Abstract

Model calibration measures the agreement between the predicted probability estimates and the true correctness likelihood. Proper model calibration is vital for high-risk applications. Unfortunately, modern deep neural networks are poorly calibrated, compromising trustworthiness and reliability. Medical image segmentation particularly suffers from this due to the natural uncertainty of tissue boundaries. This is exasperated by their loss functions, which favor overconfidence in the majority classes. We address these challenges with DOMINO, a domain-aware model calibration method that leverages the semantic confusability and hierarchical similarity between class labels. Our experiments demonstrate that our DOMINO-calibrated deep neural networks outperform non-calibrated models and state-of-the-art morphometric methods in head image segmentation. Our results show that our method can consistently achieve better calibration, higher accuracy, and faster inference times than these methods, especially on rarer classes. This performance is attributed to our domain-aware regularization to inform semantic model calibration. These findings show the importance of semantic ties between class labels in building confidence in deep learning models. The framework has the potential to improve the trustworthiness and reliability of generic medical image segmentation models.

Abstract

Background

Extracellular amyloid plaques in gray matter are the earliest pathological marker for Alzheimer’s disease (AD), followed by abnormal intraneuronal tau protein accumulation. Diffusion MRI (dMRI) is an imaging technique that estimates diffusion properties of the extracellular and tissue compartments. The link between diffusion changes and amyloid and tau pathology in gray matter is not well understood. We aimed to characterize the relationship between diffusion measures and amyloid and tau deposits in the gray matter across Braak stages, as assessed by tau PET imaging, in mild cognitive impairment (MCI) and AD patients.

Methods

Results

Discussion

Abstract

Background

Diabetic retinopathy (DR) is a leading cause of blindness in American adults. If detected, DR can be treated to prevent further damage causing blindness. There is an increasing interest in developing artificial intelligence (AI) technologies to help detect DR using electronic health records. The lesion-related information documented in fundus image reports is a valuable resource that could help diagnoses of DR in clinical decision support systems. However, most studies for AI-based DR diagnoses are mainly based on medical images; there is limited studies to explore the lesion-related information captured in the free text image reports.

Methods

Results

Conclusions

Abstract

A body of studies has proposed to obtain high-quality images from low-dose and noisy Computed Tomography (CT) scans for radiation reduction. However, these studies are designed for population-level data without considering the variation in CT devices and individuals, limiting the current approaches' performance, especially for ultra-low-dose CT imaging. Here, we proposed PIMA-CT, a physical anthropomorphic phantom model integrating an unsupervised learning framework, using a novel deep learning technique called Cyclic Simulation and Denoising (CSD), to address these limitations. We first acquired paired low-dose and standard-dose CT scans of the phantom and then developed two generative neural networks: noise simulator and denoiser. The simulator extracts real low-dose noise and tissue features from two separate image spaces (e.g., low-dose phantom model scans and standard-dose patient scans) into a unified feature space. Meanwhile, the denoiser provides feedback to the simulator on the quality of the generated noise. In this way, the simulator and denoiser cyclically interact to optimize network learning and ease the denoiser to simultaneously remove noise and restore tissue features. We thoroughly evaluate our method for removing both real low-dose noise and Gaussian simulated low-dose noise. The results show that CSD outperforms one of the state-of-the-art denoising algorithms without using any labeled data (actual patients' low-dose CT scans) nor simulated low-dose CT scans. This study may shed light on incorporating physical models in medical imaging, especially for ultra-low level dose CT scans restoration.

Abstract

In addition to the well-established somatotopy in the pre- and post-central gyrus, there is now strong evidence that somatotopic organization is evident across other regions in the sensorimotor network. This raises several experimental questions: To what extent is activity in the sensorimotor network effector-dependent and effector-independent? How important is the sensorimotor cortex when predicting the motor effector? Is there redundancy in the distributed somatotopically organized network such that removing one region has little impact on classification accuracy? To answer these questions, we developed a novel experimental approach. fMRI data were collected while human subjects performed a precisely controlled force generation task separately with their hand, foot, and mouth. We used a simple linear iterative clustering (SLIC) algorithm to segment whole-brain beta coefficient maps to build an adaptive brain parcellation and then classified effectors using extreme gradient boosting (XGBoost) based on parcellations at various spatial resolutions. This allowed us to understand how data-driven adaptive brain parcellation granularity altered classification accuracy. Results revealed effector-dependent activity in regions of the post-central gyrus, precentral gyrus, and paracentral lobule. SMA, regions of the inferior and superior parietal lobule, and cerebellum each contained effector-dependent and effector-independent representations. Machine learning analyses showed that increasing the spatial resolution of the data-driven model increased classification accuracy, which reached 94% with over 1,755 supervoxels. Our SLIC-based supervoxel parcellation outperformed classification analyses using established brain templates and random simulations. Occlusion experiments further demonstrated redundancy across the sensorimotor network when classifying effectors. Our observations extend our understanding of effector-dependent and effector-independent organization within the human brain and provide new insight into the functional neuroanatomy required to predict the motor effector used in a motor control task.

