My research focuses on the development and novel application of computer vision and computational intelligence algorithms for medical image analysis content-based image retrieval, medical decision making, and effective clinical integration of computer aids.  Specifically, there are five ongoing studies:

1.Information-Theoretic CAD System in Mammography: Computer-assisted diagnosis is an active field of research with several commercial CAD products available for the detection of breast cancer in screening mammograms. The available products are used as “black-boxes” to provide radiologists with a second opinion regarding the presence of potential abnormalities in the breast images.  However, the currently used “black-box” CAD paradigm is rather limited.  A CAD system that is more interactive and capable of justifying the oinions it provides may help radiologists’ cognitive process more effectively.  Moreover, as clinical image libraries grow rapidly in Radiology, contemporary CAD systems should be able to capitalize on accumulating image data without requiring painstaking retraining or recalibration.  We have been developing an interactive, knowledge-based CAD system that relies on content-based image retrieval and information theoretic principles. The system is designed to provide evidence-based decision support regarding the presence of potential abnormalities in a query mammogram by comparing the unknown query case with known cases stored in a knowledge database.  The main advantage of the system is its ability to capitalize on an adaptive knowledge database where new mammographic cases can be continuously deposited without disrupting the system’s operation.  Thus far, our laboratory studies have shown competitive detection performance, ability to transfer knowledge across image databases, and multiplatform adaptability (i.e., robust performance in screen-film mammograms, digital mammograms, and breast tomosynthesis data).

2.Building and Mining Knowledge Databases of Imaging Data in Radiology:  Although knowledge-based systems are adaptive and flexible, their clinical application in Radiology is often restricted due to the computational demands of maintaining and querying a continuously growing databank of radiologic images. To address this concern, we have been exploring indexing schemes for improving the speed of analysis without compromising the diagnostic performance of the knowledge-based system.   The indexing schemes are investigated in two different capacities (i) as the basis of search mechanisms to sift fast through the knowledge database, and (ii) as the basis of a selection mechanisms to build a concise knowledge database that is still effective but easier to maintain.  Initial results with an entropy-based indexing scheme for our mammography CAD system are extremely encouraging suggesting a 75% reduction in computational demands without any compromise in diagnostic performance.

3.Reliability Analysis of CAD Technology:The development of a CAD system involves careful optimization so that the diagnostic performance of the system is maximized for the target patient population. When the system is deployed for clinical use, the radiologist is informed about the system’s expected diagnostic yield.  However, the diagnostic yield may vary substantially from case to case due to the variable complexity of each case. Thus, the radiologists are left unguided as to how to integrate the CAD opinion in their decision making process on a per case basis.  We have been developing a robust computational technique that enables a CAD system to affirm its user when it offers a highly reliable opinion and alert him/her when a questionable opinion is offered.  Thus, the technique is a mechanism for risk stratification for CAD technology. The proposed technique monitors the system’s accuracy in a dynamically selected sample of known cases, similar to the one in question.  If the accuracy measured on the selected sample is significantly lower or higher than what expected on average, the CAD system will inform its user accordingly.  The long-term goal of this research is to improve the human-computer communication.  We are working towards this goal by developing an effective and generalizable mechanism for patient-specific customization of CAD technology to improve the efficacy of computerized decision aids in Radiology.

4.Advanced Computational Intelligence Techniques for CAD Optimization:  We are currently pursuing advanced computational intelligence methods such as genetic algorithms and particle swarm optimization for multiobjective optimization of our CAD systems using clinically relevant objective functions.

5.Neutron Imaging: This represents a new form of biomedical imaging in which 3D tomographic images are formed of individual stable isotopes in the subject by illuminating the body with neutrons and collecting the characteristic emitted gamma rays in a tomographic geometry. This research is conducted in collaboration with Triangle Universities Nuclear Laboratory.

Habas PA, Zurada JM, Elmaghraby AS, Tourassi GD. Reliability analysis framework for computer-assisted medical decision systems. Med Phys. 2007 Feb;34(2):763-72. Abstract

Tourassi GD, Harrawood B, Singh S, Lo JY, Floyd CE. Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms. Med Phys. 2007 Jan;34(1):140-50. Abstract

Floyd CE Jr, Bender JE, Sharma AC, Kapadia A, Xia J, Harrawood B, Tourassi GD, Lo JY, Crowell A, Howell C. Introduction to neutron stimulated emission computed tomography. Phys Med Biol. 2006 Jul 21;51(14):3375-90. Abstract

Markey MK, Tourassi GD, Margolis M, DeLong DM. Impact of missing data in evaluating artificial neural networks trained on complete data. Comput Biol Med. 2006 May;36(5):516-25. Abstract

McAdams HP, Samei E, Dobbins J 3rd, Tourassi GD, Ravin CE. Recent advances in chest radiography. Radiology. 2006 Dec;241(3):663-83. Abstract

