Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Image Segmentation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 649 records · Page 36

Visualizing the Uncertainty of Graph-based 2D Segmentation with Min-path Stability

Here, this paper presents a novel approach to visualize the uncertainty in graph-based segmentations of scalar data. Segmentation of 2D scalar data has wide application in a variety of scientific and medical domains. Typically, a segmentation is presented as a single unambiguous boundary although the solution is often uncertain due to noise or blur in the underlying data as well as imprecision in user input. Our approach provides insight into this uncertainty by computing the “min-path stability”, a scalar measure analyzing the stability of the segmentation given a set of input constraints. Our approach is efficient, easy to compute, and can be generally applied to either graph cuts or live-wire (even partial) segmentations. In addition to its general applicability, our new approach to graph cuts uncertainty visualization improves on the time complexity of the current state-of-the-art with an additional fast approximate solution. We also introduce a novel query enabled by our approach which provides users with alternate segmentations by efficiently extracting local minima of the segmentation optimization. Finally, we evaluate our approach and demonstrate its utility on data from scientific and medical applications.

97 MATHEMATICS AND COMPUTING↗

Three-dimensional visualization and characterization of bone structure using reconstructed in-vitro μCT images: A pilot study for bone microarchitecture analysis

Micro Computed Tomography (μCT) has been largely used to perform micrometer scale imaging of specimens, bone biopsies and small animals for the study of porous or cavity-containing objects. One of its favored applications is for assessing structural properties of bone. In this research, we perform a pilot study to visualize and characterize bone structure of a chicken bone thigh, as well as to delineate its cortical and trabecular bone regions. We utilize an In-Vitro μCT scanner Skyscan 1173 to acquire a three dimensional image data of a chicken bone thigh. The thigh was scanned using X-ray voltage of 45 kV and current of 150 μA. The reconstructed images have spatial resolution of 142.50 μm/pixel. Using image processing and analysis e.i segmentation by thresholding the gray values (which represent the pseudo density) and binarizing the images, we were able to visualize each part of the bone, i.e., the cortical and trabecular regions. Total volume of the bone is 4663.63 mm{sup 3}, and the surface area of the bone is 7913.42 mm{sup 2}. The volume of the cortical is approximately 1988.62 mm{sup 3} which is nearly 42.64% of the total bone volume. This pilot study has confirmed that the μCT is capable of quantifying 3D bone structural properties and defining its regions separately. For further development, these results can be improved for understanding the pathophysiology of bone abnormality, testing the efficacy of pharmaceutical intervention, or estimating bone biomechanical properties.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Automated Radiation Targeting in Head-and-Neck Cancer Using Region-Based Texture Analysis of PET and CT Images

Purpose: A co-registered multimodality pattern analysis segmentation system (COMPASS) was developed to automatically delineate the radiation targets in head-and-neck cancer (HNC) using both {sup 18}F-fluoro-deoxy glucose-positron emission tomography (PET) and computed tomography (CT) images. The performance of the COMPASS was compared with the results of existing threshold-based methods and radiation oncologist-drawn contours. Methods and Materials: The COMPASS extracted texture features from corresponding PET and CT voxels. Using these texture features, a decision-tree-based K-nearest-neighbor classifier labeled each voxel as either 'normal' or 'abnormal.' The COMPASS was applied to the PET/CT images of 10 HNC patients. Automated segmentation results were validated against the manual segmentations of three radiation oncologists using the volume, sensitivity, and specificity. The performance of the COMPASS was compared with three PET-based threshold methods: standard uptake value of 2.5, 50% maximal intensity, and signal/background ratio. Results: The tumor delineations of the COMPASS were both quantitatively and qualitatively more similar to those of the radiation oncologists than the delineations from the other methods. The specificity was 95% {+-} 2%, 84% {+-} 9%, 98% {+-} 3%, and 96% {+-} 4%, and the sensitivity was 90% {+-} 12%, 93% {+-} 10%, 48% {+-} 20%, and 68% {+-} 25% for the COMPASS, for a standard uptake value of 2.5, 50% maximal intensity, and signal/background ratio, respectively. The COMPASS distinguished HNC from adjacent normal tissues with high physiologic uptake and consistently defined tumors with large variability in {sup 18}F-fluoro-deoxy glucose uptake, which are often problematic with the threshold-based methods. Conclusion: Automated segmentation using texture analysis of PET/CT images has the potential to provide accurate delineation of HNC. This could lead to reduced interobserver variability, reduced uncertainty in target delineation, and improved treatment planning accuracy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

