Deep learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer.
Adipose Tissue
/ pathology
Biopsy
Colorectal Neoplasms
/ pathology
Deep Learning
Diagnosis, Computer-Assisted
Early Detection of Cancer
Humans
Image Interpretation, Computer-Assisted
Lymph Nodes
/ pathology
Lymphatic Metastasis
Microscopy
Neoplasm Staging
Predictive Value of Tests
Proof of Concept Study
Reproducibility of Results
Retrospective Studies
Risk Assessment
Risk Factors
AI
artificial intelligence
deep learning
digital pathology
early colorectal cancer
inflamed adipose tissue
metastasis
new predictive biomarker
pT1 and pT2 bowel cancer
prediction LNM
Journal
The Journal of pathology
ISSN: 1096-9896
Titre abrégé: J Pathol
Pays: England
ID NLM: 0204634
Informations de publication
Date de publication:
03 2022
03 2022
Historique:
revised:
18
10
2021
received:
25
05
2021
accepted:
01
11
2021
pubmed:
6
11
2021
medline:
1
3
2022
entrez:
5
11
2021
Statut:
ppublish
Résumé
The spread of early-stage (T1 and T2) adenocarcinomas to locoregional lymph nodes is a key event in disease progression of colorectal cancer (CRC). The cellular mechanisms behind this event are not completely understood and existing predictive biomarkers are imperfect. Here, we used an end-to-end deep learning algorithm to identify risk factors for lymph node metastasis (LNM) status in digitized histopathology slides of the primary CRC and its surrounding tissue. In two large population-based cohorts, we show that this system can predict the presence of more than one LNM in pT2 CRC patients with an area under the receiver operating curve (AUROC) of 0.733 (0.67-0.758) and patients with any LNM with an AUROC of 0.711 (0.597-0.797). Similarly, in pT1 CRC patients, the presence of more than one LNM or any LNM was predictable with an AUROC of 0.733 (0.644-0.778) and 0.567 (0.542-0.597), respectively. Based on these findings, we used the deep learning system to guide human pathology experts towards highly predictive regions for LNM in the whole slide images. This hybrid human observer and deep learning approach identified inflamed adipose tissue as the highest predictive feature for LNM presence. Our study is a first proof of concept that artificial intelligence (AI) systems may be able to discover potentially new biological mechanisms in cancer progression. Our deep learning algorithm is publicly available and can be used for biomarker discovery in any disease setting. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
269-281Subventions
Organisme : Wellcome Trust
ID : 104914
Pays : United Kingdom
Organisme : Wellcome Trust
ID : 104914
Pays : United Kingdom
Informations de copyright
© 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Références
Arnold M, Sierra MS, Laversanne M, et al. Global patterns and trends in colorectal cancer incidence and mortality. Gut 2017; 66: 683-691.
Weitz J, Koch M, Debus J, et al. Colorectal cancer. Lancet 2005; 365: 153-165.
Ichimasa K, Kudo SE, Miyachi H, et al. Risk stratification of T1 colorectal cancer metastasis to lymph nodes: current status and perspective. Gut Liver 2021; 15: 818-826.
McClements PL, Madurasinghe V, Thomson CS, et al. Impact of the UK colorectal cancer screening pilot studies on incidence, stage distribution and mortality trends. Cancer Epidemiol 2012; 36: e232-e242.
Ueno H, Hashiguchi Y, Shimazaki H, et al. Objective criteria for Crohn-like lymphoid reaction in colorectal cancer. Am J Clin Pathol 2013; 139: 434-441.
Bosch SL, Teerenstra S, de Wilt JH, et al. Predicting lymph node metastasis in pT1 colorectal cancer: a systematic review of risk factors providing rationale for therapy decisions. Endoscopy 2013; 45: 827-834.
Deschoolmeester V, Baay M, Specenier P, et al. A review of the most promising biomarkers in colorectal cancer: one step closer to targeted therapy. Oncologist 2010; 15: 699-731.
