Search results for "Segmentation"
showing 10 items of 674 documents
Emergency Analysis: Multitask Learning with Deep Convolutional Neural Networks for Fire Emergency Scene Parsing
2021
In this paper, we introduce a novel application of using scene semantic image segmentation for fire emergency situation analysis. To analyse a fire emergency scene, we propose to use deep convolutional image segmentation networks to identify and classify objects in a scene based on their build material and their vulnerability to catch fire. We introduce our own fire emergency scene segmentation dataset for this purpose. It consists of real world images with objects annotated on the basis of their build material. We use state-of-the-art segmentation models: DeepLabv3, DeepLabv3+, PSPNet, FCN, SegNet and UNet to compare and evaluate their performance on the fire emergency scene parsing task. …
Quantification of the heterogeneity of prognostic cellular biomarkers in ewing sarcoma using automated image and random survival forest analysis
2014
Driven by genomic somatic variation, tumour tissues are typically heterogeneous, yet unbiased quantitative methods are rarely used to analyse heterogeneity at the protein level. Motivated by this problem, we developed automated image segmentation of images of multiple biomarkers in Ewing sarcoma to generate distributions of biomarkers between and within tumour cells. We further integrate high dimensional data with patient clinical outcomes utilising random survival forest (RSF) machine learning. Using material from cohorts of genetically diagnosed Ewing sarcoma with EWSR1 chromosomal translocations, confocal images of tissue microarrays were segmented with level sets and watershed algorithm…
TMA Vessel Segmentation Based on Color and Morphological Features: Application to Angiogenesis Research
2013
Given that angiogenesis and lymphangiogenesis are strongly related to prognosis in neoplastic and other pathologies and that many methods exist that provide different results, we aim to construct a morphometric tool allowing us to measure different aspects of the shape and size of vascular vessels in a complete and accurate way. The developed tool presented is based on vessel closing which is an essential property to properly characterize the size and the shape of vascular and lymphatic vessels. The method is fast and accurate improving existing tools for angiogenesis analysis. The tool also improves the accuracy of vascular density measurements, since the set of endothelial cells forming a…
Quantification of vesicles in differentiating human SH-SY5Y neuroblastoma cells by automated image analysis
2005
A new automated image analysis method for quantification of fluorescent dots is presented. This method facilitates counting the number of fluorescent puncta in specific locations of individual cells and also enables estimation of the number of cells by detecting the labeled nuclei. The method is here used for counting the AM1-43 labeled fluorescent puncta in human SH-SY5Y neuroblastoma cells induced to differentiate with all-trans retinoic acid (RA), and further stimulated with high potassium (K+) containing solution. The automated quantification results correlate well with the results obtained manually through visual inspection. The manual method has the disadvantage of being slow, labor-i…
Manual segmentation qualification platform for the EADC-ADNI harmonized protocol for hippocampal segmentation project
2015
The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP.Thirteen new tracers' segmentations were compared with benchmark images with respect t…
A morphometric tool applied to angiogenesis research based on vessel segmentation
2013
Given that angiogenesis and lymphangiogenesis are strongly related to prognosis in neoplastic and other pathologies, and that some existing methods for their study provide different results, we aim to construct a morphometric tool to allow complete and accurate quantification and measurement of different aspects of the shape and size of vascular vessels.
Vollautomatische Detektion und Quantifizierung des Lungenemphysems in Dünnschicht-MD-CT des Thorax durch eine neue, speziell entwickelte Software
2004
Purpose: Introduction of a novel software tool (YACTA - yet another CT analyzer) for detection and quantification of pulmonary emphysema in thin-slice chest MDCT data sets. Materials and Methods: Consisting of grey-level threshold-based algorithms (e. g., region-growing), expert rules and morphological image postprocessing YACTA segments the tracheobronchial tree prior to the detection and quantification of pulmonary emphysema. In addition to general parameters, such as the mean lung density (MLD) and the emphysema index (EI - also described as pixel index PI), the previously described bullae index (BI) is transformed into a three-dimensional parameter for a morphological description of emp…
A maChine and deep Learning Approach to predict pulmoNary hyperteNsIon in newbornS with congenital diaphragmatic Hernia (CLANNISH): Protocol for a re…
2021
Introduction Outcome predictions of patients with congenital diaphragmatic hernia (CDH) still have some limitations in the prenatal estimate of postnatal pulmonary hypertension (PH). We propose applying Machine Learning (ML), and Deep Learning (DL) approaches to fetuses and newborns with CDH to develop forecasting models in prenatal epoch, based on the integrated analysis of clinical data, to provide neonatal PH as the first outcome and, possibly: favorable response to fetal endoscopic tracheal occlusion (FETO), need for Extracorporeal Membrane Oxygenation (ECMO), survival to ECMO, and death. Moreover, we plan to produce a (semi)automatic fetus lung segmentation system in Magnetic Resonanc…
Hyperspectral system for early detection of rottenness caused by Penicillium digitatum in mandarins
2008
Abstract Nowadays, the detection of fruit infected with Penicillium sp. fungi on packing lines is carried out manually under ultraviolet illumination. Ultraviolet sources induce visible fluorescence of essential oils, present in the skin of citrus and which are released by the action of fungi, thus increasing the contrast between sound and rotten skin. This work analyses a set of techniques aimed at detecting rotten citrus without the use of UV lighting. The techniques used include hyperspectral image acquisition, pre-processing and calibration, feature selection and segmentation using linear and non-linear methods for classification of fruits. Different methods such as correlation analysis…
An edge-driven 3D region-growing approach for upper airway morphology and volume evaluation in patients with Pierre Robin sequence
2015
Abstract: Pierre Robin sequence (PRS) is a pathological condition responsible for a sequence of clinical events, such as breathing and feeding difficulties, that must be addressed to give the patient at least a chance to survive. By using medical imaging techniques, in a non-intrusive way, the surgeon has the opportunity to obtain 3D views, reconstruction of the regions of interest (ROIs), useful to increase understanding of the PRS patient’s condition. In this paper, a semi-automatic approach for segmentation of the upper airways is proposed. The implemented approach uses an edge-driven 3D region-growing algorithm to segment ROIs and 3D volume-rendering technique to reconstruct the 3D mode…