Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning

Saskia Camps; Tim Houben; Christopher Edwards; Maria Antico; Matteo Dunnhofer; Esther Martens; Jose Baeza; Ben Vanneste; Evert van Limbergen; Peter de With; Frank Verhaegen; Gustavo Carneiro; Davide Fontanarosa

doi:10.1109/ULTSYM.2018.8579839

Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning

Saskia Camps
, Tim Houben
, Christopher Edwards
, Maria Antico
, Matteo Dunnhofer
, Esther Martens
, Jose Baeza
, Ben Vanneste
, Evert van Limbergen
, Peter de With
, Frank Verhaegen
, Gustavo Carneiro
, Davide Fontanarosa

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

2 Citations (Scopus)

Abstract

Ultrasound imaging is one of the image modalities that can be used for radiation dose guidance during radiotherapy workflows of prostate cancer patients. To allow for image acquisition during the treatment, the ultrasound probe needs to be positioned on the body of the patient before the radiation delivery starts using e.g. a mechanical arm. This is an essential step, as the operator cannot be present in the room when the radiation beam is turned on. Changes in anatomical structures or small motions of the patient during the dose delivery can compromise ultrasound image quality, due to e.g. loss of acoustic coupling or sudden appearance of shadowing artifacts. Currently, an operator is still needed to identify this quality loss. We introduce a prototype deep learning algorithm that can automatically assign a quality score to 2D US images of the male pelvic region based on their usability during an ultrasound guided radiotherapy workflow. It has been shown that the performance of this algorithm is comparable with a medical accredited sonographer and two radiation oncologists.

Original language	English
Title of host publication	2018 IEEE International Ultrasonics Symposium (IUS)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	4
ISBN (Electronic)	978-1-5386-3425-7
DOIs	https://doi.org/10.1109/ULTSYM.2018.8579839
Publication status	Published - 25 Feb 2019
Event	2018 IEEE International Ultrasonics Symposium, IUS 2018 - Kobe, Japan Duration: 22 Oct 2018 → 25 Oct 2018

Conference

Conference	2018 IEEE International Ultrasonics Symposium, IUS 2018
Abbreviated title	IUS 2018
Country/Territory	Japan
City	Kobe
Period	22/10/18 → 25/10/18

Bibliographical note

This article was originally incorrectly tagged as not presented at the conference. It is now included as part of the conference record.

Funding

This research forms part of a project supported by an Australia-India strategic research fund (AISRF53820). G.C. acknowledges the support received by the Australian Research Council’s Discovery Projects funding scheme (project DP180103232)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

deep learning
image guided radiotherapy
prostate
quality score
ultrasound

Access to Document

10.1109/ULTSYM.2018.8579839

Cite this

Camps, S., Houben, T., Edwards, C., Antico, M., Dunnhofer, M., Martens, E., Baeza, J., Vanneste, B., van Limbergen, E., de With, P., Verhaegen, F., Carneiro, G., & Fontanarosa, D. (2019). Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning. In 2018 IEEE International Ultrasonics Symposium (IUS) Article 8579839 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ULTSYM.2018.8579839

@inproceedings{6b1d759f958d4520b4066de56d343581,

title = "Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning",

abstract = "Ultrasound imaging is one of the image modalities that can be used for radiation dose guidance during radiotherapy workflows of prostate cancer patients. To allow for image acquisition during the treatment, the ultrasound probe needs to be positioned on the body of the patient before the radiation delivery starts using e.g. a mechanical arm. This is an essential step, as the operator cannot be present in the room when the radiation beam is turned on. Changes in anatomical structures or small motions of the patient during the dose delivery can compromise ultrasound image quality, due to e.g. loss of acoustic coupling or sudden appearance of shadowing artifacts. Currently, an operator is still needed to identify this quality loss. We introduce a prototype deep learning algorithm that can automatically assign a quality score to 2D US images of the male pelvic region based on their usability during an ultrasound guided radiotherapy workflow. It has been shown that the performance of this algorithm is comparable with a medical accredited sonographer and two radiation oncologists.",

keywords = "deep learning, image guided radiotherapy, prostate, quality score, ultrasound",

author = "Saskia Camps and Tim Houben and Christopher Edwards and Maria Antico and Matteo Dunnhofer and Esther Martens and Jose Baeza and Ben Vanneste and \{van Limbergen\}, Evert and \{de With\}, Peter and Frank Verhaegen and Gustavo Carneiro and Davide Fontanarosa",