SU-D-BRF-07: Ultrasound and Fluoroscopy Based Intraoperative Image-Guidance System for Dynamic Dosimetry in Prostate Brachytherapy

Purpose: Prostate brachytherapy is a common treatment method for low-risk prostate cancer patients. Intraoperative treatment planning is known to improve the treatment procedure and the outcome. The current limitation of intraoperative treatment planning is the inability to localize the seeds in relation to the prostate. We developed an image-guidance system to fulfill this need to achieve intraoperative dynamic dosimetry in prostate brachytherapy. Methods: Our system is based on standard imaging equipments available in the operating room, including the transrectal ultrasound (TRUS) and the mobile C-arm. A simple fiducial is added to compute the C-arm pose. Three fluoroscopic images and an ultrasound volume of the seeds and the prostate are acquired and processed by four image processing algorithms: seed segmentation, fiducial detection with pose estimation, seed reconstruction, and seeds-to-TRUS registration. The updated seed positions allow the physician to assess the quality of implantation and dynamically adjust the treatment plan during the course of surgery to achieve improved exit dosimetry. Results: The system was tested on 10 phantoms and 37 patients. Seed segmentation resulted in a 1% false negative and 2% false positive rates. Fiducial detection with pose estimation resulted in a detection rate of 98%. Seed reconstruction had a mean reconstruction error of 0.4 mm. Seeds-to-TRUS registration had a mean registration error of 1.3 mm. The total processing time from image acquisition to registration was approximately 1 minute. Conclusion: We present an image-guidance system for intraoperative dynamic dosimetry in prostate brachytherapy. Using standard imaging equipments and a simple fiducial, our system can be easily adopted in any clinics. Robust image processing algorithms enable accurate and fast computation of the delivered dose. Especially, the system enables detection of possible hot/cold spots during the surgery, allowing the physician to address these in the operating room rather than requiring additional therapy afterwards. This research was supported in part by the National Institutes of Health/National Cancer Institute (NIH/NCI) under grant 2R44CA099374 and grant 1R01CA151395, and in part by the Department of Defense (DoD) under grant W81XWH-05-1-0407.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

SU-C-12A-05: Radiation Dose in High-Pitch Pediatric Cardiac CTA: Correlation Between Lung Dose and CTDIvol, DLP, and Size Specific Dose Estimates (SSDE)

Purpose: To investigate the radiation dose for pediatric high pitch cardiac CTA Methods: A total of 14 cases were included in this study, with mean age of 6.2 years (ranges from 2 months to 15 years). Cardiac CTA was performed using a dual-source CT system (Definition Flash, Siemens). Tube voltage (70, 80 and 100kV) was chosen based on patient weight. All patients were scanned using a high-pitch spiral mode (pitch ranges from 2.5 to 3) with tube current modulation technique (CareDose4D, Siemens). For each case, the three dimensional dose distributions were calculated using a Monte Carlo software package (IMPACT-MC, CT Image GmbH). Scanning parameters of each exam, including tube voltage, tube current, beamshaping filters, beam collimation, were defined in the Monte Carlo calculation. Tube current profile along projection angles was obtained from projection data of each tube, which included data within the over-scanning range along z direction. The volume of lungs was segmented out with CT images (3DSlicer). Lung doses of all patients were calculated and compared with CTDIvol, DLP, and SSDE. Results: The average (range) of CTDIvol, DLP and SSDE of all patients was 1.19 mGy (0.58 to 3.12mGy), 31.54 mGy*cm (12.56 to 99 mGy*cm), 2.26 mGy (1.19 to 6.24 mGy), respectively. Radiation dose to the lungs ranged from 0.83 to 4.18 mGy. Lung doses correlated with CTDIvol, DLP and SSDE with correlation coefficients(k) at 0.98, 0.93, and 0.99. However, for the cases with CTDIvol less than 1mGy, only SSDE preserved a strong correlation with lung doses (k=0.83), while much weaker correlations were found for CTDIvol (k=0.29) and DLP (k=-0.47). Conclusion: Lung doses to pediatric patients during Cardiac CTA were estimated. SSDE showed the most robust correlation with lung doses in contrast to CTDIvol and DLP.

