Snakes, shapes, and gradient vector flow

A Multi-Source Circular Geodesic Voting Model for Image Segmentation

Image segmentation is a crucial task in artificial intelligence fields such as computer vision and medical imaging. While convolutional neural networks (CNNs) have achieved notable success by learning representative features from large datasets, they often lack geometric priors and global object information, limiting their accuracy in complex scenarios. Variational methods like active contours provide geometric priors and theoretical interpretability but require manual initialization and are sensitive to hyper-parameters. To overcome these challenges, we propose a novel segmentation approach, named PolarVoting, which combines the minimal path encoding rich geometric features and CNNs which can provide efficient initialization. The introduced model involves two main steps: firstly, we leverage the PolarMask model to extract multiple source points for initialization, and secondly, we construct a voting score map which implicitly contains the segmentation mask via a modified circular geometric voting (CGV) scheme. This map embeds global geometric information for finding accurate segmentation. By integrating neural network representation with geometric priors, the PolarVoting model enhances segmentation accuracy and robustness. Extensive experiments on various datasets demonstrate that the proposed PolarVoting method outperforms both PolarMask and traditional single-source CGV models. It excels in challenging imaging scenarios characterized by intensity inhomogeneity, noise, and complex backgrounds, accurately delineating object boundaries and advancing the state of image segmentation.

The impact of benign tissue within cancerous regions in the prostate: Characterizing sparse and dense prostate cancers on whole-mount histopathology and on multiparametric MRI

PURPOSE

To establish the incidence, size, zonal location and Gleason Score(GS)/Gleason Grade Group(GG) of sparse versus dense prostate cancer (PCa) lesions and to identify the imaging characteristics of sparse versus dense cancers on multiparametric MRI (mpMRI).

METHODS

Seventy-six men with untreated PCa were scanned prior to prostatectomy with endorectal-coil 3 T MRI including T2-weighted imaging, diffusion-weighted imaging and dynamic contrast-enhanced MRI. Cancerous regions were outlined and graded on the whole-mount, processed specimens, with tissue compositions estimated. Regions with cancer comprising <50 % and ≥ 50 % of the tissue were considered sparse and dense respectively. Regions of interest (ROI) were manually drawn on T2-weighted MRI. Within each patient, area-weighted ROI averages were calculated for each imaging measure for each tissue type, GS/GG, and sparse/dense composition.

RESULTS

A large number of cancer regions were identified on histopathology (n = 1193: 939 (peripheral zone (PZ)) and 254 (transition zone (TZ))). Thirty-seven percent of these lesions were sparse. Sparse lesions were primarily low-grade with the majority of PZ and 100 % of TZ sparse lesions ≤GS3 + 3/GG1. Dense lesions were significantly larger than sparse lesions in both PZ and TZ, p < 0.0001. On imaging, 246/45 PZ and 109/8 TZ dense/sparse 2D cancerous ROIs were drawn. Sparse GS3 + 3 and sparse ≥GS3 + 4 cancers did not have significantly different MRI intensities to dense GS3 + 3 cancers, while sparse GS3 + 3/GG1 cancers differed from benign, p < 0.05.

CONCLUSION

Histopathologically identified prostate cancer lesions were sparse in 37 % of cases. Sparse cancers were entirely low grade in TZ and predominantly low-grade in PZ and generally small, thus likely posing lower risk for spread and progression than dense lesions. Sparse lesions were not distinguishable from dense lesions on mpMRI, but could be distinguished from benign tissues.

Magnetic control of soft microrobots near step-out frequency: Characterization and analysis

Magnetically actuated soft microrobots hold promise for biomedical applications that necessitate precise control and adaptability in complex environments. These microrobots can be accurately steered below their step-out frequencies where they exhibit synchronized motion with external magnetic fields. However, the step-out frequencies of soft microrobots have not been investigated yet, as opposed to their rigid counterparts. In this work, we develop an analytic model from the magneto-elastohydrodynamics to establish the relationship between the step-out frequency of soft sperm-like microrobots and their magnetic properties, geometry, wave patterns, and the viscosity of the surrounding medium. We fabricate soft sperm-like microrobots using electrospinning and assess their swimming abilities in mediums with varying viscosities under an oscillating magnetic field. We observe slight variations in wave patterns of the sperm-like microrobots as the actuation frequency changes. Our theoretical model, which analyzes these wave patterns observed without exceeding the step-out threshold, quantitatively agrees with the experimentally measured step-out frequencies. By accurately predicting the step-out frequency, the proposed model lays a foundation for achieving precise control over individual soft microrobots and enabling selective control within a swarm when executing biomedical tasks.

Characterization of Retinal Arteries by Adaptive Optics Ophthalmoscopy Image Analysis

OBJECTIVE

This paper aims at quantifying biomarkers from the segmentation of retinal arteries in adaptive optics ophthalmoscopy images (AOO).

METHODS

The segmentation is based on the combination of deep learning and knowledge-driven deformable models to achieve a precise segmentation of the vessel walls, with a specific attention to bifurcations. Biomarkers (junction coefficient, branching coefficient, wall to lumen ratio ( wlr)) are derived from the resulting segmentation.

RESULTS

reliable and accurate segmentations ( mse = 1.75 ±1.24 pixel) and measurements are obtained, with high reproducibility with respect to images acquisition and users, and without bias.

SIGNIFICANCE

In a preliminary clinical study of patients with a genetic small vessel disease, some of them with vascular risk factors, an increased wlr was found in comparison to a control population.

CONCLUSION

The wlr estimated in AOO images with our method (AOV, Adaptive Optics Vessel analysis) seems to be a very robust biomarker as long as the wall is well contrasted.

Accelerated muscle mass estimation from CT images through transfer learning

BACKGROUND

The cost of labeling to collect training data sets using deep learning is especially high in medical applications compared to other fields. Furthermore, due to variances in images depending on the computed tomography (CT) devices, a deep learning based segmentation model trained with a certain device often does not work with images from a different device.

METHODS

In this study, we propose an efficient learning strategy for deep learning models in medical image segmentation. We aim to overcome the difficulties of segmentation in CT images by training a VNet segmentation model which enables rapid labeling of organs in CT images with the model obtained by transfer learning using a small number of manually labeled images, called SEED images. We established a process for generating SEED images and conducting transfer learning a model. We evaluate the performance of various segmentation models such as vanilla UNet, UNETR, Swin-UNETR and VNet. Furthermore, assuming a scenario that a model is repeatedly trained with CT images collected from multiple devices, in which is catastrophic forgetting often occurs, we examine if the performance of our model degrades.

RESULTS

We show that transfer learning can train a model that does a good job of segmenting muscles with a small number of images. In addition, it was confirmed that VNet shows better performance when comparing the performance of existing semi-automated segmentation tools and other deep learning networks to muscle and liver segmentation tasks. Additionally, we confirmed that VNet is the most robust model to deal with catastrophic forgetting problems.

CONCLUSION

In the 2D CT image segmentation task, we confirmed that the CNN-based network shows better performance than the existing semi-automatic segmentation tool or latest transformer-based networks.

Automatic classification and segmentation of blast cells using deep transfer learning and active contours

INTRODUCTION

Acute lymphoblastic leukemia (ALL) presents a formidable challenge in hematological malignancies, necessitating swift and precise diagnostic techniques for effective intervention. The conventional manual microscopy of blood smears, although widely practiced, suffers from significant limitations including labor-intensity and susceptibility to human error, particularly in distinguishing the subtle differences between normal and leukemic cells.

