An integrated model-driven method for in-treatment upper airway motion tracking using cine MRI in head and neck radiation therapy.

PURPOSE: For the first time, MRI-guided radiation therapy systems can acquire cine images to dynamically monitor in-treatment internal organ motion. However, the complex head and neck (H&N) structures and low-contrast/resolution of on-board cine MRI images make automatic motion tracking a very challenging task. In this study, the authors proposed an integrated model-driven method to automatically track the in-treatment motion of the H&N upper airway, a complex and highly deformable region wherein internal motion often occurs in an either voluntary or involuntary manner, from cine MRI images for the analysis of H&N motion patterns. METHODS: Considering the complex H&N structures and ensuring automatic and robust upper airway motion tracking, the authors firstly built a set of linked statistical shapes (including face, face-jaw, and face-jaw-palate) using principal component analysis from clinically approved contours delineated on a set of training data. The linked statistical shapes integrate explicit landmarks and implicit shape representation. Then, a hierarchical model-fitting algorithm was developed to align the linked shapes on the first image frame of a to-be-tracked cine sequence and to localize the upper airway region. Finally, a multifeature level set contour propagation scheme was performed to identify the upper airway shape change, frame-by-frame, on the entire image sequence. The multifeature fitting energy, including the information of intensity variations, edge saliency, curve geometry, and temporal shape continuity, was minimized to capture the details of moving airway boundaries. Sagittal cine MR image sequences acquired from three H&N cancer patients were utilized to demonstrate the performance of the proposed motion tracking method. RESULTS: The tracking accuracy was validated by comparing the results to the average of two manual delineations in 50 randomly selected cine image frames from each patient. The resulting average dice similarity coefficient (93.28% ± 1.46%) and margin error (0.49 ± 0.12 mm) showed good agreement between the automatic and manual results. The comparison with three other deformable model-based segmentation methods illustrated the superior shape tracking performance of the proposed method. Large interpatient variations of swallowing frequency, swallowing duration, and upper airway cross-sectional area were observed from the testing cine image sequences. CONCLUSIONS: The proposed motion tracking method can provide accurate upper airway motion tracking results, and enable automatic and quantitative identification and analysis of in-treatment H&N upper airway motion. By integrating explicit and implicit linked-shape representations within a hierarchical model-fitting process, the proposed tracking method can process complex H&N structures and low-contrast/resolution cine MRI images. Future research will focus on the improvement of method reliability, patient motion pattern analysis for providing more information on patient-specific prediction of structure displacements, and motion effects on dosimetry for better H&N motion management in radiation therapy.

A comparative study based on image quality and clinical task performance for CT reconstruction algorithms in radiotherapy.