60 APPLIED LIFE SCIENCES↗

Automated segmentation of porous thermal spray material CT scans with predictive uncertainty estimation

Abstract Thermal sprayed metal coatings are used in many industrial applications, and characterizing the structure and performance of these materials is vital to understanding their behavior in the field. X-ray computed tomography (CT) enables volumetric, nondestructive imaging of these materials, but precise segmentation of this grayscale image data into discrete material phases is necessary to calculate quantities of interest related to material structure. In this work, we present a methodology to automate the CT segmentation process as well as quantify uncertainty in segmentations via deep learning. Neural networks (NNs) have been shown to excel at segmentation tasks; however, memory constraints, class imbalance, and lack of sufficient training data often prohibit their deployment in high resolution volumetric domains. Our 3D convolutional NN implementation mitigates these challenges and accurately segments full resolution CT scans of thermal sprayed materials with maps of uncertainty that conservatively bound the predicted geometry. These bounds are propagated through calculations of material properties such as porosity that may provide an understanding of anticipated behavior in the field.

Martinez, Carianne↗

Formation of edge misfit dislocations in Ge{sub x}Si{sub 1-x}(x{approx}0.4-0.8) films grown on misoriented (001){yields}(111) Si substrates: Features before and after film annealing

The dislocation structure at the initial stage of relaxation of Ge{sub x}Si{sub 1-x} films (x{approx}0.4-0.8) grown on Si(001) substrates tilted at 6 deg. to the nearest (111) plane is studied. One of the directions along which edge dislocations are formed is no longer in the plane of the interface but crosses the latter at the angle of miscut. Therefore, long edge misfit dislocations (MDs) cannot exist in the direction of substrate misorientation, because their ends move away from the interface during dislocation propagation. Two different mechanisms of formation of short segments of edge (90 deg. ) MDs in the direction of substrate misorientation are found. The first mechanism is the correlated nucleation of complementary 60 deg. dislocation half-loops manifested in the form of the so-called Y-center consisting of a short segment of the 90 deg. MD and 60 deg. MDs diverging from this segment in form of two rays in the miscut direction. In the second mechanism, the 90 deg. MD segment is formed owing to intersection of already existing complementary 60 deg. MDs slipping in mirrorlike inclined planes {l_brace}111{r_brace}. Samples annealed at higher temperatures contain MD segments, which lose their contrast on one of the TEM images taken to detect edge dislocation segments in the two-wave diffraction mode but do not coincide with the direction [110] (they pass along the intersections of the mirrorlike inclined planes {l_brace}111{r_brace} with the surface of the misoriented Si substrate). To explain this phenomenon, a model is proposed, where one of the pair of complementary 60 deg. MDs propagating at an angle to each other continuously approaches the other by the cross-slip mechanism. Formation of a chain of edge MD segments connected by a pair of 60 deg. MDs becomes possible. The averaged direction of such a dislocation structure coincides with the direction of one of the 60 deg. MDs.

36 MATERIALS SCIENCE↗

Enhancing Diagnosis through AI-driven Analysis of Reflectance Confocal Microscopy

Reflectance Confocal Microscopy (RCM) is a non-invasive imaging technique used in biomedical research and clinical dermatology. It provides virtual high-resolution images of the skin and superficial tissues, reducing the need for physical biopsies. RCM employs a laser light source to illuminate the tissue, capturing the reflected light to generate detailed images of microscopic structures at various depths. Recent studies explored AI and machine learning, particularly CNNs, for analyzing RCM images. Our study proposes a segmentation strategy based on textural features to identify clinically significant regions, empowering dermatologists in effective image interpretation and boosting diagnostic confidence. This approach promises to advance dermatological diagnosis and treatment.

