PhD Defense: "Automated and Interactive Segmentation Methods for 5D Microscopy Images"

Diana Delibaltov

August 14th (Thursday), 2:00pm
Harold Frank Hall (HFH), Room 4164

Accurate segmentation of cells and tissues in 5D (3D + time + multiple channels) microscopy data is critical in quantitative developmental biology. This is a challenging task due to the large volumes of data (tens of gigabytes for single time lapse 3D sequence) and the inherent characteristics of microscopy image acquisition. In this research we developed new supervised and unsupervised segmentation methods with a focus on application to morphogenesis.

First, we developed a principled approach to unsupervised segmentation and fusion of multiple segmentations. A linear optimization framework is proposed for the joint correction of multiple over-segmentations obtained from different methods. The main idea motivating this approach is that over-segmentations, from a pool of methods with various parameters, are likely to agree on the correct segment boundaries, while spurious boundaries are likely to be method or parameter-dependent. Secondly, we introduced an interactive segmentation and analysis tool for 5D microscopy data, called CellECT. An adaptive confidence measure, called “cell-ness” metric is used to highlight regions of uncertainty in the segmentation. This metric quantifies how much a segment deviates from a typical correct segment. This metric adapts to the dataset and learns from the user interactions. The proposed methods are validated on ascidian time-lapse 3D volume data. CellECT is distributed as an open source software and is used in other quantitative biology applications.

About Diana Delibaltov:

Diana was born and raised in Bucharest, Romania. She received her B.S. degree from the Polytechnic Institute of New York University in 2008 from the Honors College of Electrical and Computer Engineering. During her undergraduate she received the Myron M. Rosenthal award and Helen Waren awards for highest academic achievement in 2007 and 2008, respectively. She received the Micro fellowship upon enrolling in the M.S./Ph.D program at UCSB and joined Prof. Manjunath's lab. Her work focuses on segmentation and analysis methods for 5D biological data. During her time at UCSB Diana has worked at the Xerox Research Center on parking lot occupancy determination from surveillance images, and at Qualcomm Research Center on computational photography problems. Her research interests include image segmentation, object recognition and applied optimization.

Hosted by: Prof. B.S. Manjunath