Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival

Eirini Polymeri; May Sadik; Reza Kaboteh; Pablo Borrelli; Olof Enqvist; Johannes Ulén; Mattias Ohlsson; Elin Trägårdh; Mads H Poulsen; Jane A Simonsen; Poul Flemming Hoilund-Carlsen; Åse A Johnsson; Lars Edenbrandt

doi:10.1111/cpf.12611

Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival

Eirini Polymeri, May Sadik, Reza Kaboteh, Pablo Borrelli, Olof Enqvist, Johannes Ulén, Mattias Ohlsson, Elin Trägårdh, Mads H Poulsen, Jane A Simonsen, Poul Flemming Hoilund-Carlsen, Åse A Johnsson, Lars Edenbrandt

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

78 Downloads (Pure)

Abstract

AIM: To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers.

MATERIAL AND METHODS: Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered 18 F-choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by Sørensen-Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate-specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model.

RESULTS: The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not.

CONCLUSION: Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.

Originalsprog	Engelsk
Tidsskrift	Clinical Physiology and Functional Imaging
Vol/bind	40
Udgave nummer	2
Sider (fra-til)	106-113
ISSN	1475-0961
DOI	https://doi.org/10.1111/cpf.12611
Status	Udgivet - mar. 2020

Bibliografisk note

Dokumenter og links

10.1111/cpf.12611Licens: CC BY-NC-ND

Open Access VersionForlagets udgivne version, 915 KBLicens: CC BY-NC-ND

Citationsformater

Polymeri, E., Sadik, M., Kaboteh, R., Borrelli, P., Enqvist, O., Ulén, J., Ohlsson, M., Trägårdh, E., Poulsen, M. H., Simonsen, J. A., Hoilund-Carlsen, P. F., Johnsson, Å. A., & Edenbrandt, L. (2020). Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival. Clinical Physiology and Functional Imaging, 40(2), 106-113. https://doi.org/10.1111/cpf.12611

@article{2130562b880c47d690c65b411fede0e3,

title = "Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival",

abstract = "AIM: To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers.MATERIAL AND METHODS: Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-na{\"i}ve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered 18 F-choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by S{\o}rensen-Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate-specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model.RESULTS: The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not.CONCLUSION: Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.",

author = "Eirini Polymeri and May Sadik and Reza Kaboteh and Pablo Borrelli and Olof Enqvist and Johannes Ul{\'e}n and Mattias Ohlsson and Elin Tr{\"a}g{\aa}rdh and Poulsen, {Mads H} and Simonsen, {Jane A} and Hoilund-Carlsen, {Poul Flemming} and Johnsson, {{\AA}se A} and Lars Edenbrandt",

note = "{\textcopyright} 2019 The Authors. Clinical Physiology and Functional Imaging published by John Wiley & Sons Ltd on behalf of Scandinavian Society of Clinical Physiology and Nuclear Medicine.",

year = "2020",

month = mar,

doi = "10.1111/cpf.12611",

language = "English",

volume = "40",

pages = "106--113",

journal = "Clinical Physiology and Functional Imaging",

issn = "1475-0961",

publisher = "Wiley",

number = "2",

}

Polymeri, E, Sadik, M, Kaboteh, R, Borrelli, P, Enqvist, O, Ulén, J, Ohlsson, M, Trägårdh, E, Poulsen, MH , Simonsen, JA , Hoilund-Carlsen, PF, Johnsson, ÅA & Edenbrandt, L 2020, 'Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival', Clinical Physiology and Functional Imaging, bind 40, nr. 2, s. 106-113. https://doi.org/10.1111/cpf.12611

TY - JOUR

T1 - Deep learning-based quantification of PET/CT prostate gland uptake

T2 - association with overall survival

AU - Polymeri, Eirini

AU - Sadik, May

AU - Kaboteh, Reza

AU - Borrelli, Pablo

AU - Enqvist, Olof

AU - Ulén, Johannes

AU - Ohlsson, Mattias

AU - Trägårdh, Elin

AU - Poulsen, Mads H

AU - Simonsen, Jane A

AU - Hoilund-Carlsen, Poul Flemming

AU - Johnsson, Åse A

AU - Edenbrandt, Lars

PY - 2020/3

Y1 - 2020/3

N2 - AIM: To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers.MATERIAL AND METHODS: Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered 18 F-choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by Sørensen-Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate-specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model.RESULTS: The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not.CONCLUSION: Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.

AB - AIM: To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers.MATERIAL AND METHODS: Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered 18 F-choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by Sørensen-Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate-specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model.RESULTS: The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not.CONCLUSION: Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.

U2 - 10.1111/cpf.12611

DO - 10.1111/cpf.12611

M3 - Journal article

C2 - 31794112

SN - 1475-0961

VL - 40

SP - 106

EP - 113

JO - Clinical Physiology and Functional Imaging

JF - Clinical Physiology and Functional Imaging

IS - 2

ER -

Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival

Abstract

Bibliografisk note

Dokumenter og links

Fingeraftryk

Citationsformater