3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects

by   Carole H Sudre, et al.

Extremely small objects (ESO) have become observable on clinical routine magnetic resonance imaging acquisitions, thanks to a reduction in acquisition time at higher resolution. Despite their small size (usually <10 voxels per object for an image of more than 10^6 voxels), these markers reflect tissue damage and need to be accounted for to investigate the complete phenotype of complex pathological pathways. In addition to their very small size, variability in shape and appearance leads to high labelling variability across human raters, resulting in a very noisy gold standard. Such objects are notably present in the context of cerebral small vessel disease where enlarged perivascular spaces and lacunes, commonly observed in the ageing population, are thought to be associated with acceleration of cognitive decline and risk of dementia onset. In this work, we redesign the RCNN model to scale to 3D data, and to jointly detect and characterise these important markers of age-related neurovascular changes. We also propose training strategies enforcing the detection of extremely small objects, ensuring a tractable and stable training process.


page 2

page 6

page 7

page 8


Let's agree to disagree: learning highly debatable multirater labelling

Classification and differentiation of small pathological objects may gre...

A deep learning-based method for prostate segmentation in T2-weighted magnetic resonance imaging

We propose a novel automatic method for accurate segmentation of the pro...

A Tool for Super-Resolving Multimodal Clinical MRI

We present a tool for resolution recovery in multimodal clinical magneti...

Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging

3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast bu...

Learning stochastic object models from medical imaging measurements by use of advanced AmbientGANs

In order to objectively assess new medical imaging technologies via comp...

On Learning Where To Look

Current automatic vision systems face two major challenges: scalability ...

Please sign up or login with your details

Forgot password? Click here to reset