Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos

The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall.

Download Full-text

Fibernet 2.0: An Automatic Neural Network Based Tool for Clustering White Matter Fibers in the Brain

10.1101/210781 ◽

2017 ◽

Cited By ~ 1

Author(s):

Vikash Gupta ◽

Sophia I. Thomopoulos ◽

Conor K. Corbin ◽

Faisal Rashid ◽

Paul M. Thompson

Keyword(s):

White Matter ◽

Spectral Clustering ◽

Developmental Disorders ◽

Fiber Bundles ◽

Neural Pathways ◽

Fiber Tracts ◽

Learning Techniques ◽

Segmentation Methods ◽

White Matter Fiber Tracts ◽

The Brain

ABSTRACTThe brain’s white matter fiber tracts are impaired in a range of common and devastating conditions, from Alzheimer’s disease to brain trauma, and in developmental disorders such as autism and neurogenetic syndromes. Many studies now examine the connectivity and microstructure of the brain’s neural pathways, spurring the development of algorithms to extract and measure tracts and fiber bundles. Clustering white matter (WM) fibers, from whole-brain tractography, into anatomically meaningful bundles is still a challenging problem. Existing tract segmentation methods use atlases or regions of interest (ROI) or unsupervised spectral clustering. Even so, atlas-based segmentation does not always partition the brain into a set of recognizable fiber bundles. Deep learning techniques can be applied to automatically segment and cluster white matter fibers. Here we propose a robust approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which we then exploit to cluster WM fibers into bundles. In a range of tests across diverse fiber bundles, we illustrate the accuracy of our method, and its ability to suppress false positive fibers.

Download Full-text

A large, open source dataset of stroke anatomical brain images and manual lesion segmentations

10.1101/179614 ◽

2017 ◽

Cited By ~ 2

Author(s):

Sook-Lei Liew ◽

Julia M. Anglin ◽

Nick W. Banks ◽

Matt Sondag ◽

Kaori L. Ito ◽

...

Keyword(s):

Open Source ◽

Large Scale ◽

Stroke Recovery ◽

Machine Learning Techniques ◽

Lesion Segmentation ◽

Brain Images ◽

Learning Techniques ◽

Segmentation Methods ◽

Segmentation Algorithms

AbstractStroke is the leading cause of adult disability worldwide, with up to two-thirds of individuals experiencing long-term disabilities. Large-scale neuroimaging studies have shown promise in identifying robust biomarkers (e.g., measures of brain structure) of long-term stroke recovery following rehabilitation. However, analyzing large rehabilitation-related datasets is problematic due to barriers in accurate stroke lesion segmentation. Manually-traced lesions are currently the gold standard for lesion segmentation on T1-weighted MRIs, but are labor intensive and require anatomical expertise. While algorithms have been developed to automate this process, the results often lack accuracy. Newer algorithms that employ machine-learning techniques are promising, yet these require large training datasets to optimize performance. Here we present ATLAS (Anatomical Tracings of Lesions After Stroke), an open-source dataset of 304 T1-weighted MRIs with manually segmented lesions and metadata. This large, diverse dataset can be used to train and test lesion segmentation algorithms and provides a standardized dataset for comparing the performance of different segmentation methods. We hope ATLAS release 1.1 will be a useful resource to assess and improve the accuracy of current lesion segmentation methods.

Download Full-text

Deficient Myocardial Organization and Pathological Fibrosis in Fetal Aortic Stenosis—Association of Prenatal Ultrasound with Postmortem Histology

Journal of Cardiovascular Development and Disease ◽

10.3390/jcdd8100121 ◽

2021 ◽

Vol 8 (10) ◽

pp. 121

Author(s):

Fleur Zwanenburg ◽

Marco C. DeRuiter ◽

Lambertus J. Wisse ◽

Conny J. van Munsteren ◽

Margot M. Bartelings ◽

...

Keyword(s):

Aortic Stenosis ◽

Structural Damage ◽

Fetal Echocardiography ◽

Pregnancy Termination ◽

Myocardial Strain ◽

Left Ventricular ◽

Myocardial Deformation ◽

Fetal Ultrasound ◽

Chamber View ◽

Potential Biomarker

In fetal aortic stenosis (AS), it remains challenging to predict left ventricular development over the course of pregnancy. Myocardial organization, differentiation and fibrosis could be potential biomarkers relevant for biventricular outcome. We present four cases of fetal AS with varying degrees of severity and associate myocardial deformation on fetal ultrasound with postmortem histopathological characteristics. During routine fetal echocardiography, speckle tracking recordings of the cardiac four-chamber view were performed to assess myocardial strain as parameter for myocardial deformation. After pregnancy termination, postmortem cardiac specimens were examined using immunohistochemical labeling (IHC) of key markers for myocardial organization, differentiation and fibrosis and compared to normal fetal hearts. Two cases with critical AS presented extremely decreased left ventricular (LV) strain on fetal ultrasound. IHC showed overt endocardial fibro-elastosis, which correlated with pathological fibrosis patterns in the myocardium and extremely disturbed cardiomyocyte organization. The LV in severe AS showed mildly reduced myocardial strain and less severe disorganization of the cardiomyocytes. In conclusion, the degree of reduction in myocardial deformation corresponded with high extent to the amount of pathological fibrosis patterns and cardiomyocyte disorganization. Myocardial deformation on fetal ultrasound seems to hold promise as a potential biomarker for left ventricular structural damage in AS.

Download Full-text

Automated Segmentation of Abnormal Tissues in Medical Images

Journal of Biomedical Physics and Engineering ◽

10.31661/jbpe.v0i0.958 ◽

2019 ◽

Author(s):

H Khastavaneh ◽

H Ebrahimpour-komleh

Keyword(s):

Diagnostic Procedures ◽

Skin Lesions ◽

Tissue Type ◽

Automated Segmentation ◽

Tissue Segmentation ◽

Learning Techniques ◽

Segmentation Methods ◽

Specific Tissue ◽

Better Than ◽

Abnormal Tissue

Nowadays, medical image modalities are almost available everywhere. These modalities are bases of diagnosis of various diseases sensitive to specific tissue type. Usually physicians look for abnormalities in these modalities in diagnostic procedures. Count and volume of abnormalities are very important for optimal treatment of patients. Segmentation is a preliminary step for these measurements and also further analysis. Manual segmentation of abnormalities is cumbersome, error prone, and subjective. As a result, automated segmentation of abnormal tissue is a need. In this study, representative techniques for segmentation of abnormal tissues are reviewed. Main focus is on the segmentation of multiple sclerosis lesions, breast cancer masses, lung nodules, and skin lesions. As experimental results demonstrate, the methods based on deep learning techniques perform better than other methods that are usually based on handy feature engineering techniques. Finally, the most common measures to evaluate automated abnormal tissue segmentation methods are reported.

Download Full-text

A New Classification Approach with Deep Mask R-CNN for Synthetic Aperture Radar Image Segmentation

Elektronika ir Elektrotechnika ◽

10.5755/j01.eie.26.6.25849 ◽

2020 ◽

Vol 26 (6) ◽

pp. 52-57

Author(s):

Ridvan Yayla ◽

Baha Sen

Keyword(s):

Neural Network ◽

Image Segmentation ◽

Synthetic Aperture Radar ◽

High Accuracy ◽

Synthetic Aperture ◽

Classification Approach ◽

Radar Images ◽

Learning Techniques ◽

Segmentation Methods ◽

Aperture Radar

In this paper, a hybrid classification approach which is combined with a more deep mask region-convolutional neural network and sparsity driven despeckling algorithm is proposed for synthetic aperture radar (SAR) image segmentation instead of the classical segmentation methods. In satellite technology, synthetic aperture radar images are strongly used for a lot of areas, such as evaluating air conditions, determining agricultural fields, climatic changes, and as a target in the military. Synthetic aperture radar images must be segmented to each meaningful point in the image for a quality segmentation process. In contrast, synthetic aperture radar images have a lot of noisy speckles and these speckles should be also reduced for a quality segmentation. Current studies show that deep learning techniques are widely used for segmentation methods. High accuracy and fast results can be obtained with deep learning techniques for image segmentation. Mask region-convolutional neural network can not only separate each meaningful field in the image, but it can also generate a high accuracy prediction for each meaningful field of synthetic aperture radar images. The study shows that smoothed SAR images can be classified as multiple regions with deep neural networks.

Download Full-text

A Novel Hybrid Deep Multi-Criteria Model for Recommender System

10.21203/rs.3.rs-836949/v1 ◽

2021 ◽

Author(s):

Nour Salim Nassar

Keyword(s):

Neural Network ◽

Deep Learning ◽

Recommender Systems ◽

Recommender System ◽

Real World ◽

Deep Neural Network ◽

Recommendation Systems ◽

The Other ◽

Learning Techniques ◽

Novel Model

Abstract Recommender systems are everywhere books, products, movies, and more. Traditional recommender systems typically use a single criterion in the recommendation, while studies have shown that multi-criteria recommending is more accurate. Novel deep learning techniques have produced remarkable achievements in many fields. The use of such techniques in recommendation systems has started to get attention recently, and several models of recommendation have been proposed based on deep learning. However, there is still no work for using deep learning in hybrid multi-criteria recommender systems. In this work, a model for a hybrid deep multi-criteria recommender system was presented. The model mainly includes two major parts: In the first one, the model obtains the user ID, item ID, and the item metadata to be used as input to a deep neural network in order to predict the criteria ratings. In the second part, the obtained ratings act as an input to another deep neural network, where the overall rating is predicted. Our experiments were conducted on a real-world dataset. They demonstrated the superiority of the proposed novel model over the other models in all measures used to evaluate performance. This indicates the successful use of hybrid deep multi-criteria in the recommendation systems.

Download Full-text

Segmenting the Mature Travel Market with Data Mining Tools

Encyclopedia of Data Warehousing and Mining, Second Edition ◽

10.4018/978-1-60566-010-3.ch268 ◽

2011 ◽

pp. 1759-1764

Author(s):

Yawei Wang

Keyword(s):

Data Mining ◽

Travel Behavior ◽

The United States ◽

Environmental Scanning ◽

Simple Task ◽

Segmentation Methods ◽

Critical Components ◽

Travel Industry ◽

Mature Market ◽

Tools And Techniques

The graying of America is one of the most significant demographic changes to the present and future of the United States (Moisey & Bichis, 1999). As more baby boomers enter their 50s and 60s, the mature travel market becomes a fast-growing market segment and starts to attract attention from many tourism researchers and professionals. The significant increases in size and wealth of the older population make the mature travel market a strong component of the general travel market (Reece, 2004). Understanding the mature market as well as mature travelers’ motivations are vital to the success of the travel industry (Brewer, Poffley, & Pederson, 1995; Hsu, Cai, & Wong, 2007). Today’s mature travel market can be generalized as being “different, diverse and demanding” (Harssel, 1994, p. 376). Faranda and Schmidt (1999) suggest that mature tourism marketers must recognize three critical components: the aging process comprehended from multiple disciplines, the acknowledged “heterogeneity and dynamic nature” of the mature market, and the “necessity for sound segmentation methods” (p. 24). It is not a simple task for marketers to fully understand the mature travel market. In order to better understand and serve the diverse market, tourism professionals will have to use data mining (DM) tools and techniques to discover the hidden patterns and characteristics of the mature travel market. According to Pyo, Uysal, and Chang (2002), DM can be applied to many areas in tourism research. These areas include destination quality control and perceptions, environmental scanning and optimization, travel behavior, tourism forecasting, and market segmentation and positioning. Therefore, the purpose of this study is to review and analyze the segmentation methods reported in the literature during the past seven years on the mature travel market and to explore the application of DM tools regarding the segmentation of the mature travel market in the near future.

Download Full-text

Extracting Retinal Anatomy and Pathological Structure Using Multiscale Segmentation

Applied Sciences ◽

10.3390/app9183669 ◽

2019 ◽

Vol 9 (18) ◽

pp. 3669 ◽

Cited By ~ 1

Author(s):

Geng ◽

Che ◽

Xiao ◽

Liu

Keyword(s):

Image Segmentation ◽

Medical Imaging ◽

Blood Vessels ◽

General Applicability ◽

Learning Techniques ◽

Large Databases ◽

Segmentation Methods ◽

Fundus Photographs ◽

Optic Discs ◽

Pathological Structure

Fundus image segmentation technology has always been an important tool in the medical imaging field. Recent studies have validated that deep learning techniques can effectively segment retinal anatomy and determine pathological structure in retinal fundus photographs. However, several groups of image segmentation methods used in medical imaging only provide a single retinopathic feature (e.g., roth spots and exudates). In this paper, we propose a more accurate and clinically oriented framework for the segmentation of fundus images from end-to-end input. We design a four-path multiscale input network structure that learns network features and finds overall characteristics via our network. Our network’s structure is not limited by segmentation of single retinopathic features. Our method is suitable for exudates, roth spots, blood vessels, and optic discs segmentation. The structure has general applicability to many fundus models; therefore, we use our own dataset for training. In cooperation with hospitals and board-certified ophthalmologists, the proposed framework is validated on retinal images from large databases and can improve diagnostic performance compared to state-of-the-art methods that use smaller databases for training. The proposed framework detects blood vessels with an accuracy of 0.927, which is comparable to exudate accuracy (0.939) and roth spot accuracy (0.904), providing ophthalmologists with a practical diagnostic and a robust analytical tool.

Download Full-text

Abstract 2573: Usefulness of 2D Speckle Tracking Echocardiography for Assessment of Tako-Tsubo Syndrome

Circulation ◽

10.1161/circ.116.suppl_16.ii_569-c ◽

2007 ◽

Vol 116 (suppl_16) ◽

Author(s):

Nicolas Mansencal ◽

Rémy Pillière ◽

Rami El Mahmoud ◽

Jean-Christian Farcot ◽

Thierry Joseph ◽

...

Keyword(s):

Speckle Tracking ◽

Left Ventricular ◽

Control Group ◽

Mean Values ◽

Chamber View ◽

2D Speckle Tracking ◽

Group 2 ◽

Artery Disease ◽

Basal Septum ◽

Group 1

Background: The pathogenesis of Tako-Tsubo (TT) syndrome (stress-induced cardiomyopathy) is not yet understood. Velocity vector imaging (VVI) is a new echocardiographic technology that measures myocardial velocity and deformation using 2D speckle tracking. The aim of this study was to compare the pattern of VVI in pts with TT sy, coronary artery disease (CAD) and in healthy pts. Methods: We prospectively studied 36 consecutive pts divided in 3 groups: 12 pts with confirmed TT sy (group 1), 12 pts with CAD defined as a documented LAD occlusion (group 2) and 12 healthy pts (group 3) and all groups were age- and sex-matched. We systematically performed echocardiography in all pts, with the use of VVI technology, allowing to measure peak velocity (V), strain (S) and strain rate (SR) in basal, mid and apical septum and free wall (FW) in apical 4-chamber view. Results: Mean age was 76 ± 8 yo in each group (36 women). Mean values of V, S and SR in mid and apical septum and FW were significantly lower in TT sy (p<0.04), as compared to group3, but not with group2. In group 1 as well as in control group, no significant differences for the values of V, S and SR were observed between basal septum and bas.FW, between mid septum and midFW and between apical septum and ap.FW (p=NS, Fig ), whereas in patients with CAD (group 2), basal septal V was significantly higher versus basal FW V (p=0.04) and apical septal V was significantly lower versus apical FW V (p=0.02). Conclusion: Our study suggests that VVI allows to distinguish patients with TT sy from those with CAD. In TT sy, left ventricular dysfunction is circular, whereas pts with LAD occlusion presented segmental wall motion abnormalities detected by VVI.

Download Full-text

A Recent Machine Learning Techniques for Failure Diagnosis of Rolling Element Bearing

Hungarian Agricultural Engineering ◽

10.17676/hae.2021.39.42 ◽

2021 ◽

pp. 42-53

Author(s):

Mohsin Hassan Albdery ◽

István Szabó

Keyword(s):

Machine Learning ◽

Fault Diagnosis ◽

Essential Element ◽

Rolling Element Bearing ◽

Machine Learning Techniques ◽

Learning Approaches ◽

Rotating Machines ◽

Learning Techniques ◽

Rolling Element ◽

Critical Components

Rolling element bearings are critical components of rotating machines, and fault in the bearing can cause the machine to fail. Bearing failure is one of the leading causes of failure in various rotating machines used in industry at high and low speeds. Fault diagnosis of various rotating equipment plays a significant role in industries as it guarantees safety, reliability and prevents breakdown and loss of any source of energy. Early identification is an essential element in the diagnosis of defects that saves time and expenses and avoids dangerous conditions. Investigations are being carried out for intelligent fault diagnosis using machine learning approaches. This article gives a short overview of recent trends in the use of machine learning for fault detection. Finally, Deep Learning techniques were recently developed to monitor the health of the intelligent machine are discussed.

Download Full-text