FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1929043383> ?p ?o ?g. }

• W1929043383 endingPage "166" @default.
• W1929043383 startingPage "161" @default.
• W1929043383 abstract "The importance of neuro-imaging as one of the biomarkers for diagnosis and prognosis of pathologies and traumatic cases is well established. Doctors routinely perform linear measurements on neuro-images to ascertain severity and extent of the pathology or trauma from significant anatomical changes. However, it is a tedious and time consuming process and manually assessing and reporting on large volume of data is fraught with errors and variation. In this paper we present a novel technique for segmentation of significant anatomical landmarks using artificial neural networks and estimation of various ratios and indices performed on brain CT scans. The proposed method is efficient and robust in detecting and measuring sizes of anatomical structures on noncontrast CT scans and has been evaluated on images from subjects with ages between 5 to 85 years. Results show that our method has average ICC of ≥ 0.97 and, hence, can be used in processing data for further use in research and clinical environment. 1 Overview and problem statement Linear measurements on axial CT scans provide clinicians and surgeons opportunity to ascertain differential diagnoses of neuropsychiatric disorders, outcomes of clinical and surgical interventions, geriatric changes and deleterious effects of drugs. Quantitative assessment of neuro-images is an effective approach to reveal structural changes in conditions such as Alzheimer’s disease (AD), Schizophrenia, Huntington’s disease, hydrocephalus and many other neurological and psychiatric disorders [1, 2, 11, 12]. The typical measurements performed on the axial CT scans (fig. 1a, details in table 1) are used to estimate indices and ratios such as Evan’s Ratio (ER), Bifrontal Index (BFI), Bicaudate Index (BCI), Cella Media Index (CMI), Frontal Horn Index (FHI), Ventricular index (VI), Huckman number (HN) and 3rd ventricle width (V3) [3]. Manual measurements of regions of interest (ROI) are still considered ’gold standard’, however, these are time consuming and a robust and efficient method is required to assist the researchers and to our knowledge, there is no automated system for performing measurements and calculation of these from CT scans. Computer aided quantitative radiology and volumetry studies of the human anatomy and pathology have been undertaken by many researchers and a surfeit of image segmentation methods have been proposed [10]. However, in medical images an ROI can have dissimilarity of pixel intensity, inhomogeniety of background contribution and noise, and spatially c © 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. 2 QURESHI, SCHETININ: SEGMENTATION AND ESTIMATION OF BRAIN INDICES (a) (b) (c) Figure 1: Measurements on Axial CT Scans (a) and Manual Labelling (b, c). blind methods in these cases can result in disjoint, quasi-homogeneous regions [9]. To preserve the spatial relationship between the pixels and neighbourhood information, spatially guided techniques such as region growing and merging, active contours and level sets show better results [10]. The extensive and tenable integration of computational intelligence in medical problems can be attributed to the fact that these systems can adaptively learn and optimize the relationship between inputs and outputs [4, 5, 6, 7, 8]. Medical images e.g., CT scans, usually have inhomogeniety of background and noise; and recognition of ROI in images with similar characteristics using ANN can give plausible results [13]. In addition, ANN’s can be trained using a few images which have been manually annotated and labelled in order to learn to recognize the ROI." @default.
• W1929043383 created "2016-06-24" @default.
• W1929043383 creator A5026797013 @default.
• W1929043383 creator A5048277038 @default.
• W1929043383 date "2014-01-01" @default.
• W1929043383 modified "2023-09-22" @default.
• W1929043383 title "Computer-aided segmentation and estimation of indices in brain CT scans" @default.
• W1929043383 cites W106228555 @default.
• W1929043383 cites W1972388998 @default.
• W1929043383 cites W2006327073 @default.
• W1929043383 cites W2007753381 @default.
• W1929043383 cites W2083780116 @default.
• W1929043383 cites W2101744728 @default.
• W1929043383 cites W2115656718 @default.
• W1929043383 cites W2151245645 @default.
• W1929043383 cites W292752435 @default.
• W1929043383 cites W609809536 @default.
• W1929043383 cites W8653854 @default.
• W1929043383 cites W928885820 @default.
• W1929043383 hasPublicationYear "2014" @default.
• W1929043383 type Work @default.
• W1929043383 sameAs 1929043383 @default.
• W1929043383 citedByCount "2" @default.
• W1929043383 countsByYear W19290433832014 @default.
• W1929043383 countsByYear W19290433832015 @default.
• W1929043383 crossrefType "journal-article" @default.
• W1929043383 hasAuthorship W1929043383A5026797013 @default.
• W1929043383 hasAuthorship W1929043383A5048277038 @default.
• W1929043383 hasConcept C118552586 @default.
• W1929043383 hasConcept C126838900 @default.
• W1929043383 hasConcept C154945302 @default.
• W1929043383 hasConcept C41008148 @default.
• W1929043383 hasConcept C534262118 @default.
• W1929043383 hasConcept C58693492 @default.
• W1929043383 hasConcept C71924100 @default.
• W1929043383 hasConcept C89600930 @default.
• W1929043383 hasConceptScore W1929043383C118552586 @default.
• W1929043383 hasConceptScore W1929043383C126838900 @default.
• W1929043383 hasConceptScore W1929043383C154945302 @default.
• W1929043383 hasConceptScore W1929043383C41008148 @default.
• W1929043383 hasConceptScore W1929043383C534262118 @default.
• W1929043383 hasConceptScore W1929043383C58693492 @default.
• W1929043383 hasConceptScore W1929043383C71924100 @default.
• W1929043383 hasConceptScore W1929043383C89600930 @default.
• W1929043383 hasLocation W19290433831 @default.
• W1929043383 hasOpenAccess W1929043383 @default.
• W1929043383 hasPrimaryLocation W19290433831 @default.
• W1929043383 hasRelatedWork W116643196 @default.
• W1929043383 hasRelatedWork W1650310218 @default.
• W1929043383 hasRelatedWork W1707813419 @default.
• W1929043383 hasRelatedWork W1916520413 @default.
• W1929043383 hasRelatedWork W1977877056 @default.
• W1929043383 hasRelatedWork W1979699793 @default.
• W1929043383 hasRelatedWork W2006731232 @default.
• W1929043383 hasRelatedWork W2007758071 @default.
• W1929043383 hasRelatedWork W2011044460 @default.
• W1929043383 hasRelatedWork W2044720939 @default.
• W1929043383 hasRelatedWork W2051564058 @default.
• W1929043383 hasRelatedWork W2095674432 @default.
• W1929043383 hasRelatedWork W2170324821 @default.
• W1929043383 hasRelatedWork W2184472801 @default.
• W1929043383 hasRelatedWork W2759402767 @default.
• W1929043383 hasRelatedWork W2883749477 @default.
• W1929043383 hasRelatedWork W2901304122 @default.
• W1929043383 hasRelatedWork W2968435315 @default.
• W1929043383 hasRelatedWork W3205812661 @default.
• W1929043383 hasRelatedWork W2815257279 @default.
• W1929043383 isParatext "false" @default.
• W1929043383 isRetracted "false" @default.
• W1929043383 magId "1929043383" @default.
• W1929043383 workType "article" @default.