Brian P. Harrawood

Evaluation of information-theoretic similarity measures for content-based retrieval and detection of masses in mammograms

The purpose of this study was to evaluate image similarity measures employed in an information-theoretic computer-assisted detection (IT-CAD) scheme. The scheme was developed for content-based retrieval and detection of masses in screening mammograms. The study is aimed toward an interactive clinical paradigm where physicians query the proposed IT-CAD scheme on mammographic locations that are either visually suspicious or indicated as suspicious by other cuing CAD systems. The IT-CAD scheme provides an evidence-based, second opinion for query mammographic locations using a knowledge database of mass and normal cases. In this study, eight entropy-based similarity measures were compared with respect to retrieval precision and detection accuracy using a database of 1820 mammographic regions of interest. The IT-CAD scheme was then validated on a separate database for false positive reduction of progressively more challenging visual cues generated by an existing, in-house mass detection system. The study showed that the image similarity measures fall into one of two categories; one category is better suited to the retrieval of semantically similar cases while the second is more effective with knowledge-based decisions regarding the presence of a true mass in the query location. In addition, the IT-CAD scheme yielded a substantial reduction in false-positive detections while maintaining high detection rate for malignant masses.

Introduction to neutron stimulated emission computed tomography

Neutron stimulated emission computed tomography (NSECT) is presented as a new technique for in vivo tomographic spectroscopic imaging. A full implementation of NSECT is intended to provide an elemental spectrum of the body or part of the body being interrogated at each voxel of a three-dimensional computed tomographic image. An external neutron beam illuminates the sample and some of these neutrons scatter inelastically, producing characteristic gamma emission from the scattering nuclei. These characteristic gamma rays are acquired by a gamma spectrometer and the emitting nucleus is identified by the emitted gamma energy. The neutron beam is scanned over the body in a geometry that allows for tomographic reconstruction. Tomographic images of each element in the spectrum can be reconstructed to represent the spatial distribution of elements within the sample. Here we offer proof of concept for the NSECT method, present the first single projection spectra acquired from multi-element phantoms, and discuss potential biomedical applications.

Information-theoretic CAD system in mammography: entropy-based indexing for computational efficiency and robust performance.

We have previously presented a knowledge-based computer-assisted detection (KB-CADe) system for the detection of mammographic masses. The system is designed to compare a query mammographic region with mammographic templates of known ground truth. The templates are stored in an adaptive knowledge database. Image similarity is assessed with information theoretic measures (e.g., mutual information) derived directly from the image histograms. A previous study suggested that the diagnostic performance of the system steadily improves as the knowledge database is initially enriched with more templates. However, as the database increases in size, an exhaustive comparison of the query case with each stored template becomes computationally burdensome. Furthermore, blind storing of new templates may result in redundancies that do not necessarily improve diagnostic performance. To address these concerns we investigated an entropy-based indexing scheme for improving the speed of analysis and for satisfying database storage restrictions without compromising the overall diagnostic performance of our KB-CADe system. The indexing scheme was evaluated on two different datasets as (i) a search mechanism to sort through the knowledge database, and (ii) a selection mechanism to build a smaller, concise knowledge database that is easier to maintain but still effective. There were two important findings in the study. First, entropy-based indexing is an effective strategy to identify fast a subset of templates that are most relevant to a given query. Only this subset could be analyzed in more detail using mutual information for optimized decision making regarding the query. Second, a selective entropy-based deposit strategy may be preferable where only high entropy cases are maintained in the knowledge database. Overall, the proposed entropy-based indexing scheme was shown to reduce the computational cost of our KB-CADe system by 55% to 80% while maintaining the systems diagnostic performance.

