Cluster-aware channel estimation with deep learning method in deep-water acoustic communications.

In underwater acoustic (UWA) communications, channels often exhibit a clustered-sparse structure, wherein most of the channel impulse responses are near zero, and only a small number of nonzero taps assemble to form clusters. Several algorithms have used the time-domain sparse characteristic of UWA channels to reduce the complexity of channel estimation and improve the accuracy. Employing the clustered structure to enhance channel estimation performance provides another promising research direction. In this work, a deep learning-based channel estimation method for UWA orthogonal frequency division multiplexing (OFDM) systems is proposed that leverages the clustered structure information. First, a cluster detection model based on convolutional neural networks is introduced to detect the cluster of UWA channels. This method outperforms the traditional Page test algorithm with better accuracy and robustness, particularly in low signal-to-noise ratio conditions. Based on the cluster detection model, a cluster-aware distributed compressed sensing channel estimation method is proposed, which reduces the noise-induced errors by exploiting the joint sparsity between adjacent OFDM symbols and limiting the search space of channel delay spread. Numerical simulation and sea trial results are provided to illustrate the superior performance of the proposed approach in comparison with existing sparse UWA channel estimation methods.

Data augmentation aided complex-valued network for channel estimation in underwater acoustic orthogonal frequency division multiplexing system.

In this paper, a data augmentation aided complex-valued network is proposed for underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) channel estimations, wherein empirical mode decomposition based data augmentation is proposed to solve the current dilemma in the deep learning embedded UWA-OFDM communications: data scarcity and data-sampling difficulties in real-world applications. In addition, the significance of high-frequency component augmentation for the UWA channel and how it positively influences the following model training are discussed in detail and demonstrated experimentally in this paper. In addition, the complex-valued network is specially designed for the complex-formatted UWA-OFDM signal, which can fully utilize the relationship between its real and imaginary parts with half of the spatial resources of its real-valued counterparts. The experiments with the at-sea-measured WATERMARK dataset indicate that the proposed method can perform a near-optimal channel estimation, and its low resource requirements (on dataset and model) make it more adaptable to real-world UWA applications.

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net).

Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to efficiently segment the left ventricle (LV) myocardium, myocardial infarction (MI), and microvascular-obstructed (MVO) tissues from late gadolinium enhancement magnetic resonance (LGE-MR) images. Our approach was developed using two subnets cascaded to first segment the LV cavity and myocardium. Then, we used inclusion and classification constraint networks to improve the resulting segmentation of the diseased regions within the pre-segmented LV myocardium. This network incorporates the inclusion and classification information of the LGE-MRI to maintain topological constraints of pathological areas. In the testing stage, the outputs of each segmentation network obtained with specific estimated parameters from training were fused using the majority voting technique for the final label prediction of each voxel in the LGE-MR image. The proposed method was validated by comparing its results to manual drawings by experts from 50 LGE-MR images. Importantly, compared to various deep learning-based methods participating in the EMIDEC challenge, the results of our approach have a more significant agreement with manual contouring in segmenting myocardial diseases.

SpecSeg Network for Specular Highlight Detection and Segmentation in Real-World Images.

Specular highlights detection and removal in images is a fundamental yet non-trivial problem of interest. Most modern techniques proposed are inadequate at dealing with real-world images taken under uncontrolled conditions with the presence of complex textures, multiple objects, and bright colours, resulting in reduced accuracy and false positives. To detect specular pixels in a wide variety of real-world images independent of the number, colour, or type of illuminating source, we propose an efficient Specular Segmentation (SpecSeg) network based on the U-net architecture that is expeditious to train on nominal-sized datasets. The proposed network can detect pixels strongly affected by specular highlights with a high degree of precision, as shown by comparison with the state-of-the-art methods. The technique proposed is trained on publicly available datasets and tested using a large selection of real-world images with highly encouraging results.

Effective multiscale deep learning model for COVID19 segmentation tasks: A further step towards helping radiologist.