Abstract

Background and Objectives: Prediction of decline to dementia using objective biomarkers in high-risk patients with amnestic mild cognitive impairment (aMCI) has immense utility. Our objective was to use multimodal MRI to 1) determine whether accurate and precise prediction of dementia conversion could be achieved using baseline data alone, and 2) generate a map of the brain regions implicated in longitudinal decline to dementia.

Methods: Participants meeting criteria for aMCI at baseline (N=55) were classified at follow-up as remaining stable/improved in their diagnosis (N=41) or declined to dementia (N=14). Baseline T1 structural MRI and resting-state fMRI (rsfMRI) were combined and a semi-supervised support vector machine (SVM) which separated stable participants from those who decline at follow-up with maximal margin. Cross-validated model performance metrics and MRI feature weights were calculated to include the strength of each brain voxel in its ability to distinguish the two groups.

Results: Total model accuracy for predicting diagnostic change at follow-up was 92.7% using baseline T1 imaging alone, 83.5% using rsfMRI alone, and 94.5% when combining T1 and rsfMRI modalities. Feature weights that survived the p<0.01 threshold for separation of the two groups revealed the strongest margin in the combined structural and functional regions underlying the medial temporal lobes in the limbic system.

Discussion: An MRI-driven SVM model demonstrates accurate and precise prediction of later dementia conversion in aMCI patients. The multi-modal regions driving this prediction were the strongest in the medial temporal regions of the limbic system, consistent with literature on the progression of Alzheimer’s disease.

Abstract

Recently, deep neural networks have demonstrated comparable and even better performance than board-certified ophthalmologists in well-annotated datasets. However, the diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a multi-scale input along with multiple domain adaptors applied hierarchically in both feature and output spaces. The proposed training strategy and novel unsupervised domain adaptation framework, called Collaborative Adversarial Domain Adaptation (CADA), can effectively overcome the challenge. Multi-scale inputs can reduce the information loss due to the pooling layers used in the network for feature extraction, while our proposed CADA is an interactive paradigm that presents an exquisite collaborative adaptation through both adversarial learning and ensembling weights at different network layers. In particular, to produce a better prediction for the unlabeled target domain data, we simultaneously achieve domain invariance and model generalizability via adversarial learning at multi-scale outputs from different levels of network layers and maintaining an exponential moving average (EMA) of the historical weights during training. Without annotating any sample from the target domain, multiple adversarial losses in encoder and decoder layers guide the extraction of domain-invariant features to confuse the domain classifier. Meanwhile, the ensembling of weights via EMA reduces the uncertainty of adapting multiple discriminator learning. Comprehensive experimental results demonstrate that our CADA model incorporating multi-scale input training can overcome performance degradation and outperform state-of-the-art domain adaptation methods in segmenting retinal optic disc and cup from fundus images stemming from the REFUGE, Drishti-GS, and Rim-One-r3 datasets. The code will be available at https://github.com/cswin/CADA

Abstract

This article deals with approximating steady-state particle-resolved fluid flow around a fixed particle of interest under the influence of randomly distributed stationary particles in a dispersed multiphase setup using convolutional neural network (CNN). The considered problem involves rotational symmetry about the mean velocity (streamwise) direction. Thus, this work enforces this symmetry using SE(3)-equivariant, special Euclidean group of dimension 3, CNN architecture, which is translation and three-dimensional rotation equivariant. This study mainly explores the generalization capabilities and benefits of a SE(3)-equivariant network. Accurate synthetic flow fields for Reynolds number and particle volume fraction combinations spanning over a range of [86.22, 172.96] and [0.11, 0.45], respectively, are produced with careful application of symmetry-aware data-driven approach.

