Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer.
#PCSM
#ProstateCancer
#uroonc
artificial intelligence
convolutional neural network
deep learning
machine learning
neoplasm metastasis
prostatic neoplasms
Journal
BJU international
ISSN: 1464-410X
Titre abrégé: BJU Int
Pays: England
ID NLM: 100886721
Informations de publication
Date de publication:
09 2021
09 2021
Historique:
pubmed:
12
3
2021
medline:
30
11
2021
entrez:
11
3
2021
Statut:
ppublish
Résumé
To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors. Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status. With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678-0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05-62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77-56.41%) and 69.65% (95% CI 68.21-71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02-1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96-35.7; P < 0.001) proved to be independent predictors for LNM. In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
352-360Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2021 The Authors BJU International published by John Wiley & Sons Ltd on behalf of BJU International.
Références
Ferlay J, Colombet M, Soerjomataram I et al. Cancer incidence and mortality patterns in Europe: estimates for 40 countries and 25 major cancers in 2018. Eur J Cancer 2018; 103: 356-87
Briganti A, Karnes JR, Da Pozzo LF et al. Two positive nodes represent a significant cut-off value for cancer specific survival in patients with node positive prostate cancer. A new proposal based on a two-institution experience on 703 consecutive N+ patients treated with radical prostatectomy, extended pelvic lymph node dissection and adjuvant therapy. Eur Urol 2009; 55: 261-70
EAU Guidelines. Edn. presented at the EAU Annual Congress Amsterdam 2020. ISBN 978-94-92671-07-3
Gandaglia G, Ploussard G, Valerio M et al. A novel nomogram to identify candidates for extended pelvic lymph node dissection among patients with clinically localized prostate cancer diagnosed with magnetic resonance imaging-targeted and systematic biopsies. Eur Urol 2019; 75: 506-14
Briganti A, Larcher A, Abdollah F et al. Updated nomogram predicting lymph node invasion in patients with prostate cancer undergoing extended pelvic lymph node dissection: the essential importance of percentage of positive cores. Eur Urol 2012; 61: 480-7
Oderda M, Diamand R, Albisinni S et al. Indications for and complications of pelvic lymph node dissection in prostate cancer: accuracy of available nomograms for the prediction of lymph node invasion. BJU Int 2021; 127: 318-25
Gandaglia G, Martini A, Ploussard G et al. External validation of the 2019 Briganti Nomogram for the identification of prostate cancer patients who should be considered for an extended pelvic lymph node dissection. Eur Urol 2020; 78: 138-42
Mottet N, van den Bergh RC, Briers E et al. EAU-EANM-ESTRO-ESUR-SIOG guidelines on prostate cancer-2020 update. Part 1: screening, diagnosis, and local treatment with curative intent. Eur Urol 2021; 79: 243-62
Fossati N, Willemse PM, van den Broeck T et al. The benefits and harms of different extents of lymph node dissection during radical prostatectomy for prostate cancer: a systematic review. Eur Urol 2017; 72: 84-109
Abrams-Pompe RS, Fanti S, Schoots IG et al. The role of magnetic resonance imaging and positron emission tomography/computed tomography in the primary staging of newly diagnosed prostate cancer: a systematic review of the literature. Eur Urol Oncol 2020 [Online ahead of print]. https://doi.org/10.1016/j.euo.2020.11.002
Brinker TJ, Hekler A, Enk AH et al. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. Eur J Cancer 2019; 113: 47-54
Hekler A, Utikal JS, Enk AH et al. Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images. Eur J Cancer 2019; 118: 91-6
Litjens G, Sanchez CI, Timofeeva N et al. Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci Rep 2016; 6: 26286
