Welcome to my webpage!

I am a PhD Student at the Electrical and Computer Engineering Department of Northeastern University. I received my master's degree in Computer Science from Boston University in 2009. I am a member of Cognitive Systems Lab (CSL) and my advisor is Prof. Deniz Erdogmus. My current research interests include biomedical image processing and computer vision.

Research Projects:      back to top

Real Time Lung Tumor Tracking

Radiotherapy is an effective treatment technique for lung cancer. However, the movement of lung tumors during normal respiration makes it difficult to accurately irradiate the tumor. Precise lung tumor localization is vital to efficiently treating the tumor and avoiding unnecessary radiation exposure of normal tissues. Estimating the motion model of the tumor may lead to improved treatment planning and dose calculation throughout the therapy. 4D Computed Tomography (CT) images taken prior to treatment (to develop the patient's treatment plan) provide valuable information about the movement of the thoracic organs and the tumor. For each radiotherapy treatment session, a set of kilovoltage X-ray images (kV images) are acquired to aid in the alignment of the treatment target relative to the radiation beam. This project focuses on real time lung tumor tracking by incorporating information and labels from 4DCT on kV x-ray videos for treatment-day specific tumor motion models.

Biomedical Image Segmentation using Principal Curves and Surfaces:                           

Segmentation of organs is an essential and time consuming task for radiation treatment of cancers. The aim of this project is to utilize principal curves for automatic/semi-automatic segmentation of organs.

Cell Motion Flow Analysis:

 

Analyzing motion flow of cells is a challenging problem due to noise in images and uncontrolled motion of cells. In this study, we are interested in automatically detecting the regions of organized motion and motion patterns on cell videos.

 

   

Predicting Migration of Cancer Cells using Diffusion Tensor Imaging (Past)

 

Diffusion tensor Magnetic Resonance Imaging (MRI) is a biomedical visualization technique, which shows direction of water diffusion. Diffusion Tensor Imaging (DTI) is an application of diffusion MRI aiming to extract and characterize diffusion anisotropy affects. When applied to brain, DTI shows the motion flow in the white matter of brain. Radiotherapy is widely used in treatment of malignant brain lesions. Current treatment plans include a fixed length margin around the tumor region of interest to account for the possible tumor spread. However, progressive tumors might occur outside of these margins, which requires more analysis about the spread of brain tumors. In this project, we are interested in predicting migration of cancer cells by using diffusion tensor MRI and finding out whether neuronal fiber pathways might provide possible routes for the spread of cancer cells. The outcome will help creating improved anisotropic margins for radiation treatment of brain tumors.

 

Robust Facial Feature Tracking (Past)

 

At Boston University, I worked on Camera Mouse project under the supervision of Prof. Margrit Betke. Camera Mouse is a mouse replacement interface for users with severe disabilities. I was interested in automatic re-initialization techniques in the time of tracking failure. Proposed method involves an information fusion approach using multiple cameras. You can see a video of me here using the multiview tracking system, where the system tracks my nose tip and below is the 3D reconstructed trajectories. Basically, each view has independent 2D trackers and is assigned a reliability measure, which is used to decide a tracking failure.

Publications:     back to top

Motion Flow Analysis in Cell Videos Using a Multi-Level Clustering Method
Esra Ataer-Cansizoglu
, Nastaran Ghadarghadar, Ramin Zareian, Erhan Bas, Jeffrey W. Ruberti, Deniz Erdogmus. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2011
    paper    presentation       video-1        video-2

Principal Curve Based Semi-Automatic Segmentation of Organs in 3D-CT
Sheng You, Erhan Bas, Esra Ataer-Cansizoglu, Jayashree Kalpathy-Cramer, Deniz Erdogmus. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2011
    paper    poster

A Novel Application of Principal Surfaces to Segmentation in 4D-CT for Radiation Treatment Planning, Sheng You, Esra Ataer-Cansizoglu, Deniz Erdogmus, James Tanyi, and Jayashree Kalpathy-Cramer, Deniz Erdogmus. International Conference on Machine Learning and Applications (ICMLA), 2010
    paper      presentation

Towards Respiration Management in Radiation Treatment of Lung Tumors: Transferring Region of Interest from Planning CT to Kilovoltage X-ray Images
Esra Ataer-Cansizoglu
, Erhan Bas, M. Ali Yousuf, Sheng You, Warren D. D'Souza, Deniz Erdogmus. International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),  2010
    paper     poster

An Information Fusion Approach for Multiview Feature Tracking
Esra Ataer-Cansizoglu, Margrit Betke. International Conference on Pattern Recognition (ICPR), 2010

    paper    poster

Movement and Recovery Analysis of a Mouse-Replacement Interface for Users with Severe Disabilities
Caitlin Connor, Emily Yu, John Magee, Esra Cansizoglu, Samuel Epstein, Margit Betke, HCI International Conference, 2009
    paper

Matching Ottoman Words: An Image Retrieval Approach to Historical Document Indexing
Esra Ataer, Pinar Duygulu. In Proceedings of
ACM International Conference on Image and Video Retrieval,(CIVR), 2007
    paper

Retrieval of Ottoman Documents
Esra Ataer, Pinar Duygulu. In Proceedings of
ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR) in Conjuction with ACM Multimedia, 2006

    paper

Osmanlica Kelimeleri Esleme - Matching Ottoman Words (in Turkish)
Esra Ataer, Pinar Duygulu. In Proceedings of IEEE 15. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU)
, 2007

    paper

A New Representation for Matching Words
Bilkent University, Department of Computer Engineering, Master of Science Thesis, July 2007

CV:         back to top

You can reach my CV from here.

 

  
   Esra Ataer-Cansizoglu

Department of Electrical and Computer Engineering
Northeastern University
409 Dana Research Center
360 Huntington Avenue, Boston, MA 02115
Phone: +1-617-373-4779
email: ataer [at] ece.neu.edu