Abstract

Fluid flow around a random distribution of stationary spherical particles is a problem of substantial importance in the study of dispersed multiphase flows. In this paper we present a machine learning methodology using Generative Adversarial Network framework and Convolutional Neural Network architecture to recreate particle-resolved fluid flow around a random distribution of monodispersed particles. The model was applied to various Reynolds number and par- ticle volume fraction combinations spanning over a range of [2.69, 172.96] and [0.11, 0.45] respectively. Test performance of the model for the studied cases is very promising.
Keywords: Pseudo-turbulence, Multiphase Flow prediction, Generative Adversarial Network (GAN), Convolutional Neural Network (CNN)

Abstract

Alzheimer's disease is the leading cause of dementia. The long progression period in Alzheimer's disease provides a possibility for patients to get early treatment by having routine screenings. However, current clinical diagnostic imaging tools do not meet the specific requirements for screening procedures due to high cost and limited availability. In this work, we took the initiative to evaluate the retina, especially the retinal vasculature, as an alternative for conducting screenings for dementia patients caused by Alzheimer's disease. Highly modular machine learning techniques were employed throughout the whole pipeline. Utilizing data from the UK Biobank, the pipeline achieved an average classification accuracy of 82.44%. Besides the high classification accuracy, we also added a saliency analysis to strengthen this pipeline's interpretability. The saliency analysis indicated that within retinal images, small vessels carry more information for diagnosing Alzheimer's diseases, which aligns with related studies.

Abstract

Background

Transcranial direct current stimulation (tDCS) is widely investigated as a therapeutic tool to enhance cognitive function in older adults with and without neurodegenerative disease. Prior research demonstrates that electric current delivery to the brain can vary significantly across individuals. Quantification of this variability could enable person-specific optimization of tDCS outcomes. This pilot study used machine learning and MRI-derived electric field models to predict working memory improvements as a proof of concept for precision cognitive intervention.

Methods

Fourteen healthy older adults received 20 minutes of 2 mA tDCS stimulation (F3/F4) during a two-week cognitive training intervention. Participants performed an N-back working memory task pre-/post-intervention. MRI-derived current models were passed through a linear Support Vector Machine (SVM) learning algorithm to characterize crucial tDCS current components (intensity and direction) that induced working memory improvements in tDCS responders versus non-responders.

Main results

SVM models of tDCS current components had 86% overall accuracy in classifying treatment responders vs. non-responders, with current intensity producing the best overall model differentiating changes in working memory performance. Median current intensity and direction in brain regions near the electrodes were positively related to intervention responses.

Conclusions

This study provides the first evidence that pattern recognition analyses of MRI-derived tDCS current models can provide individual prognostic classification of tDCS treatment response with 86% accuracy. Individual differences in current intensity and direction play important roles in determining treatment response to tDCS. These findings provide important insights into mechanisms of tDCS response as well as proof of concept for future precision dosing models of tDCS intervention.

Abstract

A handheld near-infrared optical scanner (NIROS) was recently developed to map for effective changes in oxy- and deoxyhemoglobin concentration in diabetic foot ulcers (DFUs) across weeks of treatment. Herein, a coregistration and image segmentation approach was implemented to overlay hemoglobin maps onto the white light images of ulcers. Validation studies demonstrated over 97% accuracy in coregistration. Coregistration was further applied to a healing DFU across weeks of healing. The potential to predict changes in wound healing was observed when comparing the coregistered and segmented hemoglobin concentration area maps to the visual area of the wound.

Abstract

OBJECTIVES/GOALS: Spinal cord stimulation (SCS) is an intervention for patients with chronic back pain. Technological advances have led to renewed optimism in the field, but mechanisms of action in the brain remain poorly understood. We hypothesize that SCS outcomes will be associated with changes in neural oscillations. METHODS/STUDY POPULATION: The goal of our team project is to test patients who receive SCS at 3 times points: baseline, at day 7 during the trial period, and day 180 after a permanent system has been implanted. At each time point participants will complete 10 minutes of eyes closed, resting electroencephalography (EEG). EEG will be collected with the ActiveTwo system, a 128-electrode cap, and a 256 channel AD box from BioSemi. Traditional machine learning methods such as support vector machine and more complex models including deep learning will be used to generate interpretable features within resting EEG signals. RESULTS/ANTICIPATED RESULTS: Through machine learning, we anticipate that SCS will have a significant effect on resting alpha and beta power in sensorimotor cortex. DISCUSSION/SIGNIFICANCE OF IMPACT: This collaborative project will further the application of machine learning in cognitive neuroscience and allow us to better understand how therapies for chronic pain alter resting brain activity.

