Description: Recent advances in imaging genetics produce large amounts of data including functional MRI images, single nucleotide polymorphisms (SNPs), and cognitive assessments. Understanding the complex interactions among these heterogeneous and complementary data has the potential to help with diagnosis and prevention of mental disorders. However, limited efforts have been made due to the high dimensionality, group structure, and mixed type of these data. In this paper, we present a novel method to detect conditional associations between imaging genetics data. We use projected distance correlation to build a conditional dependency graph among high-dimensional mixed data, and then use multiple testing to detect significant group level associations (e.g., regions of interest-gene). In addition, we introduce a scalable algorithm based on orthogonal greedy algorithm, yielding the greedy projected distance correlation (G-PDC). This can reduce the computational cost, which is critical for analyzing large volume of imaging genomics data. The results from our simulations demonstrate a higher degree of accuracy with G-PDC than distance correlation, Pearson’s correlation, and partial correlation, especially when the correlation is nonlinear. Finally, we apply our method to the Philadelphia Neurodevelopmental data cohort with 866 samples including fMRI images and SNP profiles. The results uncover several statistically significant and biologically interesting interactions, which are further validated with many existing studies. The MATLAB code is available at https://sites.google.com/site/jianfang86/gPDC .

Description: Ultrafast ultrasound imaging using plane or diverging waves, instead of focused beams, has advanced greatly the development of novel ultrasound imaging methods for evaluating tissue functions beyond anatomical information. However, the sonographic signal-to-noise ratio (SNR) of ultrafast imaging remains limited due to the lack of transmission focusing, and thus insufficient acoustic energy delivery. We hereby propose a new ultrafast ultrasound imaging methodology with cascaded dual-polarity waves (CDWs), which consists of a pulse train with positive and negative polarities. A new coding scheme and a corresponding linear decoding process were thereby designed to obtain the recovered signals with increased amplitude, thus increasing the SNR without sacrificing the frame rate. The newly designed CDW ultrafast ultrasound imaging technique achieved higher quality B-mode images than coherent plane-wave compounding (CPWC) and multiplane wave (MW) imaging in a calibration phantom, ex vivo pork belly, and in vivo human back muscle. CDW imaging shows a significant improvement in the SNR (10.71 dB versus CPWC and 7.62 dB versus MW), penetration depth (36.94% versus CPWC and 35.14% versus MW), and contrast ratio in deep regions (5.97 dB versus CPWC and 5.05 dB versus MW) without compromising other image quality metrics, such as spatial resolution and frame rate. The enhanced image qualities and ultrafast frame rates offered by CDW imaging beget great potential for various novel imaging applications.

Description: Automated cell segmentation and tracking is essential for dynamic studies of cellular morphology, movement, and interactions as well as other cellular behaviors. However, accurate, automated, and easy-to-use cell segmentation remains a challenge, especially in cases of high cell densities, where discrete boundaries are not easily discernable. Here, we present a fully automated segmentation algorithm that iteratively segments cells based on the observed distribution of optical cell volumes measured by quantitative phase microscopy. By fitting these distributions to known probability density functions, we are able to converge on volumetric thresholds that enable valid segmentation cuts. Since each threshold is determined from the observed data itself, virtually no input is needed from the user. We demonstrate the effectiveness of this approach over time using six cell types that display a range of morphologies, and evaluate these cultures over a range of confluencies. Facile dynamic measures of cell mobility and function revealed unique cellular behaviors that relate to tissue origins, state of differentiation, and real-time signaling. These will improve our understanding of multicellular communication and organization.

Description: Positron emission tomography (PET) is a functional imaging modality widely used in oncology, cardiology, and neuroscience. It is highly sensitive, but suffers from relatively poor spatial resolution, as compared with anatomical imaging modalities, such as magnetic resonance imaging (MRI). With the recent development of combined PET/MR systems, we can improve the PET image quality by incorporating MR information into image reconstruction. Previously, kernel learning has been successfully embedded into static and dynamic PET image reconstruction using either PET temporal or MRI information. Here, we combine both PET temporal and MRI information adaptively to improve the quality of direct Patlak reconstruction. We examined different approaches to combine the PET and MRI information in kernel learning to address the issue of potential mismatches between MRI and PET signals. Computer simulations and hybrid real-patient data acquired on a simultaneous PET/MR scanner were used to evaluate the proposed methods. Results show that the method that combines PET temporal information and MRI spatial information adaptively based on the structure similarity index has the best performance in terms of noise reduction and resolution improvement.

Description: The simultaneous removal of noise and preservation of the integrity of 3-D magnetic resonance (MR) images is a difficult and important task. In this paper, we consider characterizing MR images with 3-D operators, and present a novel 4-D transform-domain method termed ‘modified nonlocal tensor-SVD (MNL-tSVD)’ for MR image denoising. The proposed method is based on the grouping, hard-thresholding and aggregation paradigms, and can be viewed as a generalized nonlocal extension of tensor-SVD (t-SVD). By keeping MR images in its natural three-dimensional form, and collaboratively filtering similar patches, MNL-tSVD utilizes both the self-similarity property and 3-D structure of MR images to preserve more actual details and minimize the introduction of new artifacts. We show the adaptability of MNL-tSVD by incorporating it into a two-stage denoising strategy with a few adjustments. In addition, analysis of the relationship between MNL-tSVD and current the state-of-the-art 4-D transforms is given. Experimental comparisons over simulated and real brain data sets at different Rician noise levels show that MNL-tSVD can produce competitive performance compared with related approaches.