Komuta K, Batts K, Jessurun J, et al. Interobserver variability in the pathological assessment of malignant colorectal polyps. Br J Surg 2004; 91: 1479-1484.
Davenport A, Morris J, Pritchard SA, et al. Interobserver variability amongst gastrointestinal pathologists in assessing prognostic parameters of malignant colorectal polyps: a cause for concern. Tech Coloproctol 2016; 20: 647-652.
Kather JN, Heij LR, Grabsch HI, et al. Pan-cancer image-based detection of clinically actionable genetic alterations. Nat Cancer 2020; 1: 789-799.
Fu Y, Jung AW, Torne RV, et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat Cancer 2020; 1: 800-810.
Binder A, Bockmayr M, Hägele M, et al. Morphological and molecular breast cancer profiling through explainable machine learning. Nat Mach Intell 2021; 3: 355-366.
Schmauch B, Romagnoni A, Pronier E, et al. A deep learning model to predict RNA-Seq expression of tumours from whole slide images. Nat Commun 2020; 11: 3877.
Kather JN, Calderaro J. Development of AI-based pathology biomarkers in gastrointestinal and liver cancer. Nat Rev Gastroenterol Hepatol 2020; 17: 591-592.
Calderaro J, Kather JN. Artificial intelligence-based pathology for gastrointestinal and hepatobiliary cancers. Gut 2021; 70: 1183-1193.
Weis CA, Kather JN, Melchers S, et al. Automatic evaluation of tumor budding in immunohistochemically stained colorectal carcinomas and correlation to clinical outcome. Diagn Pathol 2018; 13: 64.
Kather JN, Pearson AT, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat Med 2019; 25: 1054-1056.
Schrammen PL, Laleh NG, Echle A, et al. Weakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology. J Pathol 2022; 256: 50-60.
Skrede OJ, De Raedt S, Kleppe A, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet 2020; 395: 350-360.
Kather JN, Krisam J, Charoentong P, et al. Predicting survival from colorectal cancer histology slides using deep learning: a retrospective multicenter study. PLoS Med 2019; 16: e1002730.
Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017; 318: 2199-2210.
Valkonen M, Kartasalo K, Liimatainen K, et al. Metastasis detection from whole slide images using local features and random forests. Cytometry A 2017; 91: 555-565.
Wessels F, Schmitt M, Krieghoff-Henning E, et al. Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer. BJU Int 2021; 128: 352-360.
Takamatsu M, Yamamoto N, Kawachi H, et al. Prediction of early colorectal cancer metastasis by machine learning using digital slide images. Comput Methods Programs Biomed 2019; 178: 155-161.
Bychkov D, Linder N, Turkki R, et al. Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci Rep 2018; 8: 3395.
Zhao Y, Yang F, Fang Y, et al. Predicting lymph node metastasis using histopathological images based on multiple instance learning with deep graph convolution. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020; 4836-4845. https://doi.org/10.1109/CVPR42600.2020.00489.
Howard FM, Dolezal J, Kochanny S, et al. The impact of site-specific digital histology signatures on deep learning model accuracy and bias. Nat Commun 2021; 12: 4423.
Wulczyn E, Steiner DF, Moran M, et al. Interpretable survival prediction for colorectal cancer using deep learning. npj Digit Med 2021; 4: 71.
Collins GS, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Ann Intern Med 2015; 162: 55-63.
McShane LM, Altman DG, Sauerbrei W, et al. REporting recommendations for tumour MARKer prognostic studies (REMARK). Br J Cancer 2005; 93: 387-391.
Levic K, Bulut O, Hansen TP, et al. Malignant colorectal polyps: endoscopic polypectomy and watchful waiting is not inferior to subsequent bowel resection. A nationwide propensity score-based analysis. Langenbecks Arch Surg 2019; 404: 231-242.