Abstract

Diabetic Retinopathy (DR) represents a highly-prevalent complication of diabetes in which individuals suffer from damage to the blood vessels in the retina. The disease manifests itself through lesion presence, starting with microaneurysms, at the nonproliferative stage before being characterized by neovascularization in the proliferative stage. Retinal specialists strive to detect DR early so that the disease can be treated before substantial, irreversible vision loss occurs. The level of DR severity indicates the extent of treatment necessary - vision loss may be preventable by effective diabetes management in mild (early) stages, rather than subjecting the patient to invasive laser surgery. Using artificial intelligence (AI), highly accurate and efficient systems can be developed to help assist medical professionals in screening and diagnosing DR earlier and without the full resources that are available in specialty clinics. In particular, deep learning facilitates diagnosis earlier and with higher sensitivity and specificity. Such systems make decisions based on minimally handcrafted features and pave the way for personalized therapies. Thus, this survey provides a comprehensive description of the current technology used in each step of DR diagnosis. First, it begins with an introduction to the disease and the current technologies and resources available in this space. It proceeds to discuss the frameworks that different teams have used to detect and classify DR. Ultimately, we conclude that deep learning systems offer revolutionary potential to DR identification and prevention of vision loss.

Abstract

Objective and quantitative assessment of fundus image quality is essential for the diagnosis of retinal diseases. The major factors in fundus image quality assessment are image artifact, clarity, and field definition. Unfortunately, most of existing quality assessment methods focus on the quality of overall image, without interpretable quality feedback for real-time adjustment. Furthermore, these models are often sensitive to the specific imaging devices, and cannot generalize well under different imaging conditions. This paper presents a new multi-task domain adaptation framework to automatically assess fundus image quality. The proposed framework provides interpretable quality assessment with both quantitative scores and quality visualization for potential real-time image recapture with proper adjustment. In particular, the present approach can detect optic disc and fovea structures as landmarks, to assist the assessment through coarse-to-fine feature encoding. The framework also exploit semi-tied adversarial discriminative domain adaptation to make the model generalizable across different data sources. Experimental results demonstrated that the proposed algorithm outperforms different state-of-the-art approaches and achieves an area under the ROC curve of 0.9455 for the overall quality classification.

Abstract

This paper presents a deep neural network (DNN) based approach for predicting mean and peak wind pressure coefficients on the surface of a scale model low-rise, gable roof residential building. Pressure data were collected on the model at multiple prescribed wind directions and terrain roughnesses. The resultant pressure coefficients quantified from a subset of these directions and terrains were used to train an DNN to predict coefficients for directions and terrains excluded from the training. The approach is able to leverage a variety of input conditions to predict pressure coefficients with high accuracy, while the prior work has limited flexibility with the number of input variables and yielded lower prediction accuracy. A two-step nested DNN procedure is introduced to improve the prediction of peak coefficients. The optimal correlation coefficients of return predictions were 0.9993 and 0.9964, for mean and peak coefficient prediction, respectively. The concept of super resolution based on global prediction was also discussed. With a sufficiently large database, the proposed DNN-based approach can augment existing experimental methods to improve the yield of knowledge while reducing the number of tests required to gain that knowledge.

Abstract

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on “Diabetic Retinopathy – Segmentation and Grading” was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

Abstract

Glaucoma is one of the leading causes of irreversible but preventable blindness in working age populations. Color fundus photography (CFP) is the most cost-effective imaging modality to screen for retinal disorders. However, its application to glaucoma has been limited to the computation of a few related biomarkers such as the vertical cup-to-disc ratio. Deep learning approaches, although widely applied for medical image analysis, have not been extensively used for glaucoma assessment due to the limited size of the available data sets. Furthermore, the lack of a standardize benchmark strategy makes difficult to compare existing methods in a uniform way. In order to overcome these issues we set up the Retinal Fundus Glaucoma Challenge, REFUGE (https://refuge.grand-challenge.org), held in conjunction with MICCAI 2018. The challenge consisted of two primary tasks, namely optic disc/cup segmentation and glaucoma classification. As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one. We have also built an evaluation framework to ease and ensure fairness in the comparison of different models, encouraging the development of novel techniques in the field. 12 teams qualified and participated in the online challenge. This paper summarizes their methods and analyzes their corresponding results. In particular, we observed that two of the top-ranked teams outperformed two human experts in the glaucoma classification task. Furthermore, the segmentation results were in general consistent with the ground truth annotations, with complementary outcomes that can be further exploited by ensembling the results.

