Virtual Lung Screening Trial (VLST): An In Silico Replica of the National Lung Screening Trial for Lung Cancer Detection.

Importance: Clinical imaging trials are crucial for definitive evaluation of medical innovations, but the process is inefficient, expensive, and ethically-constrained. Virtual imaging trial (VIT) approach address these limitations by emulating the components of a clinical trial. An in silico rendition of the National Lung Screening Trial (NCLS) via Virtual Lung Screening Trial (VLST) demonstrates the promise of VITs to expedite clinical trials, reduce risks to subjects, and facilitate the optimal use of imaging technologies in clinical settings. Objectives: To demonstrate that a virtual imaging trial platform can accurately emulate a major clinical trial, specifically the National Lung Screening Trial (NLST) that compared computed tomography (CT) and chest x-ray (CXR) imaging for lung cancer screening. Design Setting and Participants: A diverse virtual patient population of 294 subjects was created from human models (XCAT) emulating the characteristics of cases on NLST, with two types of simulated lung nodules. The cohort was assessed using simulated CT and CXR systems to generate images that reflect the NLST imaging technologies. Deep learning models trained for lesion detection in CXR and CT served as virtual readers. Main Outcomes and Measures: The primary outcome was the difference in the Receiver Operating Characteristic Area Under the Curve (AUC) for CT and CXR modalities. Lesion-level AUC was aggregated to report patient-level AUC. Results: The study analyzed 294 CT and CXR simulated images from 294 virtual patients, with a lesion-level AUC of 0.81 (95% CI: 0.79-0.84) for CT and 0.56 (95% CI: 0.54-0.58) for CXR. At the patient level, CT demonstrated an AUC of 0.84 (95% CI: 0.80-0.89), compared to 0.52 (95% CI: 0.45-0.58) for CXR. Subgroup analyses on CT results indicated superior detection of homogeneous lesions (lesion-level AUC 0.97) than heterogeneous lesions (lesion-level AUC 0.72). Performance was particularly high for identifying larger nodules (AUC of 0.98 for nodules > 8 mm). The VLST results closely mirrored the NLST, particularly in size-based detection trends, with CT achieving high AUCs for nodules ≥ 8 mm and similar challenges in detecting smaller nodules. Conclusion and Relevance: The VIT results closely replicated those of the earlier NLST, underscoring its potential to replicate real clinical imaging trials. Integration of virtual trials may aid in the evaluation and improvement of imaging-based diagnosis.

Myelography Using Energy-Integrating Detector CT Versus Photon-Counting Detector CT for Detection of CSF-Venous Fistulas in Patients With Spontaneous Intracranial Hypotension.

BACKGROUND. CSF-venous fistulas (CVFs), which are an increasingly recognized cause of spontaneous intracranial hypotension (SIH), are often diminutive in size and exceedingly difficult to detect by conventional imaging. OBJECTIVE. This purpose of this study was to compare energy-integrating detector (EID) CT myelography and photon-counting detector (PCD) CT myelography in terms of image quality and diagnostic performance for detecting CVFs in patients with SIH. METHODS. This retrospective study included 38 patients (15 men and 23 women; mean age, 55 ± 10 [SD] years) with SIH who underwent both clinically indicated EID CT myelography (slice thickness, 0.625 mm) and PCD CT myelography (slice thickness, 0.2 mm; performed in ultrahigh-resolution mode) to assess for CSF leak. Three blinded radiologists reviewed examinations in random order, assessing image noise, discernibility of spinal nerve root sleeves, and overall image quality (each assessed using a scale of 0-100, with 100 denoting highest quality) and recording locations of the CVFs. Definite CVFs were defined as CVFs described in CT myelography reports using unequivocal language and having an attenuation value greater than 70 HU. RESULTS. For all readers, PCD CT myelography, in comparison with EID CT myelography, showed higher mean image noise (reader 1: 69.9 ± 18.5 [SD] vs 37.6 ± 15.2; reader 2: 59.5 ± 8.7 vs 49.3 ± 12.7; and reader 3: 57.6 ± 13.2 vs 42.1 ± 16.6), higher mean nerve root sleeve discernibility (reader 1: 81.6 ± 21.7 [SD] vs 30.4 ± 13.6; reader 2: 83.6 ± 10 vs 70.1 ± 18.9; and reader 3: 59.6 ± 13.5 vs 50.5 ± 14.4), and higher mean overall image quality (reader 1: 83.2 ± 20.0 [SD] vs 38.1 ± 13.5; reader 2: 80.1 ± 10.1 vs 72.4 ± 19.8; and reader 3: 57.8 ± 11.2 vs 51.9 ± 13.6) (all p < .05). Eleven patients had a definite CVF. Sensitivity and specificity of EID CT myelography and PCD CT myelography for the detection of definite CVF were 45% and 96% versus 64% and 85%, respectively, for reader 1; 36% and 100% versus 55% and 96%, respectively, for reader 2; and 57% and 100% versus 55% and 93%, respectively, for reader 3. The sensitivity was significantly higher for PCD CT myelography than for EID CT myelography for reader 1 and reader 2 (both p < .05) and was not significantly different between the two techniques for reader 3 (p = .45); for all three readers, specificity was not significantly different between the two modalities (all p > .05). CONCLUSION. In comparison with EID CT myelography, PCD CT myelography yielded significantly improved image quality with significantly higher sensitivity for CVFs (for two of three readers), without significant loss of specificity. CLINICAL IMPACT. The findings support a potential role for PCD CT myelography in facilitating earlier diagnosis and targeted treatment of SIH, avoiding high morbidity during potentially prolonged diagnostic workups.