Neutron Stimulated Emission Computed Tomography for Diagnosis of Breast Cancer

Neutron stimulated emission computed tomography (NSECT) is being developed as a non-invasive spectroscopic imaging technique to determine element concentrations in the human body. NSECT uses a beam of fast neutrons that scatter inelastically from atomic nuclei in tissue, causing them to emit characteristic gamma photons that are detected and identified using an energy-sensitive gamma detector. By measuring the energy and number of emitted gamma photons, the system can determine the elemental composition of the target tissue. Such determination is useful in detecting several disorders in the human body that are characterized by changes in element concentration, such as breast cancer. In this paper we describe our experimental implementation of a prototype NSECT system for the diagnosis of breast cancer and present experimental results from sensitivity studies using this prototype. Results are shown from three sets of samples: (a) excised breast tissue samples with unknown element concentrations, (b) a multi-element calibration sample used for sensitivity studies, and (c) a small-animal specimen, to demonstrate detection ability from in-vivo tissue. Preliminary results show that NSECT has the potential to detect elements in breast tissue. Several elements were identified common to both benign and malignant samples, which were confirmed through neutron activation analysis (NAA). Statistically significant differences were seen for peaks at energies corresponding to 37Cl, 56Fe, 58Ni, 59Co, 79Br and 87Rb. The spectrum from the small animal specimen showed the presence of 12C from tissue, from bone, and elements 39K, 27Al, 37Cl, 56Fe, 68Zn and 25Mg. Threshold sensitivity for the four elements analyzed was found to range from 0.3 grams to 1 gram, which is higher than the microgram sensitivity required for cancer detection. Patient dose levels from NSECT were found to be comparable to those of screening mammography.

Breast cancer detection using neutron stimulated emission computed tomography: prominent elements and dose requirements.

Neutron stimulated emission computed tomography (NSECT) is being developed to noninvasively determine concentrations of trace elements in biological tissue. Studies have shown prominent differences in the trace element concentration of normal and malignant breast tissue. NSECT has the potential to detect these differences and diagnose malignancy with high accuracy with dose comparable to that of a single mammogram. In this study, NSECT imaging was simulated for normal and malignant human breast tissue samples to determine the significance of individual elements in determining malignancy. The normal and malignant models were designed with different elemental compositions, and each was scanned spectroscopically using a simulated 2.5 MeV neutron beam. The number of incident neutrons was varied from 0.5 million to 10 million neutrons. The resulting gamma spectra were evaluated through receiver operating characteristic (ROC) analysis to determine which trace elements were prominent enough to be considered markers for breast cancer detection. Four elemental isotopes (133Cs, 81Br, 79Br, and 87Rb) at five energy levels were shown to be promising features for breast cancer detection with an area under the ROC curve (A(Z)) above 0.85. One of these elements--87Rb at 1338 keV--achieved perfect classification at 10 million incident neutrons and could be detected with as low as 3 million incident neutrons. Patient dose was calculated for each gamma spectrum obtained and was found to range from between 0.05 and 0.112 mSv depending on the number of neutrons. This simulation demonstrates that NSECT has the potential to noninvasively detect breast cancer through five prominent trace element energy levels, at dose levels comparable to other breast cancer screening techniques.

EVALUATING THE EFFECT OF IMAGE PREPROCESSING ON AN INFORMATION-THEORETIC CAD SYSTEM IN MAMMOGRAPHY

RATIONALE AND OBJECTIVES In our earlier studies, we reported an evidence-based computer-assisted decision (CAD) system for location-specific interrogation of mammograms. A content-based image retrieval framework with information theoretic (IT) similarity measures serves as the foundation for this system. Specifically, the normalized mutual information (NMI) was shown to be the most effective similarity measure for reduction of false-positive marks generated by other prescreening mass detection schemes. The objective of this work was to investigate the importance of image filtering as a possible preprocessing step in our IT-CAD system. MATERIALS AND METHODS Different filters were applied, each one aiming to compensate for known limitations of the NMI similarity measure. The study was based on a region-of-interest database that included true masses and false-positive regions from digitized mammograms. RESULTS Receiver-operating characteristics (ROC) analysis showed that IT-CAD is affected slightly by image filtering. Modest, yet statistically significant, performance gain was observed with median filtering (overall ROC area index A(z) improved from 0.78 to 0.82). However, Gabor filtering improved performance for the high-sensitivity portion of the ROC curve where a typical false-positive reduction scheme should operate (partial ROC area index (0.90)A(z) improved from 0.33 to 0.37). Fusion of IT-CAD decisions from different filtering schemes markedly improved performance (A(z) = 0.90 and (0.90)A(z) = 0.55). At 95% sensitivity, the systems specificity improved by 36.6%. CONCLUSIONS Additional improvement in false-positive reduction can be achieved by incorporating image filtering as a preprocessing step in our IT-CAD system.

