Learn more about publications and scientific research involving Quantib.

Quantib® ND

Comparing two artificial intelligence software packages for normative
brain volumetry in memory clinic imaging

Zaki, Vernooij, Smits, Tolman, Papma, Visser, Steketee.

Neuroradiology, 2022
  • This study compares diagnostic reports from two AI software packages and show high inter-rater and high accuracy and sensitivity agreement when distinguishing normal and abnormal profiles.
  • Radiological assessment of the MRI results, clinical profile and an understanding of the software used are needed for correct diagnostic interpretation, as results from software packages are not interchangeable.

ACCESS the scientific paper

Read our review

How Machine learning is embedded to support clinician decision making: an analysis of FDA-approved medical devices

Lyell, Coiera, Chen, Shah, Magrabi.

BMJ Health & Care Informatics, 2021

Thumbnails - scientific resources - Lyell et al.

  • This study reviews the use in clinical practice, the benefits, the consequences and the possible risks of FDA cleared devices that use machine learning (up to early 2020). 
  • In this study, Quantib® ND and Quantib® Brain were are reviewed as assistive machine learning devices for quantification.

ACCESS the scientific paper

Distinctive pattern of temporal atrophy in patients with frontotemporal dementia and the I383V variant in TARDBP

Mol et al.,

Journal of Neurology, Neurosurgery & Psychiatry, 2021

Thumbnails - scientific resources - Mol et al.

  • This study examines the genetic cause of frontotemporal dementia and finds a distinctive pattern of temporal atrophy in patients with one specific gene-variant.
  • In this study, Quantib® ND was used for quantitative assessment of volume loss across lobar brain regions.

ACCESS the scientific paper

AI in de Neuroradiologische praktijk. Een aanzienlijke verandering en verbetering

Prof. Smits.

Memorad, Nedelandse Vereniging voor Radiologie, 2021

Thumbnails - scientific resources - Marion Smits

  • Commentary on Quantib® ND, and its usefulness in clinical practice (in Dutch).

ACCESS the article

Overview of MR Imaging Volumetric Quantification in Neurocognitive Disorders

Raji, Ly, Benzinger.

Topics in Magnetic Resonance Imaging, 2019

Thumbnails - scientific resources - Raji et al.

  • This study reviews the history and methods for volumetric quantification, as well as acquisition protocols for multiple cognitive disorders. 
  • In this study, Quantib® ND is listed as one of the FDA cleared software solutions.

ACCESS the scientific paper

Aortic stiffness and brain integrity in elderly patients with cognitive and functional complaints

Tap, van Opbroek, Niessen, Smits, Mattace-Raso.

Clinical Interventions in Aging, 2018

Thumbnails - scientific resources - Tap et al.

  • This study shows a partial association between higher aortic stiffness and increased volume of WMH and decreased volume of grey matter in older patients with cognitive and functional complaints.
  • In this study, Quantib® ND was used to segment brain tissue, and WMH.

ACCESS the scientific paper

Gray matter heritability in family-based and population-based studied using voxel-based morphometryortic 

Van der Lee et al.,

Human Brain Mapping, 2017

Thumbnails - scientific resources - Van der Lee et al.

  • This study looks at the influence of the genetics on gray matter heritability and showed that construction of reliable heritability maps of gray matter voxels is feasible.
  • In this study, Quantib methods were used for brain tissue segmentation.

ACCESS the scientific paper

Automatic tissue segmentation of head and neck MR images for hyperthermia treatment planning 

Fortunati et al.,

Physics in Medicine & Biology, 2015
  • Fortunati et al. investigate atlas based segmentation combined with a local intensity based classification algorithm for segmentation of different brain structures.
  • Quantib™ ND uses the same method for its hippocampus segmentation.

ACCESS the scientific paper

Accuracy and reproducibility study of automatic MRI brain tissue segmentation methods 

de Boer et al.,

NeuroImage, 2010
  • De Boer et al. investigate several methods for follow-up analysis of brain structure segmentations.
  • Quantib™ ND brain segmentation algorithm uses the automatically trained kNN classifier.

ACCESS the scientific paper

White matter lesion extension to automatic brain tissue segmentation on MRI

de Boer et al.,

NeuroImage, 2009
  • De Boer et al. describe the underlying methods used for the Quantib™ ND algorithm development of the Quantib™ ND brain structure segmentation and white matter hyperintensity segmentation as included in Quantib™ ND.
  • For further reading we refer you to the PhD thesis of Renske de Boer, the product owner of Quantib ND.

download the thesis

Quantib® Prostate

Validation of Quantib software in the mp-MRI detection of Prostate Cancer lesions  

Faiella et al.,

ECR overture poster presentation, ECR 2022

Scientific resources - Faiella et al

  • Authors compared the performance of an inexperienced radiologist (supported by Quantib Prostate 1.3 ) to the performance of an expert radiologist with more than 8 years of experience
  • The radiologist supported by Quantib Prostate, performed with a higher sensitivity and PPV regardless of lesion location and with a higher sensitivity for all lesions found regardless of their determined Gleason score after biopsy. Additionally, the use of Quantib Prostate increased the PPV for lesions given PI-RADS scores of 3 and 5.