Abstract

Deep convolutional neural networks offer state-of-the-art performance for medical image analysis. However, their architectures are manually designed for particular problems. On the one hand, a manual designing process requires many trials to tune a large number of hyperparameters and is thus quite a time-consuming task. On the other hand, the fittest hyperparameters that can adapt to source data properties (e.g., sparsity, noisy features) are not able to be quickly identified for target data properties. For instance, the realistic noise in medical images is usually mixed and complicated, and sometimes unknown, leading to challenges in applying existing methods directly and creating effective denoising neural networks easily. In this paper, we present a Genetic Algorithm (GA)-based network evolution approach to search for the fittest genes to optimize network structures automatically. We expedite the evolutionary process through an experience-based greedy exploration strategy and transfer learning. Our evolutionary algorithm procedure has flexibility, which allows taking advantage of current state-of-the-art modules (e.g., residual blocks) to search for promising neural networks. We evaluate our framework on a classic medical image analysis task: denoising. The experimental results on computed tomography perfusion (CTP) image denoising demonstrate the capability of the method to select the fittest genes for building high-performance networks, named EvoNets. Our results outperform state-of-the-art methods consistently at various noise levels.

Abstract

Computed Tomography Perfusion (CTP) imaging is a cost-effective and fast approach to provide diagnostic images for acute stroke treatment. Its cine scanning mode allows the visualization of anatomic brain structures and blood flow; however, it requires contrast agent injection and continuous CT scanning over an extended time. In fact, the accumulative radiation dose to patients will increase health risks such as skin irritation, hair loss, cataract formation, and even cancer. Solutions for reducing radiation exposure include reducing the tube current and/or shortening the X-ray radiation exposure time. However, images scanned at lower tube currents are usually accompanied by higher levels of noise and artifacts. On the other hand, shorter X-ray radiation exposure time with longer scanning intervals will lead to image information that is insufficient to capture the blood flow dynamics between frames. Thus, it is critical for us to seek a solution that can preserve the image quality when the tube current and the temporal frequency are both low. We propose STIR-Net in this paper, an end-to-end spatial-temporal convolutional neural network structure, which exploits multi-directional automatic feature extraction and image reconstruction schema to recover high-quality CT slices effectively. With the inputs of low-dose and low-resolution patches at different cross-sections of the spatio-temporal data, STIR-Net blends the features from both spatial and temporal domains to reconstruct high-quality CT volumes. In this study, we finalize extensive experiments to appraise the image restoration performance at different levels of tube current and spatial and temporal resolution scales.The results demonstrate the capability of our STIR-Net to restore high-quality scans at as low as 11% of absorbed radiation dose of the current imaging protocol, yielding an average of 10% improvement for perfusion maps compared to the patch-based log likelihood method.

Abstract

The choroid layer is a vascular layer in human retina and its main function is to provide oxygen and support to the retina. Various studies have shown that the thickness of the choroid layer is correlated with the diagnosis of several ophthalmic diseases. For example, diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. Despite contemporary advances, automatic segmentation of the choroid layer remains a challenging task due to low contrast, inhomogeneous intensity, inconsistent texture and ambiguous boundaries between the choroid and sclera in Optical Coherence Tomography (OCT) images. The majority of currently implemented methods manually or semi-automatically segment out the region of interest. While many fully automatic methods exist in the context of choroid layer segmentation, more effective and accurate automatic methods are required in order to employ these methods in the clinical sector. This paper proposed and implemented an automatic method for choroid layer segmentation in OCT images using deep learning and a series of morphological operations. The aim of this research was to segment out Bruch’s Membrane (BM) and choroid layer to calculate the thickness map. BM was segmented using a series of morphological operations, whereas the choroid layer was segmented using a deep learning approach as more image statistics were required to segment accurately. Several evaluation metrics were used to test and compare the proposed method against other existing methodologies. Experimental results showed that the proposed method greatly reduced the error rate when compared with the other state-of-the-art methods.

