Preoperative prediction of rectal Cancer staging combining MRI deep transfer learning, radiomics features, and clinical factors: accurate differentiation from stage T2 to T3

• Published in: BMC gastroenterology Vol. 24; no. 1; pp. 247 - 12
• Main Authors: Fan, Lifang, Wu, Huazhang, Wu, Yimin, Wu, Shujian, Zhao, Jinsong, Zhu, Xiangming
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 05.08.2024; BioMed Central; BMC
• Subjects: Adult; Aged; Analysis; Antigens; Artificial intelligence; Cancer; Cancer therapies; Care and treatment; Chemotherapy; Colorectal cancer; Committees; Decision Trees; Deep Learning; Deep transfer learning; Diagnosis; Ethics; Female; Humans; Logistic Models; Lymphatic system; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Medical prognosis; Metastasis; Methods; Middle Aged; Neoplasm Staging; Neural networks; Patients; Prediction models; Preoperative Period; Radiation therapy; Radiomics; Rectal cancer; Rectal Neoplasms - diagnostic imaging; Rectal Neoplasms - pathology; Rectum; Regression analysis; Retrospective Studies; Software; Staging; Support Vector Machine; Transfer learning; Tumor staging; Values; China; Rectal cancer; Staging; Deep transfer learning; Radiomics
• ISSN: 1471-230X; 1471-230X
• DOI: 10.1186/s12876-024-03316-6

This study evaluates the efficacy of integrating MRI deep transfer learning, radiomic signatures, and clinical variables to accurately preoperatively differentiate between stage T2 and T3 rectal cancer. We included 361 patients with pathologically confirmed stage T2 or T3 rectal cancer, divided into a training set (252 patients) and a test set (109 patients) at a 7:3 ratio. The study utilized features derived from deep transfer learning and radiomics, with Spearman rank correlation and the Least Absolute Shrinkage and Selection Operator (LASSO) regression techniques to reduce feature redundancy. Predictive models were developed using Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM), selecting the best-performing model for a comprehensive predictive framework incorporating clinical data. After removing redundant features, 24 key features were identified. In the training set, the area under the curve (AUC)values for LR, RF, DT, and SVM were 0.867, 0.834, 0.900, and 0.944, respectively; in the test set, they were 0.847, 0.803, 0.842, and 0.910, respectively. The combined model, using SVM and clinical variables, achieved AUCs of 0.946 in the trainingset and 0.920 in the test set. The study confirms the utility of a combined model of MRI deep transfer learning, radiomic features, and clinical factors for preoperative classification of stage T2 vs. T3 rectal cancer, offering significant technological support for precise diagnosis and potential clinical application.