Is it possible to use low-dose deep learning reconstruction for the detection of liver metastases on CT routinely?

OBJECTIVES: To compare the image quality and hepatic metastasis detection of low-dose deep learning image reconstruction (DLIR) with full-dose filtered back projection (FBP)/iterative reconstruction (IR). METHODS: A contrast-detail phantom consisting of low-contrast objects was scanned at five CT dose index levels (10, 6, 3, 2, and 1 mGy). A total of 154 participants with 305 hepatic lesions who underwent abdominal CT were enrolled in a prospective non-inferiority trial with a three-arm design based on phantom results. Data sets with full dosage (13.6 mGy) and low dosages (9.5, 6.8, or 4.1 mGy) were acquired from two consecutive portal venous acquisitions, respectively. All images were reconstructed with FBP (reference), IR (control), and DLIR (test). Eleven readers evaluated phantom data sets for object detectability using a two-alternative forced-choice approach. Non-inferiority analyses were performed to interpret the differences in image quality and metastasis detection of low-dose DLIR relative to full-dose FBP/IR. RESULTS: The phantom experiment showed the dose reduction potential from DLIR was up to 57% based on the reference FBP dose index. Radiation decreases of 30% and 50% resulted in non-inferior image quality and hepatic metastasis detection with DLIR compared to full-dose FBP/IR. Radiation reduction of 70% by DLIR performed inferiorly in detecting small metastases (< 1 cm) compared to full-dose FBP (difference: -0.112; 95% confidence interval [CI]: -0.178 to 0.047) and full-dose IR (difference: -0.123; 95% CI: -0.182 to 0.053) (p < 0.001). CONCLUSION: DLIR enables a 50% dose reduction for detecting low-contrast hepatic metastases while maintaining comparable image quality to full-dose FBP and IR. KEY POINTS: • Non-inferiority study showed that deep learning image reconstruction (DLIR) can reduce the dose to oncological patients with low-contrast lesions without compromising the diagnostic information. • Radiation dose levels for DLIR can be reduced to 50% of full-dose FBP and IR for detecting low-contrast hepatic metastases, while maintaining comparable image quality. • The reduction of radiation by 70% by DLIR is clinically acceptable but insufficient for detecting small low-contrast hepatic metastases (< 1 cm).

Development and Clinical Applications of a Virtual Imaging Framework for Optimizing Photon-counting CT.

