Mojtaba Sedigh Fazli

All Publications

• Artificial Intelligence-Aided Lung Ultrasound Detection of Interstitial Lung Disease in Systemic Sclerosis and Inflammatory Myopathy. Arthritis care & research Fairchild, R. M., Deluna, M. D., Fazli, M., Mar, D. A., Chung, M., Davuluri, S., Kawano, Y., Guo, H., Baker, M. C., Fiorentino, D., Tamang, S., Chung, L. 2026

  Abstract

  Lung ultrasound (LUS) is a sensitive, low-cost, and radiation-free modality for ILD detection. We previously developed and validated LUS interpretation criteria in systemic sclerosis (SSc) and idiopathic inflammatory myopathy (IIM) showing excellent diagnostic performance and correlations with ILD severity. In this study, we applied deep learning to evaluate whether convolutional neural networks (CNNs) can accurately detect ILD and its severity on LUS.Patients with SSc or IIM ± ILD, and paired LUS and chest computed tomography (CT) were included. LUS images were labeled using CT results and human LUS-ILD-24 interpretation. Three pretrained CNN architectures (InceptionV3, ResNet-50, VGG-16) were fine-tuned via transfer learning, and a de novo lightweight architecture (LUS-Net) was developed. Model performance for ILD detection was assessed at image and patient-levels using AUC, sensitivity, specificity, and agreement with expert interpretation. CNN outputs were correlated with pulmonary function tests (PFTs) and CT-based CALIPER indices. Grad-CAM visualized regions driving predictions.A total of 140 patients representing 3,920 LUS images were included and split into development (74) and independent test sets (66). VGG-16 achieved the best patient-level performance (AUC = 0.972; sensitivity = 97.4%; specificity = 92.6%) showing strong correlations with PFTs and CT severity. Grad-CAM highlighted pleural features as the primary regions influencing model predictions. CNN performance matched or exceeded LUS-ILD-24 interpretation.Deep learning applied to LUS enables accurate ILD detection in connective tissue disease and can enhance expert interpretation. Explainable AI suggests pleural features, even when B-lines are infrequent, are sufficient for reliable ILD recognition.

  View details for DOI 10.1002/acr.80054

  View details for PubMedID 41940478

• SynovAI: A Revolutionary AI Framework for Enhanced Detection and Differentiation of Rheumatoid Arthritis, Osteoarthritis, and Spondyloarthritis via Advanced Ultrasound Imaging Fazli, M. S., Deluna, M., Tamang, S., Fairchild, R. WILEY. 2025: 157-159

  View details for Web of Science ID 001671398100089

• An Artificial Intelligence Method for Phenotyping of OCT-Derived Thickness Maps Using Unsupervised and Self-supervised Deep Learning. Journal of imaging informatics in medicine Kazeminasab, S., Sekimitsu, S., Fazli, M., Eslami, M., Shi, M., Tian, Y., Luo, Y., Wang, M., Elze, T., Zebardast, N. 2025

  Abstract

  The objective of this study is to enhance the understanding of ophthalmic disease physiology and genetic architecture through the analysis of optical coherence tomography (OCT) images using artificial intelligence (AI). We introduce a novel AI methodology that addresses the challenge of transferring OCT phenotypes across datasets. The approach employs unsupervised and self-supervised learning techniques to phenotype and cluster OCT-derived retinal layer thicknesses, using glaucoma as a model disease. Our method integrates deep learning, manifold learning, and a Gaussian mixture model to identify distinct phenotypic clusters. Across two large datasets-Massachusetts Eye and Ear (MEE; 18,985 images) and UK Biobank (UKBB; 86,115 images)-the model identified 9 to 11 phenotypic clusters per retinal layer, which were clinically meaningful and showed consistent patterns across datasets. Pearson correlation analysis confirmed the intra-cluster similarity, with within-cluster correlations exceeding inter-cluster correlations (Supplemental Figs. 4-5). Clinical associations showed that specific phenotypes correlated strongly with glaucoma severity markers, including visual field mean deviation (e.g., 12.57±10.1 for phenotype 6) and cup-to-disc ratio (e.g., 0.694±0.237). These results validate the robustness of the model and its ability to generalize across datasets. This work advances OCT-based phenotyping, enabling phenotype transfer and facilitating translational research in disease mechanisms and genetic discovery.

