Hybrid system for prostate MR image segmentation using expert knowledge and machine learning

Lars Erik Olof Jacobson; Mohamed Bader-El-Den; Adrian Alan Hopgood; Vincenzo Tamma; David Prendergast; Peter Osborn

doi:10.1007/978-3-031-47994-6_43

Hybrid system for prostate MR image segmentation using expert knowledge and machine learning

Lars Erik Olof Jacobson, Mohamed Bader-El-Den, Adrian Alan Hopgood, Vincenzo Tamma, David Prendergast, Peter Osborn

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

3 Downloads (Pure)

Abstract

In 2020 1,414,259 new cases and 375,304 deaths were estimated for prostate cancer worldwide. Diagnosis of prostate cancer is primarily based on prostate-specific antigen (PSA) screening and trans-rectal ultrasound (TRUS)-guided prostate biopsy. PSA has a low specificity of 36% since benign conditions can elevate the PSA levels. The data set used for prostate cancer consists of t2-weighted MR images for 1,151 patients and 61,119 images. This paper presents an approach to applying knowledge-based artificial intelligence together with image segmentation to improve the diagnosis of prostate cancer using publicly available data. Complete and reliable segmentation into the transition zone (TZ) and peripheral zone (PZ) is required in order to automate and enhance the process of prostate cancer diagnosis.

Original language	English
Title of host publication	Artificial Intelligence XL
Subtitle of host publication	43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings
Editors	Max Bramer, Frederic Stahl
Publisher	Springer Nature
Pages	493–498
ISBN (Electronic)	9783031479946
ISBN (Print)	9783031479939
DOIs	https://doi.org/10.1007/978-3-031-47994-6_43
Publication status	Published - 8 Nov 2023

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Nature
Volume	14381
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Keywords

Image segmentation
Prostate
Magnetic resonance imaging
U-net

Access to Document

10.1007/978-3-031-47994-6_43

Hybrid System for Prostate MR Image Segmentation Using Expert Knowledge and Machine LearningAccepted author manuscript (Post-print), 1.39 MB

Cite this

Jacobson, L. E. O., Bader-El-Den, M., Hopgood, A. A., Tamma, V., Prendergast, D., & Osborn, P. (2023). Hybrid system for prostate MR image segmentation using expert knowledge and machine learning. In M. Bramer, & F. Stahl (Eds.), Artificial Intelligence XL: 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings (pp. 493–498). (Lecture Notes in Computer Science; Vol. 14381). Springer Nature. https://doi.org/10.1007/978-3-031-47994-6_43

Jacobson, Lars Erik Olof ; Bader-El-Den, Mohamed ; Hopgood, Adrian Alan et al. / Hybrid system for prostate MR image segmentation using expert knowledge and machine learning. Artificial Intelligence XL: 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings. editor / Max Bramer ; Frederic Stahl. Springer Nature, 2023. pp. 493–498 (Lecture Notes in Computer Science).

@inproceedings{003aa576d3ce4093ab1b1db72aeecd57,

title = "Hybrid system for prostate MR image segmentation using expert knowledge and machine learning",

abstract = "In 2020 1,414,259 new cases and 375,304 deaths were estimated for prostate cancer worldwide. Diagnosis of prostate cancer is primarily based on prostate-specific antigen (PSA) screening and trans-rectal ultrasound (TRUS)-guided prostate biopsy. PSA has a low specificity of 36% since benign conditions can elevate the PSA levels. The data set used for prostate cancer consists of t2-weighted MR images for 1,151 patients and 61,119 images. This paper presents an approach to applying knowledge-based artificial intelligence together with image segmentation to improve the diagnosis of prostate cancer using publicly available data. Complete and reliable segmentation into the transition zone (TZ) and peripheral zone (PZ) is required in order to automate and enhance the process of prostate cancer diagnosis.",

keywords = "Image segmentation, Prostate, Magnetic resonance imaging, U-net",

author = "Jacobson, {Lars Erik Olof} and Mohamed Bader-El-Den and Hopgood, {Adrian Alan} and Vincenzo Tamma and David Prendergast and Peter Osborn",

