Epsilon-optimal non-Bayesian anomaly detection for parametric tomography.

IEEE Trans Image Process

Université de Technologie de Troyes, UTT/ICD/LM2S, FRE CNRS 2848, Troyes Cedex 10010, France.

Published: November 2008

The non-Bayesian detection of an anomaly from a single or a few noisy tomographic projections is considered as a statistical hypotheses testing problem. It is supposed that a radiography is composed of an imaged nonanomalous background medium, considered as a deterministic nuisance parameter, with a possibly hidden anomaly. Because the full voxel-by-voxel reconstruction is impossible, an original tomographic method based on the parametric models of the nonanomalous background medium and radiographic process is proposed to fill up the gap in the missing data. Exploiting this "parametric tomography," a new detection scheme with a limited loss of optimality is proposed as an alternative to the nonlinear generalized likelihood ratio test, which is untractable in the context of nondestructive testing for the objects with uncertainties in their physical/geometrical properties. The theoretical results are illustrated by the processing of real radiographies for the nuclear fuel rod inspection.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2008.2004431DOI Listing

Publication Analysis

Top Keywords

nonanomalous background
8
background medium
8
epsilon-optimal non-bayesian
4
non-bayesian anomaly
4
anomaly detection
4
detection parametric
4
parametric tomography
4
tomography non-bayesian
4
non-bayesian detection
4
detection anomaly
4

Similar Publications

Background: Labor intervention is intended to prevent perinatal morbidity and mortality. Labor durations traditionally defined as 'dystocia' drive primary cesarean birth rates, yet there is mixed evidence about the association between labor duration and poor neonatal outcomes. Using latent class analysis to study unknown patterns of neonatal health can refine understanding of these relationships and effect of labor duration on newborn outcomes.

View Article and Find Full Text PDF
Article Synopsis
  • Shoulder dystocia is a childbirth complication linked to neonatal problems, with higher maternal prepregnancy body mass index (BMI) recognized as a risk factor, but the impact of BMI on neonatal outcomes specifically after shoulder dystocia isn't thoroughly researched.
  • This study aimed to explore the relationship between maternal prepregnancy BMI and neonatal adverse outcomes following shoulder dystocia, including the frequency and types of delivery maneuvers used based on the mother's BMI.
  • Analyzing data from 872 cases of shoulder dystocia, the results showed no significant difference in the duration of the complication across BMI groups, although those with a BMI ≥35 kg/m faced more delivery challenges requiring specific maneuvers. *
View Article and Find Full Text PDF

Background: Cell-free fetal DNA (cffDNA) screening is routinely performed in pregnancy. Abnormal fetal fraction has been associated with adverse pregnancy outcomes, including hypertensive disorders of pregnancy, which are associated with severe maternal and neonatal morbidity and mortality.

Objective: This study examined whether abnormal fetal fraction, defined in this study as fetal fraction either <6 or >15 on the basis of restricted-cubic-spline-plot within our study population, was associated with HDP in a retrospective sample, as well as whether fetal fraction improves the prediction of hypertensive disorders of pregnancy (HDP).

View Article and Find Full Text PDF

The current state-of-the-art anomaly detection methods based on knowledge distillation (KD) typically depend on smaller student networks or reverse distillation to address vanishing representations discrepancy on anomalies. These methods often struggle to achieve precise detection when dealing with complex texture backgrounds containing anomalies due to the similarity between anomalous and non-anomalous regions. Therefore, we propose a new paradigm-Cosine Similarity Knowledge Distillation (CSKD), for surface anomaly detection and localization.

View Article and Find Full Text PDF

Background: Respiratory distress syndrome is strongly associated with prematurity, including late preterm births. Respiratory distress syndrome has been shown to be associated with certain neonatal morbidities and mortality, but these associations are not well described among late preterm births.

Objective: We sought to determine the association between respiratory distress syndrome and adverse neonatal outcomes among late preterm (34-36 weeks) born singleton neonates.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!