Iain Carmichael | UNC Pathology and Data Science

Brief Bio

Iain is an Assistant Professor of Pathology and Data Science at UNC-Chapel Hill working in computational Pathology. His lab builds data driven, computational systems to analyze high-resolution histology images of diseased tissue (e.g. digitized clinical H&E/IHC slides or multiplex immunofluorescence imaging) as well as other clinical data sources such as genetic testing and electronic health records. Their aim is to develop artificial intelligence approaches that improve diagnostic precision, increase access to state of the art care for patients around the world, uncover novel biomarkers for disease prognosis/therapeutic response, and advance basic scientific investigation into disease processes. A major focus of the lab’s work is the development of novel machine learning approaches to address the scale and complexity of histopathology images, which are typically 10s-100s of thousands of pixels in dimension and take years of clinical training to interpret.

Prior to coming (back) to UNC, Iain held visiting faculty positions in the Departments of Statistics at UC Berkeley and Pathology at UCSF. He completed a postdoc in the Division of Computational Pathology at Brigham and Women's Hospital/Harvard Medical School and an NSF Mathematical Sciences postdoctoral fellowship in the Department of Statistics at the University of Washington. He received a PhD in Statistics from UNC.

Affiliations

Member of the UNC Lineberger Comprehensive Cancer Center and Center for Environmental Health and Susceptibility
Member of the Carolina Health Care Informatics Program, Bioinformatics and Computational Biology, and Pathobiology and Translational Science graduate programs
Adjunct Faculty, Department of Statistics and Operations Research, UNC
Visiting Assistant Professor, Department of Pathology, UCSF
Research Affiliate, Berkeley Institute of Data Science
Visiting Scientist, Memorial Sloan Kettering Cancer Center

Representative work

Carmichael, I., Song, A.H., Chen, R.J., Williamson, D.F.K., Chen, T.Y., Mahmood, F. (2022). Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling. The International Conference on Medical Image Computing and Computer Assisted Intervention. To appear.

Carmichael, I. (2021). The folded concave Laplacian spectral penalty learns block diagonal sparsity patterns with the strong oracle property. Under review.

Carmichael, I., Keefe, T., Giertych, N., Williams, J.P. (2021). yaglm: a Python package for fitting and tuning generalized linear models that supports structured, adaptive and non-convex penalties.

Carmichael, I., Calhoun, B.C., Hoadley, K.A., Troester, M.A., Geradts, J., Couture, H.D., Olsson, L,. Perou, C.M., Niethammer, M., Hannig, J., Marron, J.S. (2021). Joint and individual analysis of breast cancer histologic images and genomic covariates. The Annals of Applied Statistics, 15(4), pp.1697-1722.

Carmichael, I. (2020). Learning sparsity and block diagonal structure in multi-view mixture models. Under review.

Banerjee, S., Bhamidi, S., Carmichael, I. (2022). Fluctuation bounds for continuous time branching processes and nonparametric change point detection in growing networks. The Annals of Applied Probability. To appear.