A Primer for Utilizing Deep Learning and Abdominal MRI Imaging Features to Monitor Autosomal Dominant Polycystic Kidney Disease Progression

Abdominal imaging of autosomal dominant polycystic kidney disease (ADPKD) has historically focused on detecting complications such as cyst rupture, cyst infection, obstructing renal calculi, and pyelonephritis; discriminating complex cysts from renal cell carcinoma; and identifying sources of abdominal pain. Many imaging features of ADPKD are incompletely evaluated or not deemed to be clinically significant, and because of this, treatment options are limited. However, total kidney volume (TKV) measurement has become important for assessing the risk of disease progression (i.e., Mayo Imaging Classification) and predicting tolvaptan treatment's efficacy. Deep learning for segmenting the kidneys has improved these measurements' speed, accuracy, and reproducibility. Deep learning models can also segment other organs and tissues, extracting additional biomarkers to characterize the extent to which extrarenal manifestations complicate ADPKD. In this concept paper, we demonstrate how deep learning may be applied to measure the TKV and how it can be extended to measure additional features of this disease.

The role of AI in prostate MRI quality and interpretation: Opportunities and challenges

Prostate MRI plays an important role in imaging the prostate gland and surrounding tissues, particularly in the diagnosis and management of prostate cancer. With the widespread adoption of multiparametric magnetic resonance imaging in recent years, the concerns surrounding the variability of imaging quality have garnered increased attention. Several factors contribute to the inconsistency of image quality, such as acquisition parameters, scanner differences and interobserver variabilities. While efforts have been made to standardize image acquisition and interpretation via the development of systems, such as PI-RADS and PI-QUAL, the scoring systems still depend on the subjective experience and acumen of humans. Artificial intelligence (AI) has been increasingly used in many applications, including medical imaging, due to its ability to automate tasks and lower human error rates. These advantages have the potential to standardize the tasks of image interpretation and quality control of prostate MRI. Despite its potential, thorough validation is required before the implementation of AI in clinical practice. In this article, we explore the opportunities and challenges of AI, with a focus on the interpretation and quality of prostate MRI.

Personalized visual encoding model construction with small data

Quantifying population heterogeneity in brain stimuli-response mapping may allow insight into variability in bottom-up neural systems that can in turn be related to individual's behavior or pathological state. Encoding models that predict brain responses to stimuli are one way to capture this relationship. However, they generally need a large amount of fMRI data to achieve optimal accuracy. Here, we propose an ensemble approach to create encoding models for novel individuals with relatively little data by modeling each subject's predicted response vector as a linear combination of the other subjects' predicted response vectors. We show that these ensemble encoding models trained with hundreds of image-response pairs, achieve accuracy not different from models trained on 20,000 image-response pairs. Importantly, the ensemble encoding models preserve patterns of inter-individual differences in the image-response relationship. We also show the proposed approach is robust against domain shift by validating on data with a different scanner and experimental setup. Additionally, we show that the ensemble encoding models are able to discover the inter-individual differences in various face areas' responses to images of animal vs human faces using a recently developed NeuroGen framework. Our approach shows the potential to use existing densely-sampled data, i.e. large amounts of data collected from a single individual, to efficiently create accurate, personalized encoding models and, subsequently, personalized optimal synthetic images for new individuals scanned under different experimental conditions.

A two-dimensional feasibility study of deep learning-based feature detection and characterization directly from CT sinograms

Machine Learning, especially deep learning, has been used in typical x-ray computed tomography (CT) applications, including image reconstruction, image enhancement, image domain feature detection and image domain feature characterization. To our knowledge, this is the first study on machine learning for feature detection and analysis directly based on CT projection data. Specifically, we present neural network methods for blood vessel detection and characterization in the sinogram domain avoiding any partial volume, beam hardening, or motion artifacts introduced during reconstruction. First, we estimate sinogram domain vessel maps using a residual encoder-decoder convolutional neural network (REDCNN). Next, we estimate the vessel centerline and we extract the vessel-only sinogram from the original sinogram, eliminating any background information. Finally, we use a fully connected neural network to estimate the vessel lumen cross-sectional area from the vessel-only sinogram. We trained and tested the proposed methods using CatSim simulations, real CT measurements of vessel phantoms, and clinical data from the NIH CT image database. We achieved encouraging initial results showing the feasibility of CT analysis in the sinogram domain. In principle, sinogram domain analysis should be possible for many other and more complicated clinical CT analysis tasks. Further studies are needed for this sinogram domain analysis approach to become practical for clinical applications.