Tourassi GD, Delong DM, Floyd CE Jr. A study on the computerized fractal analysis of architectural distortion in screening mammograms. Phys Med Biol. 2006 Mar 7;51(5):1299-312. Abstract

Tourassi GD, Eltonsy NH, Graham J, Floyd CE, Elmaghraby AS. Feature and knowledge based analysis for reduction of false positives in the computerized detection of masses in screening mammography. Conf Proc IEEE Eng Med Biol Soc. 2005;6:6524-7. Abstract

Markey MK, Lo JY, Tourassi GD, Floyd CE Jr. Self-organizing map for cluster analysis of a breast cancer database.  Artif Intell Med.  2003 Feb;27(2):113-27. Abstract

Markey MK, Tourassi GD, Floyd CE Jr. Decision tree classification of proteins identified by mass spectrometry of blood serum samples from people with and without lung cancer.  Proteomics.  2003 Sep;3(9):1678-9. Abstract

Tourassi GD, Vargas-Voracek R, Catarious DM Jr, Floyd CE Jr. Computer-assisted detection of mammographic masses: a template matching scheme based on mutual information.  Med Phys.  2003 Aug;30(8):2123-30. Abstract

Markey MK, Lo JY, Vargas-Voracek R, Tourassi GD, Floyd CE Jr. Perceptron error surface analysis: a case study in breast cancer diagnosis. Comput Biol Med. 2002 Mar;32(2):99-109. Abstract

Tourassi GD, Frederick ED, Floyd CE Jr, Coleman RE. Multifractal texture analysis of perfusion lung scans as a potential diagnostic tool for acute pulmonary embolism. Comput Biol Med. 2001 Jan;31(1):15-25. Abstract

Tourassi GD, Frederick ED, Markey MK, Floyd CE Jr. Application of the mutual information criterion for feature selection in computer-aided diagnosis. Med Phys. 2001 Dec;28(12):2394-402. Abstract

Tourassi GD, Markey MK, Lo JY, Floyd CE Jr. A neural network approach to breast cancer diagnosis as a constraint satisfaction problem. Med Phys. 2001 May;28(5):804-11. Abstract

Floyd CE Jr, Lo JY, Tourassi GD. Case-based reasoning computer algorithm that uses mammographic findings for breast biopsy decisions. AJR Am J Roentgenol. 2000 Nov;175(5):1347-52. Abstract

Tourassi GD, Frederick ED, Vittitoe NF, Coleman RE. Fractal texture analysis of perfusion lung scans. Comput Biomed Res. 2000 Jun;33(3):161-71. Abstract

Tourassi GD. Journey toward computer-aided diagnosis: role of image texture analysis. Radiology. 1999 Nov;213(2):317-20. Abstract

Tourassi GD, Floyd CE, Coleman RE. Acute pulmonary embolism: cost-effectiveness analysis of the effect of artificial neural networks on patient care. Radiology. 1998 Jan;206(1):81-8. Abstract

Tourassi GD, Floyd CE, Coleman RE. Improved noninvasive diagnosis of acute pulmonary embolism with optimally selected clinical and chest radiographic findings. Acad Radiol. 1996 Dec;3(12):1012-8. Abstract

Tourassi GD, Floyd CE. The effect of data sampling on the performance evaluation of artificial neural networks in medical diagnosis. Med Decis Making. ;17(2):186-92. Abstract

Tourassi GD, Floyd CE Jr. Lesion size quantification in SPECT using an artificial neural network classification approach. Comput Biomed Res. 1995 Jun;28(3):257-70. Abstract

Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Artificial neural network for diagnosis of acute pulmonary embolism: effect of case and observer selection. Radiology. 1995 Mar;194(3):889-93. Abstract

Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Artificial neural network for diagnosis of acute pulmonary embolism: effect of case and observer selection. Radiology. 1995 Mar;194(3):889-93. Abstract

Tourassi GD, Floyd CE Jr. Artificial neural networks for single photon emission computed tomography. A study of cold lesion detection and localization. Invest Radiol. 1993 Aug;28(8):671-7. Abstract

Tourassi GD, Floyd CE Jr. Artificial neural networks for single photon emission computed tomography. A study of cold lesion detection and localization. Invest Radiol. 1993 Aug;28(8):671-7. Abstract

Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Acute pulmonary embolism: artificial neural network approach for diagnosis. Radiology. 1993 Nov;189(2):555-8. Abstract

Tourassi GD, Floyd CE, Sostman HD, Coleman RE. Acute pulmonary embolism: artificial neural network approach for diagnosis. Radiology. 1993 Nov;189(2):555-8. Abstract

Floyd CE Jr, Tourassi GD. An artificial neural network for lesion detection on single-photon emission computed tomographic images. Invest Radiol. 1992 Sep;27(9):667-72. Abstract