|
Assistant Professor
Biomedical Informatics
Ohio State University
|
333 W. 10th Ave., 3170-B Graves Hall
Columbus, OH 43210
Tel: 614-292-1084
Fax: 614-688-6600
E-mail: metin(dot)gurcan(at)osumc(dot)edu
Web: http://bmi.osu.edu/~cialab
|
Dr. Gurcan's research interests include image analysis and understanding, computer vision with applications to medicine. Over the last decade, his research contributions have concentrated on computer-aided detection and diagnosis (CAD) of cancer. He has developed CAD systems for different organs such as breast, lung and colon and for different modalities such as mammography and CT. CAD development requires interdisciplinary research. Therefore, Dr. Gurcan's research experience covers a wide variety of interrelated fields such as multi-resolution image decomposition, adaptive filtering, statistical pattern recognition, neural networks, image and volume registration, morphological image processing, multi-dimensional optimization, image segmentation, and statistical signal processing.
The qualitative analysis of histopathological and radiological images is time-consuming and subject to inter- and intra-reader variations. This affects the prediction of the clinical outcome in an undesired way. Therefore, we are developing image analysis systems, for computer-assisted interpretations of these images to help pathologists and radiologists in their decision mechanism. Our goal is to provide computational tools with which they can extract quantitative features useful for more objective and accurate prognosis. Furthermore, we are investigating high-performance computational infrastructures to efficiently process these large images. The developed systems provide promising results, both in terms of accuracy and computational efficiency.
|
Assistant Professor,
Dept. of Biomedical Engineering,
Rutgers The State University of New Jersey
Member, Cancer Institute of New Jersey
Adjunct Assistant Professor of Radiology,
UMDNJ-Robert Wood Johnson Hospital.
|
|
In recent years, whole-slide digital scanners have become commonplace in pathology labs across the country. These devices are capable of digitizing a set of histological glass slides, saving them as images on a computer. This high-resolution images, captured at 40X magnification, are similar to what a pathologist would look at under a microscope to diagnose a prostate tissue sample. From here, a Computer-Aided Diagnosis (CAD) system can take over, analyzing the images and looking for potential regions of interest for a pathologist. These systems could analyze images automatically, detect regions of concern, and classify those regions using the Gleason grading system. Such a system would help by reducing the amount of time a pathologist must spend looking at benign samples (through pre-screening), and would reduce the variability in Gleason grading by providing a quantitative standard with which classification can be performed.
Our lab's research focuses on developing novel computer-aided diagnostic (CAD) systems that can assist the doctor by automatically detecting suspicious regions in medical images, such as those obtained from the MRI, CT, and ultrasound scanners. By combining sophisticated computer vision, medical image processing, and novel classification tools we have been able to develop highly accurate CAD methods for detecting breast and prostate cancer on ultrasound and high-resolution MRI that in some instances are able to out-perform expert radiologists. Current projects include:
- Detecting prostate cancer from high resolution MRI studies.
- Detection of prostate cancer from digitized histology and defining cancer signatures for automated grading of adenocarcinoma.
- Detection of breast cancer from ultrasound and distinguishing between lesions and posterior acoustic shadowing artifacts.
- Application of a local morphometric scale notion called generalized scale (g-scale) for correcting for various MR related image artifacts.
- Use of non-linear dimensionality reduction methods such as graph embedding to detect novel tissue classes, such as pre-cancerous lesions.
- Improving classification accuracy of CAD systems by identifying mislabeled training instances and developing more sophisticated classifiers.
|
Associate Professor Pathology
University of Pennsylvania School Medicine
Assistant Dean for IT, Academic Programs
Medical Director, Pathology Informatics
Director, Tumor Tissue and Biospecimen bank (TTAB)
|
|
My professional interests revolve around the development, integration and adoption of information technologies in the discipline of Pathology. One of my main areas of interest within this broad discipline has been in the field of digital imaging. We have been exploring pathology imaging on several fronts including interactions between pathology/radiology (High resolution MRI imaging of prostate cancer), development and utilization of computer assisted diagnostic algorithms for machine vision in prostate and breast cancer (Collaboration with Dr. Anant Madabushi, Rutgers) and automated immunohistochemical scoring of TMA (Collaboration with Dr. David Foran at UMDNJ). Our newest area of investigation is the use of multispectral imaging for the analysis of multicolor immunohistochemistry and immunoflourescence and the development of a quantitative system for scoring and analyzing at a cytometric level, multicolor immunostaining on surgical pathology slides.
Nasir Rajpoot is an Associate Professor in Computer Science at the University of Warwick, United Kingdom. He joined the Computer Science department as a Lecturer in 2001, after completing his PhD in image coding at Warwick. He was a visiting postgraduate research fellow at the Applied Mathematics programme of Yale University during 1998-2000. Dr Rajpoot has published over 50 refereed articles in the areas of image coding and denoising, texture analysis, shape analysis, and histology image analysis. He is on the review panels of more than a dozen international journals and on the Programme Committee of a number of international conferences. He was co-chair of the special focus session titled Computational Histopathology: Advances and New Challenges at ISBI 2008 earlier this year. Dr Rajpoot was the technical chair of British Machine Vision Conference (BMVC), held at Warwick in September 2007. His current research interests lie in the areas of efficient image representations and computational histopathology.