Hierarchical Organization of Tau and Amyloid Deposits in the Cerebral Cortex

Importance

Abnormal accumulation of tau and amyloid-β (Aβ) proteins in the human brain are 2 pathologic hallmarks of Alzheimer disease (AD). Because pathologic processes begin decades before the onset of the clinical manifestations, the study of the cortical distribution of early-stage pathologic alterations is critical in understanding the underpinnings of the disease.

Objectives

To identify the in vivo brain spatial distributions of tau and Aβ deposits in a sample of cognitively normal participants in the Harvard Aging Brain Study, determine spatial patterns of pathologic alterations, and provide means for improved individual in vivo staging.

Design, Setting, and Participants

Eighty-eight individuals from the general community underwent flortaucipir 18 T807 (18F-T807) and carbon 11-labeled Pittsburgh Compound B (11C-PiB) positron emission tomographic (PET) imaging. A voxel-level hierarchical clustering approach was used to obtain the main clustering partitions corresponding to the cortical distribution maps of 18F-T807 and 11C-PiB. Hierarchical relationships between areas of distinctive pathologic deposits were then studied. Using cerebellar gray reference, 18F-T807 data were expressed as standardized uptake value ratio, and 11C-PiB were given as distribution volume ratio.

Main Outcomes and Measures

Main in vivo and hierarchically organized tau and Aβ deposits in the elderly brain.

Results

Of the 88 study participants, 39 (44%) were men, with a mean (SD) age of 76.2 (6.2) years. The tau and Aβ maps both displayed optimal cortical partitions at 4 clusters. The tau deposits were grouped in the temporal lobe, distributed in heteromodal areas, medial and visual regions, and primary somatomotor cortex; the Aβ deposits were clustered in the heteromodal areas and rather patchy in distributed regions involving the primary cortices, medial structures, and temporal areas. Moreover, tau deposits in the temporal lobe and distributed heteromodal areas were tightly nested.

Conclusions and Relevance

Tau and Aβ deposits in the elderly brain generally display well-defined hierarchical cortical relationships as well as overlaps between the principal clusters of both pathologic alterations in the heteromodal association regions. These findings represent systematic, large-scale mechanisms of early AD pathology.

Probabilistic Modeling of Imaging, Genetics and Diagnosis

We propose a unified Bayesian framework for detecting genetic variants associated with disease by exploiting image-based features as an intermediate phenotype. The use of imaging data for examining genetic associations promises new directions of analysis, but currently the most widely used methods make sub-optimal use of the richness that these data types can offer. Currently, image features are most commonly selected based on their relevance to the disease phenotype. Then, in a separate step, a set of genetic variants is identified to explain the selected features. In contrast, our method performs these tasks simultaneously in order to jointly exploit information in both data types. The analysis yields probabilistic measures of clinical relevance for both imaging and genetic markers. We derive an efficient approximate inference algorithm that handles the high dimensionality of image and genetic data. We evaluate the algorithm on synthetic data and demonstrate that it outperforms traditional models. We also illustrate our method on Alzheimer's Disease Neuroimaging Initiative data.

Genetic variation and neuroimaging measures in Alzheimer disease

OBJECTIVE

To investigate whether genome-wide association study (GWAS)-validated and GWAS-promising candidate loci influence magnetic resonance imaging measures and clinical Alzheimer's disease (AD) status.

DESIGN

Multicenter case-control study of genetic and neuroimaging data from the Alzheimer's Disease Neuroimaging Initiative.

