Mo Shahdloo

I am Senior Applied Scientist at Microsoft Applied Sciences Group. Most recently, I was a computer vision machine learning scientist at Vicon, developing machine learning models for markerless motion capture. I have also been a researcher at Oxford Centre for Functional MR Imaging of the Brain (FMRIB), University of Oxford.

I was trained in Electrical Engineering at Amirkabir University and Sharif University, Tehran. After working on developing industrial embedded systems in the energy sector for a couple of years, I moved to Ankara where I did my graduate work in the lab of Tolga Çukur, working on MRI and computational neuroscience.

My current work centres on developing and optimising multi-modal models for efficient inference on low-powered NPU chips. Stretching to the past, I have explored research and development of pose-estimation and subject reidentification models, as well as developing methods for (functional) MRI imaging acquisition, reconstruction, and post-processing, and using them in understanding semantic and language processing in the brain.
Below, you can peek into the stuff I have been busy doing recently.

Research

Markerless Human Pose Estimation and Tracking
Traditionally motion capture happens by tracking the photoreflective markers that are physically attached to the subject. This process involves careful requirements regarding special clothing, and difficulties in dealing with the attached markers that can limit the motion. The markerless motion capture system does not rely on physical markers, but rather uses computer vision and deep learning to estimate pose in each point in time.

Motion-correction for awake non-human primate fMRI
Functional imaging of awake non-human primates is challenging not only due to their smaller brain size, but also due to excessive local field fluctuations due to animals' motion. Using a novel pulse sequence, efficient reconstruction techniques, and a custom-made multi-channel coil we aim to perform accelerated functional scans of awake monkeys.

Attentional modulations of action-category representation in the brain
We used voxelwise models to map the semantic representation of hundreds of objects and actions across cortex. We then studied the attentional modulation of the semantic representation during action-based visual search.

Temporal receptive windows in the brain mapped via deep language networks
Using a natural story listening experimental paradigm, we use computational models based on deep neural networks to study the effect of context integration on the representation of a large dictionary of words across the cortex. We are further interested in studying the attentional modulations of this property across cortex.

Rapid self-tuning compressed sensing MRI
While parameter selection is critical for compressed-sensing reconstruction quality, the optimal parameters are subject and dataset specific. Thus, commonly practiced heuristic parameter selection generalizes poorly to independent datasets. We proposed a new self-tuning compressed-sensing reconstruction method that uses computationally efficient projections onto epigraph sets of the l1 and total-variation norms to simultaneously achieve parameter selection and regularization.

Trade off between fat-suppression and partial-voluming in bSSFP acquisitions
Fat-suppression in bSSFP can be achieved using weighted average of in-phase and out-of-phase acquisitions raised to a negative power. We studied the effects of the power parameter on the trade off between fat-suppression and partial voluming under various experimental setups. We devised optimal parameter values meeting the fat-suppression and partial voluming requirements.

Teaching

K-space and image reconstruction
This talk provides some intuition about the concept of spatial encoding in MRI by introducing the k-space, and elaborates more on some of the special sampling scenarios. Also, introduction to baiscs of parallel imaging is provided. This talk was presented during the educational course at ISMRM British Chapter MR-Fest 2021

Publications

Please use this bibliography file to cite any of the works below.