The purpose of this study was to develop a virtual imaging framework that simulates a new photon-counting CT (PCCT) system (NAEOTOM Alpha, Siemens). The PCCT simulator was built upon the DukeSim platform, which generates projection images of computational phantoms given the geometry and physics of the scanner and imaging parameters. DukeSim was adapted to account for the geometry of the PCCT prototype. To model the photon-counting detection process, we utilized a Monte Carlo-based detector model with the known properties of the detectors. We validated the simulation platform against experimental measurements. The images were acquired at four dose levels (CTDIvol of 1.5, 3.0, 6.0, and 12.0 mGy) and reconstructed with three kernels (Br36, Br40, Br48). The experimental acquisitions were replicated using our developed simulation platform. The real and simulated images were quantitatively compared in terms of image quality metrics (HU values, noise magnitude, noise power spectrum, and modulation transfer function). The clinical utility of our framework was demonstrated by conducting two clinical applications (COPD quantifications and lung nodule radiomics). The phantoms with relevant pathologies were imaged with DukeSim modeling the PCCT systems. Different imaging parameters (e.g., dose, reconstruction techniques, pixel size, and slice thickness) were altered to investigate their effects on task-based quantifications. We successfully implemented the acquisition and physics attributes of the PCCT prototype into the DukeSim platform. The discrepancy between the real and simulated data was on average about 2 HU in terms of noise magnitude, 0.002 mm-1 in terms of noise power spectrum peak frequency and 0.005 mm-1 in terms of the frequency at 50% MTF. Analysis suggested that lung lesion radiomics to be more accurate with reduced pixel size and slice thickness. For COPD quantifications, higher doses, thinner slices, and softer kernels yielded more accurate quantification of density-based biomarkers. Our developed virtual imaging platform enables systematic comparison of new PCCT technologies as well as optimization of the imaging parameters for specific clinical tasks.

A scanner-specific framework for simulating CT images with tube current modulation.

Although tube current modulation (TCM) is routinely implemented in modern computed tomography (CT) scans, no existing CT simulator is capable of generating realistic images with TCM. The goal of this study was to develop such a framework to (1) facilitate patient-specific optimization of TCM parameters and (2) enable future virtual imaging trials (VITs) with more clinically realistic image quality and x-ray flux distributions. The framework was created by developing a TCM module and integrating it with an existing CT simulator (DukeSim). The developed module utilizes scanner-calibrated TCM parameters and two localizer radiographs to compute the mAs for each simulated CT projection. This simulation pipeline was validated in two parts. First, DukeSim was validated in the context of a commercial scanner with TCM (SOMATOM Force, Siemens Healthineers) by imaging a physical CT phantom (Mercury, Sun Nuclear) and its computational analogue. Second, the TCM module was validated by imaging a computational anthropomorphic phantom (ATOM, CIRS) using DukeSim with real and module-generated TCM profiles. The validation demonstrated DukeSim's realism in terms of noise magnitude, noise texture, spatial resolution, and image contrast (with average differences of 0.38%, 6.31%, 0.43%, and -9 HU, respectively). It also demonstrated the TCM module's realism in terms of projection-level mAs and resulting noise magnitude (2.86% and -2.60%, respectively). Finally, the framework was applied to a pilot VIT simulating images of three computational anthropomorphic phantoms (XCAT, with body mass indices (BMIs) of 24.3, 28.2, and 33.0) under five different TCM settings. The optimal TCM for each phantom was characterized based on various criteria, such as minimizing mAs or maximizing image quality. 'Very Weak' TCM minimized noise for the 24.3 BMI phantom, while 'Very Strong' TCM minimized noise for the 33.0 BMI phantom. This illustrates the utility of the developed framework for future optimization studies of TCM parameters and, more broadly, large-scale VITs with scanner-specific TCM.

Virtual clinical trial for quantifying the effects of beam collimation and pitch on image quality in computed tomography.

Purpose: To utilize a virtual clinical trial (VCT) construct to investigate the effects of beam collimation and pitch on image quality (IQ) in computed tomography (CT) under different respiratory and cardiac motion rates. Approach: A computational human model [extended cardiac-torso (XCAT) phantom] with added lung lesions was used to simulate seven different rates of cardiac and respiratory motions. A validated CT simulator (DukeSim) was used in this study. A supplemental validation was done to ensure the accuracy of DukeSim across different pitches and beam collimations. Each XCAT phantom was imaged using the CT simulator at multiple pitches (0.5 to 1.5) and beam collimations (19.2 to 57.6 mm) at a constant dose level. The images were compared against the ground truth using three task-generic IQ metrics in the lungs. Additionally, the bias and variability in radiomics (morphological) feature measurements were quantified for task-specific lung lesion quantification across the studied imaging conditions. Results: All task-generic metrics degraded by 1.6% to 13.3% with increasing pitch. When imaged with motion, increasing pitch reduced motion artifacts. The IQ slightly degraded (1.3%) with changes in the studied beam collimations. Patient motion exhibited negative effects (within 7%) on the IQ. Among all features across all imaging conditions studies, compactness2 and elongation showed the largest ( - 26.5 % , 7.8%) and smallest ( - 0.8 % , 2.7%) relative bias and variability. The radiomics results were robust across the motion profiles studied. Conclusions: While high pitch and large beam collimations can negatively affect the quality of CT images, they are desirable for fast imaging. Further, our results showed no major adverse effects in morphology quantification of lung lesions with the increase in pitch or beam collimation. VCTs, such as the one demonstrated in this study, represent a viable methodology for experiments in CT.