Yoon, Hong-Jun↗

Sci—Fri PM: Topics — 06: The influence of regional dose sensitivity on salivary loss and recovery in the parotid gland

Purpose: The Quantitative Analyses of Normal Tissue Effects in the Clinic (QUANTEC 2010) survey of radiation dose-volume effects on salivary gland function has called for improved understanding of intragland dose sensitivity and the effectiveness of partial sparing in salivary glands. Regional dose susceptibility of sagittally- and coronally-sub-segmented parotid gland has been studied. Specifically, we examine whether individual consideration of sub-segments leads to improved prediction of xerostomia compared with whole parotid mean dose. Methods: Data from 102 patients treated for head-and-neck cancers at the BC Cancer Agency were used in this study. Whole mouth stimulated saliva was collected before (baseline), three months, and one year after cessation of radiotherapy. Organ volumes were contoured using treatment planning CT images and sub-segmented into regional portions. Both non-parametric (local regression) and parametric (mean dose exponential fitting) methods were employed. A bootstrap technique was used for reliability estimation and cross-comparison. Results: Salivary loss is described well using non-parametric and mean dose models. Parametric fits suggest a significant distinction in dose response between medial-lateral and anterior-posterior aspects of the parotid (p<0.01). Least-squares and least-median squares estimates differ significantly (p<0.00001), indicating fits may be skewed by noise or outliers. Salivary recovery exhibits a weakly arched dose response: the highest recovery is seen at intermediate doses. Conclusions: Salivary function loss is strongly dose dependent. In contrast no useful dose dependence was observed for function recovery. Regional dose dependence was observed, but may have resulted from a bias in dose distributions.

60 APPLIED LIFE SCIENCES↗

Construction of anthropomorphic phantoms for use in dosimetry studies

This paper reports on the methodology and materials used to construct anthropomorphic phantoms for use in dosimetry studies, improving on methods and materials previously described by Jones et al. [Med Phys. 2006;33(9):3274–82]. To date, the methodology described has been successfully used to create a series of three different adult phantoms at the University of Florida (UF). All phantoms were constructed in 5 mm transverse slices using materials designed to mimic human tissue at diagnostic photon energies: soft tissue‐equivalent substitute (STES), lung tissue‐equivalent substitute (LTES), and bone tissue‐equivalent substitute (BTES). While the formulation for BTES remains unchanged from the previous epoxy resin compound developed by Jones et al. [Med Phys. 2003;30(8):2072—81], both the STES and LTES were redesigned utilizing a urethane‐based compound which forms a pliable tissue‐equivalent material. These urethane‐based materials were chosen in part for improved phantom durability and easier accommodation of real‐time dosimeters. The production process has also been streamlined with the use of an automated machining system to create molds for the phantom slices from bitmap images based on the original segmented computed tomography (CT) datasets. Information regarding the new tissue‐equivalent materials, as well as images of the construction process and completed phantom, are included. PACS number: 87.53.Bn

61 RADIATION PROTECTION AND DOSIMETRY↗

Automated Segmentation of Porous Thermal Spray Material CT Scans with Geometric Uncertainty Estimation

Thermal sprayed metal coatings are used in many industrial applications, and characterizing the structure and performance of these materials is vital to understanding their behavior in the field. X-ray Computed Tomography (CT) machines enable volumetric, nondestructive imaging of these materials, but precise segmentation of this grayscale image data into discrete material phases is necessary to calculate quantities of interest related to material structure. In this work, we present a methodology to automate the CT segmentation process as well as quantify uncertainty in segmentations via deep learning. Neural networks (NNs) are shown to accurately segment full resolution CT scans of thermal sprayed materials and provide maps of uncertainty that conservatively bound the predicted geometry. These bounds are propagated through calculations of material properties such as porosity that may provide an understanding of anticipated behavior in the field.