Abstract

The advent of automatic tracing and reconstruction technology has led to a surge in the number of neurons 3D reconstruction data and consequently the neuromorphology research. However, the lack of machine-driven annotation schema to automatically detect the types of the neurons based on their morphology still hinders the development of this branch of science. Neuromorphology is important because of the interplay between the shape and functionality of neurons and the far-reaching impact on the diagnostics and therapeutics in neurological disorders. This survey paper provides a comprehensive research in the field of automatic neurons classification and presents the existing challenges, methods, tools, and future directions for automatic neuromorphology analytics. We summarize the major automatic techniques applicable in the field and propose a systematic data processing pipeline for automatic neuron classification, covering data capturing, preprocessing, analyzing, classification, and retrieval. Various techniques and algorithms in machine learning are illustrated and compared to the same dataset to facilitate ongoing research in the field.

Abstract

The retinal vessel is one of the determining factors in an ophthalmic examination. Automatic extraction of retinal vessels from low-quality retinal images still remains a challenging problem. In this paper, we propose a robust and effective approach that qualitatively improves the detection of low-contrast and narrow vessels. Rather than using the pixel grid, we use a superpixel as the elementary unit of our vessel segmentation scheme. We regularize this scheme by combining the geometrical structure, texture, color, and space information in the superpixel graph. And the segmentation results are then refined by employing the efficient minimum spanning superpixel tree to detect and capture both global and local structure of the retinal images. Such an effective and structure-aware tree detector significantly improves the detection around the pathologic area. Experimental results have shown that the proposed technique achieves advantageous connectivity-area-length (CAL) scores of 80.92% and 69.06% on two public datasets, namely, DRIVE and STARE, thereby outperforming state-of-the-art segmentation methods. In addition, the tests on the challenging retinal image database have further demonstrated the effectiveness of our method. Our approach achieves satisfactory segmentation performance in comparison with state-of-the-art methods. Our technique provides an automated method for effectively extracting the vessel from fundus images

Abstract

Optical coherence tomography (OCT) is an immersive technique for depth analysis of retinal layers. Automatic choroid layer segmentation is a challenging task because of the low contrast inputs. Existing methodologies carried choroid layer segmentation manually or semi-automatically. In this paper, we proposed automated choroid layer segmentation based on normalized cut algorithm, which aims at extracting the global impression of images and treats the segmentation as a graph partitioning problem. Due to the complexity of the layering structure of retinal layers and choroid layer, we employed a series of preprocessing to make the cut more deterministic and accurate. The proposed method divided the image into several patches and ran the normalized cut on every image patch separately. The aim was to avoid insignificant vertical cuts and focus on horizontal cutting. After processing every patch, we acquired a global cut on the original image by combining all the patches. Later we measured the choroidal thickness which is highly helpful in the diagnosis of several retinal diseases. The results were computed on a total of 525 images of 21 real patients. Experimental results showed that the mean relative error rate of the proposed method was around 0.4 as the compared the manual segmentation performed by the experts.

Abstract

Morphological retrieval is an effective approach to explore large-scale neuronal databases, as the morphology is correlated with neuronal types, regions, functions, etc. In this paper, we focus on the neuron identification and analysis via morphological retrieval. In our proposed framework, multiple features are extracted to represent 3D neuron data. Because each feature reflects different levels of similarity between neurons, we group features into different hierarchies to compute the similarity matrix. Then, compact binary codes are generated from hierarchical features for efficient similarity search. Since neuronal cells usually have tree-topology structure, it is hard to distinguish different types of neurons simply via traditional binary coding or hashing methods based on Euclidean distance metric and/or linear hyperplanes. Therefore, we employ an asymmetric binary coding strategy based on the maximum inner product search (MIPS), which not only makes it easier to learn the binary coding functions, but also preserves the non-linear characteristics of the neuron morphological data. We evaluate the proposed method on more than 17,000 neurons, by validating the retrieved neurons with associated cell types and brain regions. Experimental results show the superiority of our approach in neuron morphological retrieval compared with other state-of-the-art methods. Moreover, we demonstrate its potential use cases in the identification and analysis of neuron characteristics from large neuron databases.

Abstract

Segmentation of abdominal adipose tissues (AAT) into subcutaneous adipose tissues (SAT) and visceral adipose tissues (VAT) is of crucial interest for managing the obesity. Previous methods with raw or hand-crafted features rarely work well on large-scale subject cohorts, because of the inhomogeneous image intensities, artifacts and the diverse distributions of VAT. In this paper, we propose a novel two-stage coarse-to-fine algorithm for AAT seg- mentation. In the first stage, we formulate the AAT segmentation task as a pixel-wise classification problem. First, three types of features, intensity, spatial and contextual fea- tures, are adopted. Second, a new type of deep neural network, named multi-scale deep neural network (MSDNN), is provided to extract high-level features. In the second stage, to improve the segmentation accuracy, we refine coarse segmentation results by determining the internal boundary of SAT based on coarse segmentation results and continuous of SAT internal boundary. Finally, we demonstrate the efficacy of our algorithm for both 2D and 3D cases on a wide population range. Compared with other algorithms, our method is not only more suitable for large-scale dataset, but also achieves better segmentation results. Fur- thermore, our system takes about 2 seconds to segment an abdominal image, which implies potential clinical applications.