Influence of background lung characteristics on nodule detection with computed tomography.

We sought to characterize local lung complexity in chest computed tomography (CT) and to characterize its impact on the detectability of pulmonary nodules. Forty volumetric chest CT scans were created by embedding between three and five simulated 5-mm lung nodules into one of three volumetric chest CT datasets. Thirteen radiologists evaluated 157 nodules, resulting in 2041 detection opportunities. Analyzing the substrate CT data prior to nodule insertion, 14 image features were measured within a region around each nodule location. A generalized linear mixed-effects statistical model was fit to the data to verify the contribution of each metric on detectability. The model was tuned for simplicity, interpretability, and generalizability using stepwise regression applied to the primary features and their interactions. We found that variables corresponding to each of five categories (local structural distractors, local intensity, global context, local vascularity, and contiguity with structural distractors) were significant ( p < 0.01 ) factors in a standardized model. Moreover, reader-specific models conveyed significant differences among readers with significant distraction (missed detections) influenced by local intensity- versus local-structural characteristics being mutually exclusive. Readers with significant local intensity distraction ( n = 10 ) detected substantially fewer lung nodules than those who were significantly distracted by local structure ( n = 2 ), 46.1% versus 65.3% mean nodules detected, respectively.

Modeling "Textured" Bones in Virtual Human Phantoms.

The purpose of this study was to develop detailed and realistic models of the cortical and trabecular bones in the spine, ribs, and sternum and incorporate them into the library of virtual human phantoms (XCAT). Cortical bone was modeled by 3D morphological erosion of XCAT homogenously defined bones with an average thickness measured from the CT dataset upon which each individual XCAT phantom was based. The trabecular texture was modeled using a power law synthesis algorithm where the parameters were tuned using high-resolution anatomical images of the Human Visible Female. The synthesized bone textures were added into the XCAT phantoms. To qualitatively evaluate the improved realism of the bone modeling, CT simulations of the XCAT phantoms were acquired with and without the textured bone modeling. The 3D power spectrum of the anatomical images exhibited a power law behavior (R2 = 0.84), as expected in fractal and porous textures. The proposed texture synthesis algorithm was able to synthesize textures emulating real anatomical images, with the simulated CT images with the prototyped bones were more realistic than those simulated with the original XCAT models. Incorporating intra-organ structures, the "textured" phantoms are envisioned to be used to conduct virtual clinical trials in the context of medical imaging in cases where the actual trials are infeasible due to the lack of ground truth, cost, or potential risks to the patients.

Development of a scanner-specific simulation framework for photon-counting computed tomography.

The aim of this study was to develop and validate a simulation platform that generates photon-counting CT images of voxelized phantoms with detailed modeling of manufacturer-specific components including the geometry and physics of the x-ray source, source filtrations, anti-scatter grids, and photon-counting detectors. The simulator generates projection images accounting for both primary and scattered photons using a computational phantom, scanner configuration, and imaging settings. Beam hardening artifacts are corrected using a spectrum and threshold dependent water correction algorithm. Physical and computational versions of a clinical phantom (ACR) were used for validation purposes. The physical phantom was imaged using a research prototype photon-counting CT (Siemens Healthcare) with standard (macro) mode, at four dose levels and with two energy thresholds. The computational phantom was imaged with the developed simulator with the same parameters and settings used in the actual acquisition. Images from both the real and simulated acquisitions were reconstructed using a reconstruction software (FreeCT). Primary image quality metrics such as noise magnitude, noise ratio, noise correlation coefficients, noise power spectrum, CT number, in-plane modulation transfer function, and slice sensitivity profiles were extracted from both real and simulated data and compared. The simulator was further evaluated for imaging contrast materials (bismuth, iodine, and gadolinium) at three concentration levels and six energy thresholds. Qualitatively, the simulated images showed similar appearance to the real ones. Quantitatively, the average relative error in image quality measurements were all less than 4% across all the measurements. The developed simulator will enable systematic optimization and evaluation of the emerging photon-counting computed tomography technology.

