An interdisciplinary group at the intersection of artificial intelligence, statistics, and cancer research — developing computational tools that support cancer detection, diagnostic refinement, and therapeutic decision-making.
We develop deep-learning and statistical methods that turn high-dimensional biomedical measurements — genomics, proteomics, imaging, and clinical data — into interpretable, transferable representations, and translate them toward clinical practice and biological discovery.
Tabular data hides the relationships between features. We reconfigure each sample into a spatially semantic 2D topographic map (TabMap) that keeps feature values as pixel intensities and encodes feature relationships as spatial distance — letting 2D convolutional networks extract association patterns while ranking features by importance.
Nat. Biomed. Eng. 2025Most deep-learning applications are regressions, whose features lie on a complex high-dimensional continuum that resists visualization. Our manifold discovery and analysis (MDA) method learns the manifold topology tied to a network's outputs, preserving local geometry to reveal a model's appropriateness, generalizability, and adversarial robustness.
Nat. Commun. 2023In radiation oncology and medical physics, we integrate diverse data types — medical imaging, clinical records, genomic profiles, and treatment parameters — to uncover complex patterns across modalities that are invisible in any single one, improving diagnosis, prognosis, and therapeutic decision-making.
Related publicationsModels, tools, and methods we develop and share. scVision is the first; more are on the way.
A vision foundation model for single-cell biology. It renders each cell as a continuous image via optimal-transport gene cartography and learns one frozen encoder by masked-image pretraining on 72 million human cells — the most accurate zero-shot cell-type annotator on every held-out atlas we tested.
Explore scVisionAn interdisciplinary group spanning machine learning, statistics, engineering, and biology.
Md Tauhidul Islam develops novel AI techniques for biomedical applications, with a focus on translating biomedical data-science research into benefits for clinical practice and biological investigation. His work applies large foundation models and neural networks to high-dimensional medical data — genomics, radiomics, proteomics, and images across modalities — to advance patient care. He earned his PhD at Texas A&M University and trained as a postdoctoral scholar at Stanford with Dr. Lei Xing.
Machine learning, deep learning, and integrative omics. Builds AI-driven tools for multi-omics integration with applications in cancer diagnosis and precision medicine. Previously a postdoctoral associate at the National Research Council of Canada; PhD, University of Saskatchewan.
Develops robust, interpretable statistical machine-learning methods for complex biomedical data — with applications in early cancer diagnostics through cfDNA liquid biopsy, spatial transcriptomics, and imaging-based biomarker discovery. PhD in Biostatistics, UC Berkeley. Co-mentored with Dr. Mohammad Esfahani.
PhD student in Electrical Engineering, advised by Prof. Ehsan Adeli and Prof. Md Tauhidul Islam. Works on large-scale, clinically transformative brain models to advance our understanding of the human brain through AI. BS, Bilkent University; Fulbright Scholar.
Applies graph neural networks that integrate biological-pathway structure with multi-omics cancer data to better understand the interactions driving tumor behavior. BS/MS in Bioengineering, UCLA, with prior research spanning neurodegeneration, nephrotoxicity modeling, and drug-screening platforms.
A selection of recent work. See Google Scholar for the complete list.
Sakib Mostafa joined the lab as a postdoctoral fellow. Welcome, Sakib!
Seraphina Shi joined the lab as a postdoctoral fellow. Welcome, Seraphina!
We are located in the Stanford Research Park in Palo Alto.
Free visitor parking is available on-site at 3145 Porter Drive.
Get directionsMd Tauhidul Islam, PhD
Principal Investigator · Room A202
tauhid@stanford.edu
We are looking for undergraduate and graduate students and postdocs to join the lab. If your expertise and interests match our projects, please email tauhid@stanford.edu.