Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study

Abstract Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue de...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Patrick Leo, Andrew Janowczyk, Robin Elliott, Nafiseh Janaki, Kaustav Bera, Rakesh Shiradkar, Xavier Farré, Pingfu Fu, Ayah El-Fahmawi, Mohammed Shahait, Jessica Kim, David Lee, Kosj Yamoah, Timothy R. Rebbeck, Francesca Khani, Brian D. Robinson, Lauri Eklund, Ivan Jambor, Harri Merisaari, Otto Ettala, Pekka Taimen, Hannu J. Aronen, Peter J. Boström, Ashutosh Tewari, Cristina Magi-Galluzzi, Eric Klein, Andrei Purysko, Natalie NC Shih, Michael Feldman, Sanjay Gupta, Priti Lal, Anant Madabhushi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/16b0a7b31ab84b10952fac7e4ceade70
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:16b0a7b31ab84b10952fac7e4ceade70
record_format	dspace
spelling	oai:doaj.org-article:16b0a7b31ab84b10952fac7e4ceade702021-12-02T15:38:20ZComputer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study10.1038/s41698-021-00174-32397-768Xhttps://doaj.org/article/16b0a7b31ab84b10952fac7e4ceade702021-05-01T00:00:00Zhttps://doi.org/10.1038/s41698-021-00174-3https://doaj.org/toc/2397-768XAbstract Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03–3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40–3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.Patrick LeoAndrew JanowczykRobin ElliottNafiseh JanakiKaustav BeraRakesh ShiradkarXavier FarréPingfu FuAyah El-FahmawiMohammed ShahaitJessica KimDavid LeeKosj YamoahTimothy R. RebbeckFrancesca KhaniBrian D. RobinsonLauri EklundIvan JamborHarri MerisaariOtto EttalaPekka TaimenHannu J. AronenPeter J. BoströmAshutosh TewariCristina Magi-GalluzziEric KleinAndrei PuryskoNatalie NC ShihMichael FeldmanSanjay GuptaPriti LalAnant MadabhushiNature PortfolioarticleNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENnpj Precision Oncology, Vol 5, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Patrick Leo Andrew Janowczyk Robin Elliott Nafiseh Janaki Kaustav Bera Rakesh Shiradkar Xavier Farré Pingfu Fu Ayah El-Fahmawi Mohammed Shahait Jessica Kim David Lee Kosj Yamoah Timothy R. Rebbeck Francesca Khani Brian D. Robinson Lauri Eklund Ivan Jambor Harri Merisaari Otto Ettala Pekka Taimen Hannu J. Aronen Peter J. Boström Ashutosh Tewari Cristina Magi-Galluzzi Eric Klein Andrei Purysko Natalie NC Shih Michael Feldman Sanjay Gupta Priti Lal Anant Madabhushi Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
description	Abstract Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03–3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40–3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.
format	article
author	Patrick Leo Andrew Janowczyk Robin Elliott Nafiseh Janaki Kaustav Bera Rakesh Shiradkar Xavier Farré Pingfu Fu Ayah El-Fahmawi Mohammed Shahait Jessica Kim David Lee Kosj Yamoah Timothy R. Rebbeck Francesca Khani Brian D. Robinson Lauri Eklund Ivan Jambor Harri Merisaari Otto Ettala Pekka Taimen Hannu J. Aronen Peter J. Boström Ashutosh Tewari Cristina Magi-Galluzzi Eric Klein Andrei Purysko Natalie NC Shih Michael Feldman Sanjay Gupta Priti Lal Anant Madabhushi
author_facet	Patrick Leo Andrew Janowczyk Robin Elliott Nafiseh Janaki Kaustav Bera Rakesh Shiradkar Xavier Farré Pingfu Fu Ayah El-Fahmawi Mohammed Shahait Jessica Kim David Lee Kosj Yamoah Timothy R. Rebbeck Francesca Khani Brian D. Robinson Lauri Eklund Ivan Jambor Harri Merisaari Otto Ettala Pekka Taimen Hannu J. Aronen Peter J. Boström Ashutosh Tewari Cristina Magi-Galluzzi Eric Klein Andrei Purysko Natalie NC Shih Michael Feldman Sanjay Gupta Priti Lal Anant Madabhushi
author_sort	Patrick Leo
title	Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
title_short	Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
title_full	Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
title_fullStr	Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
title_full_unstemmed	Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
title_sort	computer extracted gland features from h&e predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/16b0a7b31ab84b10952fac7e4ceade70
work_keys_str_mv	AT patrickleo computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT andrewjanowczyk computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT robinelliott computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT nafisehjanaki computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT kaustavbera computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT rakeshshiradkar computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT xavierfarre computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT pingfufu computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT ayahelfahmawi computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT mohammedshahait computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT jessicakim computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT davidlee computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT kosjyamoah computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT timothyrrebbeck computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT francescakhani computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT briandrobinson computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT laurieklund computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT ivanjambor computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT harrimerisaari computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT ottoettala computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT pekkataimen computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT hannujaronen computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT peterjbostrom computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT ashutoshtewari computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT cristinamagigalluzzi computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT ericklein computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT andreipurysko computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT nataliencshih computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT michaelfeldman computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT sanjaygupta computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT pritilal computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy AT anantmadabhushi computerextractedglandfeaturesfromhepredictsprostatecancerrecurrencecomparablytoagenomiccompaniondiagnostictestalargemultisitestudy
_version_	1718386155507941376

Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study

Ejemplares similares