Danial Elyassirad, MD

Trustworthy AI for medical imaging

A model that is confidently wrong is a clinical risk. I build medical imaging AI that knows when it isn't sure, and says so with a statistical guarantee.

I'm a physician and medical AI researcher specializing in uncertainty quantification. My work gives deep learning models the ability not just to predict, but to recognize and communicate when a prediction isn't confident enough, attaching calibrated uncertainty estimates to the model's final output. I mostly use conformal prediction, which turns any trained model's scores into prediction sets or intervals with guaranteed coverage, and I've applied it to glioma segmentation, molecular classification, image registration and vision-language radiology report drafting. Two of these projects have won international awards (SIIM 2026, ASFNR 2025).

What a conformal prediction set looks like

Illustrative glioma MRI case

Required coverage (1 − α) 90%

Instead of one label, the model returns the set of labels needed to reach the requested coverage. A small set means a confident case; a large one flags the case for a closer human read. Scores here are made up for illustration.

Selected work on uncertainty quantification

CONRep: Uncertainty-aware vision-language report drafting using conformal prediction

First author · Journal of Imaging Informatics in Medicine, 2026

Adds conformal guarantees to vision-language radiology report generation, so the drafted report marks findings the model can't support with enough confidence.

SIIM 2026 Helen and Paul Chang Foundation New Investigator Award

CONSeg: Voxelwise uncertainty quantification for glioma segmentation using conformal prediction

First author · American Journal of Neuroradiology, 2025

Voxel-level conformal uncertainty for brain tumor segmentation on MRI, highlighting regions where the segmentation shouldn't be trusted without review.

ASFNR 2025 John L. Ulmer Award

Predicting IDH mutation in glioma patients using deep learning algorithms with conformal prediction

First author · Journal of Imaging Informatics in Medicine, 2026

Conformal prediction sets for MRI-based IDH mutation classification, improving the reliability of noninvasive molecular profiling.

CONReg: Uncertainty-aware medical image registration using conformal prediction

Co-author · Journal of Imaging Informatics in Medicine, 2026

Uncertainty-aware deep registration for brain MRI and lung CT that identifies anatomically ambiguous or misaligned regions.

UQMIA: An open, hands-on tutorial on uncertainty quantification in medical imaging analysis

Co-author · arXiv, 2026

An open teaching resource on UQ methods for medical imaging, with a large language model-based assessment of the educational content.

Try the interactive tutorial

NeuroAIHub: An AI-driven framework for automated curation and discovery of neuroradiology datasets

Co-founder and lead · American Journal of Neuroradiology, 2026

An open-source registry that helps researchers find and assess neuroradiology datasets.

Web app GitHub Demo video

Honors and awards

2026: SIIM Helen and Paul Chang Foundation New Investigator Award (USA) for CONRep
2025: John L. Ulmer Award, ASFNR (USA) for CONSeg
2025: Rank 3 among presented abstracts, Sharif AIH Congress
2024: Rank 1, best student idea in the final round of the Artificial Intelligence in Medical Sciences Idea Challenge
2024: Rank 1 among student presentations, Annual Congress of the Iranian Medical Council
2023: Patent certificate for mother and fetus health monitoring
2019–2026: Member of the university's Talented Students Program
2018: National Elites Foundation of Iran
National body for identifying and supporting exceptional talent
2018: Silver medal, National Student Biology Olympiad

Research experience

Led or co-led 10+ published research projects in AI for medical imaging since 2024.
First author of 3 peer-reviewed papers on uncertainty-aware AI in medical imaging: IDH conformal prediction and CONRep in the Journal of Imaging Informatics in Medicine (Q1), and CONSeg in the American Journal of Neuroradiology (Q1).
Built an interactive tutorial on uncertainty quantification in medical imaging, published as UQMIA.
Co-founded and lead NeuroAIHub, an open-source, AI-driven registry for neuroradiology dataset discovery, published in the American Journal of Neuroradiology.
Peer reviewer for npj Precision Oncology (Q1), Scientific Reports (Q1), BMC Medical Imaging (Q1), Frontiers in Medicine (Q1) and Discover Oncology (Q2).

