Dagan Feng

Noninvasive Quantification of the Cerebral Metabolic Rate for Glucose Using Positron Emission Tomography, 18F-Fluoro-2-Deoxyglucose, the Patlak Method, and an Image-Derived Input Function

The authors developed and tested a method for the noninvasive quantification of the cerebral metabolic rate for glucose (CMRglc) using positron emission tomography (PET), 18F-fluoro-2-deoxyglucose, the Patlak method, and an image-derived input function. Dynamic PET data acquired 12 to 48 seconds after rapid tracer injection were summed to identify carotid artery regions of interest (ROIs). The input function then was generated from the carotid artery ROIs. To correct spillover, the early summed image was superimposed over the last PET frame, a tissue ROI was drawn around the carotid arteries, and a tissue time activity curve (TAC) was generated. Three venous samples were drawn from the tracer injection site at a later time and used for the spillover and partial volume correction by non-negative least squares method. Twenty-six patient data sets were studied. It was found that the image-derived input function was comparable in shape and magnitude to the one obtained by arterial blood sampling. Moreover, no significant difference was found between CMRglc estimated by the Patlak method using either the arterial blood sampling data or the image-derived input function.

An evaluation of the algorithms for determining local cerebral metabolic rates of glucose using positron emission tomography dynamic data

Measurement of the local cerebral metabolic rate of glucose (LCMRGlc) and the individual rate constant parameters of the [(18 )F]2-fluoro-2-deoxy-D-glucose (FDG) model can provide a clearer understanding and insight to the physiological processes in the human brain, and a quicker and more accurate means of diagnosis in clinical applications. A systematic study using simulated and clinical tissue time activity data is presented to evaluate several existing and newly developed major algorithms used for determining LCMRGlc and the individual rate constants from positron emission tomography dynamic data. The computational and statistical properties of the autoradiographic approach, weighted and unweighted nonlinear least squares methods, Patlak graphic approach, weighted integration method, linear least squares and generalized linear least squares methods are investigated and discussed in this paper.

Content-Based Medical Image Retrieval: A Survey of Applications to Multidimensional and Multimodality Data

Medical imaging is fundamental to modern healthcare, and its widespread use has resulted in the creation of image databases, as well as picture archiving and communication systems. These repositories now contain images from a diverse range of modalities, multidimensional (three-dimensional or time-varying) images, as well as co-aligned multimodality images. These image collections offer the opportunity for evidence-based diagnosis, teaching, and research; for these applications, there is a requirement for appropriate methods to search the collections for images that have characteristics similar to the case(s) of interest. Content-based image retrieval (CBIR) is an image search technique that complements the conventional text-based retrieval of images by using visual features, such as color, texture, and shape, as search criteria. Medical CBIR is an established field of study that is beginning to realize promise when applied to multidimensional and multimodality medical data. In this paper, we present a review of state-of-the-art medical CBIR approaches in five main categories: two-dimensional image retrieval, retrieval of images with three or more dimensions, the use of nonimage data to enhance the retrieval, multimodality image retrieval, and retrieval from diverse datasets. We use these categories as a framework for discussing the state of the art, focusing on the characteristics and modalities of the information used during medical image retrieval.

Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease

The accurate diagnosis of Alzheimers disease (AD) is essential for patient care and will be increasingly important as disease modifying agents become available, early in the course of the disease. Although studies have applied machine learning methods for the computer-aided diagnosis of AD, a bottleneck in the diagnostic performance was shown in previous methods, due to the lacking of efficient strategies for representing neuroimaging biomarkers. In this study, we designed a novel diagnostic framework with deep learning architecture to aid the diagnosis of AD. This framework uses a zero-masking strategy for data fusion to extract complementary information from multiple data modalities. Compared to the previous state-of-the-art workflows, our method is capable of fusing multimodal neuroimaging features in one setting and has the potential to require less labeled data. A performance gain was achieved in both binary classification and multiclass classification of AD. The advantages and limitations of the proposed framework are discussed.

A study on statistically reliable and computationally efficient algorithms for generating local cerebral blood flow parametric images with positron emission tomography

With the advent of positron emission tomography (PET), a variety of techniques have been developed to measure local cerebral blood flow (LCBF) noninvasively in humans. A potential class of techniques, which includes linear least squares (LS), linear weighted least squares (WLS), linear generalized least squares (GLS), and linear generalized weighted least squares (GWLS), is proposed. The statistical characteristics of these methods are examined by computer simulation. The authors present a comparison of these four methods with two other rapid estimation techniques developed by Huang et al. (1982) and Alpert (1984), and two classical methods, the unweighted and weighted nonlinear least squares regression. The results show that these methods can take full advantage of the contribution from the fine temporal sampling data of modern tomographs, and thus provide statistically reliable estimates that are comparable to those obtained from nonlinear LS regression. These methods also have high computational efficiency, and the parameters can be estimated directly from operational equations in one single step. Therefore, they can potentially be used in image-wide estimation of local cerebral blood flow and distribution volume with PET.