CT image reconstruction is typically evaluated based on the ability to reduce the radiation dose to as-low-as-reasonably-achievable (ALARA) while maintaining acceptable image quality. However, the determination of common image quality metrics, such as noise, contrast, and contrast-to-noise ratio, is often insufficient for describing clinical radiotherapy task performance. In this study we designed and implemented a new comparative analysis method associating image quality, radiation dose, and patient size with radiotherapy task performance, with the purpose of guiding the clinical radiotherapy usage of CT reconstruction algorithms. The iDose4 iterative reconstruction algorithm was selected as the target for comparison, wherein filtered back-projection (FBP) reconstruction was regarded as the baseline. Both phantom and patient images were analyzed. A layer-adjustable anthropomorphic pelvis phantom capable of mimicking 38-58 cm lateral diameter-sized patients was imaged and reconstructed by the FBP and iDose4 algorithms with varying noise-reduction-levels, respectively. The resulting image sets were quantitatively assessed by two image quality indices, noise and contrast-to-noise ratio, and two clinical task-based indices, target CT Hounsfield number (for electron density determination) and structure contouring accuracy (for dose-volume calculations). Additionally, CT images of 34 patients reconstructed with iDose4 with six noise reduction levels were qualitatively evaluated by two radiation oncologists using a five-point scoring mechanism. For the phantom experiments, iDose4 achieved noise reduction up to 66.1% and CNR improvement up to 53.2%, compared to FBP without considering the changes of spatial resolution among images and the clinical acceptance of reconstructed images. Such improvements consistently appeared across different iDose4 noise reduction levels, exhibiting limited interlevel noise (< 5 HU) and target CT number variations (< 1 HU). The radiation dose required to achieve similar contouring accuracy decreased when using iDose4 in place of FBP, up to 32%. Contouring accuracy improvement for iDose4 images, when compared to FBP, was greater in larger patients than smaller-sized patients. Overall, the iDose4 algorithm provided superior radiation dose control while maintaining or improving task performance, when compared to FBP. The reader study on image quality improvement of patient cases shows that physicians preferred iDose4-reconstructed images on all cases compared to those from FBP algorithm with overall quality score: 1.21 vs. 3.15, p = 0.0022. However, qualitative evaluation strongly indicated that the radiation oncologists chose iDose4 noise reduction levels of 3-4 with additional consideration of task performance, instead of image quality metrics alone. Although higher iDose4 noise reduction levels improved the CNR through the further reduction of noise, there was pixelization of anatomical/tumor structures. Very-low-dose scans yielded severe photon starvation artifacts, which decreased target visualization on both FBP and iDose4 reconstructions, especially for the 58 cm phantom size. The iDose4 algorithm with a moderate noise reduction level is hence suggested for CT simulation and treatment planning. Quantitative task-based image quality metrics should be further investigated to accommodate additional clinical applications.

Practical considerations for noise power spectra estimation for clinical CT scanners.

Local noise power spectra (NPS) have been commonly calculated to represent the noise properties of CT imaging systems, but their properties are significantly affected by the utilized calculation schemes. In this study, the effects of varied calculation parameters on the local NPS were analyzed, and practical suggestions were provided regarding the estimation of local NPS for clinical CT scanners. The uniformity module of a Catphan phantom was scanned with a Philips Brilliance 64 slice CT simulator with varied scanning protocols. Images were reconstructed using FBP and iDose4 iterative reconstruction with noise reduction levels 1, 3, and 6. Local NPS were calculated and compared for varied region of interest (ROI) locations and sizes, image background removal methods, and window functions. Additionally, with a predetermined NPS as a ground truth, local NPS calculation accuracy was compared for computer simulated ROIs, varying the aforementioned parameters in addition to ROI number. An analysis of the effects of these varied calculation parameters on the magnitude and shape of the NPS was conducted. The local NPS varied depending on calculation parameters, particularly at low spatial frequencies below ~ 0.15 mm-1. For the simulation study, NPS calculation error decreased exponentially as ROI number increased. For the Catphan study the NPS magnitude varied as a function of ROI location, which was better observed when using smaller ROI sizes. The image subtraction method for background removal was the most effective at reducing low-frequency background noise, and produced similar results no matter which ROI size or window function was used. The PCA background removal method with a Hann window function produced the closest match to image subtraction, with an average percent difference of 17.5%. Image noise should be analyzed locally by calculating the NPS for small ROI sizes. A minimum ROI size is recommended based on the chosen radial bin size and image pixel dimensions. As the ROI size decreases, the NPS becomes more dependent on the choice of background removal method and window function. The image subtraction method is most accurate, but other methods can achieve similar accuracy if certain window functions are applied. All dependencies should be analyzed and taken into account when considering the interpretation of the NPS for task-based image quality assessment.

Identification of the Position and Thickness of the First Annular Pulley in Sonographic Images.

The purpose was to identify the A1 pulley's exact location and thickness by comparing measurements from a clinical high-frequency ultrasound scanner system (CHUS), a customized high-frequency ultrasound imaging research system (HURS) and a digital caliper. Ten cadaveric hands were used. We explored the pulley by layers, inserted guide pins and scanned it with the CHUS. After identifying the pulley, we measured each long finger's thickness using the CHUS and excised the pulley to measure its thickness with a digital caliper and the HURS. The thin hypo-echoic layer was revealed to be the synovial fluid space, and the pulley appears hyper-echoic regardless of scan direction. We also defined the pulley's boundaries. Moreover, the CHUS provided a significantly lower measurement of the pulley's thickness than the digital caliper and HURS. Likewise, based on the digital caliper's measurement, the HURS had significantly lower mean absolute and relative errors than the CHUS.