DukeSim: A Realistic, Rapid, and Scanner-Specific Simulation Framework in Computed Tomography.

The purpose of this study was to develop a CT simulation platform that is: 1) compatible with voxel-based computational phantoms; 2) capable of modeling the geometry and physics of commercial CT scanners; and 3) computationally efficient. Such a simulation platform is designed to enable the virtual evaluation and optimization of CT protocols and parameters for achieving a targeted image quality while reducing radiation dose. Given a voxelized computational phantom and a parameter file describing the desired scanner and protocol, the developed platform DukeSim calculates projection images using a combination of ray-tracing and Monte Carlo techniques. DukeSim includes detailed models for the detector quantum efficiency, quantum and electronic noise, detector crosstalk, subsampling of the detector and focal spot areas, focal spot wobbling, and the bowtie filter. DukeSim was accelerated using GPU computing. The platform was validated using physical and computational versions of a phantom (Mercury phantom). Clinical and simulated CT scans of the phantom were acquired at multiple dose levels using a commercial CT scanner (Somatom Definition Flash; Siemens Healthcare). The real and simulated images were compared in terms of image contrast, noise magnitude, noise texture, and spatial resolution. The relative error between the clinical and simulated images was less than 1.4%, 0.5%, 2.6%, and 3%, for image contrast, noise magnitude, noise texture, and spatial resolution, respectively, demonstrating the high realism of DukeSim. The runtime, dependent on the imaging task and the hardware, was approximately 2-3 minutes per rotation in our study using a computer with 4 GPUs. DukeSim, when combined with realistic human phantoms, provides the necessary toolset with which to perform large-scale and realistic virtual clinical trials in a patient and scanner-specific manner.

Local complexity metrics to quantify the effect of anatomical noise on detectability of lung nodules in chest CT imaging.

The purpose of this study is to (1) develop metrics to characterize the regional anatomical complexity of the lungs, and (2) relate these metrics with lung nodule detection in chest CT. A free-scrolling reader-study with virtually inserted nodules (13 radiologists × 157 total nodules = 2041 responses) is used to characterize human detection performance. Metrics of complexity based on the local density and orientation of distracting vasculature are developed for two-dimensional (2-D) and three-dimensional (3-D) considerations of the image volume. Assessed characteristics included the distribution of 2-D/3-D vessel structures of differing orientation (dubbed "2-D/3-D and dot-like/line-like distractor indices"), contiguity of inserted nodules with local vasculature, mean local gray-level surrounding each nodule, the proportion of lung voxels to total voxels in each section, and 3-D distance of each nodule from the trachea bifurcation. A generalized linear mixed-effects statistical model is used to determine the influence of each these metrics on nodule detectability. In order of decreasing effect size: 3-D line-like distractor index, 2-D line-like distractor index, 2-D dot-like distractor index, local mean gray-level, contiguity with 2-D dots, lung area, and contiguity with 3-D lines all significantly affect detectability ( P < 0.05 ). These data demonstrate that local lung complexity degrades detection of lung nodules.

Report of AAPM Task Group 162: Software for planar image quality metrology.

PURPOSE: The AAPM Task Group 162 aimed to provide a standardized approach for the assessment of image quality in planar imaging systems. This report offers a description of the approach as well as the details of the resultant software bundle to measure detective quantum efficiency (DQE) as well as its basis components and derivatives. METHODS: The methodology and the associated software include the characterization of the noise power spectrum (NPS) from planar images acquired under specific acquisition conditions, modulation transfer function (MTF) using an edge test object, the DQE, and effective DQE (eDQE). First, a methodological framework is provided to highlight the theoretical basis of the work. Then, a step-by-step guide is included to assist in proper execution of each component of the code. Lastly, an evaluation of the method is included to validate its accuracy against model-based and experimental data. RESULTS: The code was built using a Macintosh OSX operating system. The software package contains all the source codes to permit an experienced user to build the suite on a Linux or other *nix type system. The package further includes manuals and sample images and scripts to demonstrate use of the software for new users. The results of the code are in close alignment with theoretical expectations and published results of experimental data. CONCLUSIONS: The methodology and the software package offered in AAPM TG162 can be used as baseline for characterization of inherent image quality attributes of planar imaging systems.