36 MATERIALS SCIENCE↗

THE CORONAL LOOP INVENTORY PROJECT

Most coronal physicists now seem to agree that loops are composed of tangled magnetic strands and have both isothermal and multithermal cross-field temperature distributions. As yet, however, there is no information on the relative importance of each of these categories, and we do not know how common one is with respect to the other. In this paper, we investigate these temperature properties for all loop segments visible in the 171-Å image of AR 11294, which was observed by the Atmospheric Imaging Assembly (AIA) on 2011 September 15. Our analysis revealed 19 loop segments, but only 2 of these were clearly isothermal. Six additional segments were effectively isothermal, that is, the plasma emission to which AIA is sensitive could not be distinguished from isothermal emission, within measurement uncertainties. One loop had both isothermal transition region and multithermal coronal solutions. Another five loop segments require multithermal plasma to reproduce the AIA observations. The five remaining loop segments could not be separated reliably from the background in the crucial non-171-Å AIA images required for temperature analysis. We hope that the direction of coronal heating models and the efforts modelers spend on various heating scenarios will be influenced by these results.

79 ASTRONOMY AND ASTROPHYSICS↗

TU-FG-209-05: Demonstration of the Line Focus Principle Using the Generalized Measured-Relative Object Detectability (GM-ROD) Metric

Purpose: Demonstrate and quantify the augmented resolution due to focalspot size decrease in images acquired on the anode side of the field, for both small and medium (0.3 and 0.6mm) focal-spot sizes using the experimental task-based GM-ROD metric. Theoretical calculations have shown that a medium focal-spot can achieve the resolution of a small focal-spot if acquired with a tilted anode, effectively providing a higher-output small focal-spot. Methods: The MAF-CMOS (micro-angiographic fluoroscopic complementary-metal-oxide semiconductor) detector (75µm pixel pitch) imaged two copper wire segments of different diameter and a pipeline stent at the central axis and on the anode side of the beam, achieved by tilting the x-ray C-arm (Toshiba Infinix) to 6° and realigning the detector with the perpendicular ray to correct for x-ray obliquity. The relative gain in resolution was determined using the GM-ROD metric, which compares images on the basis of the Fourier transform of the image and the measured NNPS. To emphasize the geometric unsharpness, images were acquired at a magnification of two. Results: Images acquired on the anode side were compared to those acquired on the central axis with the same target-area focal-spot to consider the effect of an angled tube, and for all three objects the advantage of the smaller effective focal-spot was clear, showing a maximum improvement of 36% in GM-ROD. The images obtained with the small focal-spot at the central axis were compared to those of the medium focal-spot at the anode side and, for all objects, the relative performance was comparable. Conclusion: For three objects, the GM-ROD demonstrated the advantage of the anode side focal-spot. The comparable performance of the medium focal-spot on the anode side will allow for a high-output small focal-spot; a necessity in endovascular image-guided interventions. Partial support from an NIH grant R01EB002873 and an equipment grant from Toshiba Medical Systems Corp.

60 APPLIED LIFE SCIENCES↗

SwinCell: a 3D transformer and flow-based framework for improved cell segmentation

Segmentation of three-dimensional (3D) cellular images is fundamental for studying and understanding cell structure and function. However, 3D cellular segmentation is challenging, particularly for dense cells and tissues. This challenge arises mainly from the complex contextual information within 3D images, anisotropic properties, and the sensitivity to internal cellular structures, which often lead to incorrect segmentation. In this work, we introduce SwinCell, a 3D transformer-based framework that leverages Swin-transformer to predict flow and differentiate individual cell instances. We demonstrate SwinCell’s utility in the segmentation of nuclei, colon tissue cells, and densely cultured cells. SwinCell strikes a balance between maintaining detailed local feature recognition and understanding broader contextual information. Through extensive testing with both public and in-house 3D cell imaging datasets, SwinCell shows utility in segmenting dense cells, making it a valuable tool for 3D segmentation in cellular analysis that could expedite research in cell biology and tissue engineering.