METHODS

To overcome these limitations, our research introduces the ALLDet classifier, an innovative tool employing deep transfer learning for the automated analysis and categorization of ALL from White Blood Cell (WBC) nuclei images. Our investigation encompassed the evaluation of nine state-of-the-art pre-trained convolutional neural network (CNN) models, namely VGG16, VGG19, ResNet50, ResNet101, DenseNet121, DenseNet201, Xception, MobileNet, and EfficientNetB3. We augmented this approach by incorporating a sophisticated contour-based segmentation technique, derived from the Chan-Vese model, aimed at the meticulous segmentation of blast cell nuclei in blood smear images, thereby enhancing the accuracy of our analysis.

RESULTS

The empirical assessment of these methodologies underscored the superior performance of the EfficientNetB3 model, which demonstrated exceptional metrics: a recall specificity of 98.5%, precision of 95.86%, F1-score of 97.16%, and an overall accuracy rate of 97.13%. The Chan-Vese model's adaptability to the irregular shapes of blast cells and its noise-resistant segmentation capability were key to capturing the complex morphological changes essential for accurate segmentation.

CONCLUSION

The combined application of the ALLDet classifier, powered by EfficientNetB3, with our advanced segmentation approach, emerges as a formidable advancement in the early detection and accurate diagnosis of ALL. This breakthrough not only signifies a pivotal leap in leukemia diagnostic methodologies but also holds the promise of significantly elevating the standards of patient care through the provision of timely and precise diagnoses. The implications of this study extend beyond immediate clinical utility, paving the way for future research to further refine and enhance the capabilities of artificial intelligence in medical diagnostics.

SARC-UNet: A coronary artery segmentation method based on spatial attention and residual convolution

BACKGROUND AND OBJECTIVE

Coronary artery segmentation is a pivotal field that has received increasing attention in recent years. However, this task remains challenging because of the inhomogeneous distributions of the contrast agent and dim light, resulting in noise, vascular breakages and small vessel losses in the obtained segmentation results.

METHODS

To acquire better automatic blood vessel segmentation results for coronary angiography images, a UNet-based segmentation network (SARC-UNet) is constructed for coronary artery segmentation; this approach is based on residual convolution and spatial attention. First, we use the low-light image enhancement (LIME) approach to increase the contrast and clarity levels of coronary angiography images. Then, we design two residual convolution fusion modules (RCFM1 and RCFM2) that can successfully fuse the local and global information of coronary images while also capturing the characteristics of finer-grained blood vessels, hence preventing the loss of tiny blood vessels in the segmentation findings. Finally, using a cascaded waterfall structure, we create a new location-enhanced spatial attention (LESA) mechanism that can efficiently improve the long-distance dependencies between coronary vascular pixel features, eradicating vascular ruptures and noise in the segmentation results.

RESULTS

This article subjectively and objectively evaluates the experimental results. This method has performed well on five general indicators. Furthermore, it outperforms the connectivity indicators proposed in this article. This method can effectively segment blood vessels and obtain higher accuracy results.

CONCLUSIONS

Numerous experiments have shown that the suggested method outperforms the state-of-the-art approaches, particularly in terms of vessel connectivity and small blood vessel segmentation.

Patient-specific in silico 3D coronary model in cardiac catheterisation laboratories

Coronary artery disease is caused by the buildup of atherosclerotic plaque in the coronary arteries, affecting the blood supply to the heart, one of the leading causes of death around the world. X-ray coronary angiography is the most common procedure for diagnosing coronary artery disease, which uses contrast material and x-rays to observe vascular lesions. With this type of procedure, blood flow in coronary arteries is viewed in real-time, making it possible to detect stenoses precisely and control percutaneous coronary interventions and stent insertions. Angiograms of coronary arteries are used to plan the necessary revascularisation procedures based on the calculation of occlusions and the affected segments. However, their interpretation in cardiac catheterisation laboratories presently relies on sequentially evaluating multiple 2D image projections, which limits measuring lesion severity, identifying the true shape of vessels, and analysing quantitative data. In silico modelling, which involves computational simulations of patient-specific data, can revolutionise interventional cardiology by providing valuable insights and optimising treatment methods. This paper explores the challenges and future directions associated with applying patient-specific in silico models in catheterisation laboratories. We discuss the implications of the lack of patient-specific in silico models and how their absence hinders the ability to accurately predict and assess the behaviour of individual patients during interventional procedures. Then, we introduce the different components of a typical patient-specific in silico model and explore the potential future directions to bridge this gap and promote the development and utilisation of patient-specific in silico models in the catheterisation laboratories.

Cargo Size Limits and Forces of Cell-Driven Microtransport

The integration of motile cells into biohybrid microrobots offers unique properties such as sensitive responses to external stimuli, resilience, and intrinsic energy supply. Here, biohybrid cell-cargo systems that are driven by amoeboid Dictyostelium discoideum cells are studied and how the cargo speed and the resulting viscous drag force scales with increasing radius of the spherical cargo particle are explored. Using a simplified geometrical model of the cell-cargo interaction, the findings toward larger cargo sizes, which are not accessible with the experimental setup, are extrapolated and a maximal cargo size is predicted beyond which active cell-driven movements will stall. The active forces exerted by the cells to move a cargo show mechanoresponsive adaptation and increase dramatically when challenged by an external pulling force, a mechanism that may become relevant when navigating cargo through complex heterogeneous environments.

Grouping Boundary Proposals for Fast Interactive Image Segmentation

Geodesic models are known as an efficient tool for solving various image segmentation problems. Most of existing approaches only exploit local pointwise image features to track geodesic paths for delineating the objective boundaries. However, such a segmentation strategy cannot take into account the connectivity of the image edge features, increasing the risk of shortcut problem, especially in the case of complicated scenario. In this work, we introduce a new image segmentation model based on the minimal geodesic framework in conjunction with an adaptive cut-based circular optimal path computation scheme and a graph-based boundary proposals grouping scheme. Specifically, the adaptive cut can disconnect the image domain such that the target contours are imposed to pass through this cut only once. The boundary proposals are comprised of precomputed image edge segments, providing the connectivity information for our segmentation model. These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them. Experimental results show that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.

A Hands-on Guide to AmoePy - a Python-Based Software Package to Analyze Cell Migration Data

Amoeboid cell motility is fundamental for a multitude of biological processes such as embryogenesis, immune responses, wound healing, and cancer metastasis. It is characterized by specific cell shape changes: the extension and retraction of membrane protrusions, known as pseudopodia. A common approach to investigate the mechanisms underlying this type of cell motility is to study phenotypic differences in the locomotion of mutant cell lines. To characterize such differences, methods are required to quantify the contour dynamics of migrating cells. AmoePy is a Python-based software package that provides tools for cell segmentation, contour detection as well as analyzing and simulating contour dynamics. First, a digital representation of the cell contour as a chain of nodes is extracted from each frame of a time-lapse microscopy recording of a moving cell. Then, the dynamics of these nodes-referred to as virtual markers-are tracked as the cell contour evolves over time. From these data, various quantities can be calculated that characterize the contour dynamics, such as the displacement of the virtual markers or the local stretching rate of the marker chain. Their dynamics is typically visualized in space-time plots, the so-called kymographs, where the temporal evolution is displayed for the different locations along the cell contour. Using AmoePy, you can straightforwardly create kymograph plots and videos from stacks of experimental bright-field or fluorescent images of motile cells. A hands-on guide on how to install and use AmoePy is provided in this chapter.