year = "2023",

month = nov,

day = "8",

doi = "10.1007/978-3-031-47994-6_43",

language = "English",

isbn = "9783031479939",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "493–498",

editor = "Bramer, {Max } and Frederic Stahl",

booktitle = "Artificial Intelligence XL",

address = "United Kingdom",

}

Jacobson, LEO , Bader-El-Den, M , Hopgood, AA , Tamma, V, Prendergast, D & Osborn, P 2023, Hybrid system for prostate MR image segmentation using expert knowledge and machine learning. in M Bramer & F Stahl (eds), Artificial Intelligence XL: 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings. Lecture Notes in Computer Science, vol. 14381, Springer Nature, pp. 493–498. https://doi.org/10.1007/978-3-031-47994-6_43

Hybrid system for prostate MR image segmentation using expert knowledge and machine learning. / Jacobson, Lars Erik Olof ; Bader-El-Den, Mohamed ; Hopgood, Adrian Alan et al.
Artificial Intelligence XL: 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings. ed. / Max Bramer; Frederic Stahl. Springer Nature, 2023. p. 493–498 (Lecture Notes in Computer Science; Vol. 14381).

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

TY - GEN

T1 - Hybrid system for prostate MR image segmentation using expert knowledge and machine learning

AU - Jacobson, Lars Erik Olof

AU - Bader-El-Den, Mohamed

AU - Hopgood, Adrian Alan

AU - Tamma, Vincenzo

AU - Prendergast, David

AU - Osborn, Peter

PY - 2023/11/8

Y1 - 2023/11/8

N2 - In 2020 1,414,259 new cases and 375,304 deaths were estimated for prostate cancer worldwide. Diagnosis of prostate cancer is primarily based on prostate-specific antigen (PSA) screening and trans-rectal ultrasound (TRUS)-guided prostate biopsy. PSA has a low specificity of 36% since benign conditions can elevate the PSA levels. The data set used for prostate cancer consists of t2-weighted MR images for 1,151 patients and 61,119 images. This paper presents an approach to applying knowledge-based artificial intelligence together with image segmentation to improve the diagnosis of prostate cancer using publicly available data. Complete and reliable segmentation into the transition zone (TZ) and peripheral zone (PZ) is required in order to automate and enhance the process of prostate cancer diagnosis.

AB - In 2020 1,414,259 new cases and 375,304 deaths were estimated for prostate cancer worldwide. Diagnosis of prostate cancer is primarily based on prostate-specific antigen (PSA) screening and trans-rectal ultrasound (TRUS)-guided prostate biopsy. PSA has a low specificity of 36% since benign conditions can elevate the PSA levels. The data set used for prostate cancer consists of t2-weighted MR images for 1,151 patients and 61,119 images. This paper presents an approach to applying knowledge-based artificial intelligence together with image segmentation to improve the diagnosis of prostate cancer using publicly available data. Complete and reliable segmentation into the transition zone (TZ) and peripheral zone (PZ) is required in order to automate and enhance the process of prostate cancer diagnosis.

KW - Image segmentation

KW - Prostate

KW - Magnetic resonance imaging

KW - U-net

U2 - 10.1007/978-3-031-47994-6_43

DO - 10.1007/978-3-031-47994-6_43

M3 - Conference contribution

SN - 9783031479939

T3 - Lecture Notes in Computer Science

SP - 493

EP - 498

BT - Artificial Intelligence XL

A2 - Bramer, Max

A2 - Stahl, Frederic

PB - Springer Nature

ER -

Jacobson LEO , Bader-El-Den M , Hopgood AA , Tamma V, Prendergast D, Osborn P. Hybrid system for prostate MR image segmentation using expert knowledge and machine learning. In Bramer M, Stahl F, editors, Artificial Intelligence XL: 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings. Springer Nature. 2023. p. 493–498. (Lecture Notes in Computer Science). doi: 10.1007/978-3-031-47994-6_43

Hybrid system for prostate MR image segmentation using expert knowledge and machine learning

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Cite this