uncertainty Quantification for Deep Learning
Faghani, S., Gamble, C. U., & Erickson, B. J. (2024) · Korean Journal of Radiology · doi:10.3348/kjr.2024.0108 · Cited by 21 · see citing works
Self-citationA Review on Deep Learning Methods for Glioma Segmentation, Limitations, and Future Perspectives
Diana-Albelda, C., García‐Martín, Á., & Bescós, J. (2025) · Journal of Imaging · doi:10.3390/jimaging11080269 · Cited by 19 · see citing works
Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty
Mossina, L., Dalmau, J., & Andéol, L. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00361 · Cited by 18 · see citing works
Yang, Z., Lafata, K. J., Vaios, E., Hu, Z., Mullikin, T. C., Yin, F.-F., & Wang, C. (2023) · Medical Physics · doi:10.1002/mp.16695 · Cited by 17 · see citing works
Gade, M., Nguyen, K. M., Gedde, S., et al. (2024) · Insights into Imaging · doi:10.1186/s13244-024-01863-w · Cited by 12 · see citing works
Convolutional Neural Networks for Glioma Segmentation and Prognosis: A Systematic Review
Herr, J., Stoyanova, R. S., & Mellon, E. A. (2023) · Critical Reviews™ in Oncogenesis · doi:10.1615/critrevoncog.2023050852 · Cited by 8 · see citing works
Analysis of the 2024 BraTS Meningioma Radiotherapy Planning Automated Segmentation ChallengePreprint
LaBella, D., Abramova, V., Astaraki, M., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.18383 · Cited by 8 · see citing works
Self-citationRobustness of brain tumor segmentation
Müller, S., Weickert, J., & Graf, N. M. (2020) · Journal of medical imaging · doi:10.1117/1.jmi.7.6.064006 · Cited by 7 · see citing works
Elyassirad, D., Gheiji, B., Vatanparast, M., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.21091 · Cited by 3 · see citing works
Self-citationConformal confidence sets for biomedical image segmentation
Davenport, S. (2024) · arXiv · doi:10.48550/arxiv.2410.03406 · Cited by 2 · see citing works
Uncertainty Quantification using Variational Inference for Biomedical Image SegmentationPreprint
Sagar, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.07588 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- 10.48550/arxiv.2405.05145 · DOI
Cited by
Sorted by citations
Ahmadzadeh, A. M., Ashoobi, M. A., Lomer, N. B., et al. (2025) · La radiologia medica · doi:10.1007/s11547-025-02089-6 · Cited by 5 · see citing works
Self-citationAhmadzadeh, A. M., Ashoobi, M. A., Lomer, N. B., et al. (2025) · Clinical Radiology · doi:10.1016/j.crad.2025.107049 · Cited by 3 · see citing works
Self-citationCONReg: Uncertainty-Aware Medical Image Registration Using Conformal Prediction.
Gheiji, B., Elyassirad, D., Vatanparast, M., Ahmadzadeh, A. M., Faghani, S., & Tavakoli, M. (2026) · Journal of imaging informatics in medicine · doi:10.1007/s10278-026-01878-3 · Cited by 3 · see citing works
Self-citationCONRep: Uncertainty-Aware Vision-Language Report Drafting Using Conformal Prediction
Elyassirad, D., Gheiji, B., Vatanparast, M., Ahmadzadeh, A. M., Agah, S. A. A., Moassefi, M., Tavakoli, M., & Faghani, S. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02179-5
Self-citation
- Authors
- Elyassirad, D., Gheiji, B., Vatanparast, M., Ahmadzadeh, A. M., & Faghani, S.
- Affiliations
- Mayo Clinic (US)
- Venue
- American Journal of Neuroradiology
- Published
- 2025-07-03
- Volume
- 46
- Issue
- 12
- Pages
- 2553-2560
- ISSN
- 0195-6108 (ISSN-L)
- 1936-959X
- PMC
- PMC12723704
- OpenAlex
- W4411984136
- Semantic Scholar
- d4fbdc2a759e63e775821af2ee7974af89f5b282
- Cited by
- 4
- References
- 24
- Citations by year
- 2026: 2 · 2025: 2
- FWCI
- 1.45
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- American Journal of Neuroradiology (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Life Sciences › Neuroscience › Neurology › Brain Tumor Detection and Classification
- Health Sciences › Medicine › Genetics › Glioma Diagnosis and Treatment
- Keywords
- glioma segmentation, conformal prediction, uncertainty quantification, nonconformity scores, segmentation reliability, manual segmentation
- MeSH terms
- Algorithms, Brain Neoplasms, Glioma, Humans, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Sensitivity and Specificity, Reproducibility of Results, Uncertainty
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
