Research Interests

Humayun Irshad is a PostDoctoral Fellow in Beck Lab of Beth Israel Deaconess Medical Center (BIDMC) & Harvard Medical School. He joined Beck lab in March, 2014, after completing his PhD at Joseph Fourier University Grenoble 1, France (2011-2014). His current research interests lie in the areas of machine learning, microscopic Image analysis and bio-medical imaging. He is developing automated methods to combine image processing, machine learning and statistical approaches with automated image analysis of normal, pre-invasive and invasive tissue lesions, particularly breast tissue. Such methods include region of interests detection, terminal ductal lobular unit (TDLU) detection and compute its phenotypes, and nuclei and gland detection, segmentation and classification in 2D and 3D histopathological images (H&E stained, IHC stained and fluorescence images). This enables to explore the complexities of the tumors micro-environment and to develop new tools to diagnose patients, to predict how they might respond to a treatment, and to explore the consequences of how different regions and populations of cells within the tumor interact.

My major focus is the study of breast cancer, a heterogeneous disease with distinct disease grade and subtypes, driven by distinct sets of molecular abnormalities. I am interested in all stages of breast carcinogenesis: I am developing novel methods and tools to analyze samples from women with benign breast disease to identify molecular, morphological and architectural features associated with increased breast cancer risk; I am developing efficient methods to analyze samples from women with non-invasive breast cancer (DCIS, UDH) to identify markers to predict disease recurrence and progression, and I am also developing accurate automated tools to analyze samples from women with invasive breast cancer to identify clinically significant molecular alterations that impact treatment decisions and are associated with patient survival.