Reproducibility of an imaging based prostate cancer prognostic assay

Faisal M. Khan; Douglas Powell; Valentina Bayer-Zubek; Rui Soares; Allison Mott; Gerardo Fernandez; Ricardo Mesa-Tejada; Michael J. Donovan

doi:10.1117/12.878241

Reproducibility of an imaging based prostate cancer prognostic assay

Faisal M. Khan, Douglas Powell, Valentina Bayer-Zubek, Rui Soares, Allison Mott, Gerardo Fernandez, Ricardo Mesa-Tejada, Michael J. Donovan

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

Abstract

The Prostate Px⊕prognostic assay offered by Aureon Biosciences is designed to predict progression post primary treatment for prostate cancer patients based on their diagnostic biopsy specimen. The assay is driven by the automated image analysis of biological specimens. Three different histological sections are analyzed for morphometric as well as immunofluorescence protein expression properties within areas of tumor digitally masked by expert pathologists. The assay was developed on a multi-institution cohort of up to 9 images from each of 1027 patients. The variation in histological sections, staining, pathologist tumor masking and the region of image acquisition all have the potential to significantly impact imaging features and consequently the reproducibility of the assay's results for the same patient. This study analyzed the reproducibility of the assay in 50 patients who were re-processed within 3 months in a blinded fashion as de-novo patients. The key assay results reported were in agreement in 94% of the cases. The two independent endpoints of risk classification reproduced results in 90% and 92% of the predictions. This work presents one of the first assessments of the reproducibility of a commercial assay's results given the inherent variations in images and quantitative imaging characteristics in a commercial setting.

Original language	English
Title of host publication	Medical Imaging 2011
Subtitle of host publication	Image Perception, Observer Performance, and Technology Assessment
DOIs	https://doi.org/10.1117/12.878241
State	Published - 2011
Externally published	Yes
Event	Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment - Lake Buena Vista, FL, United States Duration: 16 Feb 2011 → 17 Feb 2011

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	7966
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment
Country/Territory	United States
City	Lake Buena Vista, FL
Period	16/02/11 → 17/02/11

Keywords

Image variability
Prognostic assay
Prostate biopsy
Reproducibility

Access to Document

10.1117/12.878241

Cite this

Khan, F. M., Powell, D., Bayer-Zubek, V., Soares, R., Mott, A., Fernandez, G., Mesa-Tejada, R., & Donovan, M. J. (2011). Reproducibility of an imaging based prostate cancer prognostic assay. In Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment Article 79661O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7966). https://doi.org/10.1117/12.878241

@inproceedings{c5238cde5cdb4ac390f67e4bc1185855,

title = "Reproducibility of an imaging based prostate cancer prognostic assay",

abstract = "The Prostate Px⊕prognostic assay offered by Aureon Biosciences is designed to predict progression post primary treatment for prostate cancer patients based on their diagnostic biopsy specimen. The assay is driven by the automated image analysis of biological specimens. Three different histological sections are analyzed for morphometric as well as immunofluorescence protein expression properties within areas of tumor digitally masked by expert pathologists. The assay was developed on a multi-institution cohort of up to 9 images from each of 1027 patients. The variation in histological sections, staining, pathologist tumor masking and the region of image acquisition all have the potential to significantly impact imaging features and consequently the reproducibility of the assay's results for the same patient. This study analyzed the reproducibility of the assay in 50 patients who were re-processed within 3 months in a blinded fashion as de-novo patients. The key assay results reported were in agreement in 94% of the cases. The two independent endpoints of risk classification reproduced results in 90% and 92% of the predictions. This work presents one of the first assessments of the reproducibility of a commercial assay's results given the inherent variations in images and quantitative imaging characteristics in a commercial setting.",

keywords = "Image variability, Prognostic assay, Prostate biopsy, Reproducibility",

author = "Khan, {Faisal M.} and Douglas Powell and Valentina Bayer-Zubek and Rui Soares and Allison Mott and Gerardo Fernandez and Ricardo Mesa-Tejada and Donovan, {Michael J.}",

year = "2011",

doi = "10.1117/12.878241",

language = "English",

isbn = "9780819485083",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

booktitle = "Medical Imaging 2011",

note = "Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment ; Conference date: 16-02-2011 Through 17-02-2011",

