Contrast-enhanced CT imaging for the assessment of lymph node status in patients with colorectal cancer

In-House Validated Map of Lymph Node Stations in a Prospective Cohort of Colorectal Cancer: A Tool for a Better Preoperative Staging

Preoperative staging of colorectal cancer (CRC) based on imaging techniques such as computed tomography (CT) or magnetic resonance imaging (MRI) is crucial for identification and then removal of the positive lymph nodes (LNs). The aim of this study was to evaluate the correlation between preoperatively seen morphologic criteria (number, size, shape, structure, borders, or enhancement patterns) and histopathological features of LNs using an in-house validated map of nodal stations. A total of 112 patients with CRC that underwent surgery were preoperatively evaluated by CT scans. The locoregional, intermediate, and central LNs were CT-mapped and then removed during open laparotomy and examined under microscope. The analysis of correlations was interpreted using the suspicious-to-positive ratio (SPR) parameter. The greatest correlation was found in tumors located in the sigmoid colon, descending colon and middle rectum; SPR value was 1.12, 1.18, and 1.26, respectively. SPR proved to be 0.59 for cases of the transverse colon. Regarding the enhancement type, the dotted pattern was mostly correlated with metastatic LNs (OR: 7.84; p < 0.0001), while the homogenous pattern proved a reliable indicator of nonmetastatic LNs (OR: 1.99; p < 0.05). A total of 1809 LNs were harvested, with a median value of 15 ± 1.34 LNs/case. Transdisciplinary approach of CRC focused on pre-, intra-, and postoperatively mapping of LNs might increase the accuracy of detecting metastasized nodes for tumors of the distal colon and middle rectum but not for those of the transverse colon. In addition to morphologic criteria, the enhancement pattern of LNs can be used as a predictor of nodal involvement improving the CT-based preoperative staging.

Contrast-enhanced to noncontrast CT transformation via an adjacency content-transfer-based deep subtraction residual neural network

To reduce overall patient radiation exposure in some clinical scenarios (since cancer patients need frequent follow-ups), noncontrast CT is not used in some institutions. However, although less desirable, noncontrast CT could provide additional important information. In this article, we propose a deep subtraction residual network based on adjacency content transfer to reconstruct noncontrast CT from contrast CT and maintain image quality comparable to that of a CT scan originally acquired without contrast. To address the slight structural dissimilarity of the paired CT images (noncontrast CT and contrast CT) due to involuntary physiological motion, we introduce a contrastive loss network derived from the adjacency content-transfer strategy. We evaluate the results of various similarity metrics (MSE, SSIM, NRMSE, PSNR, MAE) and the fitting curve (HU distribution) of the output mapping to estimate the reconstruction performance of the algorithm. To build the model, we randomly select a total of 15,405 CT paired images (noncontrast CT and contrast-enhanced CT) for training and 10,270 CT paired images for testing. The proposed algorithm preserves the robust structures from the contrast-enhanced CT scans and learns the noncontrast attenuation pattern from the noncontrast CT scans. During the evaluation, the deep subtraction residual network achieves higher MSE, MAE, NRMSE, and PSNR scores (by 30%) than those of the baseline models (BEGAN, CycleGAN, Pixel2Pixel) and better simulates the HU curve of noncontrast CT attenuation. After validation based on an analysis of the experimental results, we can report that the noncontrast CT images reconstructed by our proposed algorithm not only preserve the high-quality structures from the contrast-enhanced CT images, but also mimic the CT attenuation of the originally acquired noncontrast CT images.