59 BASIC BIOLOGICAL SCIENCES↗

Unsupervised learning-enabled pulsed infrared thermographic microscopy of subsurface defects in stainless steel

Metallic structures produced with laser powder bed fusion (LPBF) additive manufacturing method (AM) frequently contain microscopic porosity defects, with typical approximate size distribution from one to 100 microns. Presence of such defects could lead to premature failure of the structure. In principle, structural integrity assessment of LPBF metals can be accomplished with nondestructive evaluation (NDE). Pulsed infrared thermography (PIT) is a non-contact, one-sided NDE method that allows for imaging of internal defects in arbitrary size and shape metallic structures using heat transfer. PIT imaging is performed using compact instrumentation consisting of a flash lamp for deposition of a heat pulse, and a fast frame infrared (IR) camera for measuring surface temperature transients. However, limitations of imaging resolution with PIT include blurring due to heat diffusion, sensitivity limit of the IR camera. We demonstrate enhancement of PIT imaging capability with unsupervised learning (UL), which enables PIT microscopy of subsurface defects in high strength corrosion resistant stainless steel 316 alloy. PIT images were processed with UL spatial–temporal separation-based clustering segmentation (STSCS) algorithm, refined by morphology image processing methods to enhance visibility of defects. The STSCS algorithm starts with wavelet decomposition to spatially de-noise thermograms, followed by UL principal component analysis (PCA), fine-tuning optimization, and neural learning-based independent component analysis (ICA) algorithms to temporally compress de-noised thermograms. The compressed thermograms were further processed with UL-based graph thresholding K-means clustering algorithm for defects segmentation. The STSCS algorithm also includes online learning feature for efficient re-training of the model with new data. For this study, metallic specimens with calibrated microscopic flat bottom hole defects, with diameters in the range from 203 to 76 µm, were produced using electro discharge machining (EDM) drilling. While the raw thermograms do not show any material defects, using STSCS algorithm to process PIT images reveals defects as small as 101 µm in diameter. To the best of our knowledge, this is the smallest reported size of a sub-surface defect in a metal imaged with PIT, which demonstrates the PIT capability of detecting defects in the size range relevant to quality control requirements of LPBF-printed high-strength metals.

36 MATERIALS SCIENCE↗

Automated fibroglandular tissue segmentation and volumetric density estimation in breast MRI using an atlas-aided fuzzy C-means method

Purpose: Breast magnetic resonance imaging (MRI) plays an important role in the clinical management of breast cancer. Studies suggest that the relative amount of fibroglandular (i.e., dense) tissue in the breast as quantified in MR images can be predictive of the risk for developing breast cancer, especially for high-risk women. Automated segmentation of the fibroglandular tissue and volumetric density estimation in breast MRI could therefore be useful for breast cancer risk assessment. Methods: In this work the authors develop and validate a fully automated segmentation algorithm, namely, an atlas-aided fuzzy C-means (FCM-Atlas) method, to estimate the volumetric amount of fibroglandular tissue in breast MRI. The FCM-Atlas is a 2D segmentation method working on a slice-by-slice basis. FCM clustering is first applied to the intensity space of each 2D MR slice to produce an initial voxelwise likelihood map of fibroglandular tissue. Then a prior learned fibroglandular tissue likelihood atlas is incorporated to refine the initial FCM likelihood map to achieve enhanced segmentation, from which the absolute volume of the fibroglandular tissue (|FGT|) and the relative amount (i.e., percentage) of the |FGT| relative to the whole breast volume (FGT%) are computed. The authors' method is evaluated by a representative dataset of 60 3D bilateral breast MRI scans (120 breasts) that span the full breast density range of the American College of Radiology Breast Imaging Reporting and Data System. The automated segmentation is compared to manual segmentation obtained by two experienced breast imaging radiologists. Segmentation performance is assessed by linear regression, Pearson's correlation coefficients, Student's pairedt-test, and Dice's similarity coefficients (DSC). Results: The inter-reader correlation is 0.97 for FGT% and 0.95 for |FGT|. When compared to the average of the two readers’ manual segmentation, the proposed FCM-Atlas method achieves a correlation ofr = 0.92 for FGT% and r = 0.93 for |FGT|, and the automated segmentation is not statistically significantly different (p = 0.46 for FGT% and p = 0.55 for |FGT|). The bilateral correlation between left breasts and right breasts for the FGT% is 0.94, 0.92, and 0.95 for reader 1, reader 2, and the FCM-Atlas, respectively; likewise, for the |FGT|, it is 0.92, 0.92, and 0.93, respectively. For the spatial segmentation agreement, the automated algorithm achieves a DSC of 0.69 ± 0.1 when compared to reader 1 and 0.61 ± 0.1 for reader 2, respectively, while the DSC between the two readers’ manual segmentation is 0.67 ± 0.15. Additional robustness analysis shows that the segmentation performance of the authors' method is stable both with respect to selecting different cases and to varying the number of cases needed to construct the prior probability atlas. The authors' results also show that the proposed FCM-Atlas method outperforms the commonly used two-cluster FCM-alone method. The authors' method runs at ∼5 min for each 3D bilateral MR scan (56 slices) for computing the FGT% and |FGT|, compared to ∼55 min needed for manual segmentation for the same purpose. Conclusions: The authors' method achieves robust segmentation and can serve as an efficient tool for processing large clinical datasets for quantifying the fibroglandular tissue content in breast MRI. It holds a great potential to support clinical applications in the future including breast cancer risk assessment.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