Infection by the SARS-CoV-2 leading to COVID-19 disease is still rising and techniques to either diagnose or evaluate the disease are still thoroughly investigated. The use of CT as a complementary tool to other biological tests is still under scrutiny as the CT scans are prone to many false positives as other lung diseases display similar characteristics on CT scans. However, fully investigating CT images is of tremendous interest to better understand the disease progression and therefore thousands of scans need to be segmented by radiologists to study infected areas. Over the last year, many deep learning models for segmenting CT-lungs were developed. Unfortunately, the lack of large and shared annotated multicentric datasets led to models that were either under-tested (small dataset) or not properly compared (own metrics, none shared dataset), often leading to poor generalization performance. To address, these issues, we developed a model that uses a multiscale and multilevel feature extraction strategy for COVID19 segmentation and extensively validated it on several datasets to assess its generalization capability for other segmentation tasks on similar organs. The proposed model uses a novel encoder and decoder with a proposed kernel-based atrous spatial pyramid pooling module that is used at the bottom of the model to extract small features with a multistage skip connection concatenation approach. The results proved that our proposed model could be applied on a small-scale dataset and still produce generalizable performances on other segmentation tasks. The proposed model produced an efficient Dice score of 90% on a 100 cases dataset, 95% on the NSCLC dataset, 88.49% on the COVID19 dataset, and 97.33 on the StructSeg 2019 dataset as compared to existing state-of-the-art models. The proposed solution could be used for COVID19 segmentation in clinic applications. The source code is publicly available at https://github.com/RespectKnowledge/Mutiscale-based-Covid-_segmentation-usingDeep-Learning-models.

Meta-learning-aided orthogonal frequency division multiplexing for underwater acoustic communications.

In this paper, a meta-learning-based underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) system is proposed to deal with the environment mismatch in real-world UWA applications, which can effectively drive the model from the given UWA environment to the new UWA environment with a relatively small amount of data. With meta-learning, we consider multiple UWA environments as multi-UWA-tasks, wherein the meta-training strategy is utilized to learn a robust model from previously observed multi-UWA-tasks, and it can be quickly adapted to the unknown UWA environment with only a small number of updates. The experiments with the at-sea-measured WATERMARK dataset and the lake trial indicate that, compared with the traditional UWA-OFDM system and the conventional machine learning-based framework, the proposed method shows better bit error rate performance and stronger learning ability under various UWA scenarios.

Improved Active Disturbance Rejection Control for Trajectory Tracking Control of Lower Limb Robotic Rehabilitation Exoskeleton.

Neurological disorders such as cerebral paralysis, spinal cord injuries, and strokes, result in the impairment of motor control and induce functional difficulties to human beings like walking, standing, etc. Physical injuries due to accidents and muscular weaknesses caused by aging affect people and can cause them to lose their ability to perform daily routine functions. In order to help people recover or improve their dysfunctional activities and quality of life after accidents or strokes, assistive devices like exoskeletons and orthoses are developed. Control strategies for control of exoskeletons are developed with the desired intention of improving the quality of treatment. Amongst recent control strategies used for rehabilitation robots, active disturbance rejection control (ADRC) strategy is a systematic way out from a robust control paradox with possibilities and promises. In this modern era, we always try to find the solution in order to have minimum resources and maximum output, and in robotics-control, to approach the same condition observer-based control strategies is an added advantage where it uses a state estimation method which reduces the requirement of sensors that is used for measuring every state. This paper introduces improved active disturbance rejection control (I-ADRC) controllers as a combination of linear extended state observer (LESO), tracking differentiator (TD), and nonlinear state error feedback (NLSEF). The proposed controllers were evaluated through simulation by investigating the sagittal plane gait trajectory tracking performance of two degrees of freedom, Lower Limb Robotic Rehabilitation Exoskeleton (LLRRE). This multiple input multiple output (MIMO) LLRRE has two joints, one at the hip and other at the knee. In the simulation study, the proposed controllers show reduced trajectory tracking error, elimination of random, constant, and harmonic disturbances, robustness against parameter variations, and under the influence of noise, with improvement in performance indices, indicates its enhanced tracking performance. These promising simulation results would be validated experimentally in the next phase of research.

Evaluation of Deep Neural Networks for Semantic Segmentation of Prostate in T2W MRI.

In this paper, we present an evaluation of four encoder-decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder-decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92 . 8 % . This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.

Dependence of the Optical Constant Parameters of p-Toluene Sulfonic Acid-Doped Polyaniline and Its Composites on Dispersion Solvents.

