Evaluation of dense vessel detection in NCCT scans

Aneta Lisowska; Erin Beveridge; Alison O’Neil; Vismantas Dilys; Keith Muir; Ian Poole

doi:10.1007/978-3-319-94806-5_8

Evaluation of dense vessel detection in NCCT scans

Aneta Lisowska, Erin Beveridge, Alison O’Neil, Vismantas Dilys, Keith Muir, Ian Poole

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

Abstract

Automatic detection and measurement of dense vessels may enhance the clinical workflow for treatment triage in acute ischemic stroke. In this paper we use a 3D Convolutional Neural Network, which incorporates anatomical atlas information and bilateral comparison, to detect dense vessels. We use 112 non-contrast computed tomography (NCCT) scans for training of the detector and 58 scans for evaluation of its performance. We compare automatic dense vessel detection to identification of the dense vessels by clinical researchers in NCCT and computed tomography angiography (CTA). The automatic system is able to detect dense vessel in NCCT scans, however it shows lower specificity in relation to CTA than clinical experts.

Original language	English
Title of host publication	Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers
Editors	H.H. Ali, N. Peixoto, M. Silveira, E.L. van den Broek, C. Maciel
Publisher	Springer Verlag
Pages	134-145
ISBN (Print)	9783319948058
DOIs	https://doi.org/10.1007/978-3-319-94806-5_8
Publication status	Published - 2018
Externally published	Yes
Event	10th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2017 - Porto, Portugal Duration: 21 Feb 2017 → 23 Feb 2017

Publication series

Name	Communications in Computer and Information Science
ISSN (Print)	1865-0929

Conference

Conference	10th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2017
Country/Territory	Portugal
City	Porto
Period	21/02/17 → 23/02/17

Access to Document

10.1007/978-3-319-94806-5_8

Persistent URL (handle)

Persistent link

Cite this

Lisowska, A., Beveridge, E., O’Neil, A., Dilys, V., Muir, K., & Poole, I. (2018). Evaluation of dense vessel detection in NCCT scans. In H. H. Ali, N. Peixoto, M. Silveira, E. L. van den Broek, & C. Maciel (Eds.), Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers (pp. 134-145). (Communications in Computer and Information Science). Springer Verlag. https://doi.org/10.1007/978-3-319-94806-5_8

Lisowska, Aneta ; Beveridge, Erin ; O’Neil, Alison et al. / Evaluation of dense vessel detection in NCCT scans. Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers. editor / H.H. Ali ; N. Peixoto ; M. Silveira ; E.L. van den Broek ; C. Maciel. Springer Verlag, 2018. pp. 134-145 (Communications in Computer and Information Science).

@inproceedings{4acc70c536704556961c0718d1bf2d54,

title = "Evaluation of dense vessel detection in NCCT scans",

abstract = "Automatic detection and measurement of dense vessels may enhance the clinical workflow for treatment triage in acute ischemic stroke. In this paper we use a 3D Convolutional Neural Network, which incorporates anatomical atlas information and bilateral comparison, to detect dense vessels. We use 112 non-contrast computed tomography (NCCT) scans for training of the detector and 58 scans for evaluation of its performance. We compare automatic dense vessel detection to identification of the dense vessels by clinical researchers in NCCT and computed tomography angiography (CTA). The automatic system is able to detect dense vessel in NCCT scans, however it shows lower specificity in relation to CTA than clinical experts.",

author = "Aneta Lisowska and Erin Beveridge and Alison O{\textquoteright}Neil and Vismantas Dilys and Keith Muir and Ian Poole",

year = "2018",

doi = "10.1007/978-3-319-94806-5_8",

language = "English",

isbn = "9783319948058",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "134--145",

editor = "H.H. Ali and N. Peixoto and M. Silveira and {van den Broek}, E.L. and C. Maciel",

booktitle = "Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers",

note = "10th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2017 ; Conference date: 21-02-2017 Through 23-02-2017",

}

Lisowska, A, Beveridge, E, O’Neil, A, Dilys, V, Muir, K & Poole, I 2018, Evaluation of dense vessel detection in NCCT scans. in HH Ali, N Peixoto, M Silveira, EL van den Broek & C Maciel (eds), Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers. Communications in Computer and Information Science, Springer Verlag, pp. 134-145, 10th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2017, Porto, Portugal, 21/02/17. https://doi.org/10.1007/978-3-319-94806-5_8

Evaluation of dense vessel detection in NCCT scans. / Lisowska, Aneta; Beveridge, Erin; O’Neil, Alison et al.
Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers. ed. / H.H. Ali; N. Peixoto; M. Silveira; E.L. van den Broek; C. Maciel. Springer Verlag, 2018. p. 134-145 (Communications in Computer and Information Science).

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

TY - GEN

T1 - Evaluation of dense vessel detection in NCCT scans

AU - Lisowska, Aneta

AU - Beveridge, Erin

AU - O’Neil, Alison

AU - Dilys, Vismantas

AU - Muir, Keith

AU - Poole, Ian

PY - 2018

Y1 - 2018

N2 - Automatic detection and measurement of dense vessels may enhance the clinical workflow for treatment triage in acute ischemic stroke. In this paper we use a 3D Convolutional Neural Network, which incorporates anatomical atlas information and bilateral comparison, to detect dense vessels. We use 112 non-contrast computed tomography (NCCT) scans for training of the detector and 58 scans for evaluation of its performance. We compare automatic dense vessel detection to identification of the dense vessels by clinical researchers in NCCT and computed tomography angiography (CTA). The automatic system is able to detect dense vessel in NCCT scans, however it shows lower specificity in relation to CTA than clinical experts.

AB - Automatic detection and measurement of dense vessels may enhance the clinical workflow for treatment triage in acute ischemic stroke. In this paper we use a 3D Convolutional Neural Network, which incorporates anatomical atlas information and bilateral comparison, to detect dense vessels. We use 112 non-contrast computed tomography (NCCT) scans for training of the detector and 58 scans for evaluation of its performance. We compare automatic dense vessel detection to identification of the dense vessels by clinical researchers in NCCT and computed tomography angiography (CTA). The automatic system is able to detect dense vessel in NCCT scans, however it shows lower specificity in relation to CTA than clinical experts.

UR - http://www.scopus.com/inward/record.url?scp=85049742779&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-94806-5_8

DO - 10.1007/978-3-319-94806-5_8

M3 - Conference contribution

SN - 9783319948058

T3 - Communications in Computer and Information Science

SP - 134

EP - 145

BT - Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers

A2 - Ali, H.H.

A2 - Peixoto, N.

A2 - Silveira, M.

A2 - van den Broek, E.L.

A2 - Maciel, C.

PB - Springer Verlag

T2 - 10th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2017

Y2 - 21 February 2017 through 23 February 2017

ER -

Lisowska A, Beveridge E, O’Neil A, Dilys V, Muir K, Poole I. Evaluation of dense vessel detection in NCCT scans. In Ali HH, Peixoto N, Silveira M, van den Broek EL, Maciel C, editors, Biomedical Engineering Systems and Technologies - 10th International Joint Conference, BIOSTEC 2017, Revised Selected Papers. Springer Verlag. 2018. p. 134-145. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-94806-5_8

Evaluation of dense vessel detection in NCCT scans

Abstract

Publication series

Conference

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this