Neutron stimulated emission computed tomography: a Monte Carlo simulation approach

A Monte Carlo simulation has been developed for neutron stimulated emission computed tomography (NSECT) using the GEANT4 toolkit. NSECT is a new approach to biomedical imaging that allows spectral analysis of the elements present within the sample. In NSECT, a beam of high-energy neutrons interrogates a sample and the nuclei in the sample are stimulated to an excited state by inelastic scattering of the neutrons. The characteristic gammas emitted by the excited nuclei are captured in a spectrometer to form multi-energy spectra. Currently, a tomographic image is formed using a collimated neutron beam to define the line integral paths for the tomographic projections. These projection data are reconstructed to form a representation of the distribution of individual elements in the sample. To facilitate the development of this technique, a Monte Carlo simulation model has been constructed from the GEANT4 toolkit. This simulation includes modeling of the neutron beam source and collimation, the samples, the neutron interactions within the samples, the emission of characteristic gammas, and the detection of these gammas in a Germanium crystal. In addition, the model allows the absorbed radiation dose to be calculated for internal components of the sample. NSECT presents challenges not typically addressed in Monte Carlo modeling of high-energy physics applications. In order to address issues critical to the clinical development of NSECT, this paper will describe the GEANT4 simulation environment and three separate simulations performed to accomplish three specific aims. First, comparison of a simulation to a tomographic experiment will verify the accuracy of both the gamma energy spectra produced and the positioning of the beam relative to the sample. Second, parametric analysis of simulations performed with different user-defined variables will determine the best way to effectively model low energy neutrons in tissue, which is a concern with the high hydrogen content in biological tissue. Third, determination of the energy absorbed in tissue during neutron interrogation in order to estimate the dose. Results from these three simulation experiments demonstrate that GEANT4 is an effective simulation platform that can be used to facilitate the future development and optimization of NSECT.

Neutron Stimulated Emission Computed Tomography of Stable Isotopes

Here we report on the development of a new molecular imaging technique using inelastic scattering of fast neutrons. Earlier studies demonstrated a significant difference in trace element concentrations between benign and malignant tissue for several cancers including breast, lung, and colon. Unfortunately, the measurement techniques were not compatible with living organisms and this discovery did not translate into diagnostic techniques. Recently we have developed a tomographic approach to measuring the trace element concentrations using neutrons to stimulate characteristic gamma emission from atomic nuclei in the body. Spatial projections of the emitted energy spectra allow tomographic image reconstruction of the elemental concentrations. In preliminary experiments, spectra have been acquired using a 7.5MeV neutron beam incident on several multi-element phantoms. These experiments demonstrate our ability to determine the presence of Oxygen, Carbon, Copper, Iron, and Calcium. We describe the experimental technique and present acquired spectra.

Design and Development of a High-Energy Gamma Camera for Use With NSECT Imaging: Feasibility for Breast Imaging

A new spectroscopic imaging technique, neutron stimulated emission computed tomography (NSECT), is currently being developed to non-invasively and non-destructively measure and image elemental concentrations within the body. NSECT has potential for use in breast imaging as several studies have shown a link between elemental concentration and tumor status. In NSECT, a region of interest is illuminated with a high-energy (3-5 MeV) beam of neutrons that scatter inelastically with elemental nuclei within the body. The characteristic gamma rays that are emitted as the excited nuclei relax allow the identification of elements and the formation of elemental composition images. This imaging technique requires high-resolution and high-energy gamma spectroscopy; thereby eliminating current scintillation crystal based position sensitive gamma cameras. Instead, we propose to adapt high-energy gamma imaging techniques used in space-based imaging. A high purity germanium (HPGe) detector provides high-resolution energy spectra while a rotating modulation collimator (RMC) placed in front of the detector modulates the incoming signal to provide spatial information. Counting the number of gamma events at each collimator rotation angle allows for reconstruction of images. Herein we report on the design and testing of a prototype RMC, a Monte Carlo simulation of this camera, and the use of this simulation tool to access the feasibility of imaging a breast with such a camera. The prototype RMC was tested with a 22Na point source and verified that the RMC modulates the gamma rays in a predictable manner. The Monte Carlo simulation accurately modeled this behavior. Other simulations were used to accurately reconstruct images of a point source located within a 10 cm cube, suggesting NSECTs potential as a breast imaging method.

Neutron-stimulated emission computed tomography of a multi-element phantom

This paper describes the implementation of neutron-stimulated emission computed tomography (NSECT) for non-invasive imaging and reconstruction of a multi-element phantom. The experimental apparatus and process for acquisition of multi-spectral projection data are described along with the reconstruction algorithm and images of the two elements in the phantom. Independent tomographic reconstruction of each element of the multi-element phantom was performed successfully. This reconstruction result is the first of its kind and provides encouraging proof of concept for proposed subsequent spectroscopic tomography of biological samples using NSECT.