A region-appearance-based adaptive variational model for 3D liver segmentation

Purpose: Liver segmentation from computed tomography images is a challenging task owing to pixel intensity overlapping, ambiguous edges, and complex backgrounds. The authors address this problem with a novel active surface scheme, which minimizes an energy functional combining both edge- and region-based information. Methods: In this semiautomatic method, the evolving surface is principally attracted to strong edges but is facilitated by the region-based information where edge information is missing. As avoiding oversegmentation is the primary challenge, the authors take into account multiple features and appearance context information. Discriminative cues, such as multilayer consecutiveness and local organ deformation are also implicitly incorporated. Case-specific intensity and appearance constraints are included to cope with the typically large appearance variations over multiple images. Spatially adaptive balancing weights are employed to handle the nonuniformity of image features. Results: Comparisons and validations on difficult cases showed that the authors’ model can effectively discriminate the liver from adhering background tissues. Boundaries weak in gradient or with no local evidence (e.g., small edge gaps or parts with similar intensity to the background) were delineated without additional user constraint. With an average surface distance of 0.9 mm and an average volume overlap of 93.9% on the MICCAI data set, the authors’ model outperformed most state-of-the-art methods. Validations on eight volumes with different initial conditions had segmentation score variances mostly less than unity. Conclusions: The proposed model can efficiently delineate ambiguous liver edges from complex tissue backgrounds with reproducibility. Quantitative validations and comparative results demonstrate the accuracy and efficacy of the model.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Brachial artery vasomotion and transducer pressure effect on measurements by active contour segmentation on ultrasound

Purpose: To use feed-forward active contours (snakes) to track and measure brachial artery vasomotion on ultrasound images recorded in both transverse and longitudinal views; and to compare the algorithm's performance in each view. Methods: Longitudinal and transverse view ultrasound image sequences of 45 brachial arteries were segmented by feed-forward active contour (FFAC). The segmented regions were used to measure vasomotion artery diameter, cross-sectional area, and distention both as peak-to-peak diameter and as area. ECG waveforms were also simultaneously extracted frame-by-frame by thresholding a running finite-difference image between consecutive images. The arterial and ECG waveforms were compared as they traced each phase of the cardiac cycle. Results: FFAC successfully segmented arteries in longitudinal and transverse views in all 45 cases. The automated analysis took significantly less time than manual tracing, but produced superior, well-behaved arterial waveforms. Automated arterial measurements also had lower interobserver variability as measured by correlation, difference in mean values, and coefficient of variation. Although FFAC successfully segmented both the longitudinal and transverse images, transverse measurements were less variable. The cross-sectional area computed from the longitudinal images was 27% lower than the area measured from transverse images, possibly due to the compression of the artery along the image depth by transducer pressure. Conclusions: FFAC is a robust and sensitive vasomotion segmentation algorithm in both transverse and longitudinal views. Transverse imaging may offer advantages over longitudinal imaging: transverse measurements are more consistent, possibly because the method is less sensitive to variations in transducer pressure during imaging.

62 RADIOLOGY AND NUCLEAR MEDICINE↗