Deep Learning Prediction of Metastasis in Locally Advanced Colon Cancer Using Binary Histologic Tumor Images

• Main Authors: Stefan Schiele, Tim Tobias Arndt, Benedikt Martin, Silvia Miller, Svenja Bauer, Bettina Monika Banner, Eva-Maria Brendel, Gerhard Schenkirsch, Matthias Anthuber, Ralf Huss, Bruno Märkl, Gernot Müller
• Format: Article
• Language: English
• Published: MDPI AG 2021-04-01
• Series: Cancers
• Subjects: colon cancer; tumor stroma ratio; pattern; deep learning; tumor architecture; prognostic biomarker
• Online Access: https://www.mdpi.com/2072-6694/13/9/2074

In this study, we developed the Binary ImaGe Colon Metastasis classifier (BIg-CoMet), a semi-guided approach for the stratification of colon cancer patients into two risk groups for the occurrence of distant metastasis, using an InceptionResNetV2-based deep learning model trained on binary images. We enrolled 291 colon cancer patients with pT3 and pT4 adenocarcinomas and converted one cytokeratin-stained representative tumor section per case into a binary image. Image augmentation and dropout layers were incorporated to avoid overfitting. In a validation collective (<i>n</i> = 128), BIg-CoMet was able to discriminate well between patients with and without metastasis (AUC: 0.842, 95% CI: 0.774–0.911). Further, the Kaplan–Meier curves of the metastasis-free survival showed a highly significant worse clinical course for the high-risk group (log-rank test: <i>p</i> < 0.001), and we demonstrated superiority over other established risk factors. A multivariable Cox regression analysis adjusted for confounders supported the use of risk groups as a prognostic factor for the occurrence of metastasis (hazard ratio (HR): 5.4, 95% CI: 2.5–11.7, <i>p</i> < 0.001). BIg-CoMet achieved good performance for both UICC subgroups, especially for UICC III (<i>n</i> = 53), with a positive predictive value of 80%. Our study demonstrates the ability to stratify colon cancer patients via a semi-guided process on images that primarily reflect tumor architecture.