From CISSRS
User:Inicolaescu
Ioana Nicolaescu Fleming
PhD Candidate in Computer Science
- Company: JHU
- Department: Vision Lab
- Office phone: 1-410-516-2014
- E-Mail:
- Office:
ERC / LCSR
Johns Hopkins University
137 CSEB, 3400 North Charles St, Baltimore MD 21218-2682
[Computational Interaction and Robotics Lab]
Projects
Ultrasound Elastography Using Dynamic Programming
In this work our group proposed using dynamic programming (a mathematical optimization technique) to find tissue displacements for ultrasound elastography. The goal was to better image cancerous lesions (prostate cancer, breast cancer) or lumpectomy bed using ultrasound elastography. We demonstrated that dynamic programming elastography is much more robust to noise than conventional elastography methods. The work thus far has been extremely promising: a manuscript has already been accepted for publication in the IEEE TMI (Impact Factor 3.8). A 3D extension of this work with applications to liver ablation monitoring has recently been accepted for publication in MICCAI 2008.
Rivaz, H et. al. “Ultrasound Elastography: a Dynamic Programming Approach” IEEE TMI (in press - accepted Dec. 2007).
Rivaz, H., Fleming, I. N., Boctor, E. M., Fichtinger, G., Hager, G. D. “Ablation Monitoring with 3D Elastography: Ex-vivo and In-vivo Studies”, Eleventh International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2008 (accepted May 14th, 2008).
Ultrasound Elastography – Enabling Technology for Image Guided Laparoscopic Prostatectomy
(Dec 2007 - Present)
No real-time imaging modality exists today to guide laparoscopic prostatectomies. We investigated ultrasound elastography as an enabling technology. Fresh resected prostate specimens were used. Our 2D dynamic programming technique proved consistent in the identification of lesions; hard and soft, malignant and benign, located in the prostate’s central gland or in the prostate peripheral zone. Our results were validated by the pathology of prostatectomy specimens, as well as by in vivo and ex vivo MRI findings. This work is under review for acceptance at SPIE 2009.
Other Prostate Cancer Studies
(Dec 2007 - Present)
Investigating the ability of ultrasound advanced techniques to identify cavernous nerves. Our animal model consists of cavernous nerves of a young adult rat. We are using ultrasound elasticity to identify hard tissues as potential nerves and color Doppler to distinguish blood vessels. We are also testing nerve identification using ultrasound elastography on a training ultrasound phantom for nerve block simulation. Our preliminary results are promising, showing that the nerves can be seen as hard regions in the elastography images and are easily distinguishable from blood vessels and surrounding prostate tissue.
Neo-Adjuvant Chemotherapy Monitoring Using Ultrasound Elasticity Imaging
(future project)
For breast cancer patients primary chemotherapy (a.k.a. Neo-adjuvant chemotherapy, NAC) is quickly replacing adjuvant (post-operative) chemotherapy as the standard in the management of these patients. The benefit of NAC is two fold. Firstly, NAC has the ability to increase the rate of breast conserving therapy. Secondly, NAC allows in vivo chemo-sensitivity assessment. The ability to detect early drug resistance will prompt change from the ineffective to an effective regimen. Consequently, physicians may decrease toxicity and perhaps improve outcome. The metric most commonly used to determine in-vivo efficacy is the change in the tumor sized during NAC. Unfortunately, the clinical tools used to measure tumor size during NAC, such as physical exam, mammography, and B-mode ultrasound, have been shown to be less than ideal. We are proposing ultrasound elastography as an inexpensive, convenient and safe technique capable of accurately measuring tumor response repeatedly during NAC. The project is funded by Siemens Medical Solutions, Inc. Ultrasound Division
Steady Hand Robot for Retinal Surgery
This project focuses on delivering the Steady Hand Robotic Manipulator for retinal microsurgery. My involvement with the project consisted of running a study testing how the Steady Hand Robot improves the outcome of a specific task; vein cannulation. This work has recently been accepted for publication in MICCAI 2008.
Fleming, I. N., Balicki, M., Koo, J., Iordachita, I., Mitchell, B., Handa, J., Hager, G., Taylor, R. “Cooperative Robot Assistant for Retinal Microsurgery” Eleventh International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2008 (accepted May 14th).
Intraoperative Visualization of Anatomical Targets in Retinal Surgery
(Dec 2006 – Dec 2007)
In this project we proposed the use of preoperative information to help the surgeon with target visualization and tracking during retinal procedures. The information is first registered with the operating microscope view, and then targets are tracked in real-time, allowing the surgeon to follow them with ease. In the micrometer environment of retinal surgery improving the surgical experience by adding an information overlay can be of great importance. This work has been published in January 2008 in IEEE Proceedings Workshop in Applications of Computer Vision.
Fleming, I. N., Voros, S., Vagvolgyi, B., Pezzementi, Z., Handa, J., Taylor, R. H., Hager, G. D., “Intraoperative Visualization of Anatomical Targets in Retinal Surgery” IEEE Workshop in Applications of Computer Vision (2008).
Other Projects
Publications / Posters
Please see my publication list on my Curriculum Vitae or on my web page:
http://www.cs.jhu.edu/~ioana