Abstract

Stroke is the leading cause of long-term disability and the second leading cause of mortality in the world, and exerts an enormous burden on the public health. CT remains one of the most widely used imaging modality for stroke diagnosis. However when coupled with CT perfusion, the excessive radiation exposure in repetitive imaging to assess treatment response and prognosis has raised significant public concerns regarding its potential hazards to both short- and longterm health outcomes. Tensor total variation has been proposed to reduce the necessary radiation dose in CT perfusion without comprising the image quality by fusing the information of the local anatomical structure with the temporal blood flow model. However the local search in the framework fails to leverage the non-local information in the spatio-temporal data. In this paper, we propose TENDER, an efficient framework of non-local tensor deconvolution to maintain the accuracy of the hemodynamic parameters and the diagnostic reliability in low radiation dose CT perfusion. The tensor total variation is extended using non-local spatio-temporal cubics for regularization to integrate contextual and non-local information. We also propose an efficient framework consisting of fast nearest neighbor search, accelerated optimization and parallel computing to improve the efficiency and scalability of the non-local spatio-temporal algorithm. Evaluations on clinical data of subjects with cerebrovascular disease and normal subjects demonstrate the advantage of non-local tensor deconvolution for reducing radiation dose in CT perfusion.

Abstract

The explosive growth and widespread accessibility of digital health data have led to a surge of research activity in the healthcare and data sciences fields. The conventional approaches for health data management have achieved limited success as they are incapable of handling the huge amount of complex data with high volume, high velocity, and high variety. This article presents a comprehensive overview of the existing challenges, techniques, and future directions for computational health informatics in the big data age, with a structured analysis of the historical and state-of-the-art methods. We have summarized the challenges into four Vs (i.e., volume, velocity, variety, and veracity) and proposed a systematic data-processing pipeline for generic big data in health informatics, covering data capturing, storing, sharing, analyzing, searching, and decision support. Specifically, numerous techniques and algorithms in machine learning are categorized and compared. On the basis of this material, we identify and discuss the essential prospects lying ahead for computational health informatics in this big data age.

Abstract

Tensor total variation deconvolution has been recently proposed as a robust framework to accurately estimate the hemodynamic parameters in low-dose CT perfusion by fusing the local anatomicalstructure correlation and temporal blood flow continuation. However the locality property in the current framework constrains the search for anatomical structure similarities to the local neighborhood, missing the global and long-range correlations in the whole anatomical structure. This limitation has led to noticeable absence or artifact of delicate structures, including the critical indicators for the clinical diagnosis of cerebrovascular diseases. In this paper, we propose an extension of the TTV framework by introducing 4D non-local tensor total variation into the deconvolution to bridge the gap between non-adjacent regions of the same tissue classes. The non-local regularization using tensor total variation term is imposed on the spatio-temporal flow-scaled residue functions. An efficient algorithm and implementation of the non-local tensor total variation (NL-TTV) reduces the time complexity with fast similarity computation, accelerated optimization and parallel operations. Extensive evaluations on the clinical data with cerebrovascular diseases and normal subjects demonstrate the importance of non-local linkage and long-range connections for low-dose CT perfusion deconvolution.

Abstract

Acute brain diseases such as acute strokes and transit ischemic attacks are the leading causes of mortality and morbidity worldwide, responsible for 9% of total death every year. ‘Time is brain' is a widely accepted concept in acute cerebrovascular disease treatment. Efficient and accurate computational framework for hemodynamic parameters estimation can save critical time for thrombolytic therapy. Meanwhile the high level of accumulated radiation dosage due to continuous image acquisition in CT perfusion (CTP) raised concerns on patient safety and public health. However, low-radiation leads to increased noise and artifacts which require more sophisticated and time-consuming algorithms for robust estimation. In this paper, we focus on developing a robust and efficient framework to accurately estimate the perfusion parameters at low radiation dosage. Specifically, we present a tensor total-variation (TTV) technique which fuses the spatial correlation of the vascular structure and the temporal continuation of the blood signal flow. An efficient algorithm is proposed to find the solution with fast convergence and reduced computational complexity. Extensive evaluations are carried out in terms of sensitivity to noise levels, estimation accuracy, contrast preservation, and performed on digital perfusion phantom estimation, as well as in-vivo clinical subjects. Our framework reduces the necessary radiation dose to only 8% of the original level and outperforms the state-of-art algorithms with peak signal-to-noise ratio improved by 32%. It reduces the oscillation in the residue functions, corrects overestimation of cerebral blood flow (CBF) and under-estimation of mean transit time (MTT), and maintains the distinction between the deficit and normal regions.