Toh EW, Brown P, Morris E, et al. Area of submucosal invasion and width of invasion predicts lymph node metastasis in pT1 colorectal cancers. Dis Colon Rectum 2015; 58: 393-400.
Muti HS, Loeffler C, Echle A, et al. The Aachen Protocol for Deep Learning Histopathology: a hands-on guide for data preprocessing. Zenodo 2020. https://doi.org/10.5281/zenodo.3694994 [Not peer reviewed].
Macenko M, Niethammer M, Marron JS, et al. A method for normalizing histology slides for quantitative analysis. 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009; 1107-1110. https://doi.org/10.1109/ISBI.2009.5193250.
Echle A, Grabsch HI, Quirke P, et al. Clinical-grade detection of microsatellite instability in colorectal tumors by deep learning. Gastroenterology 2020; 159: 1406-1416.e11.
Loeffler CML, Ortiz Bruechle N, Jung M, et al. Artificial intelligence-based detection of FGFR3 mutational status directly from routine histology in bladder cancer: a possible preselection for molecular testing? Eur Urol Focus 2021. https://doi.org/10.1016/j.euf.2021.04.007
Muti HS, Heij LR, Keller G, et al. Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study. Lancet Digit Health 2021; 3: e564-e664.
Zhang X, Zhou X, Lin M, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices. arXiv [csCV] 2017; 1707.01083 [Not peer reviewed].
ImageNet. [Accessed 14 February 2021]. Available from: http://image-net.org/index.
Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv [csLG] 2014; 1412.6980 [Not peer reviewed].
Bankhead P, Loughrey MB, Fernández JA, et al. QuPath: open source software for digital pathology image analysis. Sci Rep 2017; 7: 16878.
Yamashita R, Long J, Longacre T, et al. Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study. Lancet Oncol 2021; 22: 132-141.
Greenson JK, Huang SC, Herron C, et al. Pathologic predictors of microsatellite instability in colorectal cancer. Am J Surg Pathol 2009; 33: 126-133.
Echle A, Rindtorff NT, Brinker TJ, et al. Deep learning in cancer pathology: a new generation of clinical biomarkers. Br J Cancer 2020; 124: 686-696.
Almekinders MMM, Schaapveld M, Thijssen B, et al. Breast adipocyte size associates with ipsilateral invasive breast cancer risk after ductal carcinoma in situ. NPJ Breast Cancer 2021; 7: 31.
Pakiet A, Kobiela J, Stepnowski P, et al. Changes in lipids composition and metabolism in colorectal cancer: a review. Lipids Health Dis 2019; 18: 29.
Zaytseva YY, Harris JW, Mitov MI, et al. Increased expression of fatty acid synthase provides a survival advantage to colorectal cancer cells via upregulation of cellular respiration. Oncotarget 2015; 6: 18891-18904.
Sánchez-Martínez R, Cruz-Gil S, García-Álvarez MS, et al. Complementary ACSL isoforms contribute to a non-Warburg advantageous energetic status characterizing invasive colon cancer cells. Sci Rep 2017; 7: 11143.
Currie E, Schulze A, Zechner R, et al. Cellular fatty acid metabolism and cancer. Cell Metab 2013; 18: 153-161.
Ladanyi A, Mukherjee A, Kenny HA, et al. Adipocyte-induced CD36 expression drives ovarian cancer progression and metastasis. Oncogene 2018; 37: 2285-2301.
Nieman KM, Kenny HA, Penicka CV, et al. Adipocytes promote ovarian cancer metastasis and provide energy for rapid tumor growth. Nat Med 2011; 17: 1498-1503.
McGenity C, Treanor D. Guidelines for clinical trials using artificial intelligence - SPIRIT-AI and CONSORT-AI. J Pathol 2021; 253: 14-16.
van Rijthoven M, Balkenhol M, Siliņa K, et al. HookNet: multi-resolution convolutional neural networks for semantic segmentation in histopathology whole-slide images. Med Image Anal 2021; 68: 101890.