Segmentation of Substantia Nigra in Brain Parenchyma Sonographic Images Using Deep Learning

Currently, Parkinson's Disease (PD) is diagnosed primarily based on symptoms by experts clinicians. Neuroimaging exams represent an important tool to confirm the clinical diagnosis. Among them, Brain Parenchyma Sonography (BPS) is used to evaluate the hyperechogenicity of Substantia Nigra (SN), found in more than 90% of PD patients. In this article, we exploit a new dataset of BPS images to investigate an automatic segmentation approach for SN that can increase the accuracy of the exam and its practicability in clinical routine. This study achieves state-of-the-art performance in SN segmentation of BPS images. Indeed, it is found that the modified U-Net network scores a Dice coefficient of 0.859 ± 0.037. The results presented in this study demonstrate the feasibility and usefulness of SN automatic segmentation in BPS medical images, to the point that this study can be considered as the first stage of the development of an end-to-end CAD (Computer Aided Detection) system. Furthermore, the used dataset, which will be further enriched in the future, has proven to be very effective in supporting the training of CNNs and may pave the way for future studies in the field of CAD applied to PD.

S-Net: a multiple cross aggregation convolutional architecture for automatic segmentation of small/thin structures for cardiovascular applications

With the success of U-Net or its variants in automatic medical image segmentation, building a fully convolutional network (FCN) based on an encoder-decoder structure has become an effective end-to-end learning approach. However, the intrinsic property of FCNs is that as the encoder deepens, higher-level features are learned, and the receptive field size of the network increases, which results in unsatisfactory performance for detecting low-level small/thin structures such as atrial walls and small arteries. To address this issue, we propose to keep the different encoding layer features at their original sizes to constrain the receptive field from increasing as the network goes deeper. Accordingly, we develop a novel S-shaped multiple cross-aggregation segmentation architecture named S-Net, which has two branches in the encoding stage, i.e., a resampling branch to capture low-level fine-grained details and thin/small structures and a downsampling branch to learn high-level discriminative knowledge. In particular, these two branches learn complementary features by residual cross-aggregation; the fusion of the complementary features from different decoding layers can be effectively accomplished through lateral connections. Meanwhile, we perform supervised prediction at all decoding layers to incorporate coarse-level features with high semantic meaning and fine-level features with high localization capability to detect multi-scale structures, especially for small/thin volumes fully. To validate the effectiveness of our S-Net, we conducted extensive experiments on the segmentation of cardiac wall and intracranial aneurysm (IA) vasculature, and quantitative and qualitative evaluations demonstrated the superior performance of our method for predicting small/thin structures in medical images.

Pixel Diffuser: Practical Interactive Medical Image Segmentation without Ground Truth

Medical image segmentation is essential for doctors to diagnose diseases and manage patient status. While deep learning has demonstrated potential in addressing segmentation challenges within the medical domain, obtaining a substantial amount of data with accurate ground truth for training high-performance segmentation models is both time-consuming and demands careful attention. While interactive segmentation methods can reduce the costs of acquiring segmentation labels for training supervised models, they often still necessitate considerable amounts of ground truth data. Moreover, achieving precise segmentation during the refinement phase results in increased interactions. In this work, we propose an interactive medical segmentation method called PixelDiffuser that requires no medical segmentation ground truth data and only a few clicks to obtain high-quality segmentation using a VGG19-based autoencoder. As the name suggests, PixelDiffuser starts with a small area upon the initial click and gradually detects the target segmentation region. Specifically, we segment the image by creating a distortion in the image and repeating it during the process of encoding and decoding the image through an autoencoder. Consequently, PixelDiffuser enables the user to click a part of the organ they wish to segment, allowing the segmented region to expand to nearby areas with pixel values similar to the chosen organ. To evaluate the performance of PixelDiffuser, we employed the dice score, based on the number of clicks, to compare the ground truth image with the inferred segment. For validation of our method's performance, we leveraged the BTCV dataset, containing CT images of various organs, and the CHAOS dataset, which encompasses both CT and MRI images of the liver, kidneys and spleen. Our proposed model is an efficient and effective tool for medical image segmentation, achieving competitive performance compared to previous work in less than five clicks and with very low memory consumption without additional training.

Automated Adolescence Scoliosis Detection Using Augmented U-Net With Non-square Kernels

Purpose: Scoliosis is a deformity of the spine, and as a measure of scoliosis severity, Cobb angle is fundamental to the diagnosis of deformities that require treatment. Conventional Cobb angle measurement and assessment is usually done manually, which is inherently time-consuming, and associated with high inter- and intra-observer variability. While there exist automatic scoliosis measurement methods, they suffer from insufficient accuracy. In this work, we propose a two-step segmentation-based deep learning architecture to automate Cobb angle measurement for scoliosis assessment using X-Ray images. Methods: The proposed architecture involves two steps. In the first step, we utilize a novel Augmented U-Net architecture to generate segmentations of vertebrae. The second step includes a non-learning-based pipeline to extract landmark coordinates from the segmented vertebrae and filter undesirable landmarks. Results: Our proposed Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error of 9.2%, with approximately 90% of estimations having less than 10 degrees difference compared with the AASCE-MICCAI challenge 2019 dataset ground truths. We further validated the model using an internal dataset and achieved almost the same level of performance. Conclusion: The proposed architecture is robust in providing automated spinal vertebrae segmentations and Cobb angle measurement, and is potentially generalizable to real-world clinical settings.

TaG-Net: Topology-Aware Graph Network for Centerline-Based Vessel Labeling

Anatomical labeling of head and neck vessels is a vital step for cerebrovascular disease diagnosis. However, it remains challenging to automatically and accurately label vessels in computed tomography angiography (CTA) since head and neck vessels are tortuous, branched, and often spatially close to nearby vasculature. To address these challenges, we propose a novel topology-aware graph network (TaG-Net) for vessel labeling. It combines the advantages of volumetric image segmentation in the voxel space and centerline labeling in the line space, wherein the voxel space provides detailed local appearance information, and line space offers high-level anatomical and topological information of vessels through the vascular graph constructed from centerlines. First, we extract centerlines from the initial vessel segmentation and construct a vascular graph from them. Then, we conduct vascular graph labeling using TaG-Net, in which techniques of topology-preserving sampling, topology-aware feature grouping, and multi-scale vascular graph are designed. After that, the labeled vascular graph is utilized to improve volumetric segmentation via vessel completion. Finally, the head and neck vessels of 18 segments are labeled by assigning centerline labels to the refined segmentation. We have conducted experiments on CTA images of 401 subjects, and experimental results show superior vessel segmentation and labeling of our method compared to other state-of-the-art methods.

Retina-TransNet: A Gradient-Guided Few-Shot Retinal Vessel Segmentation Net

Due to the high labor cost of physicians, it is difficult to collect a rich amount of manually-labeled medical images for developing learning-based computer-aided diagnosis (CADx) systems or segmentation algorithms. To tackle this issue, we reshape the image segmentation task as an image-to-image (I2I) translation problem and propose a retinal vascular segmentation network, which can achieve good cross-domain generalizability even with a small amount of training data. We devise primarily two components to facilitate this I2I-based segmentation method. The first is the constraints provided by the proposed gradient-vector-flow (GVF) loss, and, the second is a two-stage Unet (2Unet) generator with a skip connection. This configuration makes 2Unet's first-stage play a role similar to conventional Unet, but forces 2Unet's second stage to learn to be a refinement module. Extensive experiments show that by re-casting retinal vessel segmentation as an image-to-image translation problem, our I2I translator-based segmentation subnetwork achieves better cross-domain generalizability than existing segmentation methods. Our model, trained on one dataset, e.g., DRIVE, can produce segmentation results stably on datasets of other domains, e.g., CHASE-DB1, STARE, HRF, and DIARETDB1, even in low-shot circumstances.