Articles

Priestley L., Chiew M., Shahdloo M., Mahmoodi A., Cheng X., Rushworth M., and Khalighinejad N. (2025). Dorsal Raphe Nucleus Controls Motivational State Transitions in Monkeys. Science Advances. 10.1126/sciadv.ads1236.
Shahdloo M., Khalighinehad N., Priestley L., Rushworth M., and Chiew M. (2024). Dynamic off-resonance correction improves functional image analysis in fMRI of awake behaving non-human primates. Frontiers in Neuroimaging. 10.3389/fnimg.2024.1336887.
Shahdloo M., Çelik E., Ürgen B. A., Gallant J. L., and Çukur T. (2022). Task-Dependent Warping of Semantic Representations During Search for Visual Action Categories. Journal of Neuroscience. 10.1523/jneurosci.1372-21.2022.
Shahdloo M., Schüffelgen U., Papp D., Miller K. L., and Chiew M. (2022). Model-Based Dynamic Off-Resonance Correction for Improved Accelerated fMRI in Awake Behaving Non-Human Primates. Magnetic Resonance in Medicine. 87(6). pp 2922-2932. 10.1002/mrm.29167.
Kiremitci I., Yilmaz O., Çelik E., Shahdloo M., Huth A.G., and Çukur T. (2021). Attentional Modulation of Hierarchical Speech Representations in a Multi-Talker Environment. Cerebral Cortex. 31(11). pp 4986–5005. 10.1093/cercor/bhab136.
Dar S.U.H., Yurt M., Shahdloo M., Ildiz E., Tinaz B., and Çukur T. (2020). Prior-Guided Image Reconstruction for Accelerated Multi-Contrast MRI via Generative Adversarial Networks. IEEE Journal of Selected Topics in Signal Processing. 14(6). pp 1072-1087. 10.1109/JSTSP.2020.3001737.
Shahdloo M., Çelik E., and Çukur T. (2020). Biased Competition in Semantic Representation During Natural Visual Search. NeuroImage. 216(1). pp 116383. 10.1016/j.neuroimage.2019.116383.
Shahdloo M., Ilicak E., Tofighi M., Saritas E.U., Çetin A.E., and Çukur T. (2019). Projection onto Epigraph Sets for Rapid Self-Tuning Compressed Sensing MRI. IEEE Transactions on Medical Imaging. 38(7). pp 1677-1689. 10.1109/TMI.2018.2885599.
Dar S.U.H., Yurt M., Shahdloo M., Ildiz E., and Çukur T. (2018). Synergistic Reconstruction and Synthesis via Generative Adversarial Networks for Accelerated Multi-Contrast MRI. arXiv. 1805.10704.

Conference publications

Shahdloo M., Khalighinejad N., Harbison C., Miller K. L., Rushworth M. and Chiew M. (2022). Dynamic off-resonance correction improves functional data quality in fMRI of awake behaving NHPs. OHBM. Glasgow, Scotland.
Shahdloo M., and Chiew M. (2022). Optimal Singular-Value Shrinkage for fMRI Denoising. ISMRM. London, England.
Shahdloo M., Papp D., Schüffelgen U., Miller K. L., Rushworth M., and Chiew M. (2021). Highly accelerated fMRI of awake behaving non-human primates via model-based dynamic off-resonance correction. ISMRM. Online.
Papp D., Schüffelgen U., Shahdloo M., Rieger S. W., Hess A. T., Rushworth M., and Clare S. (2021). Imaging performance of a multi-channel non-human primate coil. ISMRM. Online.
Shahdloo M., and Çukur T. (2019). Tradeoff between fat-suppression and partial-voluming in weighted combination alternating repetition-time (ATR) balanced SSFP. ESMRMB. Rotterdam, Netherlands.
Shahdloo M., Acar M., and Çukur T. (2019). Attention During Story Listening Modulates Temporal Receptive Windows Across Human Cortex. Cognitive Computational Neuroscience (CCN). 10.32470/CCN.2019.1039-0. Berlin, Germany.
Shahdloo M., Ürgen B. A., and Çukur T. (2019). Attention to action categories shifts semantic tuning toward targets across the brain. OHBM. Rome, Italy.
Dar S.U.H., Yurt M., Shahdloo M., Ildiz E., and Çukur T. (2019). Joint recovery of variably accelerated multi-contrast MRI acquisitions via generative adversarial networks. ISMRM. Montréal, Canada.
Shahdloo M., Ilicak E., Tofighi M., Saritas E.U., Çetin A.E., and Çukur T. (2018). Rapid self-tuning compressed-sensing MRI using projection onto epigraph sets. ISMRM. Paris, France.
Shahdloo M., Ilicak E., Tofighi M., Saritas E.U., Çetin A.E., and Çukur T. (2017). Adaptive Wavelet Thresholding for Profile-Encoding Reconstruction of Balanced Steady-State Free Precession Acquisitions. ESMRMB. Barcelona, Spain.
Shahdloo M., and Çukur T. (2017). Biased competition in semantic representations during category-based visual search. OHBM. Vancouver, Canada.

Open Reviews

To encourage transparency of the academic publication ecosystem, I sign the manuscript peer reviews that I am solicited to do, and publish them both here and on PubPeer whenever possible (i.e., when a preprint is posted online).

Richard H., Martin L., Pinho A.L., Pillow J., Thirion B. (2019). FastSRM: A fast, memory efficient and identifiable implementation of the shared response model . arXiv 1909.12537.
Reply to reviewer comments on: Shahdloo M., Çelik E., Ürgen B. A., Gallant J. L., and Çukur T. (2021). Task-Dependent Warping of Semantic Representations During Search for Visual Action Categories . bioRxiv 10.1101/2021.06.17.448789.

CV

Here is my recent CV (recent-ness not guaranteed though)

Without music, life would be a mistake ― Friedrich Nietzsche