}

Khan, FM, Powell, D, Bayer-Zubek, V, Soares, R, Mott, A, Fernandez, G, Mesa-Tejada, R & Donovan, MJ 2011, Reproducibility of an imaging based prostate cancer prognostic assay. in Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment., 79661O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7966, Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment, Lake Buena Vista, FL, United States, 16/02/11. https://doi.org/10.1117/12.878241

Reproducibility of an imaging based prostate cancer prognostic assay. / Khan, Faisal M.; Powell, Douglas; Bayer-Zubek, Valentina et al.
Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment. 2011. 79661O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7966).

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

TY - GEN

T1 - Reproducibility of an imaging based prostate cancer prognostic assay

AU - Khan, Faisal M.

AU - Powell, Douglas

AU - Bayer-Zubek, Valentina

AU - Soares, Rui

AU - Mott, Allison

AU - Fernandez, Gerardo

AU - Mesa-Tejada, Ricardo

AU - Donovan, Michael J.

PY - 2011

Y1 - 2011

N2 - The Prostate Px⊕prognostic assay offered by Aureon Biosciences is designed to predict progression post primary treatment for prostate cancer patients based on their diagnostic biopsy specimen. The assay is driven by the automated image analysis of biological specimens. Three different histological sections are analyzed for morphometric as well as immunofluorescence protein expression properties within areas of tumor digitally masked by expert pathologists. The assay was developed on a multi-institution cohort of up to 9 images from each of 1027 patients. The variation in histological sections, staining, pathologist tumor masking and the region of image acquisition all have the potential to significantly impact imaging features and consequently the reproducibility of the assay's results for the same patient. This study analyzed the reproducibility of the assay in 50 patients who were re-processed within 3 months in a blinded fashion as de-novo patients. The key assay results reported were in agreement in 94% of the cases. The two independent endpoints of risk classification reproduced results in 90% and 92% of the predictions. This work presents one of the first assessments of the reproducibility of a commercial assay's results given the inherent variations in images and quantitative imaging characteristics in a commercial setting.

AB - The Prostate Px⊕prognostic assay offered by Aureon Biosciences is designed to predict progression post primary treatment for prostate cancer patients based on their diagnostic biopsy specimen. The assay is driven by the automated image analysis of biological specimens. Three different histological sections are analyzed for morphometric as well as immunofluorescence protein expression properties within areas of tumor digitally masked by expert pathologists. The assay was developed on a multi-institution cohort of up to 9 images from each of 1027 patients. The variation in histological sections, staining, pathologist tumor masking and the region of image acquisition all have the potential to significantly impact imaging features and consequently the reproducibility of the assay's results for the same patient. This study analyzed the reproducibility of the assay in 50 patients who were re-processed within 3 months in a blinded fashion as de-novo patients. The key assay results reported were in agreement in 94% of the cases. The two independent endpoints of risk classification reproduced results in 90% and 92% of the predictions. This work presents one of the first assessments of the reproducibility of a commercial assay's results given the inherent variations in images and quantitative imaging characteristics in a commercial setting.

KW - Image variability

KW - Prognostic assay

KW - Prostate biopsy

KW - Reproducibility

UR - http://www.scopus.com/inward/record.url?scp=79955828883&partnerID=8YFLogxK

U2 - 10.1117/12.878241

DO - 10.1117/12.878241

M3 - Conference contribution

AN - SCOPUS:79955828883

SN - 9780819485083

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2011

T2 - Medical Imaging 2011: Image Perception, Observer Performance, and Technology Assessment

Y2 - 16 February 2011 through 17 February 2011

ER -

Reproducibility of an imaging based prostate cancer prognostic assay

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this