A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images

被引：3

作者：

Ahmadvand, Pouya ^{[1
]}

Farahani, Hossein ^{[1
]}

Farnell, David ^{[2
,5
]}

Darbandsari, Amirali ^{[3
]}

Topham, James ^{[6
]}

Karasinska, Joanna ^{[6
]}

Nelson, Jessica ^{[8
]}

Naso, Julia ^{[2
]}

Jones, Steven J. M. ^{[7
]}

Renouf, Daniel ^{[4
]}

Schaeffer, David F. ^{[2
,5
,6
]}

Bashashati, Ali ^{[1
,2
]}

机构：

[1] Univ British Columbia, Sch Biomed Engn, Vancouver, BC, Canada

[2] Univ British Columbia, Dept Pathol & Lab Med, Vancouver, BC, Canada

[3] Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC, Canada

[4] Univ British Columbia, Dept Med, Vancouver, BC, Canada

[5] Vancouver Gen Hosp, Vancouver, BC, Canada

[6] Pancreas Ctr BC, Vancouver, BC, Canada

[7] Michael Smith Genome Sci Ctr, Vancouver, BC, Canada

[8] British Columbia Canc Res Ctr, Vancouver, BC, Canada

来源：

AMERICAN JOURNAL OF PATHOLOGY | 2024年 / 194卷 / 12期

基金：

加拿大健康研究院; 加拿大自然科学与工程研究理事会;

关键词：

CANCER; SURVIVAL; TUMOR;

D O I：

10.1016/j.ajpath.2024.08.006

中图分类号：

R36 [病理学];

学科分类号：

100104 ;

摘要：

Delayed diagnosis and treatment resistance result in high pancreatic ductal adenocarcinoma (PDAC) mortality rates. Identifying molecular subtypes can improve treatment, but current methods are costly and time-consuming. In this study, deep learning models were used to identify histologic features that classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained histopathologic slides. A total of 97 histopathology slides associated with resectable PDAC from The Cancer Genome Atlas project were used to train a deep learning model and test the performance on 44 needle biopsy material (110 slides) from a local annotated patient cohort. The model achieved balanced accuracy of 96.19% and 83.03% in identifying the classical and basal subtypes of PDAC in The Cancer Genome Atlas and the local cohort, respectively. This study provides a promising method to cost-effectively and rapidly classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained slides, potentially leading to more effective clinical management of this disease. (Am J Pathol 2024, 194: 2302-2312; https:// doi.org/10.1016/j.ajpath.2024.08.006)

引用

页码：2302 / 2312

页数：11

共 36 条

[1] Genomics-Driven Precision Medicine for Advanced Pancreatic Cancer: Early Results from the COMPASS Trial [J].

Aung, Kyaw L. ;

Fischer, Sandra E. ;

Denroche, Robert E. ;

Jang, Gun-Ho ;

Dodd, Anna ;

Creighton, Sean ;

Southwood, Bernadette ;

Liang, Sheng-Ben ;

Chadwick, Dianne ;

Zhang, Amy ;

O'Kane, Grainne M. ;

Albaba, Hamzeh ;

Moura, Shari ;

Grant, Robert C. ;

Miller, Jessica K. ;

Mbabaali, Faridah ;

Pasternack, Danielle ;

Lungu, Ilinca M. ;

Bartlett, John M. S. ;

Ghai, Sangeet ;

Lemire, Mathieu ;

Holter, Spring ;

Connor, Ashton A. ;

Moffitt, Richard A. ;

Yeh, Jen Jen ;

Timms, Lee ;

Krzyzanowski, Paul M. ;

Dhani, Neesha ;

Hedley, David ;

Notta, Faiyaz ;

Wilson, Julie M. ;

Moore, Malcolm J. ;

Gallinger, Steven ;

Knox, Jennifer J. .

CLINICAL CANCER RESEARCH, 2018, 24 (06) :1344-1354

[2] Genomic analyses identify molecular subtypes of pancreatic cancer [J].

