Faculty Profiles

Scott, Doyle
Doyle, Scott, PhDAssistant Professor
Email: scottdoy@buffalo.edu
Phone: 716-829-2005

Specialty/Research Focus:
Biomedical Image Analysis; Biomedical Imaging; Digital Pathology; Image Analysis; Machine Learning; Quantitative Histology; Bioinformatics

Research Summary:
Our group specializes in building quantitative image and data analysis algorithms for biomedical datasets. For the past 9 years, I have been developing computerized methods to quantify and analyze large medical imaging datasets. These methods include data processing, object detection / segmentation, feature extraction and selection, dimensionality reduction, and classification (supervised and unsupervised). I strongly believe in translating academic research into real-world products and services. To that end, along with my colleagues, I have worked at a start-up company to bring my work into the marketplace -- an experience that has given me great insight into the business side of academia. This experience broadened my understanding of how basic research is translated into a profitable enterprise, and I believe these lessons have made me a better engineer. I am currently working as an Assistant Professor in the Department of Pathology & Anatomical Sciences at the University at Buffalo, where I am focused on building a teaching and research program for quantitative modeling of anatomy and cell biology. This program will introduce students of both medicine and engineering to pattern classification approaches developed in recent years, applying them to real-world clinical problems.

Pinaki, Sarder
Sarder, Pinaki, PhDAssistant Professor
Email: pinakisa@buffalo.edu
Phone: (716) 829-2265

Specialty/Research Focus:
Biomedical Imaging; Biomedical Image Analysis; Image Analysis; Digital Pathology; Quantitative Histology; Machine Learning; Bioinformatics

Research Summary:
We develop novel computational methods to study and understand tissue micro-anatomy using multi-modal whole-slide microscopy images as well as associated genomic datasets. Our method facilitates decision making in a clinical work-flow (both for diagnosis and predicting progression of diseases), and also allows studying fundamental systems biology of disease dynamics. Currently, our major focus involves studying diabetic kidney diseases in mouse models and human samples.