Pooya Khosravi

UCI - Computer Science 4059 Donald Bren Hall Irvine, CA 92697-3425

I am an MD/PhD candidate at the University of California, Irvine, currently in my fourth year of the Computer Science PhD program advised by Professor Xiaohui Xie. My research lies at the intersection of artificial intelligence, medical imaging, and clinical translation, with the overarching goal of developing computational methods that enhance diagnostic precision and improve patient outcomes.

My current work focuses on AI in ophthalmology, where I develop deep learning and generative models for retinal imaging modalities such as OCT, OCTA, and fundus photography. Specifically, I investigate multimodal representation learning and cross-dimensional translation frameworks to integrate structural and functional imaging data for disease prediction and progression modeling. I am also interested in how AI can be used to interpret complex biomedical data and to build tools that enable other researchers and clinicians to conduct analyses and gain insights more effectively.

Research Interests

Deep learning and computer vision for ophthalmic imaging (OCT, OCTA, fundus)
Generative modeling and diffusion-based image translation
Multimodal and longitudinal representation learning
Medical foundation models and clinical reasoning systems
Translational AI, precision medicine, and research-enabling tools

news

Sep 27, 2025	Paper accepted to MICCAI 2025: XOCT: OCT to OCTA via Cross-Dimensional Multi-Scale Learning. Link
Jul 11, 2024	Awarded NIH F30 Individual Predoctoral Fellowship (National Eye Institute, NEI) for research on deep learning–based retinal OCT markers for optic neuropathies. Grant F30EY036725 · 2024–2029

selected publications

2025

Smartphone-Based Cognitive Behavioral Therapy and Customized Sound Therapy for Tinnitus: A Randomized Controlled Trial

Khodayar Goshtasbi, Karen Tawk, Pooya Khosravi, Mehdi Abouzari, and 1 more author

Annals of Otology, Rhinology & Laryngology, 2025
MICCAI

XOCT: Enhancing OCT to OCTA Translation via Cross-Dimensional Supervised Multi-scale Feature Learning

Pooya Khosravi, Kun Han, Anthony T Wu, Arghavan Rezvani, and 2 more authors

In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2025

2024

BMVC

Hybrid-CSR: Coupling Explicit and Implicit Reconstruction of Cortical Surface.

Shanlin Sun, Tung Le, Pooya Khosravi, Chenyu You, and 5 more authors

In BMVC, 2024
AJO

Retinal Nerve Fiber Layer Optical Texture Analysis and 10-2 Visual Field Assessment in Glaucoma

Alireza Kamalipour, Sasan Moghimi, Pooya Khosravi, Natchada Tansuebchueasai, and 8 more authors

American Journal of Ophthalmology, 2024

Abs

Purpose To apply retinal nerve fiber layer (RNFL) optical texture analysis (ROTA) to 1) investigate the association between papillomacular and papillofoveal bundle defects with 10-2 visual field (VF) sensitivity abnormalities, and 2) integrate the information from RNFL bundle defect and 24-2 VF central test locations to determine the likelihood of 10-2 VF sensitivity abnormalities. Design Cross-sectional Methods A total of 841 eyes (144 healthy, 317 glaucoma suspect, and 380 glaucoma) of 442 participants were included. Eyes underwent 24-2, and 10-2 VF testing and OCT for ROTA. The borders of RNFL defects were delineated from ROTA, and the involvement of the arcuate, papillomacular, and papillofoveal bundles was determined for each eye. Multilevel logistic regression analysis was applied to evaluate the structure–function association. Results Papillomacular (92.1%) and papillofoveal (37.9%) RNFL bundle defects were prevalent in eyes with glaucoma. A 10-2 VF location that was projected onto a papillomacular or a papillofoveal RNFL bundle defect had a significantly increased likelihood of reduced sensitivity (ORs of 18.61 at PDP < 5%, and 20.17 at TDP < 5%, respectively, P < 0.001 for both). When predicting the likelihood of VF abnormality in a 10-2 test location, noticeably higher odds ratios were observed when overlapping with an RNFL bundle defect, compared to when an abnormal corresponding 24-2 central point was present. Conclusions Papillomacular and papillofoveal RNFL bundle defects are present in a considerable proportion of eyes with glaucoma. When detected, they significantly increase the likelihood of abnormality in the corresponding central VF test locations assessed by the 10-2 test.

2023

IJMS

Deep Learning Approach for Differentiating Etiologies of Pediatric Retinal Hemorrhages: A Multicenter Study

Pooya Khosravi, Nolan A. Huck, Kourosh Shahraki, Stephen C. Hunter, and 8 more authors

International Journal of Molecular Sciences, 2023

Abs

Retinal hemorrhages in pediatric patients can be a diagnostic challenge for ophthalmologists. These hemorrhages can occur due to various underlying etiologies, including abusive head trauma, accidental trauma, and medical conditions. Accurate identification of the etiology is crucial for appropriate management and legal considerations. In recent years, deep learning techniques have shown promise in assisting healthcare professionals in making more accurate and timely diagnosis of a variety of disorders. We explore the potential of deep learning approaches for differentiating etiologies of pediatric retinal hemorrhages. Our study, which spanned multiple centers, analyzed 898 images, resulting in a final dataset of 597 retinal hemorrhage fundus photos categorized into medical (49.9%) and trauma (50.1%) etiologies. Deep learning models, specifically those based on ResNet and transformer architectures, were applied; FastViT-SA12, a hybrid transformer model, achieved the highest accuracy (90.55%) and area under the receiver operating characteristic curve (AUC) of 90.55%, while ResNet18 secured the highest sensitivity value (96.77%) on an independent test dataset. The study highlighted areas for optimization in artificial intelligence (AI) models specifically for pediatric retinal hemorrhages. While AI proves valuable in diagnosing these hemorrhages, the expertise of medical professionals remains irreplaceable. Collaborative efforts between AI specialists and pediatric ophthalmologists are crucial to fully harness AI’s potential in diagnosing etiologies of pediatric retinal hemorrhages.
MICCAI

MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation

Kun Han, Yifeng Xiong, Chenyu You, Pooya Khosravi, and 4 more authors

In Medical Image Computing and Computer Assisted Intervention – MICCAI 2023, 2023

Abs

Acquiring and annotating sufficient labeled data is crucial in developing accurate and robust learning-based models, but obtaining such data can be challenging in many medical image segmentation tasks. One promising solution is to synthesize realistic data with ground-truth mask annotations. However, no prior studies have explored generating complete 3D volumetric images with masks. In this paper, we present MedGen3D, a deep generative framework that can generate paired 3D medical images and masks. First, we represent the 3D medical data as 2D sequences and propose the Multi-Condition Diffusion Probabilistic Model (MC-DPM) to generate multi-label mask sequences adhering to anatomical geometry. Then, we use an image sequence generator and semantic diffusion refiner conditioned on the generated mask sequences to produce realistic 3D medical images that align with the generated masks. Our proposed framework guarantees accurate alignment between synthetic images and segmentation maps. Experiments on 3D thoracic CT and brain MRI datasets show that our synthetic data is both diverse and faithful to the original data, and demonstrate the benefits for downstream segmentation tasks. We anticipate that MedGen3D’s ability to synthesize paired 3D medical images and masks will prove valuable in training deep learning models for medical imaging tasks.
AJO

Deep learning estimation of 10-2 visual field map based on circumpapillary retinal nerve fiber layer thickness measurements

Alireza Kamalipour, Sasan Moghimi, Pooya Khosravi, Mohammad Sadegh Jazayeri, and 7 more authors

American Journal of Ophthalmology, 2023