Optimal image sampling schedule: a new effective way to reduce dynamic image storage space and functional image processing time

An optimal image sampling schedule for tracer dynamic studies with positron emission tomography (PET) is proposed. This schedule incorporates the characteristics of PET measurement and uses a new cost function and the D-optimal criterion. A detailed case study of the estimation of the local cerebral metabolic rate of glucose (LCMRGLc) using the tracer fluorodeoxyglucose (FDG) and the four-parameter FDG model is presented. As the sampling schedule designed requires only four dynamic images, the storage space and data processing time are greatly reduced, while the precision of the parameter estimates is almost the same as that achieved with a commonly used schedule. The effects of intersubject and intrasubject parameter variations on parameter estimation with the use of this optimal sampling schedule are investigated by computer simulation. The simulation results show that the estimation of parameters is sufficiently robust with respect to these intersubject and intrasubject variations. The optimal sampling schedule is quite suitable therefore for PET regional parameter estimation, as well as for image-wide parameter estimation, for different subjects.

Fuzzy integral for leaf image retrieval

Generally, the more features utilized, the better the retrieval performance. However, it is a very challenging task to combine different feature sets in a way reflecting human perception. This paper presents the combination of different shape based feature sets using fuzzy integral for leaf image retrieval. The feature sets used in our system include centroid-contour distance curve, eccentricity, and angle code histogram. The fuzzy integral approach can release the users burden from tuning the combination parameters. In order to reduce the matching time in the retrieval process, a thinning based method is proposed to locate the start point of a leaf contour. Experimental results on 440 leaf images from 44 plant species (10 samples from each plant species) show that the fuzzy integral approach can achieve a comparable retrieval performance with the best case of the weighted summation combination. The results also indicate that our approach, which are more efficient, can achieve a better retrieval performance than both the curvature scale space (CSS) method and the modified Fourier descriptor (MFD) method.

Early diagnosis of Alzheimer's disease with deep learning

The accurate diagnosis of Alzheimers disease (AD) plays a significant role in patient care, especially at the early stage, because the consciousness of the severity and the progression risks allows the patients to take prevention measures before irreversible brain damages are shaped. Although many studies have applied machine learning methods for computer-aided-diagnosis (CAD) of AD recently, a bottleneck of the diagnosis performance was shown in most of the existing researches, mainly due to the congenital limitations of the chosen learning models. In this study, we design a deep learning architecture, which contains stacked auto-encoders and a softmax output layer, to overcome the bottleneck and aid the diagnosis of AD and its prodromal stage, Mild Cognitive Impairment (MCI). Compared to the previous workflows, our method is capable of analyzing multiple classes in one setting, and requires less labeled training samples and minimal domain prior knowledge. A significant performance gain on classification of all diagnosis groups was achieved in our experiments.

Accelerating magnetic resonance imaging via deep learning

This paper proposes a deep learning approach for accelerating magnetic resonance imaging (MRI) using a large number of existing high quality MR images as the training datasets. An off-line convolutional neural network is designed and trained to identify the mapping relationship between the MR images obtained from zero-filled and fully-sampled k-space data. The network is not only capable of restoring fine structures and details but is also compatible with online constrained reconstruction methods. Experimental results on real MR data have shown encouraging performance of the proposed method for efficient and accurate imaging.

A new double modeling approach for dynamic cardiac PET studies using noise and spillover contaminated LV measurements

A new double modeling approach for dynamic cardiac studies with positron emission tomography (PET) to estimate physiological parameters is proposed. This approach is exemplified by tracer fluorodeoxyglucose (FDG) studies and estimation of myocardial metabolic rate of glucose (MMRGlc). A separate input function model characterising the tracer kinetics in plasma is used to account for the measurement noise and spillover problems of the input curve obtained from the left ventricular region on the PET images. Measured left ventricle (LV) plasma time-activity and tissue time-activity curves are fitted simultaneously with cross contaminations by this input function model and the FDG model. The results indicate that the MMRGlc can be estimated much more accurately and reliably by this new approach. Compared with the traditional method, an improvement of about 20% in the estimated MMRGlc was achieved when the bidirectional spillover fractions are 20% at different noise levels studied. This new double modeling approach using two models fitting both the input and the output functions simultaneously is expected to be generally applicable to a broad range of system modeling.