Bailey, Peter ;

Chang, David K. ;

Nones, Katia ;

Johns, Amber L. ;

Patch, Ann-Marie ;

Gingras, Marie-Claude ;

Miller, David K. ;

Christ, Angelika N. ;

Bruxner, Tim J. C. ;

Quinn, Michael C. ;

Nourse, Craig ;

Murtaugh, L. Charles ;

Harliwong, Ivon ;

Idrisoglu, Senel ;

Manning, Suzanne ;

Nourbakhsh, Ehsan ;

Wani, Shivangi ;

Fink, Lynn ;

Holmes, Oliver ;

Chin, Vencssa ;

Anderson, Matthew J. ;

Kazakoff, Stephen ;

Leonard, Conrad ;

Newell, Felicity ;

Waddell, Nick ;

Wood, Scott ;

Xu, Qinying ;

Wilson, Peter J. ;

Cloonan, Nicole ;

Kassahn, Karin S. ;

Taylor, Darrin ;

Quek, Kelly ;

Robertson, Alan ;

Pantano, Lorena ;

Mincarelli, Laura ;

Sanchez, Luis N. ;

Evers, Lisa ;

Wu, Jianmin ;

Pinese, Mark ;

Cowley, Mark J. ;

Jones, Marc D. ;

Colvin, Emily K. ;

Nagrial, Adnan M. ;

Humphrey, Emily S. ;

Chantrill, Lorraine A. ;

Mawson, Amanda ;

Humphris, Jeremy ;

Chou, Angela ;

Pajic, Marina ;

Scarlett, Christopher J. .

NATURE, 2016, 531 (7592) :47-+

[3] Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer [J].

Bejnordi, Babak Ehteshami ;

Veta, Mitko ;

van Diest, Paul Johannes ;

van Ginneken, Bram ;

Karssemeijer, Nico ;

Litjens, Geert ;

van der Laak, Jeroen A. W. M. .

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2017, 318 (22) :2199-2210

[4] Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study [J].

Bilal, Mohsin ;

Raza, Shan E. Ahmed ;

Azam, Ayesha ;

Graham, Simon ;

Ilyas, Mohammad ;

Cree, Ian A. ;

Snead, David ;

Minhas, Fayyaz ;

Rajpoot, Nasir M. .

LANCET DIGITAL HEALTH, 2021, 3 (12) :E763-E772

[5] The utility of color normalization for AI-based diagnosis of hematoxylin and eosin-stained pathology images [J].

Boschman, Jeffrey ;

Farahani, Hossein ;

Darbandsari, Amirali ;

Ahmadvand, Pouya ;

Van Spankeren, Ashley ;

Farnell, David ;

Levine, Adrian B. ;

Naso, Julia R. ;

Churg, Andrew ;

Jones, Steven J. M. ;

Yip, Stephen ;

Kobel, Martin ;

Huntsman, David G. ;

Gilks, C. Blake ;

Bashashati, Ali .

JOURNAL OF PATHOLOGY, 2022, 256 (01) :15-24

[6] Clinical-grade computational pathology using weakly supervised deep learning on whole slide images [J].

Campanella, Gabriele ;

Hanna, Matthew G. ;

Geneslaw, Luke ;

Miraflor, Allen ;

Silva, Vitor Werneck Krauss ;

Busam, Klaus J. ;

Brogi, Edi ;

Reuter, Victor E. ;

Klimstra, David S. ;

Fuchs, Thomas J. .

NATURE MEDICINE, 2019, 25 (08) :1301-+

[7] Subtypes of pancreatic ductal adenocarcinoma and their differing responses to therapy [J].

Collisson, Eric A. ;

Sadanandam, Anguraj ;

Olson, Peter ;

Gibb, William J. ;

Truitt, Morgan ;

Gu, Shenda ;

Cooc, Janine ;

Weinkle, Jennifer ;

Kim, Grace E. ;

Jakkula, Lakshmi ;

Feiler, Heidi S. ;

Ko, Andrew H. ;

Olshen, Adam B. ;

Danenberg, Kathleen L. ;

Tempero, Margaret A. ;

Spellman, Paul T. ;

Hanahan, Douglas ;

Gray, Joe W. .

NATURE MEDICINE, 2011, 17 (04) :500-U140

[8] Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning [J].

Coudray, Nicolas ;

Ocampo, Paolo Santiago ;

Sakellaropoulos, Theodore ;

Narula, Navneet ;

Snuderl, Matija ;

Fenyo, David ;

Moreira, Andre L. ;

Razavian, Narges ;

Tsirigos, Aristotelis .

NATURE MEDICINE, 2018, 24 (10) :1559-+

[9] Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent [J].

Cruz-Roa, Angel ;

Gilmore, Hannah ;

Basavanhally, Ajay ;

Feldman, Michael ;

Ganesan, Shridar ;

Shih, Natalie N. C. ;

Tomaszewski, John ;

Gonzalez, Fabio A. ;

Madabhushi, Anant .

SCIENTIFIC REPORTS, 2017, 7

[10]

Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848

← 1 2 3 4 →