Saliency-aware food image segmentation for personal dietary assessment using a wearable computer.

Image-based dietary assessment has recently received much attention in the community of obesity research. In this assessment, foods in digital pictures are specified, and their portion sizes (volumes) are estimated. Although manual processing is currently the most utilized method, image processing holds much promise since it may eventually lead to automatic dietary assessment. In this paper we study the problem of segmenting food objects from images. This segmentation is difficult because of various food types, shapes and colors, different decorating patterns on food containers, and occlusions of food and non-food objects. We propose a novel method based on a saliency-aware active contour model (ACM) for automatic food segmentation from images acquired by a wearable camera. An integrated saliency estimation approach based on food location priors and visual attention features is designed to produce a salient map of possible food regions in the input image. Next, a geometric contour primitive is generated and fitted to the salient map by means of multi-resolution optimization with respect to a set of affine and elastic transformation parameters. The food regions are then extracted after contour fitting. Our experiments using 60 food images showed that the proposed method achieved significantly higher accuracy in food segmentation when compared to conventional segmentation methods.

Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: a general strategy.

PURPOSE: One of the most critical steps in radiation therapy treatment is accurate tumor and critical organ-at-risk (OAR) contouring. Both manual and automated contouring processes are prone to errors and to a large degree of inter- and intraobserver variability. These are often due to the limitations of imaging techniques in visualizing human anatomy as well as to inherent anatomical variability among individuals. Physicians/physicists have to reverify all the radiation therapy contours of every patient before using them for treatment planning, which is tedious, laborious, and still not an error-free process. In this study, the authors developed a general strategy based on novel geometric attribute distribution (GAD) models to automatically detect radiation therapy OAR contouring errors and facilitate the current clinical workflow. METHODS: Considering the radiation therapy structures' geometric attributes (centroid, volume, and shape), the spatial relationship of neighboring structures, as well as anatomical similarity of individual contours among patients, the authors established GAD models to characterize the interstructural centroid and volume variations, and the intrastructural shape variations of each individual structure. The GAD models are scalable and deformable, and constrained by their respective principal attribute variations calculated from training sets with verified OAR contours. A new iterative weighted GAD model-fitting algorithm was developed for contouring error detection. Receiver operating characteristic (ROC) analysis was employed in a unique way to optimize the model parameters to satisfy clinical requirements. A total of forty-four head-and-neck patient cases, each of which includes nine critical OAR contours, were utilized to demonstrate the proposed strategy. Twenty-nine out of these forty-four patient cases were utilized to train the inter- and intrastructural GAD models. These training data and the remaining fifteen testing data sets were separately employed to test the effectiveness of the proposed contouring error detection strategy. RESULTS: An evaluation tool was implemented to illustrate how the proposed strategy automatically detects the radiation therapy contouring errors for a given patient and provides 3D graphical visualization of error detection results as well. The contouring error detection results were achieved with an average sensitivity of 0.954/0.906 and an average specificity of 0.901/0.909 on the centroid/volume related contouring errors of all the tested samples. As for the detection results on structural shape related contouring errors, an average sensitivity of 0.816 and an average specificity of 0.94 on all the tested samples were obtained. The promising results indicated the feasibility of the proposed strategy for the detection of contouring errors with low false detection rate. CONCLUSIONS: The proposed strategy can reliably identify contouring errors based upon inter- and intrastructural constraints derived from clinically approved contours. It holds great potential for improving the radiation therapy workflow. ROC and box plot analyses allow for analytically tuning of the system parameters to satisfy clinical requirements. Future work will focus on the improvement of strategy reliability by utilizing more training sets and additional geometric attribute constraints.

An exploratory study on a chest-worn computer for evaluation of diet, physical activity and lifestyle.