Attractive deep morphology-aware active contour network for vertebral body contour extraction with extensions to heterogeneous and semi-supervised scenarios

Automatic vertebral body contour extraction (AVBCE) from heterogeneous spinal MRI is indispensable for the comprehensive diagnosis and treatment of spinal diseases. However, AVBCE is challenging due to data heterogeneity, image characteristics complexity, and vertebral body morphology variations, which may cause morphology errors in semantic segmentation. Deep active contour-based (deep ACM-based) methods provide a promising complement for tackling morphology errors by directly parameterizing the contour coordinates. Extending the target contours' capture range and providing morphology-aware parameter maps are crucial for deep ACM-based methods. For this purpose, we propose a novel Attractive Deep Morphology-aware actIve contouR nEtwork (ADMIRE) that embeds an elaborated contour attraction term (CAT) and a comprehensive contour quality (CCQ) loss into the deep ACM-based framework. The CAT adaptively extends the target contours' capture range by designing an all-to-all force field to enable the target contours' energy to contribute to farther locations. Furthermore, the CCQ loss is carefully designed to generate morphology-aware active contour parameters by simultaneously supervising the contour shape, tension, and smoothness. These designs, in cooperation with the deep ACM-based framework, enable robustness to data heterogeneity, image characteristics complexity, and target contour morphology variations. Furthermore, the deep ACM-based ADMIRE is able to cooperate well with semi-supervised strategies such as mean teacher, which enables its function in semi-supervised scenarios. ADMIRE is trained and evaluated on four challenging datasets, including three spinal datasets with more than 1000 heterogeneous images and more than 10000 vertebrae bodies, as well as a cardiac dataset with both normal and pathological cases. Results show ADMIRE achieves state-of-the-art performance on all datasets, which proves ADMIRE's accuracy, robustness, and generalization ability.

A novel ex vivo tracheobronchomalacia model for airway stent testing and in vivo model refinement

OBJECTIVES

We sought to develop an ex vivo trachea model capable of producing mild, moderate, and severe tracheobronchomalacia for optimizing airway stent design. We also aimed to determine the amount of cartilage resection required for achieving different tracheobronchomalacia grades that can be used in animal models.

METHODS

We developed an ex vivo trachea test system that enabled video-based measurement of internal cross-sectional area as intratracheal pressure was cyclically varied for peak negative pressures of 20 to 80 cm H2O. Fresh ovine tracheas were induced with tracheobronchomalacia by single mid-anterior incision (n = 4), mid-anterior circumferential cartilage resection of 25% (n = 4), and 50% per cartilage ring (n = 4) along an approximately 3-cm length. Intact tracheas (n = 4) were used as control. All experimental tracheas were mounted and experimentally evaluated. In addition, helical stents of 2 different pitches (6 mm and 12 mm) and wire diameters (0.52 mm and 0.6 mm) were tested in tracheas with 25% (n = 3) and 50% (n = 3) circumferentially resected cartilage rings. The percentage collapse in tracheal cross-sectional area was calculated from the recorded video contours for each experiment.

RESULTS

Ex vivo tracheas compromised by single incision and 25% and 50% circumferential cartilage resection produce tracheal collapse corresponding to clinical grades of mild, moderate, and severe tracheobronchomalacia, respectively. A single anterior cartilage incision produces saber-sheath type tracheobronchomalacia, whereas 25% and 50% circumferential cartilage resection produce circumferential tracheobronchomalacia. Stent testing enabled the selection of stent design parameters such that airway collapse associated with moderate and severe tracheobronchomalacia could be reduced to conform to, but not exceed, that of intact tracheas (12-mm pitch, 0.6-mm wire diameter).

CONCLUSIONS

The ex vivo trachea model is a robust platform that enables systematic study and treatment of different grades and morphologies of airway collapse and tracheobronchomalacia. It is a novel tool for optimization of stent design before advancing to in vivo animal models.

DRU-Net: Pulmonary Artery Segmentation via Dense Residual U-Network with Hybrid Loss Function

The structure and topology of the pulmonary arteries is crucial to understand, plan, and conduct medical treatment in the thorax area. Due to the complex anatomy of the pulmonary vessels, it is not easy to distinguish between the arteries and veins. The pulmonary arteries have a complex structure with an irregular shape and adjacent tissues, which makes automatic segmentation a challenging task. A deep neural network is required to segment the topological structure of the pulmonary artery. Therefore, in this study, a Dense Residual U-Net with a hybrid loss function is proposed. The network is trained on augmented Computed Tomography volumes to improve the performance of the network and prevent overfitting. Moreover, the hybrid loss function is implemented to improve the performance of the network. The results show an improvement in the Dice and HD95 scores over state-of-the-art techniques. The average scores achieved for the Dice and HD95 scores are 0.8775 and 4.2624 mm, respectively. The proposed method will support physicians in the challenging task of preoperative planning of thoracic surgery, where the correct assessment of the arteries is crucial.

Magnetic resonance imaging assessments for knee segmentation and their use in combination with machine/deep learning as predictors of early osteoarthritis diagnosis and prognosis

Knee osteoarthritis (OA) is a prevalent and disabling disease that can develop over decades. This disease is heterogeneous and involves structural changes in the whole joint, encompassing multiple tissue types. Detecting OA before the onset of irreversible changes is crucial for early management, and this could be achieved by allowing knee tissue visualization and quantifying their changes over time. Although some imaging modalities are available for knee structure assessment, magnetic resonance imaging (MRI) is preferred. This narrative review looks at existing literature, first on MRI-developed approaches for evaluating knee articular tissues, and second on prediction using machine/deep-learning-based methodologies and MRI as input or outcome for early OA diagnosis and prognosis. A substantial number of MRI methodologies have been developed to assess several knee tissues in a semi-quantitative and quantitative fashion using manual, semi-automated and fully automated systems. This dynamic field has grown substantially since the advent of machine/deep learning. Another active area is predictive modelling using machine/deep-learning methodologies enabling robust early OA diagnosis/prognosis. Moreover, incorporating MRI markers as input/outcome in such predictive models is important for a more accurate OA structural diagnosis/prognosis. The main limitation of their usage is the ability to move them in rheumatology practice. In conclusion, MRI knee tissue determination and quantification provide early indicators for individuals at high risk of developing this disease or for patient prognosis. Such assessment of knee tissues, combined with the development of models/tools from machine/deep learning using, in addition to other parameters, MRI markers for early diagnosis/prognosis, will maximize opportunities for individualized risk assessment for use in clinical practice permitting precision medicine. Future efforts should be made to integrate such prediction models into open access, allowing early disease management to prevent or delay the OA outcome.

Longitudinal changes in quantitative magnetic resonance imaging metrics in children and young adults with autoimmune liver disease

PURPOSE

To assess longitudinal changes in quantitative MRI metrics in pediatric and young adult patients with autoimmune liver disease (AILD).