  View details for DOI 10.1007/s10278-025-01539-x

  View details for PubMedID 40394321

  View details for PubMedCentralID 7595218

• Regulation of calcium entry by cyclic GMP signaling in Toxoplasma gondii. The Journal of biological chemistry Hortua Triana, M. A., Márquez-Nogueras, K. M., Fazli, M. S., Quinn, S., Moreno, S. N. 2024; 300 (3): 105771

  Abstract

  Ca2+ signaling impacts almost every aspect of cellular life. Ca2+ signals are generated through the opening of ion channels that permit the flow of Ca2+ down an electrochemical gradient. Cytosolic Ca2+ fluctuations can be generated through Ca2+ entry from the extracellular milieu or release from intracellular stores. In Toxoplasma gondii, Ca2+ ions play critical roles in several essential functions for the parasite, like invasion of host cells, motility, and egress. Plasma membrane Ca2+ entry in T. gondii was previously shown to be activated by cytosolic calcium and inhibited by the voltage-operated Ca2+ channel blocker nifedipine. However, Ca2+ entry in T. gondii did not show the classical characteristics of store regulation. In this work, we characterized the mechanism by which cytosolic Ca2+ regulates plasma membrane Ca2+ entry in extracellular T. gondii tachyzoites loaded with the Ca2+ indicator Fura-2. We compared the inhibition by nifedipine with the effect of the broad spectrum TRP channel inhibitor, anthranilic acid or ACA, and we find that both inhibitors act on different Ca2+ entry activities. We demonstrate, using pharmacological and genetic tools, that an intracellular signaling pathway engaging cyclic GMP, protein kinase G, Ca2+, and the phosphatidyl inositol phospholipase C affects Ca2+ entry and we present a model for crosstalk between cyclic GMP and cytosolic Ca2+ for the activation of T. gondii's lytic cycle traits.

  View details for DOI 10.1016/j.jbc.2024.105771

  View details for PubMedID 38382669

  View details for PubMedCentralID PMC10959671

• Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images in Glaucoma. IEEE journal of biomedical and health informatics Shi, M., Lokhande, A., Fazli, M. S., Sharma, V., Tian, Y., Luo, Y., Pasquale, L. R., Elze, T., Boland, M. V., Zebardast, N., Friedman, D. S., Shen, L. Q., Wang, M. 2023; 27 (9): 4329-4340

  Abstract

  Ophthalmic images, along with their derivatives like retinal nerve fiber layer (RNFL) thickness maps, play a crucial role in detecting and monitoring eye diseases such as glaucoma. For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) associated with functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. This challenge is further amplified by the presence of image artifacts, commonly resulting from image acquisition and automated segmentation issues. In this paper, we present an artifact-tolerant unsupervised learning framework called EyeLearn for learning ophthalmic image representations in glaucoma cases. EyeLearn includes an artifact correction module to learn representations that optimally predict artifact-free images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the affinities within and between images. During training, images are dynamically organized into clusters to form contrastive samples, which encourage learning similar or dissimilar representations for images in the same or different clusters, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection with a real-world dataset of glaucoma patient ophthalmic images. Extensive experiments and comparisons with state-of-the-art methods confirm the effectiveness of EyeLearn in learning optimal feature representations from ophthalmic images.

  View details for DOI 10.1109/JBHI.2023.3288830

  View details for PubMedID 37347633

  View details for PubMedCentralID PMC10560582

• PyVisualFields: A Python Package for Visual Field Analysis. Translational vision science & technology Eslami, M., Kazeminasab, S., Sharma, V., Li, Y., Fazli, M., Wang, M., Zebardast, N., Elze, T. 2023; 12 (2): 6

  Abstract

  Artificial intelligence (AI) methods are changing all areas of research and have a variety of capabilities of analysis in ophthalmology, specifically in visual fields (VFs) to detect or predict vision loss progression. Whereas most of the AI algorithms are implemented in Python language, which offers numerous open-source functions and algorithms, the majority of algorithms in VF analysis are offered in the R language. This paper introduces PyVisualFields, a developed package to address this gap and make available VF analysis in the Python language.For the first version, the R libraries for VF analysis provided by vfprogression and visualFields packages are analyzed to define the overlaps and distinct functions. Then, we defined and translated this functionality into Python with the help of the wrapper library rpy2. Besides maintaining, the subsequent versions' milestones are established, and the third version will be R-independent.The developed Python package is available as open-source software via the GitHub repository and is ready to be installed from PyPI. Several Jupyter notebooks are prepared to demonstrate and describe the capabilities of the PyVisualFields package in the categories of data presentation, normalization and deviation analysis, plotting, scoring, and progression analysis.We developed a Python package and demonstrated its functionality for VF analysis and facilitating ophthalmic research in VF statistical analysis, illustration, and progression prediction.Using this software package, researchers working on VF analysis can more quickly create algorithms for clinical applications using cutting-edge AI techniques.