Recently, wearable computers have become new members in the family of mobile electronic devices, adding new functions to those provided by smart-phones and tablets. As "always-on" miniature computers in the personal space, they will play increasing roles in the field of healthcare. In this work, we present our development of eButton, a wearable computer designed as a personalized, attractive, and convenient chest pin in a circular shape. It contains a powerful microprocessor, numerous electronic sensors, and wireless communication links. We describe its design concepts, electronic hardware, data processing algorithms, and its applications to the evaluation of diet, physical activity and lifestyle in the study of obesity and other chronic diseases.

Multiview stereo and silhouette fusion via minimizing generalized reprojection error.

Accurate reconstruction of 3D geometrical shape from a set of calibrated 2D multiview images is an active yet challenging task in computer vision. The existing multiview stereo methods usually perform poorly in recovering deeply concave and thinly protruding structures, and suffer from several common problems like slow convergence, sensitivity to initial conditions, and high memory requirements. To address these issues, we propose a two-phase optimization method for generalized reprojection error minimization (TwGREM), where a generalized framework of reprojection error is proposed to integrate stereo and silhouette cues into a unified energy function. For the minimization of the function, we first introduce a convex relaxation on 3D volumetric grids which can be efficiently solved using variable splitting and Chambolle projection. Then, the resulting surface is parameterized as a triangle mesh and refined using surface evolution to obtain a high-quality 3D reconstruction. Our comparative experiments with several state-of-the-art methods show that the performance of TwGREM based 3D reconstruction is among the highest with respect to accuracy and efficiency, especially for data with smooth texture and sparsely sampled viewpoints.

eButton: A Wearable Computer for Health Monitoring and Personal Assistance.

Recent advances in mobile devices have made profound changes in people's daily lives. In particular, the impact of easy access of information by the smartphone has been tremendous. However, the impact of mobile devices on healthcare has been limited. Diagnosis and treatment of diseases are still initiated by occurrences of symptoms, and technologies and devices that emphasize on disease prevention and early detection outside hospitals are under-developed. Besides healthcare, mobile devices have not yet been designed to fully benefit people with special needs, such as the elderly and those suffering from certain disabilities, such blindness. In this paper, an overview of our research on a new wearable computer called eButton is presented. The concepts of its design and electronic implementation are described. Several applications of the eButton are described, including evaluating diet and physical activity, studying sedentary behavior, assisting the blind and visually impaired people, and monitoring older adults suffering from dementia.

Clinical and pathological correlates of severity classifications in trigger fingers based on computer-aided image analysis.

BACKGROUND: The treatment of trigger finger so far has heavily relied on clinicians' evaluations for the severity of patients' symptoms and the functionality of affected fingers. However, there is still a lack of pathological evidence supporting the criteria of clinical evaluations. This study's aim was to correlate clinical classification and pathological changes for trigger finger based on the tissue abnormality observed from microscopic images. METHODS: Tissue samples were acquired, and microscopic images were randomly selected and then graded by three pathologists and two physicians, respectively. Moreover, the acquired images were automatically analyzed to derive two quantitative parameters, the size ratio of the abnormal tissue region and the number ratio of the abnormal nuclei, which can reflect tissue abnormality caused by trigger finger. A self-developed image analysis system was used to avoid human subjectivity during the quantification process. Finally, correlations between the quantitative image parameters, pathological grading, and clinical severity classification were assessed. RESULTS: One-way ANOVA tests revealed significant correlations between the image quantification and pathological grading as well as between the image quantification and clinical severity classification. The Cohen's kappa coefficient test also depicted good consistency between pathological grading and clinical severity classification. CONCLUSIONS: The criteria of clinical classification were found to be highly associated with the pathological changes of affected tissues. The correlations serve as explicit evidence supporting clinicians in making a treatment strategy of trigger finger. In addition, our proposed computer-aided image analysis system was considered to be a promising and objective approach to determining trigger finger severity at the microscopic level.

Automatic CT simulation optimization for radiation therapy: A general strategy.