Volumetric x-ray coherent scatter imaging of cancer in resected breast tissue: a Monte Carlo study using virtual anthropomorphic phantoms.

Breast cancer patients undergoing surgery often choose to have a breast conserving surgery (BCS) instead of mastectomy for removal of only the breast tumor. If post-surgical analysis such as histological assessment of the resected tumor reveals insufficient healthy tissue margins around the cancerous tumor, the patient must undergo another surgery to remove the missed tumor tissue. Such re-excisions are reported to occur in 20%-70% of BCS patients. A real-time surgical margin assessment technique that is fast and consistently accurate could greatly reduce the number of re-excisions performed in BCS. We describe here a tumor margin assessment method based on x-ray coherent scatter computed tomography (CSCT) imaging and demonstrate its utility in surgical margin assessment using Monte Carlo simulations. A CSCT system was simulated in GEANT4 and used to simulate two virtual anthropomorphic CSCT scans of phantoms resembling surgically resected tissue. The resulting images were volume-rendered and found to distinguish cancerous tumors embedded in complex distributions of adipose and fibroglandular breast tissue (as is expected in the breast). The images exhibited sufficient spatial and spectral (i.e. momentum transfer) resolution to classify the tissue in any given voxel as healthy or cancerous. ROC analysis of the classification accuracy revealed an area under the curve of up to 0.97. These results indicate that coherent scatter imaging is promising as a possible fast and accurate surgical margin assessment technique.

Characterizing search, recognition, and decision in the detection of lung nodules on CT scans: elucidation with eye tracking.

PURPOSE: To determine the effectiveness of radiologists' search, recognition, and acceptance of lung nodules on computed tomographic (CT) images by using eye tracking. MATERIALS AND METHODS: This study was performed with a protocol approved by the institutional review board. All study subjects provided informed consent, and all private health information was protected in accordance with HIPAA. A remote eye tracker was used to record time-varying gaze paths while 13 radiologists interpreted 40 lung CT images with an average of 3.9 synthetic nodules (5-mm diameter) embedded randomly in the lung parenchyma. The radiologists' gaze volumes ( GV gaze volume s) were defined as the portion of the lung parenchyma within 50 pixels (approximately 3 cm) of all gaze points. The fraction of the total lung volume encompassed within the GV gaze volume s, the fraction of lung nodules encompassed within each GV gaze volume (search effectiveness), the fraction of lung nodules within the GV gaze volume detected by the reader (recognition-acceptance effectiveness), and overall sensitivity of lung nodule detection were measured. RESULTS: Detected nodules were within 50 pixels of the nearest gaze point for 990 of 992 correct detections. On average, radiologists searched 26.7% of the lung parenchyma in 3 minutes and 16 seconds and encompassed between 86 and 143 of 157 nodules within their GV gaze volume s. Once encompassed within their GV gaze volume , the average sensitivity of nodule recognition and acceptance ranged from 47 of 100 nodules to 103 of 124 nodules (sensitivity, 0.47-0.82). Overall sensitivity ranged from 47 to 114 of 157 nodules (sensitivity, 0.30-0.73) and showed moderate correlation (r = 0.62, P = .02) with the fraction of lung volume searched. CONCLUSION: Relationships between reader search, recognition and acceptance, and overall lung nodule detection rate can be studied with eye tracking. Radiologists appear to actively search less than half of the lung parenchyma, with substantial interreader variation in volume searched, fraction of nodules included within the search volume, sensitivity for nodules within the search volume, and overall detection rate.

Simulations of breast cancer imaging using gamma-ray stimulated emission computed tomography.

