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

Carole H. Sudre; Beatriz Gomez Anson; Silvia Ingala; Chris D. Lane; Daniel Jimenez; Lukas Haider; Thomas Varsavsky; Lorna Smith; S. bastien Ourselin; Rolf H. Jäger; M. Jorge Cardoso

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

Carole H. Sudre, Beatriz Gomez Anson, Silvia Ingala, Chris D. Lane, Daniel Jimenez, Lukas Haider, Thomas Varsavsky, Lorna Smith, S. bastien Ourselin, Rolf H. Jäger, M. Jorge Cardoso

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

Abstract

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 106 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.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019
Editors	M. Jorge Cardoso, Aasa Feragen, Ben Glocker, Ender Konukoglu, Ipek Oguz, Gozde Unal, Tom Vercauteren
Publisher	ML Research Press
Pages	447-456
Volume	102
Publication status	Published - 2019
Event	2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019 - London, United Kingdom Duration: 8 Jul 2019 → 10 Jul 2019

Publication series

Name	Proceedings of Machine Learning Research

Conference

Conference	2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019
Country/Territory	United Kingdom
City	London
Period	8/07/2019 → 10/07/2019

Cite this

Sudre, C. H., Anson, B. G., Ingala, S., Lane, C. D., Jimenez, D., Haider, L., Varsavsky, T., Smith, L., Ourselin, S. B., Jäger, R. H., & Cardoso, M. J. (2019). 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. In M. J. Cardoso, A. Feragen, B. Glocker, E. Konukoglu, I. Oguz, G. Unal, & T. Vercauteren (Eds.), Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019 (Vol. 102, pp. 447-456). (Proceedings of Machine Learning Research). ML Research Press.

Sudre, Carole H. ; Anson, Beatriz Gomez ; Ingala, Silvia et al. / 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019. editor / M. Jorge Cardoso ; Aasa Feragen ; Ben Glocker ; Ender Konukoglu ; Ipek Oguz ; Gozde Unal ; Tom Vercauteren. Vol. 102 ML Research Press, 2019. pp. 447-456 (Proceedings of Machine Learning Research).

@inproceedings{631b43e0e6ad427a8f78e55a9ea0c489,

title = "3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects",

abstract = "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 106 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.",

author = "Sudre, {Carole H.} and Anson, {Beatriz Gomez} and Silvia Ingala and Lane, {Chris D.} and Daniel Jimenez and Lukas Haider and Thomas Varsavsky and Lorna Smith and Ourselin, {S. bastien} and J{\"a}ger, {Rolf H.} and Cardoso, {M. Jorge}",

year = "2019",

language = "English",

volume = "102",

series = "Proceedings of Machine Learning Research",

publisher = "ML Research Press",

pages = "447--456",

editor = "Cardoso, {M. Jorge} and Aasa Feragen and Ben Glocker and Ender Konukoglu and Ipek Oguz and Gozde Unal and Tom Vercauteren",

booktitle = "Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019",

note = "2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019 ; Conference date: 08-07-2019 Through 10-07-2019",

}

Sudre, CH, Anson, BG, Ingala, S, Lane, CD, Jimenez, D, Haider, L, Varsavsky, T, Smith, L, Ourselin, SB, Jäger, RH & Cardoso, MJ 2019, 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. in MJ Cardoso, A Feragen, B Glocker, E Konukoglu, I Oguz, G Unal & T Vercauteren (eds), Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019. vol. 102, Proceedings of Machine Learning Research, ML Research Press, pp. 447-456, 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019, London, United Kingdom, 8/07/2019.

3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. / Sudre, Carole H.; Anson, Beatriz Gomez; Ingala, Silvia et al.
Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019. ed. / M. Jorge Cardoso; Aasa Feragen; Ben Glocker; Ender Konukoglu; Ipek Oguz; Gozde Unal; Tom Vercauteren. Vol. 102 ML Research Press, 2019. p. 447-456 (Proceedings of Machine Learning Research).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects

AU - Sudre, Carole H.

AU - Anson, Beatriz Gomez

AU - Ingala, Silvia

AU - Lane, Chris D.

AU - Jimenez, Daniel

AU - Haider, Lukas

AU - Varsavsky, Thomas

AU - Smith, Lorna

AU - Ourselin, S. bastien

AU - Jäger, Rolf H.

AU - Cardoso, M. Jorge

PY - 2019

Y1 - 2019

N2 - 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 106 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.

AB - 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 106 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.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85160818385&origin=inward

M3 - Conference contribution

VL - 102

T3 - Proceedings of Machine Learning Research

SP - 447

EP - 456

BT - Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019

A2 - Cardoso, M. Jorge

A2 - Feragen, Aasa

A2 - Glocker, Ben

A2 - Konukoglu, Ender

A2 - Oguz, Ipek

A2 - Unal, Gozde

A2 - Vercauteren, Tom

PB - ML Research Press

T2 - 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019

Y2 - 8 July 2019 through 10 July 2019

ER -

Sudre CH, Anson BG, Ingala S, Lane CD, Jimenez D, Haider L et al. 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. In Cardoso MJ, Feragen A, Glocker B, Konukoglu E, Oguz I, Unal G, Vercauteren T, editors, Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning, MIDL 2019. Vol. 102. ML Research Press. 2019. p. 447-456. (Proceedings of Machine Learning Research).

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

Abstract

Publication series

Conference

Other files and links

Cite this