Description: We present the first in vivo images of anisotropic conductivity distribution in the human head, measured at a frequency of approximately 10 Hz. We used magnetic resonance electrical impedance tomography techniques to encode phase changes caused by current flow within the head via two independent electrode pairs. These results were then combined with diffusion tensor imaging data to reconstruct full anisotropic conductivity distributions in 5-mm-thick slices of the brains of two participants. Conductivity values recovered in this paper were broadly consistent with literature values. We anticipate that this technique will be of use in many areas of neuroscience, most importantly in functional imaging via inverse electroencephalogram. Future studies will involve pulse sequence acceleration to maximize brain coverage and resolution.

Description: We present a novel reconstruction algorithm based on a general cone-beam CT forward model, which is capable of incorporating the blur and noise correlations that are exhibited in flat-panel CBCT measurement data. Specifically, the proposed model may include scintillator blur, focal-spot blur, and noise correlations due to light spread in the scintillator. The proposed algorithm (GPL-BC) uses a Gaussian Penalized-Likelihood objective function, which incorporates models of blur and correlated noise. In a simulation study, GPL-BC was able to achieve lower bias as compared with deblurring followed by FDK as well as a model-based reconstruction method without integration of measurement blur. In the same study, GPL-BC was able to achieve better line-pair reconstructions (in terms of segmented-image accuracy) as compared with deblurring followed by FDK, a model-based method without blur, and a model-based method with blur but not noise correlations. A prototype extremities quantitative cone-beam CT test-bench was used to image a physical sample of human trabecular bone. These data were used to compare reconstructions using the proposed method and model-based methods without blur and/or correlation to a registered $mu $ CT image of the same bone sample. The GPL-BC reconstructions resulted in more accurate trabecular bone segmentation. Multiple trabecular bone metrics, including trabecular thickness (Tb.Th.) were computed for each reconstruction approach as well as the $mu $ CT volume. The GPL-BC reconstruction provided the most accurate Tb.Th. measurement, 0.255 mm, as compared with the $mu $ CT derived value of 0.193 mm, followed by the GPL-B reconstruction, the GPL-I reconstruction, and then the FDK reconstruction (0.271 mm, 0.309 mm, and 0.335 mm, respect- vely).

Description: Computer-aided diagnosis (CAD) of retinal pathologies is a current active area in medical image analysis. Due to the increasing use of retinal optical coherence tomography (OCT) imaging technique, a CAD system in retinal OCT is essential to assist ophthalmologist in the early detection of ocular diseases and treatment monitoring. This paper presents a novel CAD system based on a multi-scale convolutional mixture of expert (MCME) ensemble model to identify normal retina, and two common types of macular pathologies, namely, dry age-related macular degeneration, and diabetic macular edema. The proposed MCME modular model is a data-driven neural structure, which employs a new cost function for discriminative and fast learning of image features by applying convolutional neural networks on multiple-scale sub-images. MCME maximizes the likelihood function of the training data set and ground truth by considering a mixture model, which tries also to model the joint interaction between individual experts by using a correlated multivariate component for each expert module instead of only modeling the marginal distributions by independent Gaussian components. Two different macular OCT data sets from Heidelberg devices were considered for the evaluation of the method, i.e., a local data set of OCT images of 148 subjects and a public data set of 45 OCT acquisitions. For comparison purpose, we performed a wide range of classification measures to compare the results with the best configurations of the MCME method. With the MCME model of four scale-dependent experts, the precision rate of 98.86%, and the area under the receiver operating characteristic curve (AUC) of 0.9985 were obtained on average.

Description: The most commonly used evaluation metrics for quality assessment of retinal vessel segmentation are sensitivity, specificity, and accuracy, which are based on pixel-to-pixel matching. However, due to the inter-observer problem that vessels annotated by different observers vary in both thickness and location, pixel-to-pixel matching is too restrictive to fairly evaluate the results of vessel segmentation. In this paper, the proposed skeletal similarity metric is constructed by comparing the skeleton maps generated from the reference and the source vessel segmentation maps. To address the inter-observer problem, instead of using a pixel-to-pixel matching strategy, each skeleton segment in the reference skeleton map is adaptively assigned with a searching range whose radius is determined based on its vessel thickness. Pixels in the source skeleton map located within the searching range are then selected for similarity calculation. The skeletal similarity consists of a curve similarity, which measures the structural similarity between the reference and the source skeleton maps and a thickness similarity, which measures the thickness consistency between the reference and the source vessel segmentation maps. In contrast to other metrics that provide a global score for the overall performance, we modify the definitions of true positive, false negative, true negative, and false positive based on the skeletal similarity, based on which sensitivity, specificity, accuracy, and other objective measurements can be constructed. More importantly, the skeletal similarity metric has better potential to be used as a pixelwise loss function for training deep learning models for retinal vessel segmentation. Through comparison of a set of examples, we demonstrate that the redefined metrics based on the skeletal similarity are more effective for quality evaluation, especially with greater tolerance to the inter-observer problem.