METHODS

This prospective, IRB-approved study included 20 children and young adults (median age = 15 years) with primary sclerosing cholangitis (PSC)/autoimmune sclerosing cholangitis (ASC) and 19 (median age = 17 years) with autoimmune hepatitis (AIH). At a field strength of 1.5-T, T2*-corrected T1 mapping (cT1), 3D fast spin-echo MRCP, and 2D gradient recalled echo MR elastography (MRE) were performed at baseline, one year, and two years. cT1 and quantitative MRCP were processed using LiverMultiScan and MRCP + , respectively (Perspectum Ltd, Oxford, UK). Linear mixed models were used to assess longitudinal changes in quantitative MRI metrics. Spearman rank-order correlation was used to assess relationships between changes in quantitative MRI metrics.

RESULTS

Changes in quantitative MRI metrics greater than established repeatability coefficients were measured in six (cT1) and five (MRE) patients with PSC/ASC as well as in six patients (cT1 and MRE) with AIH, although linear mixed models identified no significant changes for the subgroups as a whole. For PSC/ASC, there were positive correlations between change in liver stiffness and changes in bile duct strictures (ρ = 0.68; p = 0.005) and bile duct dilations (ρ = 0.70; p = 0.004) between baseline and Year 2.

CONCLUSION

On average, there were no significant changes in quantitative MRI metrics over a two-year period in children and young adults with AILD. However, worsening cholangiopathy was associated with increasing liver stiffness by MRE in patients with PSC/ASC.

Fully Automatic Liver and Tumor Segmentation from CT Image Using an AIM-Unet

The segmentation of the liver is a difficult process due to the changes in shape, border, and density that occur in each section in computed tomography (CT) images. In this study, the Adding Inception Module-Unet (AIM-Unet) model, which is a hybridization of convolutional neural networks-based Unet and Inception models, is proposed for computer-assisted automatic segmentation of the liver and liver tumors from CT scans of the abdomen. Experimental studies were carried out on four different liver CT image datasets, one of which was prepared for this study and three of which were open (CHAOS, LIST, and 3DIRCADb). The results obtained using the proposed method and the segmentation results marked by the specialist were compared with the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and accuracy (ACC) measurement parameters. In this study, we obtained the best DSC, JSC, and ACC liver segmentation performance metrics on the CHAOS dataset as 97.86%, 96.10%, and 99.75%, respectively, of the AIM-Unet model we propose, which is trained separately on three datasets (LiST, CHAOS, and our dataset) containing liver images. Additionally, 75.6% and 65.5% of the DSC tumor segmentation metrics were calculated on the proposed model LiST and 3DIRCADb datasets, respectively. In addition, the segmentation success results on the datasets with the AIM-Unet model were compared with the previous studies. With these results, it has been seen that the method proposed in this study can be used as an auxiliary tool in the decision-making processes of physicians for liver segmentation and detection of liver tumors. This study is useful for medical images, and the developed model can be easily developed for applications in different organs and other medical fields.

A State-Of-The-Art Review on Coronary Artery Border Segmentation Algorithms for Intravascular Ultrasound (IVUS) Images

Intravascular Ultrasound images (IVUS) is a useful guide for medical practitioners to identify the vascular status of coronary arteries in human beings. IVUS is a unique intracoronary imaging modality that is used as an adjunct to angioplasty to view vessel structures using a catheter with high resolutions. Segmentation of IVUS images has always remained a challenging task due to various impediments, for example, similar tissue components, vessel structures, and artifacts imposed during the acquisition process. Many researchers have applied various techniques to develop standard methods of image interpretation, however, the ultimate goal is still elusive to most researchers. This challenge was presented at the MICCAI- Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop in 2011. This paper presents a major review of recently reported work in the field, with a detailed analysis of various segmentation techniques applied in IVUS, and highlights the directions for future research. The findings recommend a reference database with a larger number of samples acquired at varied transducer frequencies with special consideration towards complex lesions, suitable validation metrics, and ground-truth definition as a standard against which to compare new and current algorithms.

Combining natural and artificial intelligence for robust automatic anatomy segmentation: Application in neck and thorax auto-contouring

BACKGROUND

Automatic segmentation of 3D objects in computed tomography (CT) is challenging. Current methods, based mainly on artificial intelligence (AI) and end-to-end deep learning (DL) networks, are weak in garnering high-level anatomic information, which leads to compromised efficiency and robustness. This can be overcome by incorporating natural intelligence (NI) into AI methods via computational models of human anatomic knowledge.

PURPOSE

We formulate a hybrid intelligence (HI) approach that integrates the complementary strengths of NI and AI for organ segmentation in CT images and illustrate performance in the application of radiation therapy (RT) planning via multisite clinical evaluation.

METHODS

The system employs five modules: (i) body region recognition, which automatically trims a given image to a precisely defined target body region; (ii) NI-based automatic anatomy recognition object recognition (AAR-R), which performs object recognition in the trimmed image without DL and outputs a localized fuzzy model for each object; (iii) DL-based recognition (DL-R), which refines the coarse recognition results of AAR-R and outputs a stack of 2D bounding boxes (BBs) for each object; (iv) model morphing (MM), which deforms the AAR-R fuzzy model of each object guided by the BBs output by DL-R; and (v) DL-based delineation (DL-D), which employs the object containment information provided by MM to delineate each object. NI from (ii), AI from (i), (iii), and (v), and their combination from (iv) facilitate the HI system.

RESULTS

The HI system was tested on 26 organs in neck and thorax body regions on CT images obtained prospectively from 464 patients in a study involving four RT centers. Data sets from one separate independent institution involving 125 patients were employed in training/model building for each of the two body regions, whereas 104 and 110 data sets from the 4 RT centers were utilized for testing on neck and thorax, respectively. In the testing data sets, 83% of the images had limitations such as streak artifacts, poor contrast, shape distortion, pathology, or implants. The contours output by the HI system were compared to contours drawn in clinical practice at the four RT centers by utilizing an independently established ground-truth set of contours as reference. Three sets of measures were employed: accuracy via Dice coefficient (DC) and Hausdorff boundary distance (HD), subjective clinical acceptability via a blinded reader study, and efficiency by measuring human time saved in contouring by the HI system. Overall, the HI system achieved a mean DC of 0.78 and 0.87 and a mean HD of 2.22 and 4.53 mm for neck and thorax, respectively. It significantly outperformed clinical contouring in accuracy and saved overall 70% of human time over clinical contouring time, whereas acceptability scores varied significantly from site to site for both auto-contours and clinically drawn contours.

CONCLUSIONS

The HI system is observed to behave like an expert human in robustness in the contouring task but vastly more efficiently. It seems to use NI help where image information alone will not suffice to decide, first for the correct localization of the object and then for the precise delineation of the boundary.

Toward evaluation of multiresolution cortical thickness estimation with FreeSurfer, MaCRUISE, and BrainSuite

Advances in Magnetic Resonance Imaging hardware and methodologies allow for promoting the cortical morphometry with submillimeter spatial resolution. In this paper, we generated 3D self-enhanced high-resolution (HR) MRI imaging, by adapting 1 deep learning architecture, and 3 standard pipelines, FreeSurfer, MaCRUISE, and BrainSuite, have been collectively employed to evaluate the cortical thickness. We systematically investigated the differences in cortical thickness estimation for MRI sequences at multiresolution homologously originated from the native image. It has been revealed that there systematically exhibited the preferences in determining both inner and outer cortical surfaces at higher resolution, yielding most deeper cortical surface placements toward GM/WM or GM/CSF boundaries, which directs a consistent reduction tendency of mean cortical thickness estimation; on the contrary, the lower resolution data will most probably provide a more coarse and rough evaluation in cortical surface reconstruction, resulting in a relatively thicker estimation. Although the differences of cortical thickness estimation at the diverse spatial resolution varied with one another, almost all led to roughly one-sixth to one-fifth significant reduction across the entire brain at the HR, independent to the pipelines we applied, which emphasizes on generally coherent improved accuracy in a data-independent manner and endeavors to cost-efficiency with quantitative opportunities.

