Parameter set for computer-assisted texture analysis of fetal brain

Abstract

BackgroundMagnetic resonance data were collected from a diverse population of gravid women to objectively compare the quality of 1.5-tesla (1.5 T) versus 3-T magnetic resonance imaging of the developing human brain. MaZda and B11 computational-visual cognition tools were used to process 2D images. We proposed a wavelet-based parameter and two novel histogram-based parameters for Fisher texture analysis in three-dimensional space.ResultsWavenhl, focus index, and dispersion index revealed better quality for 3 T. Though both 1.5 and 3 T images were 16-bit DICOM encoded, nearly 16 and 12 usable bits were measured in 3 and 1.5 T images, respectively. The four-bit padding observed in 1.5 T K-space encoding mimics noise by adding illusionistic details, which are not really part of the image. In contrast, zero-bit padding in 3 T provides space for storing more details and increases the likelihood of noise but as well as edges, which in turn are very crucial for differentiation of closely related anatomical structures.ConclusionsBoth encoding modes are possible with both units, but higher 3 T resolution is the main difference. It contributes to higher perceived and available dynamic range. Apart from surprisingly larger Fisher coefficient, no significant difference was observed when testing was conducted with down-converted 8-bit BMP images.Electronic supplementary materialThe online version of this article (doi:10.1186/s13104-016-2300-3) contains supplementary material, which is available to authorized users.

Artificial intelligence applied to fetal MRI: A scoping review of current research

“…The ‘use cases’ for AI in fetal MRI imaging were broadly classified into several main categories, and a selection of the most clinically relevant papers are expanded upon in more detail in the text below: Image pre-processing: Dynamic motion correction ( n = 8, 21%) 7–9,14,17,19,22,28 Image post-processing: Segmentation of anatomy ( n = 16, 41%), 6,12,13,15,16,20,21,24,26,27,29,32,34,36,37,40 Automated fetal biometry measurement ( n = 1, 3%), 11 Texture analysis ( n = 1, 3%), 33 Classification of image quality ( n = 1, 3%) 39 Data interpretation: Classification of disease ( n = 3, 8%), 18,30,31 Prognostication of outcomes ( n = 4, 10%), 23,41–43 Gestational age prediction ( n = 2, 5%), 38,44 Generation of clinical 3-D models ( n = 1, 3%) 25 Miscellaneous: Generation of synthetic data ( n = 2, 5%) 10,35 …”

Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes

“…AI has been applied to improve knowledge and treatment of ectopic pregnancy, using ML classifiers [ 57 ] and using gene stability algorithms [ 58 ]. Studies aim to improve imaging of fetal organ development with virtual organ computer-aided analysis (VOCAL) [ 55 ], texture analysis [ 52 ] and CNN [ 53 , 59 ]. Three studies observe EHR data; higher performing classification ML approaches used in these studies include DF [ 36 , 56 ] and SVM [ 57 ].…”

Optimal and Efficient Auctions for the Gradual Procurement of Strategic Service Provider Agents

“…, (s m , τ m )), we define the dispersion index as D I = σ 2 /µ, where σ 2 and µ are the variance and mean of the recruitment times. This metric, which is also called variance-to-mean ratio (VMR), is a standard measure to quantify whether a set of observed occurrences are clustered or dispersed compared to a standard statistical model (Akbarov & Wu, 2012;Gentillon et al, 2016). Low values of D I shows that the recruitment is more centered around time 0, while high values of D I shows that the recruitment is distributed over a longer period of time.…”