Kott O, Linsley D, Amin A et al. Development of a deep learning algorithm for the histopathologic diagnosis and gleason grading of prostate cancer biopsies: a pilot study. Eur Urol Focus. 2019 [Online ahead of print]. https://doi.org/10.1016/j.euf.2019.11.003
Epstein JI. An update of the Gleason grading system. J Urol 2010; 183: 433-40
Bulten W, Pinckaers H, van Boven H et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol 2020; 21: 233-41
Xu H, Park S, Hwang TH. Computerized classification of prostate cancer Gleason scores from whole slide images. IEEE/ACM Trans Comput Biol Bioinform 2020; 17: 1871-82
Kather JN, Heij LR, Grabsch HI et al. Pan-cancer image-based detection of clinically actionable genetic alterations. Nature Cancer 2020; 1: 789-99
Fu Y, Jung AW, Torne RV et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat Cancer 2020; 1: 800-10
Yamamoto Y, Tsuzuki T, Akatsuka J et al. Automated acquisition of explainable knowledge from unannotated histopathology images. Nat Commun 2019; 10: 5642
Bankhead P, Loughrey MB, Fernández JA et al. QuPath: open source software for digital pathology image analysis. Sci Rep 2017; 7: 1-7
Loshchilov I, Hutter F. SGDR: Stochastic gradient descent with warm restarts, 2016
Howard J, Gugger S. Fastai: a layered API for deep learning. Information 2020; 11: 108
Wang G, Li W, Aertsen M, Deprest J, Ourselin S, Vercauteren TJ. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 2019; 338: 34-45
Paszke A, Gross S, Massa F, editors et al. Pytorch: an imperative style, high-performance deep learning library. Advances in neural information processing systems, 2019
Memorial Sloan-Kettering Cancer Center. Prediction Tools/Prostate Cancer Nomograms. Available at: https://www.mskcc.org/nomograms/prostate/pre_op. Accessed January 2021
Suhovskih AV, Kashuba VI, Klein G, Grigorieva EV. Prostate cancer cells specifically reorganize epithelial cell-fibroblast communication through proteoglycan and junction pathways. Cell Adh Migr 2017; 11: 39-53
Russo MV, Esposito S, Tupone MG et al. SOX2 boosts major tumor progression genes in prostate cancer and is a functional biomarker of lymph node metastasis. Oncotarget 2016; 7: 12372-85
Wang Q, Diao X, Sun J, Chen Z. Stromal cell-derived factor-1 and vascular endothelial growth factor as biomarkers for lymph node metastasis and poor cancer-specific survival in prostate cancer patients after radical prostatectomy. Urol Oncol 2013; 31: 312-7
Castro E, Goh C, Olmos D et al. Germline BRCA mutations are associated with higher risk of nodal involvement, distant metastasis, and poor survival outcomes in prostate cancer. J Clin Oncol 2013; 31: 1748-57
Barron DA, Rowley DR. The reactive stroma microenvironment and prostate cancer progression. Endocr Relat Cancer 2012; 19: R187-204
Zeng Y, Opeskin K, Horvath LG, Sutherland RL, Williams ED. Lymphatic vessel density and lymph node metastasis in prostate cancer. Prostate 2005; 65: 222-30
Singh S, Singh UP, Grizzle WE, Lillard JW Jr. CXCL12-CXCR4 interactions modulate prostate cancer cell migration, metalloproteinase expression and invasion. Lab Invest 2004; 84: 1666-76
Kapil A, Meier A, Zuraw A et al. Deep semi supervised generative learning for automated tumor proportion scoring on NSCLC tissue needle biopsies. Sci Rep 2018; 8: 17343
Luo HL, Chiang PH, Chen YT, Cheng YT. Lymphovascular invasion is a pathological feature related to aggressive cancer behavior and predicts early recurrence in prostate cancer. Kaohsiung J Med Sci 2012; 28: 327-30
Grignon DJ. Prostate cancer reporting and staging: needle biopsy and radical prostatectomy specimens. Mod Pathol 2018; 31(Suppl. 1): S96-109
Heck MM, Retz M, Bandur M et al. Topography of lymph node metastases in prostate cancer patients undergoing radical prostatectomy and extended lymphadenectomy: results of a combined molecular and histopathologic mapping study. Eur Urol 2014; 66: 222-9