An intensity-based post-processing tool for 3D instance segmentation of organelles in soft X-ray tomograms

Investigating the 3D structures and rearrangements of organelles within a single cell is critical for better characterizing cellular function. Imaging approaches such as soft X-ray tomography have been widely applied to reveal a complex subcellular organization involving multiple inter-organelle interactions. However, 3D segmentation of organelle instances has been challenging despite its importance in organelle characterization. Here we propose an intensity-based post-processing tool to identify and separate organelle instances. Our tool separates sphere-like (insulin vesicle) and columnar-shaped organelle instances (mitochondrion) based on the intensity of raw tomograms, semantic segmentation masks, and organelle morphology. We validate our tool using synthetic tomograms of organelles and experimental tomograms of pancreatic β-cells to separate insulin vesicle and mitochondria instances. As compared to the commonly used connected regions labeling, watershed, and watershed + Gaussian filter methods, our tool results in improved accuracy in identifying organelles in the synthetic tomograms and an improved description of organelle structures in β-cell tomograms. In addition, under different experimental treatment conditions, significant changes in volumes and intensities of both insulin vesicle and mitochondrion are observed in our instance results, revealing their potential roles in maintaining normal β-cell function. Our tool is expected to be applicable for improving the instance segmentation of other images obtained from different cell types using multiple imaging modalities.

Water extraction from SAR images based on improved geodesic active contour

The rapid and accurate acquisition of water body information is of great significance to water resource investigation, flood disaster monitoring, ecological environment protection, and other fields. In this paper, the water boundary is optimized and extracted from single-polarization SAR images based on an improved geodesic active contour model (IMGAC). Firstly, the rough extraction results of the water body were obtained according to the adaptive threshold, and then a narrowband model was established, and the signed pressure force (SPF) function was introduced into the geodesic active contour (GAC) model. Finally, the optimal water boundary was obtained through continuous iteration. Compared with the active contour (AC) model without edge and the traditional GAC model, the results show that the IMGAC model proposed in this paper can reduce the calculation efficiency and improve the accuracy of water boundary detection. The F-measure index was used to evaluate the extraction accuracy of the three methods. IMGAC method had the highest extraction accuracy, which was 96.43%. The kappa coefficient reached 0.929. The F-measure index was 96.20%. Our study can provide a reference for water extraction and water boundary optimization.

Quantitative magnetic resonance imaging measures as biomarkers of disease progression in boys with Duchenne muscular dystrophy: a phase 2 trial of domagrozumab

Duchenne muscular dystrophy (DMD) is a progressive, neuromuscular disorder caused by mutations in the DMD gene that results in a lack of functional dystrophin protein. Herein, we report the use of quantitative magnetic resonance imaging (MRI) measures as biomarkers in the context of a multicenter phase 2, randomized, placebo-controlled clinical trial evaluating the myostatin inhibitor domagrozumab in ambulatory boys with DMD (n = 120 aged 6 to < 16 years). MRI scans of the thigh to measure muscle volume, muscle volume index (MVI), fat fraction, and T2 relaxation time were obtained at baseline and at weeks 17, 33, 49, and 97 as per protocol. These quantitative MRI measurements appeared to be sensitive and objective biomarkers for evaluating disease progression, with significant changes observed in muscle volume, MVI, and T2 mapping measures over time. To further explore the utility of quantitative MRI measures as biomarkers to inform longer term functional changes in this cohort, a regression analysis was performed and demonstrated that muscle volume, MVI, T2 mapping measures, and fat fraction assessment were significantly correlated with longer term changes in four-stair climb times and North Star Ambulatory Assessment functional scores. Finally, less favorable baseline measures of MVI, fat fraction of the muscle bundle, and fat fraction of lean muscle were significant risk factors for loss of ambulation over a 2-year monitoring period. These analyses suggest that MRI can be a valuable tool for use in clinical trials and may help inform future functional changes in DMD.Trial registration: ClinicalTrials.gov identifier, NCT02310763; registered December 2014.

Four decades of image processing: a bibliometric analysis

Purpose

Image Processing is an emerging field that is used to extract information from images. In recent years, this field has received immense attention from researchers, especially in the research domains of object detection, Biomedical Imaging and Semantic segmentation. In this study, a bibliometric analysis of publications related to image processing in the Science Expanded Index Extended (SCI-Expanded) has been performed. Several parameters have been analyzed such as annual scientific production, citations per article, most cited documents, top 20 articles, most relevant authors, authors evaluation using y-index, top and most relevant sources (journals) and hot topics.

Design/methodology/approach

The Bibliographic data has been extracted from the Web of Science which is well known and the world's top database of bibliographic citations of multidisciplinary areas that covers the various journals of computer science, engineering, medical and social sciences.

Findings

The research work in image processing is meager in the past decade, however, from 2014 to 2019, it increases dramatically. Recently, the IEEE Access journal is the most relevant source with an average of 115 publications per year. The USA is most productive and its publications are highly cited while China comes in second place. Image Segmentation, Feature Extraction and Medical Image Processing are hot topics in recent years. The National Natural Science Foundation of China provides 8% of all funds for Image Processing. As Image Processing is now becoming one of the most critical fields, the research productivity has enhanced during the past five years and more work is done while the era of 2005–2013 was the area with the least amount of work in this area.

Originality/value

This research is novel in this regard that no previous research focuses on Bibliometric Analysis in the Image Processing domain, which is one of the hot research areas in computer science and engineering.

Image Segmentation Using Active Contours with Hessian-Based Gradient Vector Flow External Force

The gradient vector flow (GVF) model has been widely used in the field of computer image segmentation. In order to achieve better results in image processing, there are many research papers based on the GVF model. However, few models include image structure. In this paper, the smoothness constraint formula of the GVF model is re-expressed in matrix form, and the image knot represented by the Hessian matrix is included in the GVF model. Through the processing of this process, the relevant diffusion partial differential equation has anisotropy. The GVF model based on the Hessian matrix (HBGVF) has many advantages over other relevant GVF methods, such as accurate convergence to various concave surfaces, excellent weak edge retention ability, and so on. The following will prove the advantages of our proposed model through theoretical analysis and various comparative experiments.

Bio-hybrid micro-swimmers propelled by flagella isolated from C. reinhardtii

Bio-hybrid micro-swimmers, composed of biological entities integrated with synthetic constructs, actively transport cargo by converting chemical energy into mechanical work. Here, using isolated and demembranated flagella from green algae Chlamydomonas reinhardtii (C. reinhardtii), we build efficient axonemally-driven micro-swimmers that consume ATP to propel micron-sized beads. Depending on the calcium concentration, we observed two main classes of motion: whereas beads move along curved trajectories at calcium concentrations below 0.03 mM, they are propelled along straight paths when the calcium concentration increases. In this regime, they reached velocities of approximately 20 μm s^-1, comparable to human sperm velocity in vivo. We relate this transition to the properties of beating axonemes, in particular the reduced static curvature with increasing calcium concentration. Our designed system has potential applications in the fabrication of synthetic micro-swimmers, and in particular, bio-actuated medical micro-robots for targeted drug delivery.

