Deep learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer

Autor: Jakob Nikolas Kather, Marie Louise Malmstrøm, Tine Plato Kuhlmann, Nicholas P. West, I. Gögenur, Heike I. Grabsch, Narmin Ghaffari Laleh, Katarina Levic, Lara R. Heij, Susanne Eiholm, Oliver Lester Saldanha, Aurora Bono, Amelie Echle, Katerina Kouvidi, Titus J. Brinker, Philip Quirke, Scarlet Brockmoeller
Přispěvatelé: RS: GROW - R2 - Basic and Translational Cancer Biology, Pathologie, MUMC+: DA Pat AIOS (9), MUMC+: DA Pat Pathologie (9)
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Oncology
POLYPS
medicine.medical_specialty
Colorectal cancer
MICROSATELLITE INSTABILITY
PREDICTION
Biopsy
pT1 and pT2 bowel cancer
new predictive biomarker
Disease
Proof of Concept Study
Risk Assessment
Pathology and Forensic Medicine
Metastasis
Predictive Value of Tests
Risk Factors
Internal medicine
Image Interpretation
Computer-Assisted
medicine
Humans
metastasis
Diagnosis
Computer-Assisted
Biomarker discovery
Risk factor
Early Detection of Cancer
Neoplasm Staging
Retrospective Studies
Microscopy
Receiver operating characteristic
business.industry
inflamed adipose tissue
Digital pathology
Cancer
Reproducibility of Results
deep learning
medicine.disease
artificial intelligence
early colorectal cancer
prediction LNM
MODEL
INTEROBSERVER VARIABILITY
Adipose Tissue
AI
Lymphatic Metastasis
Lymph Nodes
business
Colorectal Neoplasms
digital pathology
Zdroj: Journal of Pathology, 256(3), 269-281. Wiley
Brockmoeller, S, Echle, A, Ghaffari Laleh, N, Eiholm, S, Malmstrøm, M L, Plato Kuhlmann, T, Levic, K, Grabsch, H I, West, N P, Saldanha, O L, Kouvidi, K, Bono, A, Heij, L R, Brinker, T J, Gögenür, I, Quirke, P & Kather, J N 2022, ' Deep learning identifies inflamed fat as a risk factor for lymph node metastasis in early colorectal cancer ', Journal of Pathology, vol. 256, no. 3, pp. 269-281 . https://doi.org/10.1002/path.5831
ISSN: 0022-3417
Popis: 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 WileySons, Ltd.
Databáze: OpenAIRE
Externí odkaz: