Search results for "SEGMENTATION"
showing 10 items of 674 documents
Deep learning approach for the segmentation of aneurysmal ascending aorta.
2020
Diagnosis of ascending thoracic aortic aneurysm (ATAA) is based on the measurement of the maximum aortic diameter, but size is not a good predictor of the risk of adverse events. There is growing interest in the development of novel image-derived risk strategies to improve patient risk management towards a highly individualized level. In this study, the feasibility and efficacy of deep learning for the automatic segmentation of ATAAs was investigated using UNet, ENet, and ERFNet techniques. Specifically, CT angiography done on 72 patients with ATAAs and different valve morphology (i.e., tricuspid aortic valve, TAV, and bicuspid aortic valve, BAV) were semi-automatically segmented with Mimic…
Artificial intelligence for image-guided prostate brachytherapy procedures
2020
Radiotherapy procedures aim at exposing cancer cells to ionizing radiation. Permanently implanting radioactive sources near to the cancer cells is a typical technique to cure early-stage prostate cancer. It involves image acquisition of the patient, delineating the target volumes and organs at risk on different medical images, treatment planning, image-guided radioactive seed delivery, and post-implant evaluation. Artificial intelligence-based medical image analysis can benefit radiotherapy procedures. It can help to facilitate and improve the efficiency of the procedures by automatically segmenting target organs and extrapolating clinically relevant information. However, manual delineation…
Comparison of Micro X-ray Computer Tomography Image Segmentation Methods: Artificial Neural Networks Versus Least Square Support Vector Machine
2013
Micro X-ray computer tomography (XCT) is a powerful non-destructive method for obtaining information about rock structures and mineralogy. A new methodology to obtain porosity from 2D XCT digital images using artificial neural network and least square support vector machine is demonstrated following these steps: the XCT image was first preprocessed, thereafter clustering algorithms such as K-means, Fuzzy c-means and self-organized maps was used for image segmentation. Then artificial neural network was applied for image classification. For comparison, least square support vector machine approach was used for classification labeling of the scan images. The methodology shows how artificial ne…
Fuzzy C-Means Segmentation on Brain MR Slices Corrupted by RF-Inhomogeneity
2007
Brain MR Images corrupted by RF-Inhomogeneity exhibit brightness variations in such a way that a standard Fuzzy C-Means (fcm) segmentation algorithm fails. As a consequence, modified versions of the algorithm can be found in literature, which take into account the artifact. In this work we show that the application of a suitable pre-processing algorithm, already presented by the authors, followed by a standard fcm segmentation achieves good results also. The experimental results ones are compared with those obtained using SPM5, which can be considered the state of the art algorithm oriented to brain segmentation and bias removal.
Simultaneous segmentation and beam-hardening correction in computed microtomography of rock cores
2013
We propose a post-reconstruction correction procedure for the beam-hardening artifact that neither requires knowledge of the X-ray spectrum nor of the attenuation coefficients in multi-mineral geologic samples. The beam-hardening artifact in polychromatic X-ray computer tomography (CT) hampers segmentation of the phase assemblage in geologic samples. We show that in cylindrically shaped samples like rock cores, the X-ray attenuation value for a single phase depends mainly on the distance from the center of the cylinder. This relationship could be easily extracted from the CT data for every phase and used to infer the presence of these phases at all positions in the sample. Our new approach …
Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors
2021
AbstractThis study aims to investigate the influence of interobserver manual segmentation variability on the reproducibility of 2D and 3D unenhanced computed tomography (CT)- and magnetic resonance imaging (MRI)-based texture analysis. Thirty patients with cartilaginous bone tumors (10 enchondromas, 10 atypical cartilaginous tumors, 10 chondrosarcomas) were retrospectively included. Three radiologists independently performed manual contour-focused segmentation on unenhanced CT and T1-weighted and T2-weighted MRI by drawing both a 2D region of interest (ROI) on the slice showing the largest tumor area and a 3D ROI including the whole tumor volume. Additionally, a marginal erosion was applied…
A Segmentation System for Soccer Robot Based on Neural Networks
2000
An innovative technique for segmentation of color images is proposed. The technique implements an approach based on thresholding of the hue histogram and a feed-forward neural network that learns to recognize the hue ranges of meaningful objects. A new function for detecting valleys of the histogram has been devised and tested. A novel blurring algorithm for noise reduction that works effectively when used over hue image has been employed. The reported experimental results show that the technique is reliable and robust even in presence of changing environmental conditions. Extended experimentation has been carried on the framework of the Robot Soccer World Cup Initiative (RoboCup).
A Study of Perceptron Mapping Capability to Design Speech Event Detectors
2006
Event detection is a fundamental yet critical component in automatic speech recognition (ASR) systems that attempt to extract knowledge-based features at the front-end level. In this context, it is common practice to design the detectors inside well-known frameworks based on artificial neural network (ANN) or support vector machine (SVM). In the case of ANN, speech scientists often design their detector architecture relying on conventional feed-forward multi-layer perceptron (MLP) with sigmoidal activation function. The aim of this paper is to introduce other ANN architectures inside the context of detection-based ASR. In particular, a bank of feed-forward MLPs using sinusoidal activation f…
Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI Using Deep Convolutional Networks
2021
In this paper, we propose a new deep learning framework for an automatic myocardial infarction evaluation from clinical information and delayed enhancement-MRI (DE-MRI). The proposed framework addresses two tasks. The first task is automatic detection of myocardial contours, the infarcted area, the no-reflow area, and the left ventricular cavity from a short-axis DE-MRI series. It employs two segmentation neural networks. The first network is used to segment the anatomical structures such as the myocardium and left ventricular cavity. The second network is used to segment the pathological areas such as myocardial infarction, myocardial no-reflow, and normal myocardial region. The segmented …
Distinguishing Onion Leaves from Weed Leaves Based on Segmentation of Color Images and a BP Neural Network
2006
A new algorithm to distinguish onion leaves from weed leaves in images is suggested. This algorithm is based on segmentation of color images and on BP neural network. It includes: discarding soil for conserving only plants in the image, color image segmentation, merging small regions by analyzing the frontier rates and the averages of color indices of the regions, at last a BP neural network is used to determine if the small regions belongs to onion leaf or not. The algorithm has been applied to many images and the correct identifiable percents for onion leaves are between 80%~ 90%.