Beyond automatic medical image segmentation-the spectrum between fully manual and fully automatic delineation

Semi-automatic and fully automatic contouring tools have emerged as an alternative to fully manual segmentation to reduce time spent contouring and to increase contour quality and consistency. Particularly, fully automatic segmentation has seen exceptional improvements through the use of deep learning in recent years. These fully automatic methods may not require user interactions, but the resulting contours are often not suitable to be used in clinical practice without a review by the clinician. Furthermore, they need large amounts of labelled data to be available for training. This review presents alternatives to manual or fully automatic segmentation methods along the spectrum of variable user interactivity and data availability. The challenge lies to determine how much user interaction is necessary and how this user interaction can be used most effectively. While deep learning is already widely used for fully automatic tools, interactive methods are just at the starting point to be transformed by it. Interaction between clinician and machine, via artificial intelligence, can go both ways and this review will present the avenues that are being pursued to improve medical image segmentation.

Live cell microscopy: From image to insight

Live-cell microscopy is a powerful tool that can reveal cellular behavior as well as the underlying molecular processes. A key advantage of microscopy is that by visualizing biological processes, it can provide direct insights. Nevertheless, live-cell imaging can be technically challenging and prone to artifacts. For a successful experiment, many careful decisions are required at all steps from hardware selection to downstream image analysis. Facing these questions can be particularly intimidating due to the requirement for expertise in multiple disciplines, ranging from optics, biophysics, and programming to cell biology. In this review, we aim to summarize the key points that need to be considered when setting up and analyzing a live-cell imaging experiment. While we put a particular focus on yeast, many of the concepts discussed are applicable also to other organisms. In addition, we discuss reporting and data sharing strategies that we think are critical to improve reproducibility in the field.

Beyond transparency: architectural application of robotically fabricated polychromatic float glass

This research investigates robotically fabricated polychromatic float glass for architectural applications. Polychromatic glass elements usually require labor-intensive processes or are limited to film applications of secondary materials onto the glass. Previous research employs computer numerical control (CNC) based multi-channel granule deposition to manufacture polychromatic relief glass; however, it is limited in motion, channel control, and design space. To expand the design and fabrication space for the manufacture of mono-material polychromatic glass elements, this paper presents further advancements using a UR robotic arm with an advanced multi-channel dispenser, linear and curved-paths granule deposition, customized color pattern design approaches, and a computational tool for the prediction and rendering of outcomes. A large-scale demonstrator serves as a case study for upscaling. Robotic multi-channel deposition and tailored computational design tools are employed to facilitate a full-scale installation consisting of eighteen large glass panels. Novel optical properties include locally varying color, opacity, and texture filter light and view. The resulting product constructs sublime architectural experiences through light refraction, reflection, color, opacity - beyond mere transparency.

Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening

Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administering drugs and surgical treatments. In this study, we will establish a multilayer one-dimensional (1D) convolutional neural network (CNN)-based classifier for automatic cardiomegaly level screening based on chest X-ray (CXR) image classification in frontal posteroanterior view. Using two-round 1D convolutional processes in the convolutional pooling layer, two-dimensional (2D) feature maps can be converted into feature signals, which can enhance their characteristics for identifying normal condition and cardiomegaly levels. In the classification layer, a classifier based on gray relational analysis, which has a straightforward mathematical operation, is used to screen the cardiomegaly levels. Based on the collected datasets from the National Institutes of Health CXR image database, the proposed multilayer 1D CNN-based classifier with K-fold cross-validation has promising results for the intended medical purpose, with precision of 97.80%, recall of 98.20%, accuracy of 98.00%, and F1 score of 0.9799.

ANALYSIS OF SPECIFIC PARAMETERS FOR SKIN TUMOR CLASSIFICATION

During the last years, computer vision-based diagnosis systems have been widely used in several hospitals and dermatology clinics, aiming mostly at the early detection of malignant melanoma tumor, which is among the most frequent types of skin cancer, versus other types of nonmalignant cutaneous diseases. They grow in melanocytes, the cells responsible for pigmentation. This type of cancer is increasing rapidly and its related mortality rate is increasing more modestly, and inversely proportional to the tumor’s thickness. The mortality rate can be decreased by earlier detection of suspicious lesions and better prevention. In this work, we are interested in extracting all specific attributes which can be used for computer-aided diagnosis of melanoma. In the first step of the proposed work, we applied the Dull Razor [Lee T et al., Dullrazor: A software approach to hair removal from images, Cancer Control Research, British Columbia Cancer Agency, Vancouver, Canada, Vol. 21, No. 6, pp. 533–543, 1997] technique to images to reduce the influence of small structures, hairs, bubbles, light reflection. In the second step, a new fuzzy level set algorithm is proposed in order to facilitate the medical image segmentation task. It is able to directly evolve from the initial segmentation proposed that uses a spatial fuzzy clustering approach. The controlling parameters of the level set evolution are also estimated from the results of the fuzzy clustering step. This step is essential to characterize the shape of the lesion and also to locate the tumor to be analyzed. In this paper, we have also treated the necessity to extract all the specific attributes used to develop a characterization methodology that enables specialists to take the best possible diagnosis. For this purpose, our proposal relies largely on visual observation of the tumor while dealing with some characteristics as color, texture or form. The method used in this paper is called ABCD. It requires calculating four factors: Asymmetry ([Formula: see text], Border ([Formula: see text], Color ([Formula: see text], and Diversity ([Formula: see text]. Finally, these parameters are used to construct a classification module based on artificial neural network for the recognition of malignant melanoma.

Automation of Cranial Nerve Tractography by Filtering Tractograms for Skull Base Surgery

Fiber tractography enables the in vivo reconstruction of white matter fibers in 3 dimensions using data collected by diffusion tensor imaging, thereby helping to understand functional neuroanatomy. In a pre-operative context, it provides essential information on the trajectory of fiber bundles of medical interest, such as cranial nerves. However, the optimization of tractography parameters is a time-consuming process and requires expert neuroanatomical knowledge, making the use of tractography difficult in clinical routine. Tractogram filtering is a method used to isolate the most relevant fibers. In this work, we propose to use filtering as a post-processing of tractography to avoid the manual optimization of tracking parameters and therefore making a step forward automation of tractography. To question the feasibility of automated tractography of cranial nerves, we perform an analysis of main cranial nerves on a series of patients with skull base tumors. A quantitative evaluation of the filtering performance of two state-of-the-art and a new entropy-based methods is carried out on the basis of reference tractograms produced by experts. Our approach proves to be more stable in the selection of the optimal filtering threshold and turns out to be interesting in terms of computational time complexity.

A Review on the Rule-Based Filtering Structure with Applications on Computational Biomedical Images

In this paper, we present rule-based fuzzy inference systems that consist of a series of mathematical representations based on fuzzy concepts in the filtering structure. It is crucial for understanding and discussing different principles associated with fuzzy filter design procedures. A number of typical fuzzy multichannel filtering approaches are provided in order to clarify the different fuzzy filter designs and compare different algorithms. In particular, in most practical applications (i.e., biomedical image analysis), the emphasis is placed primarily on fuzzy filtering algorithms, with the main advantages of restoration of corrupted medical images and the interpretation capability, along with the capability of edge preservation and relevant image information for accurate diagnosis of diseases.

