Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
MRI-Based Deep Learning Analysis Can Predict Microsatellite Instability in Rectal Cancer
21 Pages Posted: 25 Jun 2020
More...Abstract
Background: Microsatellite instability (MSI) predetermines responses to adjuvant 5-fluorouracil and immunotherapy in rectal cancer and serves as a prognostic biomarker for clinical outcomes. Our objectives were to develop and validate a deep learning model that could preoperatively predict the MSI status of rectal cancer based on magnetic resonance images.
Methods: In total, 491 rectal cancer patients with pathologically proven MSI status were retrospectively recruited in this study. Patients were randomly divided into the training/validation cohort (n=395) and the testing cohort (n=96). A clinical model using logistic regression was constructed to discriminate MSI status using only clinical factors. Deep learning models based on a modified MobileNetV2 architecture were tested for predictive ability of MSI status from magnetic resonance images, with or without integrating clinical factors. These three models were developed in the training/validation cohort, and their performances were evaluated in the testing cohort based on area under the curve (AUC), sensitivity, specificity, and accuracy.
Findings: The clinical model correctly classified 62.5% of MSI status in the testing cohort, with an AUC value of 0.563. The pure imaging-based model and the combined model correctly classified 79.2% and 81.3% of MSI status in the testing cohort, with AUC values of 0.811 and 0.839, respectively. Both deep learning models performed better than the clinical model (P<0.05). There was no statistically significant difference between the deep learning models that did and did not integrate clinical factors.
Interpretation: Deep learning based on high-resolution T2-weighted magnetic resonance images showed a good predictive performance for MSI status in rectal cancer patients. The proposed model may also help determine individualized therapeutic strategies for these patients.
Funding Statement: This study was supported by the National Natural Science Foundation of China (No. 81971571).
Declaration of Interests: The authors declare that they have no conflict of interest.
Ethics Approval Statement: This study was approved by the Medical Ethics Committee of West China Hospital, and informed consent was waived due to its retrospective nature.
Keywords: rectal cancer; microsatellite instability; magnetic resonance imaging; deep learning
Suggested Citation: Suggested Citation