The optical constants of Para-Toluene sulfonic acid-doped polyaniline (PANI), PANIchitosan composites, PANI-reduced graphene-oxide composites and a ternary composite comprising of PANI, chitosan and reduced graphene-oxide dispersed in diluted p-toluene sulfonic acid (PTSA) solution and N-Methyl-2-Pyrrolidone (NMP) solvent have been evaluated and compared. The optical constant values were extracted from the absorbance spectra of thin layers of the respective samples. The potential utilization of the materials as the active sensing materials of surface plasmon resonance biosensors has also been assessed in terms of the estimated value of the penetration depth through a dielectric medium. The results show a reasonable dependence of the optical constant parameters on the solvent type. Higher real part refractive index (n) and real part complex dielectric permittivity (ε') values were observed for the samples prepared using PTSA solution, while higher optical conductivity values were observed for the NMP-based samples due to their relatively higher imaginary part refractive index (k) and imaginary part complex dielectric permittivity (ε″) values. In addition, NMP-based samples show improvement in terms of the penetration depth through a dielectric medium by around 9.5, 1.6, 4.4 and 2.9 times compared to PTSA-based samples for the PANI, PANI-chitosan, PANI-RGO and the ternary composites, respectively. Based on these, it is concluded that preparation of these materials using different dispersion solvents could produce materials of different optical properties. Thus, the variation of the dispersion solvent will allow the flexible utilization of the PANI and the composites for diverse applications.

Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images.

BACKGROUND: Spectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology of the retina as well as the retina layers. METHODS: The dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px × 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations. RESULTS AND CONCLUSION: Besides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP[Formula: see text] vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5%, respectively.

Reproducibility of multiphase pseudo-continuous arterial spin labeling and the effect of post-processing analysis methods.

Arterial spin labeling (ASL) is an emerging MRI technique for non-invasive measurement of cerebral blood flow (CBF). Compared to invasive perfusion imaging modalities, ASL suffers from low sensitivity due to poor signal-to-noise ratio (SNR), susceptibility to motion artifacts and low spatial resolution, all of which limit its reliability. In this work, the effects of various state of the art image processing techniques for addressing these ASL limitations are investigated. A processing pipeline consisting of motion correction, ASL motion correction imprecision removal, temporal and spatial filtering, partial volume effect correction, and CBF quantification was developed and assessed. To further improve the SNR for pseudo-continuous ASL (PCASL) by accounting for errors in tagging efficiency, the data from multiphase (MP) acquisitions were analyzed using a novel weighted-averaging scheme. The performances of each step in terms of SNR and reproducibility were evaluated using test-retest ASL data acquired from 12 young healthy subjects. The proposed processing pipeline was shown to improve the within-subject coefficient of variation and regional reproducibility by 17% and 16%, respectively, compared to CBF maps computed following motion correction but without the other processing steps. The CBF measurements of MP-PCASL compared to PCASL had on average 23% and 10% higher SNR and reproducibility, respectively.

Automatic measurement of wood fiber orientation and knot detection using an optical system based on heating conduction.

In this paper, a new approach to computing the deviation of wood grain is proposed. To do this, the thermal conduction properties of timber are used (higher conduction in the fiber direction). Exciting the surface of the wood with a laser and capturing the thermal conduction using a thermal camera, an ellipse can be observed. Using a method similar to the tracheid effect, it is possible to extract information from this ellipse, such as the slope of grain and the presence of knots. With this method it is therefore possible to extend the mechanical model (assessing the mechanical properties of timber) to take certain singularities into account. Using this approach, the slope of grain can be estimated for any wood species, either hardwood or softwood, which was not possible with the existing tracheid effect.

Hyperspectral venous image quality assessment for optimum illumination range selection based on skin tone characteristics.

BACKGROUND: Subcutaneous veins localization is usually performed manually by medical staff to find suitable vein to insert catheter for medication delivery or blood sample function. The rule of thumb is to find large and straight enough vein for the medication to flow inside of the selected blood vessel without any obstruction. The problem of peripheral difficult venous access arises when patient's veins are not visible due to any reason like dark skin tone, presence of hair, high body fat or dehydrated condition, etc. METHODS: To enhance the visibility of veins, near infrared imaging systems is used to assist medical staff in veins localization process. Optimum illumination is crucial to obtain a better image contrast and quality, taking into consideration the limited power and space on portable imaging systems. In this work a hyperspectral image quality assessment is done to get the optimum range of illumination for venous imaging system. A database of hyperspectral images from 80 subjects has been created and subjects were divided in to four different classes on the basis of their skin tone. In this paper the results of hyper spectral image analyses are presented in function of the skin tone of patients. For each patient, four mean images were constructed by taking mean with a spectral span of 50 nm within near infrared range, i.e. 750-950 nm. Statistical quality measures were used to analyse these images. CONCLUSION: It is concluded that the wavelength range of 800 to 850 nm serve as the optimum illumination range to get best near infrared venous image quality for each type of skin tone.