An Integrative Segmentation Framework for Cell Nucleus of Fluorescence Microscopy

Nucleus segmentation of fluorescence microscopy is a critical step in quantifying measurements in cell biology. Automatic and accurate nucleus segmentation has powerful applications in analyzing intrinsic characterization in nucleus morphology. However, existing methods have limited capacity to perform accurate segmentation in challenging samples, such as noisy images and clumped nuclei. In this paper, inspired by the idea of cascaded U-Net (or W-Net) and its remarkable performance improvement in medical image segmentation, we proposed a novel framework called Attention-enhanced Simplified W-Net (ASW-Net), in which a cascade-like structure with between-net connections was used. Results showed that this lightweight model could reach remarkable segmentation performance in the BBBC039 testing set (aggregated Jaccard index, 0.90). In addition, our proposed framework performed better than the state-of-the-art methods in terms of segmentation performance. Moreover, we further explored the effectiveness of our designed network by visualizing the deep features from the network. Notably, our proposed framework is open source.

Evaluation of carotid intima media thickness measurement from ultrasound images

A third of deaths in the world are due to cardiovascular diseases [1]. Atherosclerosis is the major cause of myocardial infarction, which occurs by deposition of plaque in the coronary artery. The chance of stroke rises with the thickening of carotid artery due to the plaque. Hence, accurate measurement of the intima-media thickness is necessary for predicting the chance of stroke. The stopping criterion and active resampling are incorporated in greedy snake segmentation technique. This modified algorithm segmented and extracted the intima-media complex in the ultrasound images. The snake control points obtained from the boundary of the region of interest forms the contour and demarcates the boundary of intima-media complex. The thickness ± standard deviation and the intra-observer error values obtained by modified algorithm are in conformity with the measurements by expert. The intra-observer error values for greedy snake segmentation methods were 0.10 and 0.09 for manual snake initialization and automatic snake initialization, respectively. Shapiro-Wilk test and One-way ANOVA test explains there is no statistical difference between group means obtained from these segmentation techniques and the expert measurement. The statistical analysis proves values of the intima-media thickness obtained from both snake segmentation techniques are very close to expert measurements.

Sequential shape similarity for active contour based left ventricle segmentation in cardiac cine MR image

Delineation of the boundaries of the Left Ventricle (LV) in cardiac Magnetic Resonance Images (MRI) is a hot topic due to its important diagnostic power. In this paper, an approach is proposed to extract the LV in a sequence of MR images. In the proposed paper, all images in the sequence are segmented simultaneously and the shape of the LV in each image is supposed to be similar to that of the LV in nearby images in the sequence. We coined the novel shape similarity constraint, and it is called sequential shape similarity (SSS in short). The proposed segmentation method takes the Active Contour Model as the base model and our previously proposed Gradient Vector Convolution (GVC) external force is also adopted. With the SSS constraint, the snake contour can accurately delineate the LV boundaries. We evaluate our method on two cardiac MRI datasets and the Mean Absolute Distance (MAD) metric and the Hausdorff Distance (HD) metric demonstrate that the proposed approach has good performance on segmenting the boundaries of the LV.

Automatic breast tissue segmentation in MRIs with morphology snake and deep denoiser training via extended Stein's unbiased risk estimator

Accurate segmentation of the breast tissue is a significant challenge in the analysis of breast MR images, especially analysis of breast images with low contrast. Most of the existing methods for breast segmentation are semi-automatic and limited in their ability to achieve accurate results. This is because of difficulties in removing landmarks from noisy magnetic resonance images (MRI). Especially, when tumour is imaged for scanning, how to isolate the tumour region from chest will directly affect the accuracy for tumour to be detected. Due to low intensity levels and the close connection between breast and chest portion in MRIs, this study proposes an innovative, fully automatic and fast segmentation approach which combines histogram with inverse Gaussian gradient for morphology snakes, along with extended Stein's unbiased risk estimator (eSURE) applied for unsupervised learning of deep neural network Gaussian denoisers, aimed at accurate identification of landmarks such as chest and breast.

3D Interactive Segmentation With Semi-Implicit Representation and Active Learning

Segmenting complex 3D geometry is a challenging task due to rich structural details and complex appearance variations of target object. Shape representation and foreground-background delineation are two of the core components of segmentation. Explicit shape models, such as mesh based representations, suffer from poor handling of topological changes. On the other hand, implicit shape models, such as level-set based representations, have limited capacity for interactive manipulation. Fully automatic segmentation for separating foreground objects from background generally utilizes non-interoperable machine learning methods, which heavily rely on the off-line training dataset and are limited to the discrimination power of the chosen model. To address these issues, we propose a novel semi-implicit representation method, namely Non-Uniform Implicit B-spline Surface (NU-IBS), which adaptively distributes parametrically blended patches according to geometrical complexity. Then, a two-stage cascade classifier is introduced to carry out efficient foreground and background delineation, where a simplistic Naïve-Bayesian model is trained for fast background elimination, followed by a stronger pseudo-3D Convolutional Neural Network (CNN) multi-scale classifier to precisely identify the foreground objects. A localized interactive and adaptive segmentation scheme is incorporated to boost the delineation accuracy by utilizing the information iteratively gained from user intervention. The segmentation result is obtained via deforming an NU-IBS according to the probabilistic interpretation of delineated regions, which also imposes a homogeneity constrain for individual segments. The proposed method is evaluated on a 3D cardiovascular Computed Tomography Angiography (CTA) image dataset and Brain Tumor Image Segmentation Benchmark 2015 (BraTS2015) 3D Magnetic Resonance Imaging (MRI) dataset.

Towards real time guide wire shape extraction in fluoroscopic sequences: A two phase deep learning scheme to extract sparse curvilinear structures

BACKGROUND AND OBJECTIVE

Real time localization and shape extraction of guide wire in fluoroscopic images plays a significant role in the image guided navigation during cerebral and cardiovascular interventions. Given the complexity of the non-rigid and sparse characteristics of guide wire structures, and the low SNR(Signal Noise Ratio) of fluoroscopic images, traditional handcrafted guide wire tracking methods such as Frangi filter, Hessian Matrix, or open active contour usually produce insufficient accuracy with high computational cost, and may require extra human intervention for proper initialization or correction. The application of deep learning techniques to guide wire tracking is reported to produce significant improvement in guide wire localization accuracy, but the heavy calculation cost is still a concern.

METHOD

In this paper we propose a two phase deep learning scheme for accurate and real time guide wire shape extraction in fluoroscopic sequences. In the first phase we train a guide wire localization network to pick image regions containing guide wire structures. From the picked image regions, we train a guide wire shape extraction network in the second phase to mark the guide wire pixels.

RESULTS

We report that our proposed method can accurately distinguish about 99% of the guide wire structure pixels, and the falsely detected pixels in the background are close to 0, the average offset from the ground truth is less than 1 pixel. For extreme cases where traditional handcrafted method may fail, our proposed method can still extract guide wire completely and accurately. The processing time for a 512 × 512 pixels image is 78 ms.

CONCLUSION

Compared with the traditional filtering based method from our previous work, we show that our proposed method can achieve more accurate and stable performance. Compared with other deep learning methods, our proposed method significantly improve calculation efficiency to meet the real time requirement of clinical applications.