SETTING

Multicenter GWAS. Patients A total of 168 individuals with probable AD, 357 with mild cognitive impairment, and 215 cognitively normal control individuals recruited from more than 50 Alzheimer's Disease Neuroimaging Initiative centers in the United States and Canada. All study participants had APOE and genome-wide genetic data available.

MAIN OUTCOME MEASURES

We investigated the influence of GWAS-validated and GWAS-promising novel AD loci on hippocampal volume, amygdala volume, white matter lesion volume, entorhinal cortex thickness, parahippocampal gyrus thickness, and temporal pole cortex thickness.

RESULTS

Markers at the APOE locus were associated with all phenotypes except white matter lesion volume (all false discovery rate-corrected P values < .001). Novel and established AD loci identified by prior GWASs showed a significant cumulative score-based effect (false discovery rate P = .04) on all analyzed neuroimaging measures. The GWAS-validated variants at the CR1 and PICALM loci and markers at 2 novel loci (BIN1 and CNTN5) showed association with multiple magnetic resonance imaging characteristics (false discovery rate P < .05).

CONCLUSIONS

Loci associated with AD also influence neuroimaging correlates of this disease. Furthermore, neuroimaging analysis identified 2 additional loci of high interest for further study.

Task-optimal registration cost functions

In this paper, we propose a framework for learning the parameters of registration cost functions--such as the tradeoff between the regularization and image similiarity term--with respect to a specific task. Assuming the existence of labeled training data, we specialize the framework for the task of localizing hidden labels via image registration. We learn the parameters of the weighted sum of squared differences (wSSD) image similarity term that are optimal for the localization of Brodmann areas (BAs) in a new subject based on cortical geometry. We demonstrate state-of-the-art localization of V1, V2, BA44 and BA45.

Spherical demons: fast surface registration

We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently implemented on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, the resulting registration is diffeomorphic and fast - registration of two cortical mesh models with more than 100k nodes takes less than 5 minutes, comparable to the fastest surface registration algorithms. Moreover, the accuracy of our method compares favorably to the popular FreeSurfer registration algorithm. We validate the technique in two different settings: (1) parcellation in a set of in-vivo cortical surfaces and (2) Brodmann area localization in ex-vivo cortical surfaces.

Superiority of entangled measurements over all local strategies for the estimation of product coherent states

It is shown that the ensemble {P(alpha),|alpha|alpha;{*}}, where P(alpha) is a Gaussian distribution of finite variance and |alpha is a coherent state, can be better discriminated with an entangled measurement than with any local strategy supplemented by classical communication. Although this ensemble consists of products of quasiclassical states without any squeezing, it thus exhibits a purely quantum feature. This remarkable effect is demonstrated experimentally by implementing the optimal local strategy on coherent states of light together with a global strategy that yields a higher fidelity.

Gradient based nonuniform subsampling for information-theoretic alignment methods

We examine the computation of information-theoretic image registration metrics and propose two (deterministic and stochastic) nonuniform subsampling methods for improving the efficiency. The proposed schemes attempt to use only the most relevant information as the basis of the computation. Both methods are shown to yield considerable improvement over the current practice of uniform subsampling. Theoretical and experimental evidence is provided.

What Data to Co-register for Computing Atlases

We argue that registration should be thought of as a means to an end, and not as a goal by itself. In particular, we consider the problem of predicting the locations of hidden labels of a test image using observable features, given a training set with both the hidden labels and observable features. For example, the hidden labels could be segmentation labels or activation regions in fMRI, while the observable features could be sulcal geometry or MR intensity. We analyze a probabilistic framework for computing an optimal atlas, and the subsequent registration of a new subject using only the observable features to optimize the hidden label alignment to the training set. We compare two approaches for co-registering training images for the atlas construction: the traditional approach of only using observable features and a novel approach of only using hidden labels. We argue that the alternative approach is superior particularly when the relationship between the hidden labels and observable features is complex and unknown. As an application, we consider the task of registering cortical folds to optimize Brodmann area localization. We show that the alignment of the Brodmann areas improves by up to 25% when using the alternative atlas compared with the traditional atlas. To the best of our knowledge, these are the most accurate Brodmann area localization results (achieved via cortical fold registration) reported to date.