Here, we present an innovative imaging technology for breast cancer using gamma-ray stimulated spectroscopy based on the nuclear resonance fluorescence (NRF) technique. In NRF, a nucleus of a given isotope selectively absorbs gamma rays with energy exactly equal to one of its quantized energy states, emitting an outgoing gamma ray with energy nearly identical to that of the incident gamma ray. Due to its application of NRF, gamma-ray stimulated spectroscopy is sensitive to trace element concentration changes, which are suspected to occur at early stages of breast cancer, and therefore can be potentially used to noninvasively detect and diagnose cancer in its early stages. Using Monte-Carlo simulations, we have designed and demonstrated an imaging system that uses gamma-ray stimulated spectroscopy for visualizing breast cancer. We show that gamma-ray stimulated spectroscopy is able to visualize breast cancer lesions based primarily on the differences in the concentrations of trace elements between diseased and healthy tissue, rather than differences in density that are crucial for X-ray mammography. The technique shows potential for early breast cancer detection; however, improvements are needed in gamma-ray laser technology for the technique to become a clinically feasible method of detecting and diagnosing cancer at early stages.

Mutual information-based template matching scheme for detection of breast masses: from mammography to digital breast tomosynthesis.

Development of a computational decision aid for a new medical imaging modality typically is a long and complicated process. It consists of collecting data in the form of images and annotations, development of image processing and pattern recognition algorithms for analysis of the new images and finally testing of the resulting system. Since new imaging modalities are developed more rapidly than ever before, any effort for decreasing the time and cost of this development process could result in maximizing the benefit of the new imaging modality to patients by making the computer aids quickly available to radiologists that interpret the images. In this paper, we make a step in this direction and investigate the possibility of translating the knowledge about the detection problem from one imaging modality to another. Specifically, we present a computer-aided detection (CAD) system for mammographic masses that uses a mutual information-based template matching scheme with intelligently selected templates. We presented principles of template matching with mutual information for mammography before. In this paper, we present an implementation of those principles in a complete computer-aided detection system. The proposed system, through an automatic optimization process, chooses the most useful templates (mammographic regions of interest) using a large database of previously collected and annotated mammograms. Through this process, the knowledge about the task of detecting masses in mammograms is incorporated in the system. Then, we evaluate whether our system developed for screen-film mammograms can be successfully applied not only to other mammograms but also to digital breast tomosynthesis (DBT) reconstructed slices without adding any DBT cases for training. Our rationale is that since mutual information is known to be a robust inter-modality image similarity measure, it has high potential of transferring knowledge between modalities in the context of the mass detection task. Experimental evaluation of the system on mammograms showed competitive performance compared to other mammography CAD systems recently published in the literature. When the system was applied "as-is" to DBT, its performance was notably worse than that for mammograms. However, with a simple additional preprocessing step, the performance of the system reached levels similar to that obtained for mammograms. In conclusion, the presented CAD system not only performed competitively on screen-film mammograms but it also performed robustly on DBT showing that direct transfer of knowledge across breast imaging modalities for mass detection is in fact possible.

Exploring the potential of context-sensitive CADe in screening mammography.

PURPOSE: Conventional computer-assisted detection (CADe) systems in screening mammography provide the same decision support to all users. The aim of this study was to investigate the potential of a context-sensitive CADe system which provides decision support guided by each user's focus of attention during visual search and reporting patterns for a specific case. METHODS: An observer study for the detection of malignant masses in screening mammograms was conducted in which six radiologists evaluated 20 mammograms while wearing an eye-tracking device. Eye-position data and diagnostic decisions were collected for each radiologist and case they reviewed. These cases were subsequently analyzed with an in-house knowledge-based CADe system using two different modes: Conventional mode with a globally fixed decision threshold and context-sensitive mode with a location-variable decision threshold based on the radiologists' eye dwelling data and reporting information. RESULTS: The CADe system operating in conventional mode had 85.7% per-image malignant mass sensitivity at 3.15 false positives per image (FPsI). The same system operating in context-sensitive mode provided personalized decision support at 85.7%-100% sensitivity and 0.35-0.40 FPsI to all six radiologists. Furthermore, context-sensitive CADe system could improve the radiologists' sensitivity and reduce their performance gap more effectively than conventional CADe. CONCLUSIONS: Context-sensitive CADe support shows promise in delineating and reducing the radiologists' perceptual and cognitive errors in the diagnostic interpretation of screening mammograms more effectively than conventional CADe.

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 system's 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 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.

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.