PURPOSE: In radiation therapy, x-ray computed tomography (CT) simulation protocol specifications should be driven by the treatment planning requirements in lieu of duplicating diagnostic CT screening protocols. The purpose of this study was to develop a general strategy that allows for automatically, prospectively, and objectively determining the optimal patient-specific CT simulation protocols based on radiation-therapy goals, namely, maintenance of contouring quality and integrity while minimizing patient CT simulation dose. METHODS: The authors proposed a general prediction strategy that provides automatic optimal CT simulation protocol selection as a function of patient size and treatment planning task. The optimal protocol is the one that delivers the minimum dose required to provide a CT simulation scan that yields accurate contours. Accurate treatment plans depend on accurate contours in order to conform the dose to actual tumor and normal organ positions. An image quality index, defined to characterize how simulation scan quality affects contour delineation, was developed and used to benchmark the contouring accuracy and treatment plan quality within the predication strategy. A clinical workflow was developed to select the optimal CT simulation protocols incorporating patient size, target delineation, and radiation dose efficiency. An experimental study using an anthropomorphic pelvis phantom with added-bolus layers was used to demonstrate how the proposed prediction strategy could be implemented and how the optimal CT simulation protocols could be selected for prostate cancer patients based on patient size and treatment planning task. Clinical IMRT prostate treatment plans for seven CT scans with varied image quality indices were separately optimized and compared to verify the trace of target and organ dosimetry coverage. RESULTS: Based on the phantom study, the optimal image quality index for accurate manual prostate contouring was 4.4. The optimal tube potentials for patient sizes of 38, 43, 48, 53, and 58 cm were 120, 140, 140, 140, and 140 kVp, respectively, and the corresponding minimum CTDIvol for achieving the optimal image quality index 4.4 were 9.8, 32.2, 100.9, 241.4, and 274.1 mGy, respectively. For patients with lateral sizes of 43-58 cm, 120-kVp scan protocols yielded up to 165% greater radiation dose relative to 140-kVp protocols, and 140-kVp protocols always yielded a greater image quality index compared to the same dose-level 120-kVp protocols. The trace of target and organ dosimetry coverage and the γ passing rates of seven IMRT dose distribution pairs indicated the feasibility of the proposed image quality index for the predication strategy. CONCLUSIONS: A general strategy to predict the optimal CT simulation protocols in a flexible and quantitative way was developed that takes into account patient size, treatment planning task, and radiation dose. The experimental study indicated that the optimal CT simulation protocol and the corresponding radiation dose varied significantly for different patient sizes, contouring accuracy, and radiation treatment planning tasks.

Accuracy of food portion size estimation from digital pictures acquired by a chest-worn camera.

OBJECTIVE: Accurate estimation of food portion size is of paramount importance in dietary studies. We have developed a small, chest-worn electronic device called eButton which automatically takes pictures of consumed foods for objective dietary assessment. From the acquired pictures, the food portion size can be calculated semi-automatically with the help of computer software. The aim of the present study is to evaluate the accuracy of the calculated food portion size (volumes) from eButton pictures. DESIGN: Participants wore an eButton during their lunch. The volume of food in each eButton picture was calculated using software. For comparison, three raters estimated the food volume by viewing the same picture. The actual volume was determined by physical measurement using seed displacement. SETTING: Dining room and offices in a research laboratory. SUBJECTS: Seven lab member volunteers. RESULTS: Images of 100 food samples (fifty Western and fifty Asian foods) were collected and each food volume was estimated from these images using software. The mean relative error between the estimated volume and the actual volume over all the samples was -2·8 % (95 % CI -6·8 %, 1·2 %) with sd of 20·4 %. For eighty-five samples, the food volumes determined by computer differed by no more than 30 % from the results of actual physical measurements. When the volume estimates by the computer and raters were compared, the computer estimates showed much less bias and variability. CONCLUSIONS: From the same eButton pictures, the computer-based method provides more objective and accurate estimates of food volume than the visual estimation method.

Model-based measurement of food portion size for image-based dietary assessment using 3D/2D registration.