  View details for DOI 10.1167/tvst.12.2.6

  View details for PubMedID 36745440

  View details for PubMedCentralID PMC9910386

• Assessing Surface Shapes of the Optic Nerve Head and Peripapillary Retinal Nerve Fiber Layer in Glaucoma with Artificial Intelligence. Ophthalmology science Saini, C., Shen, L. Q., Pasquale, L. R., Boland, M. V., Friedman, D. S., Zebardast, N., Fazli, M., Li, Y., Eslami, M., Elze, T., Wang, M. 2022; 2 (3): 100161

  Abstract

  To assess 3-dimensional surface shape patterns of the optic nerve head (ONH) and peripapillary retinal nerve fiber layer (RNFL) in glaucoma with unsupervised artificial intelligence (AI).Retrospective study.Patients with OCT scans obtained between 2016 and 2020 from Massachusetts Eye and Ear.The first reliable Cirrus (Carl Zeiss Meditec, Inc) ONH OCT scans from each eye were selected. The ONH and RNFL surface shape was represented by the vertical positions of the inner limiting membrane (ILM) relative to the lowest ILM vertical position in each eye. Nonnegative matrix factorization was applied to determine the ONH and RNFL surface shape patterns, which then were correlated with OCT and visual field (VF) loss parameters and subsequent VF loss rate. We tested whether using ONH and RNFL surface shape patterns improved the prediction accuracy for associated VF loss and subsequent VF loss rates measured by adjusted r 2 and Bayesian information criterion (BIC) difference compared with using established OCT parameters alone.Optic nerve head and RNFL surface shape patterns and prediction of the associated VF loss and subsequent VF loss rates.We determined 14 ONH and RNFL surface shape patterns using 9854 OCT scans from 5912 participants. Worse mean deviation (MD) was most correlated (r = 0.29 and r = 0.24, Pearson correlation; each P < 0.001) with lower coefficients of patterns 10 and 12 representing inferior and superior para-ONH nerve thinning, respectively. Worse MD was associated most with higher coefficients of patterns 5, 4, and 9 (r = -0.16, r = -0.13, and r = -0.13, respectively), representing higher peripheral ONH and RNFL surfaces. In addition to established ONH summary parameters and 12-clock-hour RNFL thickness, using ONH and RNFL surface patterns improved (BIC decrease: 182, 144, and 101, respectively; BIC decrease ≥ 6; strong model improvement) the prediction of accompanied MD (r 2 from 0.32 to 0.37), superior (r 2 from 0.27 to 0.31), and inferior (r 2 from 0.17 to 0.21) paracentral loss and improved (BIC decrease: 8 and 8, respectively) the prediction of subsequent VF MD loss rates (r 2 from 0 to 0.13) and inferior paracentral loss rates (r 2 from 0 to 0.16).The ONH and RNFL surface shape patterns quantified by unsupervised AI techniques improved the structure-function relationship and subsequent VF loss rate prediction.

  View details for DOI 10.1016/j.xops.2022.100161

  View details for PubMedID 36245761

  View details for PubMedCentralID PMC9562352

• The Impact of Inflammatory Markers on the Ganglion Cell Complex in Non-Glaucoma Subjects Fazli, M., Rauscher, F. G., Wirkner, K., Engel, C., Kirsten, T., Loeffler, M., Thiery, J., Elze, T., Ebert, T., Wang, M. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022

  View details for Web of Science ID 000844401305027

• A Python collection of tools for analyzing visual fields Kazeminasab, S., Eslami, M., Li, Y., Fazli, M., Sharma, V., Wang, M., Zebardast, N., Elze, T. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022

  View details for Web of Science ID 000844401306056

• Glaucomatous progressive retinal nerve fiber layer thinning and its association with patient race Jin, Q., Halawa, O., Li, Y., Eslami, M., Kazeminasab, S., Fazli, M., Sharma, V., Zebardast, N., Wang, M., Elze, T. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022