note = "This article was originally incorrectly tagged as not presented at the conference. It is now included as part of the conference record.; 2018 IEEE International Ultrasonics Symposium, IUS 2018, IUS 2018 ; Conference date: 22-10-2018 Through 25-10-2018",

year = "2019",

month = feb,

day = "25",

doi = "10.1109/ULTSYM.2018.8579839",

language = "English",

booktitle = "2018 IEEE International Ultrasonics Symposium (IUS)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Camps, S, Houben, T, Edwards, C, Antico, M, Dunnhofer, M, Martens, E, Baeza, J, Vanneste, B, van Limbergen, E, de With, P, Verhaegen, F, Carneiro, G & Fontanarosa, D 2019, Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning. in 2018 IEEE International Ultrasonics Symposium (IUS)., 8579839, Institute of Electrical and Electronics Engineers, Piscataway, 2018 IEEE International Ultrasonics Symposium, IUS 2018, Kobe, Japan, 22/10/18. https://doi.org/10.1109/ULTSYM.2018.8579839

Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning. / Camps, Saskia; Houben, Tim; Edwards, Christopher et al.
2018 IEEE International Ultrasonics Symposium (IUS). Piscataway: Institute of Electrical and Electronics Engineers, 2019. 8579839.

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

TY - GEN

T1 - Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning

AU - Camps, Saskia

AU - Houben, Tim

AU - Edwards, Christopher

AU - Antico, Maria

AU - Dunnhofer, Matteo

AU - Martens, Esther

AU - Baeza, Jose

AU - Vanneste, Ben

AU - van Limbergen, Evert

AU - de With, Peter

AU - Verhaegen, Frank

AU - Carneiro, Gustavo

AU - Fontanarosa, Davide

N1 - This article was originally incorrectly tagged as not presented at the conference. It is now included as part of the conference record.

PY - 2019/2/25

Y1 - 2019/2/25

N2 - Ultrasound imaging is one of the image modalities that can be used for radiation dose guidance during radiotherapy workflows of prostate cancer patients. To allow for image acquisition during the treatment, the ultrasound probe needs to be positioned on the body of the patient before the radiation delivery starts using e.g. a mechanical arm. This is an essential step, as the operator cannot be present in the room when the radiation beam is turned on. Changes in anatomical structures or small motions of the patient during the dose delivery can compromise ultrasound image quality, due to e.g. loss of acoustic coupling or sudden appearance of shadowing artifacts. Currently, an operator is still needed to identify this quality loss. We introduce a prototype deep learning algorithm that can automatically assign a quality score to 2D US images of the male pelvic region based on their usability during an ultrasound guided radiotherapy workflow. It has been shown that the performance of this algorithm is comparable with a medical accredited sonographer and two radiation oncologists.

AB - Ultrasound imaging is one of the image modalities that can be used for radiation dose guidance during radiotherapy workflows of prostate cancer patients. To allow for image acquisition during the treatment, the ultrasound probe needs to be positioned on the body of the patient before the radiation delivery starts using e.g. a mechanical arm. This is an essential step, as the operator cannot be present in the room when the radiation beam is turned on. Changes in anatomical structures or small motions of the patient during the dose delivery can compromise ultrasound image quality, due to e.g. loss of acoustic coupling or sudden appearance of shadowing artifacts. Currently, an operator is still needed to identify this quality loss. We introduce a prototype deep learning algorithm that can automatically assign a quality score to 2D US images of the male pelvic region based on their usability during an ultrasound guided radiotherapy workflow. It has been shown that the performance of this algorithm is comparable with a medical accredited sonographer and two radiation oncologists.

KW - deep learning

KW - image guided radiotherapy

KW - prostate

KW - quality score

KW - ultrasound

UR - https://www.scopus.com/pages/publications/85062500357

U2 - 10.1109/ULTSYM.2018.8579839

DO - 10.1109/ULTSYM.2018.8579839

M3 - Conference contribution

AN - SCOPUS:85062500357

BT - 2018 IEEE International Ultrasonics Symposium (IUS)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 2018 IEEE International Ultrasonics Symposium, IUS 2018

Y2 - 22 October 2018 through 25 October 2018

ER -

Quality assessment of transperineal ultrasound images of the male pelvic region using deep learning

Abstract

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this