Multi-modality multi-label ocular abnormalities detection with transformer-based semantic dictionary learning.

Blindness is preventable by early detection of ocular abnormalities. Computer-aided diagnosis for ocular abnormalities is built by analyzing retinal imaging modalities, for instance, Color Fundus Photography (CFP). This research aims to propose a multi-label detection of 28 ocular abnormalities consisting of frequent and rare abnormalities from a single CFP by using transformer-based semantic dictionary learning. Rare labels are usually ignored because of a lack of features. We tackle this condition by adding the co-occurrence dependency factor to the model from the linguistic features of the labels. The model learns the relation between spatial features and linguistic features represented as a semantic dictionary. The proposed method treats the semantic dictionary as one of the main important parts of the model. It acts as the query while the spatial features are the key and value. The experiments are conducted on the RFMiD dataset. The results show that the proposed method achieves the top 30% in Evaluation Set on the RFMiD dataset challenge. It also shows that treating the semantic dictionary as one of the strong factors in model detection increases the performance when compared with the method that treats the semantic dictionary as a weak factor.

Navigating the nuances: comparative analysis and hyperparameter optimisation of neural architectures on contrast-enhanced MRI for liver and liver tumour segmentation.

In medical imaging, accurate segmentation is crucial to improving diagnosis, treatment, or both. However, navigating the multitude of available architectures for automatic segmentation can be overwhelming, making it challenging to determine the appropriate type of architecture and tune the most crucial parameters during dataset optimisation. To address this problem, we examined and refined seven distinct architectures for segmenting the liver, as well as liver tumours, with a restricted training collection of 60 3D contrast-enhanced magnetic resonance images (CE-MRI) from the ATLAS dataset. Included in these architectures are convolutional neural networks (CNNs), transformers, and hybrid CNN/transformer architectures. Bayesian search techniques were used for hyperparameter tuning to hasten convergence to the optimal parameter mixes while also minimising the number of trained models. It was unexpected that hybrid models, which typically exhibit superior performance on larger datasets, would exhibit comparable performance to CNNs. The optimisation of parameters contributed to better segmentations, resulting in an average increase of 1.7% and 5.0% in liver and tumour segmentation Dice coefficients, respectively. In conclusion, the findings of this study indicate that hybrid CNN/transformer architectures may serve as a practical substitute for CNNs even in small datasets. This underscores the significance of hyperparameter optimisation.

Placental vessel segmentation and registration in fetoscopy: Literature review and MICCAI FetReg2021 challenge findings.

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon's side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.

HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness.

RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with semantic cues. Thus, despite the auxiliary depth information, it is still challenging for existing models to distinguish objects with similar appearances but at distinct camera distances. In this paper, from a new perspective, we propose a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection. Our motivation comes from the observation that the multi-granularity properties of geometric priors correlate well with the neural network hierarchies. To realize multi-modal and multi-level fusion, we first use a granularity-based attention scheme to strengthen the discriminatory power of RGB and depth features separately. Then we introduce a unified cross dual-attention module for multi-modal and multi-level fusion in a coarse-to-fine manner. The encoded multi-modal features are gradually aggregated into a shared decoder. Further, we exploit a multi-scale loss to take full advantage of the hierarchical information. Extensive experiments on challenging benchmark datasets demonstrate that our HiDAnet performs favorably over the state-of-the-art methods by large margins. The source code can be found in https://github.com/Zongwei97/HIDANet/.

Automatic uncertainty-based quality controlled T1 mapping and ECV analysis from native and post-contrast cardiac T1 mapping images using Bayesian vision transformer.