  View details for Web of Science ID 000844437000114

• Evaluation of Deep Learning Visual Field Prediction Models for Clinical Relevance Eslami, M., Zhang, M., Kim, J., Chang, D., Li, Y., Kazeminasab, S., Fazli, M., Sharma, V., Boland, M., Zebardast, N., Wang, M., Elze, T. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022

  View details for Web of Science ID 000844401306059

• The Impact of Race on the Relationship Between Cup-To-Disc Ratio and Glaucomatous Visual Field Loss Zhao, P., Li, Y., Eslami, M., Kazeminasab, S., Fazli, M., Sharma, V., Halawa, O., Zebardast, N., Wang, M., Elze, T. ASSOC RESEARCH VISION OPHTHALMOLOGY INC. 2022

  View details for Web of Science ID 000844401305026

• Ca2+ entry at the plasma membrane and uptake by acidic stores is regulated by the activity of the V-H+ -ATPase in Toxoplasma gondii. Molecular microbiology Stasic, A. J., Dykes, E. J., Cordeiro, C. D., Vella, S. A., Fazli, M. S., Quinn, S., Docampo, R., Moreno, S. N. 2021; 115 (5): 1054-1068

  Abstract

  Ca2+ is a universal intracellular signal that regulates many cellular functions. In Toxoplasma gondii, the controlled influx of extracellular and intracellular Ca2+ into the cytosol initiates a signaling cascade that promotes pathogenic processes like tissue destruction and dissemination. In this work, we studied the role of proton transport in cytosolic Ca2+ homeostasis and the initiation of Ca2+ signaling. We used a T. gondii mutant of the V-H+ -ATPase, a pump previously shown to transport protons to the extracellular medium, and to control intracellular pH and membrane potential and we show that proton gradients are important for maintaining resting cytosolic Ca2+ at physiological levels and for Ca2+ influx. Proton transport was also important for Ca2+ storage by acidic stores and, unexpectedly, the endoplasmic reticulum. Proton transport impacted the amount of polyphosphate (polyP), a phosphate polymer that binds Ca2+ and concentrates in acidocalcisomes. This was supported by the co-localization of the vacuolar transporter chaperone 4 (VTC4), the catalytic subunit of the VTC complex that synthesizes polyP, with the V-ATPase in acidocalcisomes. Our work shows that proton transport regulates plasma membrane Ca2+ transport and control acidocalcisome polyP and Ca2+ content, impacting Ca2+ signaling and downstream stimulation of motility and egress in T. gondii.

  View details for DOI 10.1111/mmi.14722

  View details for PubMedID 33793004

  View details for PubMedCentralID PMC9142151

• Lightweight and Scalable Particle Tracking and Motion Clustering of 3D Cell Trajectories Fazli, M. S., Stadler, R., Alaila, B., Vella, S. A., Moreno, S. N. J., Ward, G. E., Quinn, S. edited by Singh, L., DeVeaux, R., Karypis, G., Bonchi, F., Hill, J. IEEE COMPUTER SOC. 2019: 412-421

  View details for DOI 10.1109/DSAA.2019.00056

  View details for Web of Science ID 000540890900040

• Toward Simple & Scalable 3D Cell Tracking Fazli, M. S., Vella, S. A., Moreno, S. N. J., Ward, G. E., Quinn, S. P. edited by Abe, N., Liu, H., Pu, C., Hu, Ahmed, N., Qiao, M., Song, Y., Kossmann, D., Liu, B., Lee, K., Tang, J., He, J., Saltz, J. IEEE. 2018: 3217-3225

  View details for Web of Science ID 000468499303039

• UNSUPERVISED DISCOVERY OF <i>TOXOPLASMA GONDII</i> MOTILITY PHENOTYPES Fazli, M. S., Vella, S. A., Moreno, S. N. J., Quinn, S., IEEE IEEE. 2018: 981-984

  View details for Web of Science ID 000455045600224

• Scalable Fast Rank-1 Dictionary Learning for fMRI Big Data Analysis Li, X., Makkie, M., Lin, B., Fazli, M., Davidson, I., Ye, J., Liu, T., Quinn, S., Assoc Comp Machinery ASSOC COMPUTING MACHINERY. 2016: 511-519

  View details for DOI 10.1145/2939672.2939730

  View details for Web of Science ID 000485529800065

• A Comparative Study on Forecasting Polyester Chips Prices for 15 Days, Using Different Hybrid Intelligent Systems Fazli, M., Lebraty, J., IEEE IEEE. 2013

  View details for Web of Science ID 000349557200260