CT-Based Radiomics Analysis for Noninvasive Prediction of Perineural Invasion of Perihilar Cholangiocarcinoma

Abstract

PurposeThe study aimed to construct and evaluate a CT-Based radiomics model for noninvasive detecting perineural invasion (PNI) of perihilar cholangiocarcinoma (pCCA) preoperatively.Materials and MethodsFrom February 2012 to October 2021, a total of 161 patients with pCCA who underwent resection were retrospectively enrolled in this study. Patients were allocated into the training cohort and the validation cohort according to the diagnostic time. Venous phase images of contrast-enhanced CT were used for radiomics analysis. The intraclass correlation efficient (ICC), the correlation analysis, and the least absolute shrinkage and selection operator (LASSO) regression were applied to select radiomics features and built radiomics signature. Logistic regression analyses were performed to establish a clinical model, a radiomics model, and a combined model. The performance of the predictive models was measured by area under the receiver operating characteristic curve (AUC), and pairwise ROC comparisons between models were tested using the Delong method. Finally, the model with the best performance was presented as a nomogram, and its calibration and clinical usefulness were assessed.ResultsFinally, 15 radiomics features were selected to build a radiomics signature, and three models were developed through logistic regression. In the training cohort, the combined model showed a higher predictive capability (AUC = 0.950) than the radiomics model and the clinical model (AUC: radiomics = 0.914, clinical = 0.756). However, in the validation cohort, the AUC of the radiomics model (AUC = 0.885) was significantly higher than the other two models (AUC: combined = 0.791, clinical = 0.567). After comprehensive consideration, the radiomics model was chosen to develop the nomogram. The calibration curve and decision curve analysis (DCA) suggested that the nomogram had a good consistency and clinical utility.ConclusionWe developed a CT-based radiomics model with good performance to noninvasively predict PNI of pCCA preoperatively.

Periampullary cancer and neurological interactions: current understanding and future research directions

“…The key lies in the accurate preoperative prediction of potential PNI occurrence. Advances have been made, such as the development of radiomic-based predictive models that forecast the PNI status in cholangiocarcinoma non-invasively, enabling more tailored surgical planning and precise targeted and immunotherapy regimens ( 128 , 129 ). Yet, when considering therapies targeting neural pathways, potential side effects cannot be overlooked, given the autonomic nervous system’s critical role in digestive functions.…”

Nomogram predicts risk of perineural invasion based on serum biomarkers for pancreatic cancer

“…They found that the fusion radiomics signature performed better predictive capability to evaluate prognosis [ 35 ]. Zhang and Zhan et al also constructed radiomics model for the preoperative prediction of PNI in patients with prostate cancer and perihilar cholangiocarcinoma, respectively [ 36 , 37 ]. However, no predictive nomogram was constructed to predict the PNI probability of PHAC patients, and single CA19-9 or blood glucose level reflected the PNI probability was limited, thus, it needs to development a novel predictive model to assess the PNI probability accurately in PHAC patients.…”

The value of machine learning based radiomics model in preoperative detection of perineural invasion in gastric cancer: a two-center study

“…The predictive value of radiomics-based techniques for PNI has been widely studied in various types of cancer (12)(13)(14)(15). However, radiomic studies focusing on PNI in GC are limited, and the sample sizes are relatively small (16).…”