Search

Objectives: The aim of this study is to evaluate the feasibility of clinicopathological characteristics and computed tomography (CT) morphological features in predicting lymph node metastasis (LNM) for patients with T1 colorectal cancer (CRC)., Methods: A total of 144 patients with T1 CRC who underwent CT scans and surgical resection were retrospectively included in our study. The clinicopathological characteristics and CT morphological features were assessed by two observers. Univariate and multiple logistic regression analyses were used to identify significant LNM predictive variables. Then a model was developed using the independent predictive factors. The predictive model was subjected to bootstrapping validation (1000 bootstrap resamples) to calculate the calibration curve and relative C-index., Results: LNM were found in 30/144 patients (20.83%). Four independent risk factors were determined in the multiple logistic regression analysis, including presence of necrosis (adjusted odds ratio [OR] = 10.32, 95% confidence interval [CI] 1.96-54.3, p = 0.004), irregular outer border (adjusted OR = 5.94, 95% CI 1.39-25.45, p = 0.035), and heterogeneity enhancement (adjusted OR = 7.35, 95% CI 3.11-17.38, p = 0.007), as well as tumor location (adjusted OR right-sided colon  = 0.05 [0.01-0.60], p = 0.018; adjusted OR rectum  = 0.22 [0.06-0.83], p = 0.026). In the internal validation cohort, the model showed good calibration and good discrimination with a C-index of 0.89., Conclusions: There are significant associations between lymphatic metastasis status and tumor location as well as CT morphologic features in T1 CRC, which could help the doctor make decisions for additional surgery after endoscopic resection., Key Points: • LNM more frequently occurs in left-sided T1 colon cancer than in right-sided T1 colon and rectal cancer. • CT morphologic features are risk factors for LNM of T1 CRC, which may be related to fundamental biological behaviors. • The combination of tumor location and CT morphologic features can more effectively assist in predicting LNM in patients with T1 CRC, and decrease the rate of unnecessary extra surgeries after endoscopic resection., (© 2023. The Author(s), under exclusive licence to European Society of Radiology.)

Rationale and Objectives: We assess the performance of a model combining a deep convolutional neural network and a hand-crafted radiomics signature for predicting KRAS status in patients with colorectal cancer (CRC)., Materials and Methods: The primary cohort consisted of 279 patients with clinicopathologically confirmed CRC between April 2011 and April 2015. Portal venous phase computed tomographic images were analyzed to extract traditional hand-crafted radiomics features as well as deep learning features. A Wilcoxon rank sum test, the minimum redundancy maximum relevance algorithm, and multivariable logistic regression analysis were used to select features and build a radiomics signature. A combined model was then developed using multivariable logistic regression analysis. An independent validation cohort of 119 patients from May 2015 to April 2016 was used to confirm the combined model's predictive performance., Results: The C-index of hand-crafted radiomics signature's discriminative ability was 0.719 (95% confidence interval, CI: 0.658-0.776) for the primary cohort and 0.720 (95% CI: 0.625-0.813) for the validation cohort. The C-index of the deep radiomics signature's discriminative ability was 0.754 (95% CI: 0.696-0.813) for the primary cohort and 0.786 (95% CI: 0.702-0.863) for the validation cohort. The combined model, which merged the hand-crafted radiomics features and deep radiomics features, achieve a C-index of 0.815 (95% CI: 0.766-0.868) for the primary cohort and 0.832 (95% CI: 0.762-0.905) for the validation cohort., Conclusion: This study presents a model that incorporates the hand-crafted and deep radiomics signature, which can be used for individualized preoperative prediction of KRAS mutations in patients with CRC., (Copyright © 2020 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)