Dietary assessment is important in health maintenance and intervention in many chronic conditions, such as obesity, diabetes, and cardiovascular disease. However, there is currently a lack of convenient methods for measuring the volume of food (portion size) in real-life settings. We present a computational method to estimate food volume from a single photographical image of food contained in a typical dining plate. First, we calculate the food location with respect to a 3D camera coordinate system using the plate as a scale reference. Then, the food is segmented automatically from the background in the image. Adaptive thresholding and snake modeling are implemented based on several image features, such as color contrast, regional color homogeneity and curve bending degree. Next, a 3D model representing the general shape of the food (e.g., a cylinder, a sphere, etc.) is selected from a pre-constructed shape model library. The position, orientation and scale of the selected shape model are determined by registering the projected 3D model and the food contour in the image, where the properties of the reference are used as constraints. Experimental results using various realistically shaped foods with known volumes demonstrated satisfactory performance of our image based food volume measurement method even if the 3D geometric surface of the food is not completely represented in the input image.

Anthropometric body measurements based on multi-view stereo image reconstruction.

Anthropometric measurements, such as the circumferences of the hip, arm, leg and waist, waist-to-hip ratio, and body mass index, are of high significance in obesity and fitness evaluation. In this paper, we present a home based imaging system capable of conducting anthropometric measurements. Body images are acquired at different angles using a home camera and a simple rotating disk. Advanced image processing algorithms are utilized for 3D body surface reconstruction. A coarse body shape model is first established from segmented body silhouettes. Then, this model is refined through an inter-image consistency maximization process based on an energy function. Our experimental results using both a mannequin surrogate and a real human body validate the feasibility of the proposed system.

Automatic and Quantitative Measurement of Collagen Gel Contraction Using Model-Guided Segmentation.

Quantitative measurement of collagen gel contraction plays a critical role in the field of tissue engineering because it provides spatial-temporal assessment (e.g., changes of gel area and diameter during the contraction process) reflecting the cell behaviors and tissue material properties. So far the assessment of collagen gels relies on manual segmentation, which is time-consuming and suffers from serious intra- and inter-observer variability. In this study, we propose an automatic method combining various image processing techniques to resolve these problems. The proposed method first detects the maximal feasible contraction range of circular references (e.g., culture dish) and avoids the interference of irrelevant objects in the given image. Then, a three-step color conversion strategy is applied to normalize and enhance the contrast between the gel and background. We subsequently introduce a deformable circular model (DCM) which utilizes regional intensity contrast and circular shape constraint to locate the gel boundary. An adaptive weighting scheme was employed to coordinate the model behavior, so that the proposed system can overcome variations of gel boundary appearances at different contraction stages. Two measurements of collagen gels (i.e., area and diameter) can readily be obtained based on the segmentation results. Experimental results, including 120 gel images for accuracy validation, showed high agreement between the proposed method and manual segmentation with an average dice similarity coefficient larger than 0.95. The results also demonstrated obvious improvement in gel contours obtained by the proposed method over two popular, generic segmentation methods.

Computer aided quantification of pathological features for flexor tendon pulleys on microscopic images.

Quantifying the pathological features of flexor tendon pulleys is essential for grading the trigger finger since it provides clinicians with objective evidence derived from microscopic images. Although manual grading is time consuming and dependent on the observer experience, there is a lack of image processing methods for automatically extracting pulley pathological features. In this paper, we design and develop a color-based image segmentation system to extract the color and shape features from pulley microscopic images. Two parameters which are the size ratio of abnormal tissue regions and the number ratio of abnormal nuclei are estimated as the pathological progression indices. The automatic quantification results show clear discrimination among different levels of diseased pulley specimens which are prone to misjudgments for human visual inspection. The proposed system provides a reliable and automatic way to obtain pathological parameters instead of manual evaluation which is with intra- and interoperator variability. Experiments with 290 microscopic images from 29 pulley specimens show good correspondence with pathologist expectations. Hence, the proposed system has great potential for assisting clinical experts in routine histopathological examinations.

A knowledge-based approach for carpal tunnel segmentation from magnetic resonance images.