ACCESS the poster

An AI-powered radiomics model for the detection of extraprostatic extension

Van den berg et al.,

ISUI conference presentation 2021

Scientific resources - van den Berg et al

  • Won best abstract award
  • This work assessed new radiomic features for the prediction of extraprostatic extension (EPE) on lesion level using artificial intelligence.
  • The AI-powered radiomics model achieved good diagnostic discrimination for lesion-specific EPE prediction, with lesion volume and tumor contact volume being most predictive.

ACCESS abstract

Effect of varying DWI b values on prostate lesion segmentation accuracy and robustness

Postigo Filiquete et al.,

ESMRMB conference presentation 2021

Scientific resources - Postigo Filiquete et al

  • They investigated prostate lesion segmentation accuracy by training a segmentation network using acquired DWI (aDWI) or computed DWI (cDWI) at different b values. 
  • The results showed, best segmentation accuracy with a network trained and tested with high b values (b1500), robustness against different b values during training, and a general finding that lesion segmentation networks are less sensitive to different measured b values, than to computed higher b values.

ACCESS abstract

 

Quantib Brain

Accuracy of the compressed sensing accelerated 3D-Flair sequence for the detection of MS plaques at 3T

Toledano-Massiah et al., 

American Journal of Neuro-Radiology, 2018

Thumbnails - scientific resources - Toledano-Massiah et al.

  • The authors evaluate the diagnostic performance for the detection of MS lesion of 3D-Flair sequences without and with compressed sensing. Diagnostic performance is preserved with faster acquisition in compressed sensing of 3D-Flair sequences.
  • In this study, Quantib Brain was used to quantify the volume and total number of MS lesions on both Flair sequences.

ACCESS the scientific paper

 

Quantib AI algorithm for Body Composition

The Association between Muscle Quantity and Overall Survival Depends on Muscle Radiodensity: A Cohort Study in Non-Small-Cell Lung Cancer Patients

van Amsterdam et al.,

Journal of personalized medicine, 2022
Thumbnails - scientific resources - van Amsterdam et al.
  • Survival of lung cancer patients is associated with an interaction between both muscle area and muscle density. High muscle quantity is associated with better overall survival (OS) when muscle radiodensity is higher.
  • Quantib Body Composition software was used for the extraction of the psoas muscle index (PMI) and psoas muscle radiodensity (PMD).

ACCESS the article

Deep learning body-composition analysis of clinically acquired CT-scans estimates creatinine excretion with high accuracy in patients and healthy individuals

Pieters et al.,

Scientific Reports, 2022

Thumbnails - publication page

  • New automated equations that use the body composition analysis, instead of traditional clinical characteristics, are better at estimating creatine production.
  • The authors showed on a large set of data that the proposed method provides an improved estimation of renal function.

ACCESS the article

Subcutaneous and visceral fat density is associated with long-term mortality after transcatheter aortic valve implantation

Van Erck et al.,

European Journal of Preventive Cardiology, 2022

Thumbnail Erck et al. - publications page

  • Despite a technically successful procedure, not all patients with severe aortic valve stenosis benefit from Transcatheter Aortic Valve Implantation (TAVI).
  • The authors show that the density of subcutaneous and visceral fat is associated with mortality in TAVI patients. These results show that future risk models in TAVI patients should take fat density into account. 

ACCESS the abstract

Evaluation of a fully automatic deep learning-based method for the measurement of psoas muscle area

Van Erck et al.,

FRONTIERS IN NURITION, 2022
  • The study evaluates if fully automatic DL methods can substitute manual psoas annotation, for the assessment of muscle mass. Manual segmentation is cumbersome and time consuming but has shown to be a good marker for malnutrition, sarcopenia, and adverse outcomes.
  • Assessment with Quantib Body Composition software demonstrates accurate performance and is a reliable tool that offers great opportunities for analysis in large scale studies and in clinical applications. 

ACCESS the scientific paper

Towards personalized contrast injection: artificial-intelligence-derived body composition and liver enhancement in computed tomography

De Jong, Veldhuis, Wessels, de Vos, Moeskops, Kok.

Journal of personalized medicine, 2021

Thumbnails - scientific resources - De Jong et al.

  • This study shows that contrast injections should be personalized. Liver enhancement is more strongly associated with the percentage of lean body weight than with total body weight or body mass index.
  • In this study, Quantib’s AI algorithm for body composition was used to segment and determine the body composition and calculated percentages of lean body weight. 

ACCESS the scientific paper

Automatic quantification of body composition at L3 vertebra level with convolutional neural networks

Moeskops, de Vos, Veldhuis, de Jong, Išgum, Leiner.

ECR 2020 conference poster

Thumbnails - scientific resources - Moeskops et al.

  • Investigation of feasibility of a deep learning-based method for automatic segmentation of fat, visceral fat, psoas muscle, abdominal muscle and long spine muscles at the level of L3

ACCESS the poster

Automatic Quantification of 3D Body Composition from Abdominal CT with an Ensemble of Convolutional Neural Networks

Moeskops et al.,

RSNA 2019 conference pRESENTATION
  • This study shows that accurate fully automatic segmentation of subcutaneous fat, visceral fat and psoas muscle from full abdominal CT scans is feasible.
  • The proposed method allows fast and fully automatic analysis of 3D body composition in abdominal CT that can aid in individualized risk assessment in cardiovascular disease and cancer.

ACCESS the abstract

Curious for more detailed info on Quantib® Prostate or Quantib® ND?

We are happy to schedule a call and give you the full tour of the solutions during a video conference.