Deep learning-based methods for cardiac MR segmentation have achieved state-of-the-art results. However, these methods can generate incorrect segmentation results which can lead to wrong clinical decisions in the downstream tasks. Automatic and accurate analysis of downstream tasks, such as myocardial tissue characterization, is highly dependent on the quality of the segmentation results. Therefore, it is of paramount importance to use quality control methods to detect the failed segmentations before further analysis. In this work, we propose a fully automatic uncertainty-based quality control framework for T1 mapping and extracellular volume (ECV) analysis. The framework consists of three parts. The first one focuses on segmentation of cardiac structures from a native and post-contrast T1 mapping dataset (n=295) using a Bayesian Swin transformer-based U-Net. In the second part, we propose a novel uncertainty-based quality control (QC) to detect inaccurate segmentation results. The QC method utilizes image-level uncertainty features as input to a random forest-based classifier/regressor to determine the quality of the segmentation outputs. The experimental results from four different types of segmentation results show that the proposed QC method achieves a mean area under the ROC curve (AUC) of 0.927 on binary classification and a mean absolute error (MAE) of 0.021 on Dice score regression, significantly outperforming other state-of-the-art uncertainty based QC methods. The performance gap is notably higher in predicting the segmentation quality from poor-performing models which shows the robustness of our method in detecting failed segmentations. After the inaccurate segmentation results are detected and rejected by the QC method, in the third part, T1 mapping and ECV values are computed automatically to characterize the myocardial tissues of healthy and cardiac pathological cases. The native myocardial T1 and ECV values computed from automatic and manual segmentations show an excellent agreement yielding Pearson coefficients of 0.990 and 0.975 (on the combined validation and test sets), respectively. From the results, we observe that the automatically computed myocardial T1 and ECV values have the ability to characterize myocardial tissues of healthy and cardiac diseases like myocardial infarction, amyloidosis, Tako-Tsubo syndrome, dilated cardiomyopathy, and hypertrophic cardiomyopathy.

Using Artificial Intelligence to Analyse the Retinal Vascular Network: The Future of Cardiovascular Risk Assessment Based on Oculomics? A Narrative Review.

The healthcare burden of cardiovascular diseases remains a major issue worldwide. Understanding the underlying mechanisms and improving identification of people with a higher risk profile of systemic vascular disease through noninvasive examinations is crucial. In ophthalmology, retinal vascular network imaging is simple and noninvasive and can provide in vivo information of the microstructure and vascular health. For more than 10 years, different research teams have been working on developing software to enable automatic analysis of the retinal vascular network from different imaging techniques (retinal fundus photographs, OCT angiography, adaptive optics, etc.) and to provide a description of the geometric characteristics of its arterial and venous components. Thus, the structure of retinal vessels could be considered a witness of the systemic vascular status. A new approach called "oculomics" using retinal image datasets and artificial intelligence algorithms recently increased the interest in retinal microvascular biomarkers. Despite the large volume of associated research, the role of retinal biomarkers in the screening, monitoring, or prediction of systemic vascular disease remains uncertain. A PubMed search was conducted until August 2022 and yielded relevant peer-reviewed articles based on a set of inclusion criteria. This literature review is intended to summarize the state of the art in oculomics and cardiovascular disease research.

Detecting global and local hippocampal shape changes in Alzheimer's disease using statistical shape models.

The hippocampus is affected at an early stage in the development of Alzheimer's disease (AD). With the use of structural magnetic resonance (MR) imaging, we can investigate the effect of AD on the morphology of the hippocampus. The hippocampal shape variations among a population can be usually described using statistical shape models (SSMs). Conventional SSMs model the modes of variations among the population via principal component analysis (PCA). Although these modes are representative of variations within the training data, they are not necessarily discriminative on labeled data or relevant to the differences between the subpopulations. We use the shape descriptors from SSM as features to classify AD from normal control (NC) cases. In this study, a Hotelling's T2 test is performed to select a subset of landmarks which are used in PCA. The resulting variation modes are used as predictors of AD from NC. The discrimination ability of these predictors is evaluated in terms of their classification performances with bagged support vector machines (SVMs). Restricting the model to landmarks with better separation between AD and NC increases the discrimination power of SSM. The predictors extracted on the subregions also showed stronger correlation with the memory-related measurements such as Logical Memory, Auditory Verbal Learning Test (AVLT) and the memory subscores of Alzheimer Disease Assessment Scale (ADAS).