MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds

Marta Girones Sanguesa; Denis Kutnar; Bas van der Velden; Hugo Kuijf

doi:10.48550/arXiv.2108.02482

MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds

Marta Girones Sanguesa
, Denis Kutnar
, Bas van der Velden
, Hugo Kuijf

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

6 Downloads (Pure)

Abstract

Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the "Where is VALDO?" challenge of MICCAI 2021.

Original language	English
Title of host publication	"Where is VALDO?" challenge, MICCAI 2021
Number of pages	8
DOIs	https://doi.org/10.48550/arXiv.2108.02482
Publication status	Published - 2021

Access to Document

10.48550/arXiv.2108.02482Licence: CC BY

2108.02482Final published version, 494 KBLicence: CC BY

Cite this

@inproceedings{a5674e073c794792a917a3669aae164e,

title = "MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds",

abstract = "Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the {"}Where is VALDO?{"} challenge of MICCAI 2021.",

author = "\{Girones Sanguesa\}, Marta and Denis Kutnar and \{van der Velden\}, Bas and Hugo Kuijf",

year = "2021",

doi = "10.48550/arXiv.2108.02482",

language = "English",

booktitle = "{"}Where is VALDO?{"} challenge, MICCAI 2021",

}

TY - GEN

T1 - MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds

AU - Girones Sanguesa, Marta

AU - Kutnar, Denis

AU - van der Velden, Bas

AU - Kuijf, Hugo

PY - 2021

Y1 - 2021

N2 - Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the "Where is VALDO?" challenge of MICCAI 2021.

AB - Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible microbleed location, a simple U-Net performs the final segmentation. This work used the 72 subjects as training data provided by the "Where is VALDO?" challenge of MICCAI 2021.

U2 - 10.48550/arXiv.2108.02482

DO - 10.48550/arXiv.2108.02482

M3 - Conference contribution

BT - "Where is VALDO?" challenge, MICCAI 2021

ER -

MixMicrobleed: Multi-stage detection and segmentation of cerebral microbleeds

Abstract

Access to Document

Fingerprint

Cite this