Abstract

With the advent of the age for big data and complex structure, sparsity has been an important modeling tool in compressed sensing, machine learning, image processing, neuroscience and statistics. In the medical imaging field, sparsity methods have been successfully used in image reconstruction, image enhancement, image segmentation, anomaly detection, disease classification, and image database retrieval. Developing more powerful sparsity models for a large range of medical imaging and medical image analysis problems as well as efficient optimization and learning algorithm will keep being a main research topic in this field. The goal of this special issue is to publish original and high quality papers on innovation research and development in medical imaging and medical image analysis using sparsity techniques. This special issue will help advance the scientific research within the field of sparsity methods for medical imaging.

Abstract

Enhancing perfusion maps in low-dose computed tomography perfusion (CTP) for cerebrovascular disease diagnosis is a challenging task, especially for lowcontrast tissue categories where infarct core and ischemic penumbra usually occur. Sparse perfusion deconvolution has been recently proposed to effectively improve the image quality and diagnostic accuracy of low-dose perfusion CT by extracting the complementary information from the high-dose perfusion maps to restore the low-dose using a joint spatio-temporal model. However the lowcontrast tissue classes where infarct core and ischemic penumbra are likely to occur in cerebral perfusion CT tend to be over-smoothed, leading to loss of essential biomarkers. In this paper, we propose a tissue-specific sparse deconvolution approach to preserve the subtle perfusion information in the low-contrast tissue classes. We first build tissue-specific dictionaries from segmentations of high-dose perfusion maps using online dictionary learning, and then perform deconvolution-based hemodynamic parameters estimation for block-wise tissue segments on the low-dose CTP data. Extensive validation on clinical datasets of patients with cerebrovascular disease demonstrates the superior performance of our proposed method compared to state-of-art, and potentially improve diagnostic accuracy by increasing the differentiation between normal and ischemic tissues in the brain

Abstract

Blood-brain barrier permeability (BBBP) measurements extracted from the perfusion computed tomography (PCT) using the Patlak model can be a valuable indicator to predict hemorrhagic transformation in patients with acute stroke. Unfortunately, the standard Patlak model based PCT requires excessive radiation exposure, which raised attention on radiation safety. Minimizing radiation dose is of high value in clinical practice but can degrade the image quality due to the introduced severe noise. The purpose of this work is to construct high quality BBBP maps from low-dose PCT data by using the brain structural similarity between different individuals and the relations between the high- and low-dose maps. The proposed sparse high-dose induced (shd-Patlak) model performs by building a high-dose induced prior for the Patlak model with a set of location adaptive dictionaries, followed by an optimized estimation of BBBP map with the prior regularized Patlak model. Evaluation with the simulated low-dose clinical brain PCT datasets clearly demonstrate that the shd-Patlak model can achieve more significant gains than the standard Patlak model with improved visual quality, higher fidelity to the gold standard and more accurate details for clinical analysis.

Abstract

Computed tomography perfusion (CTP) is an important functional imaging modality in the evaluation of cerebrovascular diseases, particularly in acute stroke and vasospasm. However, the post-processed parametric maps of blood flow tend to be noisy, especially in low-dose CTP, due to the noisy contrast enhancement profile and the oscillatory nature of the results generated by the current computational methods. In this paper, we propose a robust sparse perfusion deconvolution method (SPD) to estimate cerebral blood flow in CTP performed at low radiation dose. We first build a dictionary from high-dose perfusion maps using online dictionary learning and then perform deconvolution-based hemodynamic parameters estimation on the low-dose CTP data. Our method is validated on clinical data of patients with normal and pathological CBF maps. The results show that we achieve superior performance than existing methods, and potentially improve the differentiation between normal and ischemic tissue in the brain.