Grants

2024: Principal investigator, "The Comparison of the Efficacy of Two Assistant Tools, ChatGPT-4 and UpToDate, in the Management of Complicated Cases"
Peer-reviewed and approved by the MUMS Research Council; funded by the Vice Chancellery for Research

Publications

Elyassirad D, Gheiji B, Vatanparast M, Ahmadzadeh AM, Agah SA, Moassefi M, Tavakoli M, Faghani S. CONRep: uncertainty-aware vision-language report drafting using conformal prediction. J Imaging Inform Med. 2026. UQ
Elyassirad D, Gheiji B, Vatanparast M, Ahmadzadeh AM, Masoudi M, Gholami M, Moassefi M, Faghani S. Predicting IDH mutation in glioma patients using deep learning algorithms with conformal prediction. J Imaging Inform Med. 2026. UQ
Gheiji B, Elyassirad D, Vatanparast M, Ahmadzadeh AM, Faghani S, Tavakoli M. CONReg: uncertainty-aware medical image registration using conformal prediction. J Imaging Inform Med. 2026. UQ
Gheiji B, Elyassirad D, et al. UQMIA: an open, hands-on tutorial on uncertainty quantification in medical imaging analysis with large language model-based assessment of educational content. arXiv. 2026. UQ
Elyassirad D, Gheiji B, Vatanparast M, Ahmadzadeh AM, Faghani S. CONSeg: voxelwise uncertainty quantification for glioma segmentation using conformal prediction. AJNR Am J Neuroradiol. 2025. UQ
Elyassirad D, Gheiji B, Vatanparast M, Ahmadzadeh AM, Kamandi N, Soleimanian A, Salehi S, Faghani S. Comparative analysis of 2D and 3D ResNet architectures for IDH and MGMT mutation detection in glioma patients. arXiv. 2024.
Gheiji B, Moradi S, Vatanparast M, Shokrani S, Bagherzadeh MA, Elyassirad D, Akinmuleya OI, Goodarzi S, Heidari-Foroozan M, Moassefi M, Rudie JD. NeuroAIHub: an AI-driven framework for automated curation and discovery of neuroradiology datasets. AJNR Am J Neuroradiol. 2026.
Kamandi N, Mohammadzadeh S, Mirzai M, Ghasemi M, Elyassirad D, et al. Artificial intelligence for rupture risk stratification of small unruptured intracranial aneurysms (≤7 mm): a systematic review and meta-analysis. J Imaging Inform Med. 2026.
Ahmadzadeh AM, Ashoobi MA, Lomer NB, Vatanparast M, Gheiji B, Elyassirad D, Faghani S. Radiomics and deep learning models for predicting glioma p53 status: a diagnostic accuracy systematic review and meta-analysis. Clin Imaging. 2026.
Hasanpour M, Elyassirad D, Gheiji B, Vatanparast M, Keykhosravi E, Shafiei M, Daneshkhah S, Fayyazi A, Faghani S. Predicting epidural hematoma expansion in traumatic brain injury: a machine learning approach. Neuroradiol J. 2025.
Ahmadzadeh AM, Jafarnezhad A, Elyassirad D, Vatanparast M, Gheiji B, Faghani S. Improving radiomics-based isocitrate dehydrogenase 1 prediction in glioma patients using semi-supervised machine learning models. BMC Med Imaging. 2025.
Ahmadzadeh AM, Lomer NB, Ashoobi MA, Elyassirad D, et al. Predicting 1p/19q codeletion status in glioma using MRI-derived radiomics: a systematic review and meta-analysis of diagnostic accuracy. AJNR Am J Neuroradiol. 2025.
Ahmadzadeh AM, Broomand Lomer N, Ashoobi MA, Elyassirad D, Gheiji B, Vatanparast M, Rostami A, Abouei Mehrizi MA, Tabari A, Bathla G, Faghani S. MRI-derived deep learning models for predicting 1p/19q codeletion status in glioma patients: a systematic review and meta-analysis of diagnostic test accuracy studies. Neuroradiology. 2025.
Ahmadzadeh AM, Ashoobi MA, Broomand Lomer N, Elyassirad D, Gheiji B, Vatanparast M, Bathla G, Tu L. Application of deep learning for predicting hematoma expansion in intracerebral hemorrhage using computed tomography scans: a systematic review and meta-analysis. Radiol Med. 2025.
Rostami A, Elyassirad D, Vatanparast M, Mehrizi MA, Hasanpour M, Rezaee H, Haghir A, Keykhosravi E. Functional outcome and mortality predictors in patients with cerebral ischemic infarction after decompressive craniectomy: cross-sectional study. World Neurosurg. 2024.
Ghorbani M, Keykhosravi E, Vatanparast M, Elyassirad D, Kakhki FT, Gheiji B, Golchin N, Zamani Z, Lafta G, Hasanpour M. Flow diverting stent monotherapy as the best choice in the treatment of intracranial blood blister-like aneurysms: a systematic review. Neurosurg Rev. 2024.
Ghorbani M, Keykhosravi E, Vatanparast M, Elyassirad D, Golchin N, Mirsardoo H, Hasanpour M. Traumatic middle meningeal artery aneurysm: a case report. Neurochirurgie. 2024.
Hasanpour M, Golchin N, Mirsardoo H, Alagha A, Elyassirad D, Keykhosravi E. Pseudoaneurysm formation after placement of a FRED flow diverter stent in a patient with iatrogenic ICA injury during transsphenoidal surgery: a case report. Neurochirurgie. 2024.
Dashti S, Bolghanabadi N, Ghavami V, Elyassirad D, Bahri N, Kermani F, Fathi Najafi T. The impact of COVID-19 on female sexual function: a systematic review and meta-analysis. J Sex Marital Ther. 2022.