Carpal tunnel syndrome (CTS) has been reported as one of the most common peripheral neuropathies. Carpal tunnel segmentation from magnetic resonance (MR) images is important for the evaluation of CTS. To date, manual segmentation, which is time-consuming and operator dependent, remains the most common approach for the analysis of the carpal tunnel structure. Therefore, we propose a new knowledge-based method for automatic segmentation of the carpal tunnel from MR images. The proposed method first requires the segmentation of the carpal tunnel from the most proximally cross-sectional image. Three anatomical features of the carpal tunnel are detected by watershed and polygonal curve fitting algorithms to automatically initialize a deformable model as close to the carpal tunnel in the given image as possible. The model subsequently deforms toward the tunnel boundary based on image intensity information, shape bending degree, and the geometry constraints of the carpal tunnel. After the deformation process, the carpal tunnel in the most proximal image is segmented and subsequently applied to a contour propagation step to extract the tunnel contours sequentially from the remaining cross-sectional images. MR volumes from 15 subjects were included in the validation experiments. Compared with the ground truth of two experts, our method showed good agreement on tunnel segmentations by an average margin of error within 1 mm and dice similarity coefficient above 0.9.

Registration-based segmentation of three-dimensional ultrasound images for quantitative measurement of fetal craniofacial structure.

Segmentation of a fetal head from three-dimensional (3-D) ultrasound images is a critical step in the quantitative measurement of fetal craniofacial structure. However, two main issues complicate segmentation, including fuzzy boundaries and large variations in pose and shape among different ultrasound images. In this article, we propose a new registration-based method for automatically segmenting the fetal head from 3-D ultrasound images. The proposed method first detects the eyes based on Gabor features to identify the pose of the fetus image. Then, a reference model, which is constructed from a fetal phantom and contains prior knowledge of head shape, is aligned to the image via feature-based registration. Finally, 3-D snake deformation is utilized to improve the boundary fitness between the model and image. Four clinically useful parameters including inter-orbital diameter (IOD), bilateral orbital diameter (BOD), occipital frontal diameter (OFD) and bilateral parietal diameter (BPD) are measured based on the results of the eye detection and head segmentation. Ultrasound volumes from 11 subjects were used for validation of the method accuracy. Experimental results showed that the proposed method was able to overcome the aforementioned difficulties and achieve good agreement between automatic and manual measurements.

3D/2D Model-to-Image Registration for Quantitative Dietary Assessment.

Image-based dietary assessment is important for health monitoring and management because it can provide quantitative and objective information, such as food volume, nutrition type, and calorie intake. In this paper, a new framework, 3D/2D model-to-image registration, is presented for estimating food volume from a single-view 2D image containing a reference object (i.e., a circular dining plate). First, the food is segmented from the background image based on Otsu's thresholding and morphological operations. Next, the food volume is obtained from a user-selected, 3D shape model. The position, orientation and scale of the model are optimized by a model-to-image registration process. Then, the circular plate in the image is fitted and its spatial information is used as constraints for solving the registration problem. Our method takes the global contour information of the shape model into account to obtain a reliable food volume estimate. Experimental results using regularly shaped test objects and realistically shaped food models with known volumes both demonstrate the effectiveness of our method.

Automatic Insall-Salvati ratio measurement on lateral knee x-ray images using model-guided landmark localization.

The Insall-Salvati ratio (ISR) is important for detecting two common clinical signs of knee disease: patella alta and patella baja. Furthermore, large inter-operator differences in ISR measurement make an objective measurement system necessary for better clinical evaluation. In this paper, we define three specific bony landmarks for determining the ISR and then propose an x-ray image analysis system to localize these landmarks and measure the ISR. Due to inherent artifacts in x-ray images, such as unevenly distributed intensities, which make landmark localization difficult, we hence propose a registration-assisted active-shape model (RAASM) to localize these landmarks. We first construct a statistical model from a set of training images based on x-ray image intensity and patella shape. Since a knee x-ray image contains specific anatomical structures, we then design an algorithm, based on edge tracing, for patella feature extraction in order to automatically align the model to the patella image. We can estimate the landmark locations as well as the ISR after registration-assisted model fitting. Our proposed method successfully overcomes drawbacks caused by x-ray image artifacts. Experimental results show great agreement between the ISRs measured by the proposed method and by orthopedic clinicians.