Citations and full texts are on Google Scholar.

Conference presentations

SIIM 2026: Oral, award winner. CONRep: Improving reliability of vision-language report generation via conformal prediction
SIIM 2026: Poster. Uncertainty quantification for vision-language model classification in medical imaging
RSNA 2025: Oral. NeuroAIHub: An AI-driven framework for automated discovery and retrieval of neuroradiology datasets
ASFNR 2025: Oral, award winner. CONSeg: Voxelwise uncertainty quantification for glioma segmentation using conformal prediction
AIH 2024: Oral. Improving IDH mutation prediction using conformal prediction
CARDIOHTMEDIC 2024: Oral. Interpretable deep learning model for uncertainty-based left ventricle ejection fraction estimation in echocardiography
ASFNR 2024: Poster. Machine learning and deep learning performance in predicting IDH mutation, 1p/19q co-deletion and MGMT promoter status among glioma patients using MRI
IMC 2024: Oral. Predicting epidural hematoma expansion from brain CT
Annual Congress of the Iranian Medical Council

Teaching and leadership

2025–now: Founded and lead a research team
The team has published 10+ Q1–Q2 studies in 2025–2026.
2025–2026: Mentored 2 medical students in AI for medical imaging
Both have since published in top-tier journals.
2025–2026: Mentored a medical intern on the MUMS-funded ChatGPT-4 vs UpToDate grant project
Her contribution became the basis of her MD thesis.
2025: Ran a series of AI fundamentals workshops for medical sciences students
2019–2023: Lecturer and mentor, Biology Olympiad preparation program
100+ lectures on mathematical and informatics-based problem solving in biology to 500+ high school students across Iran; mentored 5 Olympiad candidates.

Education

2019–2026: Doctor of Medicine (MD)
Mashhad University of Medical Sciences, Mashhad, Iran
2013–2019: National Organization for Development of Exceptional Talents (NODET/Sampad)
Iran's selective national program for gifted students, entered through a competitive nationwide exam

Technical skills

ML / AI methods: Conformal prediction, uncertainty quantification, deep learning (CNNs), LLMs, VLMs, classical ML
Medical imaging: MRI and CT image processing, segmentation, registration, feature extraction
Frameworks: PyTorch, TensorFlow, scikit-learn, pandas, NumPy
Programming: Python
Tools: Git, GitHub, Streamlit
Research: Study design and method planning, statistical modeling, systematic reviews and meta-analysis, scientific writing

References

Dr. Shahriar Faghani

Adjunct Assistant Professor, Department of Radiology, Mayo Clinic, MN, USA; Department of Radiology, University of Pennsylvania, PA, USA

Email LinkedIn Google Scholar

Dr. Mana Moassefi

Diagnostic Radiology Resident and Adjunct Assistant Professor, Department of Radiology, Mayo Clinic, Rochester, MN, USA

Email LinkedIn Google Scholar

Dr. Meysam Tavakoli

Assistant Professor, Department of Radiation Oncology, Winship Cancer Institute, Emory University, Atlanta, GA, USA

Email LinkedIn Google Scholar